技术领域technical field
本申请涉及流量控制技术领域，且更为具体地，涉及一种基于驱动电机电流控制协同的煤流量控制系统及其方法。The present application relates to the technical field of flow control, and more specifically, relates to a coal flow control system and method thereof based on coordination of drive motor current control.
背景技术Background technique
堆取料设备在实现无人值守前，通过操作员的眼睛，人工观察取煤流量的大小并加以控制。实现无人值守后，人的眼睛不用了，技术的“眼睛”必须跟上。Before the stacking and reclaiming equipment is unattended, the operator's eyes can be used to manually observe the size of the coal flow and control it. After the realization of unattended, human eyes are no longer needed, and the "eyes" of technology must keep up.
堆取料设备实现智能无人化后，煤流量自动控制技术是斗轮机智能化运行的一项重要技术，其一项重要的技术目的是控制煤流量的稳定和均衡，也就是，保持煤流量的波动在可接受的范围内。After the intelligent and unmanned stacking and reclaiming equipment is realized, the automatic coal flow control technology is an important technology for the intelligent operation of the bucket wheel machine. One of its important technical purposes is to control the stability and balance of the coal flow, that is, to keep the fluctuation of the coal flow within an acceptable range.
因此，期待一种煤流量控制方案。Therefore, a coal flow control scheme is desired.
发明内容Contents of the invention
为了解决上述技术问题，提出了本申请。本申请的实施例提供了一种基于驱动电机电流控制协同的煤流量控制系统及其方法，其基于深度学习的人工智能监控技术，以通过分别捕捉煤流量数据和驱动电机的电流数据中局部时间窗口内数据离散分布的高维隐含关联模式特征，并利用两者之间存在的响应性逻辑关联关系来对所述驱动电机的驱动电流进行自适应调整以使得煤流量能够保持稳定和均衡。In order to solve the above-mentioned technical problems, the present application is proposed. The embodiment of the present application provides a coal flow control system and method based on driving motor current control coordination, which is based on deep learning artificial intelligence monitoring technology to capture the high-dimensional implicit correlation mode characteristics of the discrete distribution of data in the local time window in the coal flow data and the current data of the driving motor respectively, and use the responsive logical relationship between the two to adaptively adjust the driving current of the driving motor so that the coal flow can be kept stable and balanced.
相应地，根据本申请的一个方面，提供了一种基于驱动电机电流控制协同的煤流量控制系统，其包括：Accordingly, according to one aspect of the present application, a coal flow control system based on drive motor current control coordination is provided, which includes:
传感器监控模块，用于获取预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值；A sensor monitoring module, configured to acquire coal flow values at multiple predetermined time points within a predetermined time period and current values of the drive motor at the multiple predetermined time points;
时序向量化模块，用于将所述多个预定时间点的煤流量值按照时间维度排列为煤流量输入向量，且将所述多个预定时间点的驱动电机的电流值按照时间维度排列为电流输入向量；A timing vectorization module, configured to arrange the coal flow values at the multiple predetermined time points into a coal flow input vector according to the time dimension, and arrange the current values of the drive motor at the multiple predetermined time points into a current input vector according to the time dimension;
煤流量特征提取模块，用于将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量；A coal flow feature extraction module, configured to input the coal flow input vector through the first convolutional neural network model using a one-dimensional convolution kernel to obtain a time series feature vector of coal flow;
电流提取模块，用于将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量；A current extraction module, configured to pass the current input vector through a second convolutional neural network model using a one-dimensional convolution kernel to obtain a current time series feature vector;
响应性估计模块，用于基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵；A responsiveness estimation module, configured to calculate the responsiveness estimation of the coal flow time-series feature vector relative to the current time-series feature vector based on a Gaussian density map to obtain a classification feature matrix;
特征分布优化模块，用于对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；以及A feature distribution optimization module, configured to perform feature local distribution optimization on the classification feature matrix to obtain an optimized classification feature vector; and
驱动电流控制结果，用于将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小。The driving current control result is used to pass the optimized classification feature vector through a classifier to obtain a classification result, and the classification result is used to indicate that the current value of the driving motor at the current time point should be increased or decreased.
在上述基于驱动电机电流控制协同的煤流量控制系统中，所述煤流量特征提取模块，进一步用于：使用所述第一卷积神经网络模型的各层在层的正向传递中对输入数据分别进行基于一维卷积核的卷积处理和非线性激活处理以由所述第一卷积神经网络模型的最后一层输出所述煤流量时序特征向量，其中，所述第一卷积神经网络模型的第一层的输入为所述煤流量输入向量。In the above-mentioned coal flow control system based on drive motor current control coordination, the coal flow feature extraction module is further configured to: use each layer of the first convolutional neural network model to perform convolution processing and nonlinear activation processing based on a one-dimensional convolution kernel on the input data in the forward transfer of the layer, so that the coal flow time-series feature vector is output from the last layer of the first convolutional neural network model, wherein the input of the first layer of the first convolutional neural network model is the coal flow input vector.
在上述基于驱动电机电流控制协同的煤流量控制系统中，所述电流提取模块，进一步用于：使用所述第二卷积神经网络模型的各层在层的正向传递中对输入数据分别进行基于一维卷积核的卷积处理和非线性激活处理以由所述第二卷积神经网络模型的最后一层输出所述电流时序特征向量，其中，所述第二卷积神经网络模型的第一层的输入为所述电流输入向量。In the above-mentioned coal flow control system based on drive motor current control coordination, the current extraction module is further configured to: use each layer of the second convolutional neural network model to perform convolution processing based on a one-dimensional convolution kernel and nonlinear activation processing on the input data in the forward transfer of the layer, so that the last layer of the second convolutional neural network model outputs the current sequence feature vector, wherein the input of the first layer of the second convolutional neural network model is the current input vector.
在上述基于驱动电机电流控制协同的煤流量控制系统中，所述响应性估计模块，包括：高斯密度图构造单元，用于构造所述煤流量时序特征向量和所述电流时序特征向量的高斯密度图以得到第一高斯密度图和第二高斯密度图；响应单元，用于以如下公式计算所述第一高斯密度图相对于所述第二高斯密度图的响应性估计以得到响应性高斯密度图，其中，所述公式为：In the above-mentioned coal flow control system based on drive motor current control coordination, the responsiveness estimation module includes: a Gaussian density map construction unit, configured to construct a Gaussian density map of the coal flow time-series feature vector and the current time-series feature vector to obtain a first Gaussian density map and a second Gaussian density map; a response unit, used to calculate the responsiveness estimation of the first Gaussian density map relative to the second Gaussian density map by the following formula to obtain a responsive Gaussian density map, wherein the formula is:
其中Fa表示所述第一高斯密度图，Fb表示所述第二高斯密度图，Fc表示所述响应性高斯密度图，表示矩阵相乘；以及，高斯离散化单元，用于对所述响应性高斯密度图进行高斯离散化以得到所述分类特征矩阵。Wherein Fa represents described first Gaussian density figure, Fb represents described second Gaussian density figure, Fc represents described responsiveness Gaussian density figure, represents matrix multiplication; and, a Gaussian discretization unit, configured to perform Gaussian discretization on the responsive Gaussian density map to obtain the classification feature matrix.
在上述基于驱动电机电流控制协同的煤流量控制系统中，所述特征分布优化模块，进一步用于：以如下公式对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；其中，所述公式为：In the above-mentioned coal flow control system based on drive motor current control coordination, the feature distribution optimization module is further used to: perform feature local distribution optimization on the classification feature matrix with the following formula to obtain an optimized classification feature vector; wherein, the formula is:
其中，V是所述分类特征矩阵按照行向量或列向量展开后得到的分类特征向量，‖V‖2表示所述分类特征向量的二范数，表示其平方，即所述分类特征向量自身的内积，vi是所述分类特征向量的第i个特征值，且vi′是所述优化分类特征向量的第i个特征值，exp(·)表示向量的指数运算，所述向量的指数运算表示计算以向量中各个位置的特征值为幂的自然指数函数值。Wherein, V is the classification feature vector obtained after the classification feature matrix is expanded according to the row vector or column vector, ‖ V ‖2 represents the two norms of the classification feature vector, Represents its square, i.e. the inner product of the classification feature vector itself, vi is the i-th eigenvalue of the classification feature vector, and vi ' is the i-th eigenvalue of the optimized classification feature vector, exp( ) represents the exponential operation of the vector, and the exponential operation of the vector represents the calculation of the natural exponential function value of the power of the eigenvalue of each position in the vector.
在上述基于驱动电机电流控制协同的煤流量控制系统中，所述驱动电流控制结果，包括：全连接编码单元，用于使用所述分类器的全连接层对所述优化分类特征向量进行全连接编码以得到编码分类特征向量；以及，分类结果生成单元，用于将所述编码分类特征向量输入所述分类器的Softmax分类函数以得到所述分类结果。In the above-mentioned coal flow control system based on driving motor current control coordination, the driving current control result includes: a fully-connected encoding unit, configured to use the fully-connected layer of the classifier to perform fully-connected encoding on the optimized classification feature vector to obtain an encoded classification feature vector; and a classification result generation unit, configured to input the encoded classification feature vector into the Softmax classification function of the classifier to obtain the classification result.
