技术领域Technical field
本公开涉及电机故障分析技术领域，具体涉及一种电机故障分析方法。The present disclosure relates to the technical field of motor fault analysis, and in particular to a motor fault analysis method.
背景技术Background technique
在工业生产中，设备故障经常发生，设备发生故障后严重的影响了日常的生产工作，因此，如何有效的分析故障原因以及预测故障，越来越被人们关注。In industrial production, equipment failures often occur, and equipment failures seriously affect daily production work. Therefore, how to effectively analyze the causes of failures and predict failures has attracted more and more attention.
故障模式影响及危害性分析(Failure Mode Effects and CriticalityAnalysis，FMECA)，是针对产品所有可能的故障，并根据对故障模式的分析，确定每种故障模式对产品工作的影响，找出单点故障，并按故障模式的严重度及其发生概率确定其危害性。所谓单点故障指的是引起产品故障的，且没有冗余或替代的工作程序作为补救的局部故障。FMECA包括故障模式及影响分析和危害性分析。Failure Mode Effects and Criticality Analysis (FMECA) is aimed at all possible failures of the product, and based on the analysis of the failure modes, determines the impact of each failure mode on the product's work, and identifies single points of failure. And determine the hazard according to the severity of the failure mode and its probability of occurrence. The so-called single point of failure refers to a local failure that causes product failure and has no redundant or alternative work procedures as a remedy. FMECA includes failure mode and effects analysis and hazard analysis.
但是，目前的FMECA分析方法存在以下问题：多为检查(遏制)而不是预防(控制)；其中的风险系数(Risk Priority Number，RPN)为严重度S、频度O、探测度D三者的乘积，计算方法缺少科学性；S、O、D为主观得分，没有可定义的距离度量。However, the current FMECA analysis method has the following problems: it is mostly inspection (containment) rather than prevention (control); the risk coefficient (Risk Priority Number, RPN) is the combination of severity S, frequency O, and detection D. Product, the calculation method lacks scientificity; S, O, and D are subjective scores, and there is no definable distance measure.
需要说明的是，在上述背景技术部分公开的信息仅用于加强对本公开的背景的理解，因此可以包括不构成对本领域普通技术人员已知的现有技术的信息。It should be noted that the information disclosed in the above background section is only used to enhance understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to those of ordinary skill in the art.
发明内容Contents of the invention
本公开的目的在于提供一种故障分析方法、装置、存储介质及计算机系统，进而至少在一定程度上克服由于相关技术的限制和缺陷而导致的多为检查(遏制)而不是预防(控制)；其中的RPN为严重度S、频度O、探测度D三者的乘积，计算方法缺少科学性；S、O、D主观得分，没有可定义的距离度量的情况。The purpose of this disclosure is to provide a fault analysis method, device, storage medium and computer system, thereby overcoming, at least to a certain extent, the limitations and defects of related technologies that lead to inspection (containment) rather than prevention (control); The RPN is the product of severity S, frequency O, and detection D, and the calculation method lacks scientificity; S, O, and D are subjective scores, and there is no definable distance measurement.
本公开的其他特性和优点将通过下面的详细描述变得显然，或部分地通过本公开的实践而习得。Additional features and advantages of the disclosure will be apparent from the following detailed description, or, in part, may be learned by practice of the disclosure.
本公开提供了一种电机故障分析方法，包括：在电机本体上设置有传感器，传感器实时采集电机运行参数，定位和识别电机故障模式；The present disclosure provides a motor fault analysis method, which includes: a sensor is provided on the motor body, and the sensor collects the motor operating parameters in real time, and locates and identifies the motor fault mode;
在所述电机本体的底部设置有振动传感器，所述振动传感器用于检测所述电机本体在运行过程中的振动数据；A vibration sensor is provided at the bottom of the motor body, and the vibration sensor is used to detect vibration data of the motor body during operation;
在所述电机本体上设置有用于检测所述电机本体的转轴转速数据的速度传感器，以及设置有用于检测电机本体转动扭矩数据的扭矩传感器，以及用于检测电机本体温度数据的温度传感器；The motor body is provided with a speed sensor for detecting the rotational speed data of the rotating shaft of the motor body, a torque sensor for detecting the rotational torque data of the motor body, and a temperature sensor for detecting the temperature data of the motor body;
在所述电机本体上还设置有用于检测电机输入电流稳定性数据的电流传感器；The motor body is also provided with a current sensor for detecting motor input current stability data;
所述故障分析装置用于接收并基于所述振动数据、所述转速数据、所述转动扭矩数据、所述温度数据、所述电流稳定性数据分析所述电机故障的类型。The fault analysis device is configured to receive and analyze the type of motor fault based on the vibration data, the rotation speed data, the rotation torque data, the temperature data, and the current stability data.
可选的，确定导致的电机故障的多个变量；Optionally, identify multiple variables that contributed to the motor failure;
利用智能解耦算法将多个变量系统转化为多个独立的单变量系统映射；Use intelligent decoupling algorithms to transform multiple variable systems into multiple independent single-variable system mappings;
系统解耦成若干个子系统，再进行独立分析和诊断，实现单一故障或多故障下的失效原因追溯。The system is decoupled into several subsystems and then independently analyzed and diagnosed to achieve traceability of failure causes under single or multiple faults.
可选的，包括：Optional, including:
收集设备的历史故障数据和运行数据；其中，