根据本申请的另一方面，还提供了一种基于驱动电机电流控制协同的煤流量控制方法，其包括：According to another aspect of the present application, there is also provided a coal flow control method based on drive motor current control coordination, which includes:
获取预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值；Obtain coal flow values at multiple predetermined time points within a predetermined time period and current values of the drive motor at the multiple predetermined time points;
将所述多个预定时间点的煤流量值按照时间维度排列为煤流量输入向量，且将所述多个预定时间点的驱动电机的电流值按照时间维度排列为电流输入向量；Arranging the coal flow values at the multiple predetermined time points as a coal flow input vector according to the time dimension, and arranging the current values of the drive motor at the multiple predetermined time points as a current input vector according to the time dimension;
将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量；The coal flow input vector is passed through the first convolutional neural network model using a one-dimensional convolution kernel to obtain a time series feature vector of coal flow;
将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量；Passing the current input vector through a second convolutional neural network model using a one-dimensional convolution kernel to obtain a current time-series feature vector;
基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵；calculating a responsiveness estimate of the coal flow time-series feature vector relative to the current time-series feature vector based on a Gaussian density map to obtain a classification feature matrix;
对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；以及performing feature local distribution optimization on the classification feature matrix to obtain an optimized classification feature vector; and
将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小。The optimized classification feature vector is passed through a classifier to obtain a classification result, and the classification result is used to indicate that the current value of the driving motor at the current time point should be increased or decreased.
在上述基于驱动电机电流控制协同的煤流量控制方法中，所述将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量，包括：使用所述第一卷积神经网络模型的各层在层的正向传递中对输入数据分别进行基于一维卷积核的卷积处理和非线性激活处理以由所述第一卷积神经网络模型的最后一层输出所述煤流量时序特征向量，其中，所述第一卷积神经网络模型的第一层的输入为所述煤流量输入向量。In the above coal flow control method based on drive motor current control coordination, the coal flow input vector is passed through a first convolutional neural network model using a one-dimensional convolution kernel to obtain a coal flow time-series feature vector, including: using each layer of the first convolutional neural network model to perform convolution processing and nonlinear activation processing based on a one-dimensional convolution kernel on the input data in the forward pass of the layer to output the coal flow time-series feature vector from the last layer of the first convolutional neural network model, wherein the input of the first layer of the first convolutional neural network model is the coal flow Flow input vector.
在上述基于驱动电机电流控制协同的煤流量控制方法中，所述将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量，包括：使用所述第二卷积神经网络模型的各层在层的正向传递中对输入数据分别进行基于一维卷积核的卷积处理和非线性激活处理以由所述第二卷积神经网络模型的最后一层输出所述电流时序特征向量，其中，所述第二卷积神经网络模型的第一层的输入为所述电流输入向量。In the above -mentioned coal flow control method based on the driving motor current control, the current input vector will use the second convolutional neural network model to obtain the current sequencing feature vector through the second convolutional neural network model of the one -dimensional convolution nucleus, including the use of the input data based on the volume processing and non -linear activation of the input data based on the first -dimensional convolution nuclear convolution nucleus in the positive transmission of the second convolutional neural network model. The current order feature vector of the current sequencing is based on the last layer output of the second convolutional neural network model. Among them, the input of the first layer of the second convolutional neural network model is the input vector of the current.
在上述基于驱动电机电流控制协同的煤流量控制方法中，所述基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵，包括：构造所述煤流量时序特征向量和所述电流时序特征向量的高斯密度图以得到第一高斯密度图和第二高斯密度图；以如下公式计算所述第一高斯密度图相对于所述第二高斯密度图的响应性估计以得到响应性高斯密度图，其中，所述公式为：In the above-mentioned coal flow control method based on drive motor current control coordination, calculating the response estimation of the coal flow time-series feature vector relative to the current time-series feature vector based on a Gaussian density map to obtain a classification feature matrix includes: constructing a Gaussian density map of the coal flow time-series feature vector and the current time-series feature vector to obtain a first Gaussian density map and a second Gaussian density map; calculating the responsiveness estimate of the first Gaussian density map relative to the second Gaussian density map according to the following formula to obtain a responsive Gaussian density map, wherein the formula is:
其中Fa表示所述第一高斯密度图，Fb表示所述第二高斯密度图，Fc表示所述响应性高斯密度图，表示矩阵相乘；以及，对所述响应性高斯密度图进行高斯离散化以得到所述分类特征矩阵。Wherein Fa represents described first Gaussian density figure, Fb represents described second Gaussian density figure, Fc represents described responsiveness Gaussian density figure, representing matrix multiplication; and performing Gaussian discretization on the responsive Gaussian density map to obtain the classification feature matrix.
在上述基于驱动电机电流控制协同的煤流量控制方法中，所述对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量，包括：以如下公式对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；其中，所述公式为：In the above-mentioned coal flow control method based on the coordination of drive motor current control, the optimization of the local distribution of features on the classification feature matrix to obtain an optimized classification feature vector includes: performing local distribution optimization on the classification feature matrix with the following formula to obtain an optimized classification feature vector; wherein, the formula is:
其中，V是所述分类特征矩阵按照行向量或列向量展开后得到的分类特征向量，‖V‖2表示所述分类特征向量的二范数，表示其平方，即所述分类特征向量自身的内积，vi是所述分类特征向量的第i个特征值，且vi′是所述优化分类特征向量的第i个特征值，exp(·)表示向量的指数运算，所述向量的指数运算表示计算以向量中各个位置的特征值为幂的自然指数函数值。Wherein, V is the classification feature vector obtained after the classification feature matrix is expanded according to the row vector or column vector, ‖ V ‖2 represents the two norms of the classification feature vector, Represents its square, i.e. the inner product of the classification feature vector itself, vi is the i-th eigenvalue of the classification feature vector, and vi ' is the i-th eigenvalue of the optimized classification feature vector, exp( ) represents the exponential operation of the vector, and the exponential operation of the vector represents the calculation of the natural exponential function value of the power of the eigenvalue of each position in the vector.
在上述基于驱动电机电流控制协同的煤流量控制方法中，所述将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小，包括：使用所述分类器的全连接层对所述优化分类特征向量进行全连接编码以得到编码分类特征向量；以及，将所述编码分类特征向量输入所述分类器的Softmax分类函数以得到所述分类结果。In the coal flow control method based on the coordination of drive motor current control, the classifier is used to pass the optimized classification feature vector through a classifier to obtain a classification result, and the classification result is used to indicate that the current value of the drive motor at the current time point should be increased or decreased, including: using the fully connected layer of the classifier to perform fully connected encoding on the optimized classification feature vector to obtain an encoded classification feature vector; and inputting the encoded classification feature vector into the Softmax classification function of the classifier to obtain the classification result.
根据本申请的再一方面，提供了一种电子设备，包括：处理器；以及，存储器，在所述存储器中存储有计算机程序指令，所述计算机程序指令在被所述处理器运行时使得所述处理器执行如上所述的基于驱动电机电流控制协同的煤流量控制方法。According to yet another aspect of the present application, an electronic device is provided, including: a processor; and a memory, in which computer program instructions are stored, and when the computer program instructions are executed by the processor, the processor executes the coal flow control method based on the coordination of drive motor current control as described above.
根据本申请的又一方面，提供了一种计算机可读介质，其上存储有计算机程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行如上所述的基于驱动电机电流控制协同的煤流量控制方法。According to yet another aspect of the present application, a computer-readable medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the processor executes the coal flow control method based on driving motor current control coordination as described above.
与现有技术相比，本申请提供的基于驱动电机电流控制协同的煤流量控制系统及其方法，其基于深度学习的人工智能监控技术，以通过分别捕捉煤流量数据和驱动电机的电流数据中局部时间窗口内数据离散分布的高维隐含关联模式特征，并利用两者之间存在的响应性逻辑关联关系来对所述驱动电机的驱动电流进行自适应调整以使得煤流量能够保持稳定和均衡。Compared with the prior art, the coal flow control system and method based on the coordination of driving motor current control provided by the present application is based on the artificial intelligence monitoring technology of deep learning, so as to separately capture the high-dimensional implicit correlation mode characteristics of the discrete distribution of data in the local time window in the coal flow data and the current data of the driving motor, and use the responsive logical relationship between the two to adaptively adjust the driving current of the driving motor so that the coal flow can be kept stable and balanced.
附图说明Description of drawings
通过结合附图对本申请实施例进行更详细的描述，本申请的上述以及其他目的、特征和优势将变得更加明显。附图用来提供对本申请实施例的进一步理解，并且构成说明书的一部分，与本申请实施例一起用于解释本申请，并不构成对本申请的限制。在附图中，相同的参考标号通常代表相同部件或步骤。The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used together with the embodiments of the present application to explain the present application, and do not constitute limitations to the present application. In the drawings, the same reference numerals generally represent the same components or steps.
图1为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统的应用场景图。Fig. 1 is an application scene diagram of a coal flow control system based on driving motor current control coordination according to an embodiment of the present application.
图2为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统的框图。Fig. 2 is a block diagram of a coal flow control system based on driving motor current control coordination according to an embodiment of the present application.
图3为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统的架构示意图。Fig. 3 is a schematic diagram of the architecture of a coal flow control system based on drive motor current control coordination according to an embodiment of the present application.
图4为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统中响应性估计模块的框图。Fig. 4 is a block diagram of a responsiveness estimation module in a coal flow control system based on driving motor current control cooperation according to an embodiment of the present application.
图5为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制方法的流程图。Fig. 5 is a flowchart of a coal flow control method based on driving motor current control coordination according to an embodiment of the present application.
图6为根据本申请实施例的电子设备的框图。FIG. 6 is a block diagram of an electronic device according to an embodiment of the present application.
具体实施方式Detailed ways
下面，将参考附图详细地描述根据本申请的示例实施例。显然，所描述的实施例仅仅是本申请的一部分实施例，而不是本申请的全部实施例，应理解，本申请不受这里描述的示例实施例的限制。Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described here.
申请概述Application overview
如上所述，煤流量自动控制技术是斗轮机智能化运行的一项重要技术，其一项重要的技术目的是控制煤流量的稳定和均衡，也就是，保持煤流量的波动在可接受的范围内。因此，期待一种煤流量控制方案来使得煤流量能够保持稳定和均衡。As mentioned above, the coal flow automatic control technology is an important technology for the intelligent operation of the bucket wheel machine. One of its important technical purposes is to control the stability and balance of the coal flow, that is, to keep the fluctuation of the coal flow within an acceptable range. Therefore, a coal flow control scheme is expected to keep the coal flow stable and balanced.
相应地，在本申请的技术方案中，通过对煤流量监测可得到实时的煤流量数据，进而通过所得到的煤流量数据来自适应地调整驱动电机的电流控制值，通过这样的方式，来保持煤流量的稳定和均衡。Correspondingly, in the technical solution of the present application, real-time coal flow data can be obtained by monitoring the coal flow, and then the current control value of the drive motor can be adaptively adjusted through the obtained coal flow data. In this way, the stability and balance of the coal flow can be maintained.
具体地，获取预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值。具体地，在本申请的技术方案中，可通过电子皮带秤或激光扫描仪来得到所述多个预定时间点的煤流量值。这里，在利用所述激光扫描仪来采集所述煤流量值的过程中，其利用扫描煤流表面形状计算体积的方式，加上密度的估算,换算成流量，这种方式的优点是误差漂移少，相对稳定，不太需要经常校正。Specifically, coal flow values at multiple predetermined time points within a predetermined time period and current values of the drive motor at the multiple predetermined time points are acquired. Specifically, in the technical solution of the present application, the coal flow values at the multiple predetermined time points can be obtained through an electronic belt scale or a laser scanner. Here, in the process of using the laser scanner to collect the coal flow value, it uses the method of scanning the surface shape of the coal flow to calculate the volume, plus the estimation of the density, and converts it into a flow rate. The advantage of this method is that the error drift is small, relatively stable, and does not require frequent corrections.
接着，将所述多个预定时间点的煤流量值按照时间维度排列为煤流量输入向量，且将所述多个预定时间点的驱动电机的电流值按照时间维度排列为电流输入向量。也就是，将所述煤流量值的时序离散分布和所述电流值的时序离散分布构造为结构化的所述煤流量输入向量和所述电流输入向量。继而，将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量，同时，将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量。Next, arrange the coal flow values at the multiple predetermined time points into a coal flow input vector according to the time dimension, and arrange the current values of the driving motor at the multiple predetermined time points into a current input vector according to the time dimension. That is, the time-series discrete distribution of the coal flow value and the time-series discrete distribution of the current value are constructed as the structured coal flow input vector and the current input vector. Then, the coal flow input vector is passed through a first convolutional neural network model using a one-dimensional convolution kernel to obtain a coal flow time-series feature vector, and at the same time, the current input vector is passed through a second convolutional neural network model using a one-dimensional convolution kernel to obtain a current time-series feature vector.
也就是，在本申请的技术方案中，使用一维卷积神经网络模型对所述煤流量输入向量和所述电流输入向量进行一维卷积编码以捕捉所述煤流量输入向量和所述电流输入向量中局部时间窗口内煤流量离散分布和电流值离散分布的高维隐含关联模式特征以得到所述煤流量时序特征向量和所述电流时序特征向量。特别地，所述第一卷积神经网络模型和所述第二卷积神经网络模型所使用的一维卷积核具有可学习的神经网络权重参数，其能够在训练过程中，基于训练目的进行参数自适应调整以满足训练目标。That is, in the technical solution of the present application, a one-dimensional convolutional neural network model is used to perform one-dimensional convolutional encoding on the coal flow input vector and the current input vector to capture the high-dimensional implicit correlation mode characteristics of the coal flow discrete distribution and the current value discrete distribution in the local time window in the coal flow input vector and the current input vector to obtain the coal flow time-series feature vector and the current time-series feature vector. In particular, the one-dimensional convolution kernels used by the first convolutional neural network model and the second convolutional neural network model have learnable neural network weight parameters, which can be adaptively adjusted based on the training purpose during the training process to meet the training objectives.
特别地，在本申请的技术方案中，驱动电机的驱动电流变化会引起煤流量的波动，也就是说，在高维逻辑空间中，所述煤流量时序特征向量和所述电流时序特征向量之间存在响应性逻辑关联，如果能够利用上述逻辑关系，则显然能够提高所述驱动电机的驱动电流自适应控制的精准度。在本申请的技术方案中，基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵。In particular, in the technical solution of the present application, the change of the driving current of the driving motor will cause fluctuations in the coal flow, that is, in the high-dimensional logic space, there is a responsive logical relationship between the coal flow time-series feature vector and the current time-series feature vector. If the above logical relationship can be used, the accuracy of the drive current adaptive control of the driving motor can obviously be improved. In the technical solution of the present application, the estimate of the responsiveness of the coal flow time-series feature vector to the current time-series feature vector is calculated based on a Gaussian density map to obtain a classification feature matrix.
具体地，首先构造所述煤流量时序特征向量和所述电流时序特征向量的高斯密度图以得到第一高斯密度图和第二高斯密度图，其中，所述第一高斯密度图的均值向量为所述煤流量时序特征向量，所述第一高斯密度图的协方差矩阵中各个位置的值为所述煤流量时序特征向量中相应两个位置的特征值之间的方差，所述第二高斯密度图的均值向量为所述电流时序特征向量，所述第二高斯密度图的协方差矩阵中各个位置的值为所述电流时序特征向量中相应两个位置的特征值之间的方差。这里，构造所述煤流量时序特征向量和所述电流时序特征向量的高斯密度图的目的是对所述煤流量时序特征向量和所述电流时序特征向量进行基于后验分布的特征级数据增强以提高特征表示的精准度和后续响应性估计的精准度。接着，计算所述第一高斯密度图相对于所述第二高斯密度图的响应性估计以得到响应性高斯密度图，并通过对所述响应性高斯密度图进行高斯离散化以得到所述分类特征矩阵。Specifically, first construct the Gaussian density map of the coal flow time-series feature vector and the current time-series feature vector to obtain the first Gaussian density map and the second Gaussian density map, wherein the mean vector of the first Gaussian density map is the coal flow time-series feature vector, the value of each position in the covariance matrix of the first Gaussian density map is the variance between the eigenvalues of two corresponding positions in the coal flow time-series feature vector, the mean vector of the second Gaussian density map is the current time-series feature vector, and the covariance of the second Gaussian density map The value of each position in the matrix is the variance between the eigenvalues of corresponding two positions in the current time series eigenvector. Here, the purpose of constructing the Gaussian density map of the coal flow time-series feature vector and the current time-series feature vector is to perform feature-level data enhancement based on the posterior distribution on the coal flow time-series feature vector and the current time-series feature vector to improve the accuracy of feature representation and the accuracy of subsequent responsiveness estimation. Next, calculating the responsiveness estimate of the first Gaussian density map relative to the second Gaussian density map to obtain a responsive Gaussian density map, and performing Gaussian discretization on the responsive Gaussian density map to obtain the classification feature matrix.
在得到所述分类特征矩阵后，将所述分类特征矩阵通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大应减小。也就是，使用所述分类器来确定所述分类特征矩阵所属的类概率标签，其中，所述类概率标签包括当前时间点的驱动电机的电流值应增大(第一标签)以及，当前时间点的驱动电机的电流值应减小(第二标签)。应注意到，所述分类器的类概率标签为驱动电机的驱动电流控制策略标签，因此，在得到所述分类结果后，能够基于所述分类结果对所述驱动电机的驱动电流进行自适应调整以使得煤流量能够保持稳定和均衡。After the classification feature matrix is obtained, the classification feature matrix is passed through a classifier to obtain a classification result, and the classification result is used to indicate that the current value of the driving motor at the current time point should be increased or decreased. That is, the classifier is used to determine the class probability label to which the classification feature matrix belongs, wherein the class probability label includes that the current value of the driving motor at the current time point should increase (the first label) and that the current value of the driving motor at the current time point should decrease (the second label). It should be noted that the class probability label of the classifier is the drive current control strategy label of the drive motor. Therefore, after the classification result is obtained, the drive current of the drive motor can be adaptively adjusted based on the classification result so that the coal flow can be kept stable and balanced.
特别地，在本申请的技术方案中，在使用高斯密度图计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计得到所述分类特征矩阵时，由于在高斯离散化的过程中的随机性，会在所述分类特征矩阵内引入存在特殊的异常局部分布，这会导致所述分类特征矩阵在通过分类器进行分类时对单一分类结果的依赖性差，影响分类结果的准确性。In particular, in the technical solution of the present application, when the Gaussian density map is used to calculate the responsivity of the coal flow time-series feature vector relative to the current time-series feature vector to obtain the classification feature matrix, due to the randomness in the Gaussian discretization process, a special abnormal local distribution will be introduced into the classification feature matrix, which will lead to poor dependence of the classification feature matrix on a single classification result when it is classified by a classifier, affecting the accuracy of the classification result.
因此，对所述分类特征矩阵展开后得到的分类特征向量进行向量赋范的希尔伯特概率空间化，具体表示为：Therefore, the Hilbert probability space of vector normation is performed on the classification feature vector obtained after the classification feature matrix is expanded, specifically expressed as:
V是所述分类特征向量，‖V‖2表示所述分类特征向量的二范数，表示其平方，即所述分类特征向量自身的内积，vi是所述分类特征向量V的第i个特征值，且vi′是优化后的分类特征向量V′的第i个特征值。V is the categorical feature vector, ‖ V ‖2 represents the two norms of the categorical feature vector, represents its square, that is, the inner product of the classification feature vector itself, vi is the ith eigenvalue of the classification feature vector V, and vi ' is the ith eigenvalue of the optimized classification feature vector V'.
这里，所述向量赋范的希尔伯特概率空间化通过所述分类特征向量V自身的赋范在定义了向量内积的希尔伯特空间内进行所述分类特征向量V的概率性解释，并降低所述分类特征向量V的特殊的局部分布的类表达对整体希尔伯特空间拓扑的类表达的隐蔽扰动，由此提高所述分类特征向量V的特征分布收敛到预定分类概率的分类回归的鲁棒性，同时依靠度量诱导概率空间结构的建立来提升所述分类特征向量V的特征分布对分类结果的跨分类器的长程依赖。这样，再将优化后的分类特征向量V′直接通过分类器进行分类，就提升了所述分类特征矩阵在通过分类器进行分类时对分类结果的依赖性，改进了分类结果的准确性。Here, the vector-normed Hilbert probability spatialization performs the probabilistic interpretation of the classification feature vector V in the Hilbert space that defines the vector inner product through the norming of the classification feature vector V itself, and reduces the hidden disturbance of the class expression of the special local distribution of the classification feature vector V to the class expression of the overall Hilbert space topology, thereby improving the robustness of the classification regression in which the feature distribution of the classification feature vector V converges to a predetermined classification probability. Long-range dependencies of classifiers. In this way, the optimized classification feature vector V' is directly classified by the classifier, which increases the dependence of the classification feature matrix on the classification result when it is classified by the classifier, and improves the accuracy of the classification result.
基于此，本申请提供了一种基于驱动电机电流控制协同的煤流量控制系统，其包括：传感器监控模块，用于获取预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值；时序向量化模块，用于将所述多个预定时间点的煤流量值按照时间维度排列为煤流量输入向量，且将所述多个预定时间点的驱动电机的电流值按照时间维度排列为电流输入向量；煤流量特征提取模块，用于将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量；电流提取模块，用于将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量；响应性估计模块，用于基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵；特征分布优化模块，用于对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；以及，驱动电流控制结果，用于将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小。Based on this, the present application provides a coal flow control system based on drive motor current control coordination, which includes: a sensor monitoring module, used to obtain coal flow values at multiple predetermined time points within a predetermined time period and the current values of the drive motors at the multiple predetermined time points; a timing vectorization module, used to arrange the coal flow values at the multiple predetermined time points as coal flow input vectors according to the time dimension, and arrange the current values of the drive motors at the multiple predetermined time points according to the time dimension as current input vectors; coal flow feature extraction module, used to obtain the coal flow input vectors by using one-dimensional convolution The first convolutional neural network model of the kernel to obtain the coal flow time-series feature vector; the current extraction module is used to pass the current input vector through the second convolutional neural network model using a one-dimensional convolution kernel to obtain the current time-series feature vector; the responsiveness estimation module is used to calculate the response estimation of the coal flow time-series feature vector relative to the current time-series feature vector based on a Gaussian density map to obtain a classification feature matrix; The vector is passed through the classifier to obtain a classification result, which is used to indicate that the current value of the driving motor at the current time point should be increased or decreased.
图1为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统的应用场景图。如图1所示，在该应用场景中，首先获取由激光扫描仪(例如，如图1中所示意的Sc)采集的预定时间段内多个预定时间点的煤流量值和由电流监测仪(例如，如图1中所示意的M)采集的所述多个预定时间段的驱动电机(例如，如图1中所示意的D)的电流值。进而，将所述预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值输入至部署有基于驱动电机电流控制协同的煤流量控制算法的服务器(例如，如图1所示意的S)中，其中，所述服务器能够基于所述基于驱动电机电流控制协同的煤流量控制算法对所述预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值进行处理，以得到用于表示当前时间点的驱动电机的电流值应增大或应减小的分类结果。Fig. 1 is an application scene diagram of a coal flow control system based on driving motor current control coordination according to an embodiment of the present application. As shown in FIG. 1 , in this application scenario, the coal flow values collected by a laser scanner (for example, Sc as shown in FIG. 1 ) at multiple predetermined time points within a predetermined time period and the current values of the drive motor (for example, D as shown in FIG. 1 ) collected by a current monitor (for example, M as shown in FIG. 1 ) are collected at first. Furthermore, the coal flow values at multiple predetermined time points within the predetermined time period and the current values of the driving motors at the multiple predetermined time points are input to a server (for example, S as shown in FIG. Reduced classification results.
在介绍了本申请的基本原理之后，下面将参考附图来具体介绍本申请的各种非限制性实施例。After introducing the basic principles of the application, various non-limiting embodiments of the application will be described in detail below with reference to the accompanying drawings.
示例性系统exemplary system
图2为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统的框图。如图2所示，根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统100，包括：传感器监控模块110，用于获取预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值；时序向量化模块120，用于将所述多个预定时间点的煤流量值按照时间维度排列为煤流量输入向量，且将所述多个预定时间点的驱动电机的电流值按照时间维度排列为电流输入向量；煤流量特征提取模块130，用于将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量；电流提取模块140，用于将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量；响应性估计模块150，用于基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵；特征分布优化模块160，用于对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；以及，驱动电流控制结果170，用于将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小。Fig. 2 is a block diagram of a coal flow control system based on driving motor current control coordination according to an embodiment of the present application. As shown in FIG. 2 , the coal flow control system 100 based on the coordination of drive motor current control according to the embodiment of the present application includes: a sensor monitoring module 110 for acquiring coal flow values at multiple predetermined time points within a predetermined time period and current values of the drive motors at the multiple predetermined time points; a timing vectorization module 120 for arranging the coal flow values at the multiple predetermined time points as coal flow input vectors according to the time dimension, and arranging the current values of the drive motors at the multiple predetermined time points as current input vectors according to the time dimension; coal flow feature extraction module 130, It is used to pass the coal flow input vector through the first convolutional neural network model using a one-dimensional convolution kernel to obtain a coal flow time-series feature vector; the current extraction module 140 is used to pass the current input vector through a second convolutional neural network model using a one-dimensional convolution kernel to obtain a current time-series feature vector; the responsiveness estimation module 150 is used to calculate the response estimation of the coal flow time-series feature vector relative to the current time-series feature vector based on a Gaussian density map to obtain a classification feature matrix; the feature distribution optimization module 160 is used to perform feature localization on the classification feature matrix distribution optimization to obtain an optimized classification feature vector; and the driving current control result 170, used to pass the optimized classification feature vector through a classifier to obtain a classification result, the classification result is used to indicate that the current value of the driving motor at the current time point should be increased or decreased.
图3为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统的架构示意图。如图3所示，首先，获取预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值；接着，将所述多个预定时间点的煤流量值按照时间维度排列为煤流量输入向量，且将所述多个预定时间点的驱动电机的电流值按照时间维度排列为电流输入向量；然后，将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量，同时，将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量；继而，基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵；随后，对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；最后，将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小。Fig. 3 is a schematic diagram of the architecture of a coal flow control system based on drive motor current control coordination according to an embodiment of the present application. As shown in Figure 3, firstly, the coal flow values at multiple predetermined time points and the current values of the driving motors at the multiple predetermined time points within the predetermined time period are obtained; then, the coal flow values at the multiple predetermined time points are arranged as coal flow input vectors according to the time dimension, and the current values of the drive motors at the multiple predetermined time points are arranged as current input vectors according to the time dimension; The second convolutional neural network model is used to obtain the current time-series feature vector; then, based on the Gaussian density map, calculate the response estimate of the coal flow time-series feature vector relative to the current time-series feature vector to obtain a classification feature matrix; then, perform feature local distribution optimization on the classification feature matrix to obtain an optimized classification feature vector; finally, pass the optimized classification feature vector through a classifier to obtain a classification result, and the classification result is used to indicate that the current value of the driving motor at the current time point should be increased or decreased.
如上所述，煤流量自动控制技术是斗轮机智能化运行的一项重要技术，其一项重要的技术目的是控制煤流量的稳定和均衡，也就是，保持煤流量的波动在可接受的范围内。因此，期待一种煤流量控制方案来使得煤流量能够保持稳定和均衡。As mentioned above, the coal flow automatic control technology is an important technology for the intelligent operation of the bucket wheel machine. One of its important technical purposes is to control the stability and balance of the coal flow, that is, to keep the fluctuation of the coal flow within an acceptable range. Therefore, a coal flow control scheme is expected to keep the coal flow stable and balanced.
相应地，在本申请的技术方案中，通过对煤流量监测可得到实时的煤流量数据，进而通过所得到的煤流量数据来自适应地调整驱动电机的电流控制值，通过这样的方式，来保持煤流量的稳定和均衡。Correspondingly, in the technical solution of the present application, real-time coal flow data can be obtained by monitoring the coal flow, and then the current control value of the drive motor can be adaptively adjusted through the obtained coal flow data. In this way, the stability and balance of the coal flow can be maintained.
在上述基于驱动电机电流控制协同的煤流量控制系统100中，所述传感器监控模块110，用于获取预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值。具体地，在本申请的技术方案中，可通过电子皮带秤或激光扫描仪来得到所述多个预定时间点的煤流量值。这里，在利用所述激光扫描仪来采集所述煤流量值的过程中，其利用扫描煤流表面形状计算体积的方式，加上密度的估算,换算成流量，这种方式的优点是误差漂移少，相对稳定，不太需要经常校正。In the above-mentioned coal flow control system 100 based on driving motor current control coordination, the sensor monitoring module 110 is used to obtain coal flow values at multiple predetermined time points within a predetermined time period and the current values of the driving motor at the multiple predetermined time points. Specifically, in the technical solution of the present application, the coal flow values at the multiple predetermined time points can be obtained through an electronic belt scale or a laser scanner. Here, in the process of using the laser scanner to collect the coal flow value, it uses the method of scanning the surface shape of the coal flow to calculate the volume, plus the estimation of the density, and converts it into a flow rate. The advantage of this method is that the error drift is small, relatively stable, and does not require frequent corrections.
在上述基于驱动电机电流控制协同的煤流量控制系统100中，所述时序向量化模块120，用于将所述多个预定时间点的煤流量值按照时间维度排列为煤流量输入向量，且将所述多个预定时间点的驱动电机的电流值按照时间维度排列为电流输入向量。也就是，将所述煤流量值的时序离散分布和所述电流值的时序离散分布构造为结构化的所述煤流量输入向量和所述电流输入向量。In the coal flow control system 100 based on the coordination of drive motor current control, the time sequence vectorization module 120 is used to arrange the coal flow values at the multiple predetermined time points into a coal flow input vector according to the time dimension, and arrange the current values of the drive motors at the multiple predetermined time points into a current input vector according to the time dimension. That is, the time-series discrete distribution of the coal flow value and the time-series discrete distribution of the current value are constructed as the structured coal flow input vector and the current input vector.
在上述基于驱动电机电流控制协同的煤流量控制系统100中，所述煤流量特征提取模块130，用于将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量。也就是，在本申请的技术方案中，使用一维卷积神经网络模型对所述煤流量输入向量进行一维卷积编码以捕捉所述煤流量输入向量中局部时间窗口内煤流量离散分布的高维隐含关联模式特征以得到所述煤流量时序特征向量。特别地，所述第一卷积神经网络模型所使用的一维卷积核具有可学习的神经网络权重参数，其能够在训练过程中，基于训练目的进行参数自适应调整以满足训练目标。In the above-mentioned coal flow control system 100 based on driving motor current control coordination, the coal flow feature extraction module 130 is used to pass the coal flow input vector through the first convolutional neural network model using a one-dimensional convolution kernel to obtain a time series feature vector of coal flow. That is, in the technical solution of the present application, a one-dimensional convolutional neural network model is used to perform one-dimensional convolutional encoding on the coal flow input vector to capture the high-dimensional implicit correlation mode characteristics of the discrete distribution of coal flow in a local time window in the coal flow input vector to obtain the coal flow time series feature vector. In particular, the one-dimensional convolution kernel used in the first convolutional neural network model has learnable neural network weight parameters, which can be adaptively adjusted based on the training purpose to meet the training goal during the training process.
具体地，在本申请实施例中，所述煤流量特征提取模块130，进一步用于：使用所述第一卷积神经网络模型的各层在层的正向传递中对输入数据分别进行基于一维卷积核的卷积处理和非线性激活处理以由所述第一卷积神经网络模型的最后一层输出所述煤流量时序特征向量，其中，所述第一卷积神经网络模型的第一层的输入为所述煤流量输入向量。Specifically, in the embodiment of the present application, the coal flow feature extraction module 130 is further configured to: use each layer of the first convolutional neural network model to perform convolution processing based on a one-dimensional convolution kernel and nonlinear activation processing on the input data in the forward pass of the layer to output the coal flow time-series feature vector from the last layer of the first convolutional neural network model, wherein the input of the first layer of the first convolutional neural network model is the coal flow input vector.
在上述基于驱动电机电流控制协同的煤流量控制系统100中，所述电流提取模块140，用于将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量。同样地，在本申请的技术方案中，使用一维卷积神经网络模型对所述电流输入向量进行一维卷积编码以捕捉所述所述电流输入向量中局部时间窗口内电流值离散分布的高维隐含关联模式特征以得到所述电流时序特征向量。特别地，所述第二卷积神经网络模型所使用的一维卷积核具有可学习的神经网络权重参数，其能够在训练过程中，基于训练目的进行参数自适应调整以满足训练目标。In the above-mentioned coal flow control system 100 based on driving motor current control coordination, the current extraction module 140 is used to pass the current input vector through a second convolutional neural network model using a one-dimensional convolution kernel to obtain a current time-series feature vector. Similarly, in the technical solution of the present application, a one-dimensional convolutional neural network model is used to perform one-dimensional convolutional encoding on the current input vector to capture the high-dimensional implicit correlation mode characteristics of the discrete distribution of current values in the local time window in the current input vector to obtain the current time series feature vector. In particular, the one-dimensional convolution kernel used in the second convolutional neural network model has learnable neural network weight parameters, which can be adaptively adjusted based on the training purpose during the training process to meet the training goal.
具体地，在本申请实施例中，所述电流提取模块140，进一步用于：使用所述第二卷积神经网络模型的各层在层的正向传递中对输入数据分别进行基于一维卷积核的卷积处理和非线性激活处理以由所述第二卷积神经网络模型的最后一层输出所述电流时序特征向量，其中，所述第二卷积神经网络模型的第一层的输入为所述电流输入向量。Specifically, in the embodiment of the present application, the current extraction module 140 is further configured to: use each layer of the second convolutional neural network model to perform convolution processing based on a one-dimensional convolution kernel and nonlinear activation processing on the input data in the forward pass of the layer, so as to output the current sequence feature vector from the last layer of the second convolutional neural network model, wherein the input of the first layer of the second convolutional neural network model is the current input vector.
在上述基于驱动电机电流控制协同的煤流量控制系统100中，所述响应性估计模块150，用于基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵。特别地，在本申请的技术方案中，驱动电机的驱动电流变化会引起煤流量的波动，也就是说，在高维逻辑空间中，所述煤流量时序特征向量和所述电流时序特征向量之间存在响应性逻辑关联，如果能够利用上述逻辑关系，则显然能够提高所述驱动电机的驱动电流自适应控制的精准度。在本申请的技术方案中，基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵。In the above-mentioned coal flow control system 100 based on driving motor current control cooperation, the responsiveness estimation module 150 is used to calculate the responsiveness estimation of the coal flow time-series feature vector relative to the current time-series feature vector based on the Gaussian density map to obtain a classification feature matrix. In particular, in the technical solution of the present application, the change of the driving current of the driving motor will cause fluctuations in the coal flow, that is, in the high-dimensional logic space, there is a responsive logical relationship between the coal flow time-series feature vector and the current time-series feature vector. If the above logical relationship can be used, the accuracy of the drive current adaptive control of the driving motor can obviously be improved. In the technical solution of the present application, the estimate of the responsiveness of the coal flow time-series feature vector to the current time-series feature vector is calculated based on a Gaussian density map to obtain a classification feature matrix.
具体地，首先构造所述煤流量时序特征向量和所述电流时序特征向量的高斯密度图以得到第一高斯密度图和第二高斯密度图，其中，所述第一高斯密度图的均值向量为所述煤流量时序特征向量，所述第一高斯密度图的协方差矩阵中各个位置的值为所述煤流量时序特征向量中相应两个位置的特征值之间的方差，所述第二高斯密度图的均值向量为所述电流时序特征向量，所述第二高斯密度图的协方差矩阵中各个位置的值为所述电流时序特征向量中相应两个位置的特征值之间的方差。这里，构造所述煤流量时序特征向量和所述电流时序特征向量的高斯密度图的目的是对所述煤流量时序特征向量和所述电流时序特征向量进行基于后验分布的特征级数据增强以提高特征表示的精准度和后续响应性估计的精准度。接着，计算所述第一高斯密度图相对于所述第二高斯密度图的响应性估计以得到响应性高斯密度图，并通过对所述响应性高斯密度图进行高斯离散化以得到所述分类特征矩阵。Specifically, first construct the Gaussian density map of the coal flow time-series feature vector and the current time-series feature vector to obtain the first Gaussian density map and the second Gaussian density map, wherein the mean vector of the first Gaussian density map is the coal flow time-series feature vector, the value of each position in the covariance matrix of the first Gaussian density map is the variance between the eigenvalues of two corresponding positions in the coal flow time-series feature vector, the mean vector of the second Gaussian density map is the current time-series feature vector, and the covariance of the second Gaussian density map The value of each position in the matrix is the variance between the eigenvalues of corresponding two positions in the current time series eigenvector. Here, the purpose of constructing the Gaussian density map of the coal flow time-series feature vector and the current time-series feature vector is to perform feature-level data enhancement based on the posterior distribution on the coal flow time-series feature vector and the current time-series feature vector to improve the accuracy of feature representation and the accuracy of subsequent responsiveness estimation. Next, calculating the responsiveness estimate of the first Gaussian density map relative to the second Gaussian density map to obtain a responsive Gaussian density map, and performing Gaussian discretization on the responsive Gaussian density map to obtain the classification feature matrix.
图4为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统中响应性估计模块的框图。如图4所示，所述响应性估计模块150，包括：高斯密度图构造单元151，用于构造所述煤流量时序特征向量和所述电流时序特征向量的高斯密度图以得到第一高斯密度图和第二高斯密度图；响应单元152，用于以如下公式计算所述第一高斯密度图相对于所述第二高斯密度图的响应性估计以得到响应性高斯密度图，其中，所述公式为：Fig. 4 is a block diagram of a responsiveness estimation module in a coal flow control system based on driving motor current control cooperation according to an embodiment of the present application. As shown in FIG. 4 , the responsiveness estimation module 150 includes: a Gaussian density map construction unit 151, configured to construct a Gaussian density map of the coal flow time-series feature vector and the current time-series feature vector to obtain a first Gaussian density map and a second Gaussian density map; a response unit 152, used to calculate the responsiveness estimate of the first Gaussian density map relative to the second Gaussian density map by the following formula to obtain a responsive Gaussian density map, wherein the formula is:
其中Fa表示所述第一高斯密度图，Fb表示所述第二高斯密度图，Fc表示所述响应性高斯密度图，表示矩阵相乘；以及，高斯离散化单元153，用于对所述响应性高斯密度图进行高斯离散化以得到所述分类特征矩阵。Wherein Fa represents described first Gaussian density figure, Fb represents described second Gaussian density figure, Fc represents described responsiveness Gaussian density figure, represents matrix multiplication; and, a Gaussian discretization unit 153, configured to perform Gaussian discretization on the responsive Gaussian density map to obtain the classification feature matrix.
在上述基于驱动电机电流控制协同的煤流量控制系统100中，所述特征分布优化模块160，用于对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量。特别地，在本申请的技术方案中，在使用高斯密度图计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计得到所述分类特征矩阵时，由于在高斯离散化的过程中的随机性，会在所述分类特征矩阵内引入存在特殊的异常局部分布，这会导致所述分类特征矩阵在通过分类器进行分类时对单一分类结果的依赖性差，影响分类结果的准确性。In the coal flow control system 100 based on the coordination of drive motor current control, the feature distribution optimization module 160 is configured to optimize the local feature distribution of the classification feature matrix to obtain an optimized classification feature vector. In particular, in the technical solution of the present application, when the Gaussian density map is used to calculate the responsivity of the coal flow time-series feature vector relative to the current time-series feature vector to obtain the classification feature matrix, due to the randomness in the Gaussian discretization process, a special abnormal local distribution will be introduced into the classification feature matrix, which will lead to poor dependence of the classification feature matrix on a single classification result when it is classified by a classifier, affecting the accuracy of the classification result.
因此，对所述分类特征矩阵展开后得到的分类特征向量进行向量赋范的希尔伯特概率空间化，具体表示为：Therefore, the Hilbert probability space of vector normation is performed on the classification feature vector obtained after the classification feature matrix is expanded, specifically expressed as:
其中，V是所述分类特征矩阵按照行向量或列向量展开后得到的分类特征向量，‖V‖2表示所述分类特征向量的二范数，表示其平方，即所述分类特征向量自身的内积，vi是所述分类特征向量的第i个特征值，且vi′是所述优化分类特征向量的第i个特征值，exp(·)表示向量的指数运算，所述向量的指数运算表示计算以向量中各个位置的特征值为幂的自然指数函数值。Wherein, V is the classification feature vector obtained after the classification feature matrix is expanded according to the row vector or column vector, ‖ V ‖2 represents the two norms of the classification feature vector, Represents its square, i.e. the inner product of the classification feature vector itself, vi is the i-th eigenvalue of the classification feature vector, and vi ' is the i-th eigenvalue of the optimized classification feature vector, exp( ) represents the exponential operation of the vector, and the exponential operation of the vector represents the calculation of the natural exponential function value of the power of the eigenvalue of each position in the vector.
这里，所述向量赋范的希尔伯特概率空间化通过所述分类特征向量V自身的赋范在定义了向量内积的希尔伯特空间内进行所述分类特征向量V的概率性解释，并降低所述分类特征向量V的特殊的局部分布的类表达对整体希尔伯特空间拓扑的类表达的隐蔽扰动，由此提高所述分类特征向量V的特征分布收敛到预定分类概率的分类回归的鲁棒性，同时依靠度量诱导概率空间结构的建立来提升所述分类特征向量V的特征分布对分类结果的跨分类器的长程依赖。这样，提升了所述分类特征矩阵在通过分类器进行分类时对分类结果的依赖性，改进了分类结果的准确性。Here, the vector-normed Hilbert probability spatialization performs the probabilistic interpretation of the classification feature vector V in the Hilbert space that defines the vector inner product through the norming of the classification feature vector V itself, and reduces the hidden disturbance of the class expression of the special local distribution of the classification feature vector V to the class expression of the overall Hilbert space topology, thereby improving the robustness of the classification regression in which the feature distribution of the classification feature vector V converges to a predetermined classification probability. Long-range dependencies of classifiers. In this way, the dependence of the classification feature matrix on the classification result when it is classified by the classifier is improved, and the accuracy of the classification result is improved.
在上述基于驱动电机电流控制协同的煤流量控制系统100中，所述驱动电流控制结果170，用于将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小。也就是，使用所述分类器来确定所述分类特征矩阵所属的类概率标签，其中，所述类概率标签包括当前时间点的驱动电机的电流值应增大(第一标签)以及，当前时间点的驱动电机的电流值应减小(第二标签)。应注意到，所述分类器的类概率标签为驱动电机的驱动电流控制策略标签，因此，在得到所述分类结果后，能够基于所述分类结果对所述驱动电机的驱动电流进行自适应调整以使得煤流量能够保持稳定和均衡。In the coal flow control system 100 based on the coordination of driving motor current control, the driving current control result 170 is used to pass the optimized classification feature vector through a classifier to obtain a classification result, and the classification result is used to indicate that the current value of the driving motor at the current time point should be increased or decreased. That is, the classifier is used to determine the class probability label to which the classification feature matrix belongs, wherein the class probability label includes that the current value of the driving motor at the current time point should increase (the first label) and that the current value of the driving motor at the current time point should decrease (the second label). It should be noted that the class probability label of the classifier is the drive current control strategy label of the drive motor. Therefore, after the classification result is obtained, the drive current of the drive motor can be adaptively adjusted based on the classification result so that the coal flow can be kept stable and balanced.
具体地，在本申请实施例中，所述驱动电流控制结果170，包括：全连接编码单元，用于使用所述分类器的全连接层对所述优化分类特征向量进行全连接编码以得到编码分类特征向量；以及，分类结果生成单元，用于将所述编码分类特征向量输入所述分类器的Softmax分类函数以得到所述分类结果。Specifically, in the embodiment of the present application, the driving current control result 170 includes: a fully-connected encoding unit configured to use the fully-connected layer of the classifier to perform fully-connected encoding on the optimized classification feature vector to obtain a coded classification feature vector; and a classification result generating unit configured to input the coded classification feature vector into the Softmax classification function of the classifier to obtain the classification result.
综上，基于本申请实施例的基于驱动电机电流控制协同的煤流量控制系统100被阐明，其基于深度学习的人工智能监控技术，以通过分别捕捉煤流量数据和驱动电机的电流数据中局部时间窗口内数据离散分布的高维隐含关联模式特征，并利用两者之间存在的响应性逻辑关联关系来对所述驱动电机的驱动电流进行自适应调整以使得煤流量能够保持稳定和均衡。In summary, based on the embodiment of the present application, the coal flow control system 100 based on the coordination of drive motor current control is elucidated. Its artificial intelligence monitoring technology based on deep learning can capture the high-dimensional implicit correlation mode characteristics of the discrete distribution of data in the local time window in the coal flow data and the current data of the drive motor respectively, and use the responsive logical relationship between the two to adaptively adjust the drive current of the drive motor so that the coal flow can be kept stable and balanced.
如上所述，根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统100可以实现在各种终端设备中，例如用于基于驱动电机电流控制协同的煤流量控制的服务器等。在一个示例中，根据本申请实施例的基于驱动电机电流控制协同的煤流量控制系统100可以作为一个软件模块和/或硬件模块而集成到终端设备中。例如，该基于驱动电机电流控制协同的煤流量控制系统100可以是该终端设备的操作系统中的一个软件模块，或者可以是针对于该终端设备所开发的一个应用程序；当然，该基于驱动电机电流控制协同的煤流量控制系统100同样可以是该终端设备的众多硬件模块之一。As mentioned above, the coal flow control system 100 based on driving motor current control coordination according to the embodiment of the present application can be implemented in various terminal devices, such as a server for coal flow control based on driving motor current control coordination. In an example, the coal flow control system 100 based on driving motor current control coordination according to an embodiment of the present application may be integrated into a terminal device as a software module and/or a hardware module. For example, the coal flow control system 100 based on drive motor current control coordination can be a software module in the operating system of the terminal equipment, or can be an application program developed for the terminal equipment; of course, the coal flow control system 100 based on drive motor current control coordination can also be one of the many hardware modules of the terminal equipment.
替换地，在另一示例中，该基于驱动电机电流控制协同的煤流量控制系统100与该终端设备也可以是分立的设备，并且该基于驱动电机电流控制协同的煤流量控制系统100可以通过有线和/或无线网络连接到该终端设备，并且按照约定的数据格式来传输交互信息。Alternatively, in another example, the coal flow control system 100 based on driving motor current control cooperation and the terminal device may also be separate devices, and the coal flow control system 100 based on driving motor current control cooperation may be connected to the terminal device through a wired and/or wireless network, and transmit interactive information in accordance with an agreed data format.
示例性方法exemplary method
图5为根据本申请实施例的基于驱动电机电流控制协同的煤流量控制方法的流程图。如图5所示，根据本申请实施例的基于驱动电机电流控制协同的煤流量控制方法，包括：S110，获取预定时间段内多个预定时间点的煤流量值和所述多个预定时间点的驱动电机的电流值；S120，将所述多个预定时间点的煤流量值按照时间维度排列为煤流量输入向量，且将所述多个预定时间点的驱动电机的电流值按照时间维度排列为电流输入向量；S130，将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量；S140，将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量；S150，基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵；S160，对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；以及，S170，将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小。Fig. 5 is a flowchart of a coal flow control method based on driving motor current control coordination according to an embodiment of the present application. As shown in FIG. 5 , the coal flow control method based on the driving motor current control coordination according to the embodiment of the present application includes: S110, acquiring the coal flow values at multiple predetermined time points within a predetermined time period and the current values of the driving motors at the multiple predetermined time points; Convolving the neural network model to obtain the coal flow time series feature vector; S140, passing the current input vector through the second convolutional neural network model using a one-dimensional convolution kernel to obtain the current time series feature vector; S150, calculating the response estimation of the coal flow time series feature vector relative to the current time series feature vector based on the Gaussian density map to obtain a classification feature matrix; S160, performing feature local distribution optimization on the classification feature matrix to obtain an optimized classification feature vector; and, S170, passing the optimized classification feature vector through a classifier to obtain A classification result, the classification result is used to indicate that the current value of the driving motor at the current time point should be increased or decreased.
在一个示例中，在上述基于驱动电机电流控制协同的煤流量控制方法中，所述将所述煤流量输入向量通过使用一维卷积核的第一卷积神经网络模型以得到煤流量时序特征向量，包括：使用所述第一卷积神经网络模型的各层在层的正向传递中对输入数据分别进行基于一维卷积核的卷积处理和非线性激活处理以由所述第一卷积神经网络模型的最后一层输出所述煤流量时序特征向量，其中，所述第一卷积神经网络模型的第一层的输入为所述煤流量输入向量。In one example, in the above-mentioned coal flow control method based on drive motor current control coordination, the coal flow input vector is passed through a first convolutional neural network model using a one-dimensional convolution kernel to obtain a time-series feature vector of coal flow, comprising: using each layer of the first convolutional neural network model to perform convolution processing and nonlinear activation processing based on a one-dimensional convolution kernel on the input data in the forward pass of the layer, so that the last layer of the first convolutional neural network model outputs the coal flow time-series feature vector, wherein the first layer of the first convolutional neural network model The input of is the coal flow input vector.
在一个示例中，在上述基于驱动电机电流控制协同的煤流量控制方法中，所述将所述电流输入向量通过使用一维卷积核的第二卷积神经网络模型以得到电流时序特征向量，包括：使用所述第二卷积神经网络模型的各层在层的正向传递中对输入数据分别进行基于一维卷积核的卷积处理和非线性激活处理以由所述第二卷积神经网络模型的最后一层输出所述电流时序特征向量，其中，所述第二卷积神经网络模型的第一层的输入为所述电流输入向量。In one example, in the above-mentioned coal flow control method based on drive motor current control coordination, the said current input vector is passed through a second convolutional neural network model using a one-dimensional convolution kernel to obtain a current time-series feature vector, including: using each layer of the second convolutional neural network model to perform convolution processing and nonlinear activation processing based on a one-dimensional convolution kernel on the input data in the forward pass of the layer to output the current time-series feature vector from the last layer of the second convolutional neural network model, wherein the input of the first layer of the second convolutional neural network model is The current input vector.
在一个示例中，在上述基于驱动电机电流控制协同的煤流量控制方法中，所述基于高斯密度图来计算所述煤流量时序特征向量相对于所述电流时序特征向量的响应性估计以得到分类特征矩阵，包括：构造所述煤流量时序特征向量和所述电流时序特征向量的高斯密度图以得到第一高斯密度图和第二高斯密度图；以如下公式计算所述第一高斯密度图相对于所述第二高斯密度图的响应性估计以得到响应性高斯密度图，其中，所述公式为：In one example, in the above-mentioned coal flow control method based on drive motor current control coordination, calculating the responsiveness estimation of the coal flow time-series feature vector relative to the current time-series feature vector based on a Gaussian density map to obtain a classification feature matrix includes: constructing a Gaussian density map of the coal flow time-series feature vector and the current time-series feature vector to obtain a first Gaussian density map and a second Gaussian density map; calculating the responsiveness estimate of the first Gaussian density map relative to the second Gaussian density map to obtain a responsive Gaussian density map according to the following formula, wherein, The formula is:
其中Fa表示所述第一高斯密度图，Fb表示所述第二高斯密度图，Fc表示所述响应性高斯密度图，表示矩阵相乘；以及，对所述响应性高斯密度图进行高斯离散化以得到所述分类特征矩阵。Wherein Fa represents described first Gaussian density figure, Fb represents described second Gaussian density figure, Fc represents described responsiveness Gaussian density figure, representing matrix multiplication; and performing Gaussian discretization on the responsive Gaussian density map to obtain the classification feature matrix.
在一个示例中，在上述基于驱动电机电流控制协同的煤流量控制方法中，所述对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量，包括：以如下公式对所述分类特征矩阵进行特征局部分布优化以得到优化分类特征向量；其中，所述公式为：In one example, in the above-mentioned coal flow control method based on the coordination of drive motor current control, the optimization of the feature local distribution of the classification feature matrix to obtain the optimized classification feature vector includes: performing feature local distribution optimization on the classification feature matrix with the following formula to obtain the optimized classification feature vector; wherein, the formula is:
其中，V是所述分类特征矩阵按照行向量或列向量展开后得到的分类特征向量，‖V‖2表示所述分类特征向量的二范数，表示其平方，即所述分类特征向量自身的内积，vi是所述分类特征向量的第i个特征值，且vi′是所述优化分类特征向量的第i个特征值，exp(·)表示向量的指数运算，所述向量的指数运算表示计算以向量中各个位置的特征值为幂的自然指数函数值。Wherein, V is the classification feature vector obtained after the classification feature matrix is expanded according to the row vector or column vector, ‖ V ‖2 represents the two norms of the classification feature vector, Represents its square, i.e. the inner product of the classification feature vector itself, vi is the i-th eigenvalue of the classification feature vector, and vi ' is the i-th eigenvalue of the optimized classification feature vector, exp( ) represents the exponential operation of the vector, and the exponential operation of the vector represents the calculation of the natural exponential function value of the power of the eigenvalue of each position in the vector.
在一个示例中，在上述基于驱动电机电流控制协同的煤流量控制方法中，所述将所述优化分类特征向量通过分类器以得到分类结果，所述分类结果用于表示当前时间点的驱动电机的电流值应增大或应减小，包括：使用所述分类器的全连接层对所述优化分类特征向量进行全连接编码以得到编码分类特征向量；以及，将所述编码分类特征向量输入所述分类器的Softmax分类函数以得到所述分类结果。In one example, in the above-mentioned coal flow control method based on the coordination of drive motor current control, passing the optimized classification feature vector through a classifier to obtain a classification result, the classification result being used to indicate that the current value of the drive motor at the current time point should increase or decrease, includes: using the fully connected layer of the classifier to perform fully-connected encoding on the optimized classification feature vector to obtain an encoded classification feature vector; and inputting the encoded classification feature vector into the Softmax classification function of the classifier to obtain the classification result.
综上，本申请实施例的基于驱动电机电流控制协同的煤流量控制方法被阐明，其基于深度学习的人工智能监控技术，以通过分别捕捉煤流量数据和驱动电机的电流数据中局部时间窗口内数据离散分布的高维隐含关联模式特征，并利用两者之间存在的响应性逻辑关联关系来对所述驱动电机的驱动电流进行自适应调整以使得煤流量能够保持稳定和均衡。To sum up, the coal flow control method based on the coordination of drive motor current control in the embodiment of the present application is clarified. It is based on the artificial intelligence monitoring technology of deep learning to capture the high-dimensional implicit correlation mode characteristics of the discrete distribution of data in the local time window in the coal flow data and the current data of the drive motor respectively, and use the responsive logical relationship between the two to adaptively adjust the drive current of the drive motor so that the coal flow can be kept stable and balanced.
示例性电子设备Exemplary electronic device
下面，参考图6来描述根据本申请实施例的电子设备。图6为根据本申请实施例的电子设备的框图。如图6所示，电子设备10包括一个或多个处理器11和存储器12。Next, an electronic device according to an embodiment of the present application will be described with reference to FIG. 6 . FIG. 6 is a block diagram of an electronic device according to an embodiment of the present application. As shown in FIG. 6 , an electronic device 10 includes one or more processors 11 and a memory 12 .
处理器11可以是中央处理单元(CPU)或者具有数据处理能力和/或指令执行能力的其他形式的处理单元，并且可以控制电子设备10中的其他组件以执行期望的功能。Processor 11 may be a central processing unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in electronic device 10 to perform desired functions.
存储器12可以包括一个或多个计算机程序产品，所述计算机程序产品可以包括各种形式的计算机可读存储介质，例如易失性存储器和/或非易失性存储器。所述易失性存储器例如可以包括随机存取存储器(RAM)和/或高速缓冲存储器(cache)等。所述非易失性存储器例如可以包括只读存储器(ROM)、硬盘、闪存等。在所述计算机可读存储介质上可以存储一个或多个计算机程序指令，处理器11可以运行所述程序指令，以实现上文所述的本申请的各个实施例的基于驱动电机电流控制协同的煤流量控制方法中的功能以及/或者其他期望的功能。在所述计算机可读存储介质中还可以存储诸如煤流量值和驱动电机的电流值等各种内容。Memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and/or cache memory (cache). The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, and the like. One or more computer program instructions can be stored on the computer-readable storage medium, and the processor 11 can execute the program instructions to realize the functions and/or other desired functions in the coal flow control method based on the driving motor current control coordination of the various embodiments of the application described above. Various contents such as a coal flow value and a current value of a driving motor may also be stored in the computer-readable storage medium.
在一个示例中，电子设备10还可以包括：输入装置13和输出装置14，这些组件通过总线系统和/或其他形式的连接机构(未示出)互连。In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected through a bus system and/or other forms of connection mechanisms (not shown).
该输入装置13可以包括例如键盘、鼠标等等。The input device 13 may include, for example, a keyboard, a mouse, and the like.
该输出装置14可以向外部输出各种信息，包括分类结果等。该输出装置14可以包括例如显示器、扬声器、打印机、以及通信网络及其所连接的远程输出设备等等。The output device 14 can output various information to the outside, including classification results and the like. The output device 14 may include, for example, a display, a speaker, a printer, a communication network and its connected remote output devices, and the like.
当然，为了简化，图6中仅示出了该电子设备10中与本申请有关的组件中的一些，省略了诸如总线、输入/输出接口等等的组件。除此之外，根据具体应用情况，电子设备10还可以包括任何其他适当的组件。Of course, for the sake of simplicity, only some of the components related to the present application in the electronic device 10 are shown in FIG. 6 , and components such as bus, input/output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 10 may also include any other suitable components.
示例性计算机程序产品和计算机可读存储介质Exemplary computer program product and computer readable storage medium
除了上述方法和设备以外，本申请的实施例还可以是计算机程序产品，其包括计算机程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行本说明书上述“示例性方法”部分中描述的根据本申请各种实施例的基于驱动电机电流控制协同的煤流量控制方法中的功能中的步骤。In addition to the above-mentioned methods and devices, embodiments of the present application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to execute the steps in the functions of the coal flow control method based on drive motor current control coordination according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.
所述计算机程序产品可以以一种或多种程序设计语言的任意组合来编写用于执行本申请实施例操作的程序代码，所述程序设计语言包括面向对象的程序设计语言，诸如Java、C++等，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。The computer program product can be written in any combination of one or more programming languages for executing the program codes for the operations of the embodiments of the present application, and the programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as "C" language or similar programming languages. The program code may execute entirely on the user computing device, partly on the user device, as a stand-alone software package, partly on the user computing device and partly on a remote computing device, or entirely on the remote computing device or server.
此外，本申请的实施例还可以是计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令在被处理器运行时使得所述处理器执行本说明书上述“示例性方法”部分中描述的根据本申请各种实施例的基于驱动电机电流控制协同的煤流量控制方法中的功能中的步骤。In addition, the embodiment of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by the processor, the processor executes the steps in the functions of the coal flow control method based on the driving motor current control cooperation described in the above-mentioned "Exemplary Method" section of this specification according to various embodiments of the present application.
所述计算机可读存储介质可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以包括但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof, for example. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
以上结合具体实施例描述了本申请的基本原理，但是，需要指出的是，在本申请中提及的优点、优势、效果等仅是示例而非限制，不能认为这些优点、优势、效果等是本申请的各个实施例必须具备的。另外，上述公开的具体细节仅是为了示例的作用和便于理解的作用，而非限制，上述细节并不限制本申请为必须采用上述具体的细节来实现。The basic principles of the present application have been described above in conjunction with specific embodiments, but it should be pointed out that the advantages, advantages, effects, etc. mentioned in the application are only examples and not limitations, and it cannot be considered that these advantages, advantages, effects, etc. must be possessed by each embodiment of the application. In addition, the specific details disclosed above are only for the purpose of illustration and understanding, rather than limitation, and the above details do not limit the application to be implemented by using the above specific details.
本申请中涉及的器件、装置、设备、系统的方框图仅作为例示性的例子并且不意图要求或暗示必须按照方框图示出的方式进行连接、布置、配置。如本领域技术人员将认识到的，可以按任意方式连接、布置、配置这些器件、装置、设备、系统。诸如“包括”、“包含”、“具有”等等的词语是开放性词汇，指“包括但不限于”，且可与其互换使用。这里所使用的词汇“或”和“和”指词汇“和/或”，且可与其互换使用，除非上下文明确指示不是如此。这里所使用的词汇“诸如”指词组“诸如但不限于”，且可与其互换使用。The block diagrams of devices, devices, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, devices, systems may be connected, arranged, configured in any manner. Words such as "including", "comprising", "having" and the like are open-ended words meaning "including but not limited to" and may be used interchangeably therewith. As used herein, the words "or" and "and" refer to the word "and/or" and are used interchangeably therewith, unless the context clearly dictates otherwise. As used herein, the word "such as" refers to the phrase "such as but not limited to" and can be used interchangeably therewith.
还需要指出的是，在本申请的装置、设备和方法中，各部件或各步骤是可以分解和/或重新组合的。这些分解和/或重新组合应视为本申请的等效方案。It should also be pointed out that in the devices, equipment and methods of the present application, each component or each step can be decomposed and/or reassembled. These decompositions and/or recombinations should be considered equivalents of this application.
提供所公开的方面的以上描述以使本领域的任何技术人员能够做出或者使用本申请。对这些方面的各种修改对于本领域技术人员而言是非常显而易见的，并且在此定义的一般原理可以应用于其他方面而不脱离本申请的范围。因此，本申请不意图被限制到在此示出的方面，而是按照与在此公开的原理和新颖的特征一致的最宽范围。The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
为了例示和描述的目的已经给出了以上描述。此外，此描述不意图将本申请的实施例限制到在此公开的形式。尽管以上已经讨论了多个示例方面和实施例，但是本领域技术人员将认识到其某些变型、修改、改变、添加和子组合。The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310195957.5ACN116483132A (en) | 2023-03-03 | 2023-03-03 | Coal flow control system and method based on drive motor current control coordination |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310195957.5ACN116483132A (en) | 2023-03-03 | 2023-03-03 | Coal flow control system and method based on drive motor current control coordination |
| Publication Number | Publication Date |
|---|---|
| CN116483132Atrue CN116483132A (en) | 2023-07-25 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310195957.5APendingCN116483132A (en) | 2023-03-03 | 2023-03-03 | Coal flow control system and method based on drive motor current control coordination |
| Country | Link |
|---|---|
| CN (1) | CN116483132A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117134958A (en)* | 2023-08-23 | 2023-11-28 | 台州市云谷信息技术有限公司 | Information processing method and system for network technology service |
| CN118134356A (en)* | 2024-04-02 | 2024-06-04 | 石家庄冀染化工科技有限公司 | Intelligent distribution system and method for dyeing machine auxiliaries |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009080282A2 (en)* | 2007-12-20 | 2009-07-02 | Alstom Technology Ltd | Optimizing the operation of a power plant |
| US20090238234A1 (en)* | 2006-09-18 | 2009-09-24 | Manfred Schubert | Method for operating a melt-metallurgic furnace, and furnace |
| CN111897376A (en)* | 2020-06-10 | 2020-11-06 | 常州联力自动化科技有限公司 | Automatic speed regulation method for conveyor and coal mining machine without coal flow sensor |
| RU2747136C1 (en)* | 2020-10-26 | 2021-04-28 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Тульский государственный университет" (ТулГУ) | Automatic load control device for a coal miner |
| WO2022221719A2 (en)* | 2021-04-16 | 2022-10-20 | Strong Force Vcn Portfolio 2019, Llc | Systems, methods, kits, and apparatuses for digital product network systems and biology-based value chain networks |
| CN115526736A (en)* | 2022-08-08 | 2022-12-27 | 北京华能新锐控制技术有限公司 | Automatic regulation and control system and method for peak valley of generated energy of fan |
| CN115653589A (en)* | 2022-11-11 | 2023-01-31 | 陕西煤业化工集团孙家岔龙华矿业有限公司 | Method, system, equipment and medium for cooperation of coal mining machine and transportation equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090238234A1 (en)* | 2006-09-18 | 2009-09-24 | Manfred Schubert | Method for operating a melt-metallurgic furnace, and furnace |
| WO2009080282A2 (en)* | 2007-12-20 | 2009-07-02 | Alstom Technology Ltd | Optimizing the operation of a power plant |
| CN111897376A (en)* | 2020-06-10 | 2020-11-06 | 常州联力自动化科技有限公司 | Automatic speed regulation method for conveyor and coal mining machine without coal flow sensor |
| RU2747136C1 (en)* | 2020-10-26 | 2021-04-28 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Тульский государственный университет" (ТулГУ) | Automatic load control device for a coal miner |
| WO2022221719A2 (en)* | 2021-04-16 | 2022-10-20 | Strong Force Vcn Portfolio 2019, Llc | Systems, methods, kits, and apparatuses for digital product network systems and biology-based value chain networks |
| CN115526736A (en)* | 2022-08-08 | 2022-12-27 | 北京华能新锐控制技术有限公司 | Automatic regulation and control system and method for peak valley of generated energy of fan |
| CN115653589A (en)* | 2022-11-11 | 2023-01-31 | 陕西煤业化工集团孙家岔龙华矿业有限公司 | Method, system, equipment and medium for cooperation of coal mining machine and transportation equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117134958A (en)* | 2023-08-23 | 2023-11-28 | 台州市云谷信息技术有限公司 | Information processing method and system for network technology service |
| CN118134356A (en)* | 2024-04-02 | 2024-06-04 | 石家庄冀染化工科技有限公司 | Intelligent distribution system and method for dyeing machine auxiliaries |
| CN118134356B (en)* | 2024-04-02 | 2025-03-21 | 江西华远针织有限公司 | Intelligent distribution system and method for dyeing machine auxiliaries |
| Publication | Publication Date | Title |
|---|---|---|
| US20230116117A1 (en) | Federated learning method and apparatus, and chip | |
| CN111414987B (en) | Training method and training device of neural network and electronic equipment | |
| CN116483132A (en) | Coal flow control system and method based on drive motor current control coordination | |
| Zadrozny | Reducing multiclass to binary by coupling probability estimates | |
| JP7474446B2 (en) | Projection Layer of Neural Network Suitable for Multi-Label Prediction | |
| CN110799995A (en) | Data recognizer training method, data recognizer training device, program, and training method | |
| CN116052050A (en) | Intelligent production system and method for detergent | |
| CN116383714A (en) | Equipment protection system for bucket wheel machine and method thereof | |
| US20220019900A1 (en) | Method and system for learning perturbation sets in machine learning | |
| US12136259B2 (en) | Method and apparatus for detecting face, computer device and computer-readable storage medium | |
| CN115759658B (en) | Enterprise energy consumption data management system suitable for smart city | |
| CN116038854A (en) | Molding control system and method for door processing | |
| CN117688974B (en) | Knowledge graph-based generation type large model modeling method, system and equipment | |
| CN110111365B (en) | Training method and device based on deep learning and target tracking method and device | |
| CN115699029A (en) | Knowledge distillation using back-propagation knowledge in neural networks | |
| Du et al. | Exploring Kernel Machines and Support Vector Machines: Principles, Techniques, and Future Directions. | |
| CN116247824A (en) | Control method and system for power equipment | |
| CN115723287A (en) | Production equipment for controlling polyurethane foaming based on temperature | |
| CN116151545A (en) | Multi-wind motor group power control optimization system | |
| CN116434117A (en) | Preparation method of composite polyacrylamide oil displacement agent | |
| US20230185998A1 (en) | System and method for ai-assisted system design | |
| CN115984745A (en) | Moisture control method for black garlic fermentation | |
| CN115495804A (en) | Auxiliary system for industrial design and method thereof | |
| JP7626132B2 (en) | Learning device, generation method, inference device, inference method, and program | |
| CN118779435A (en) | Natural language knowledge extraction method and device based on large and small model collaboration |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |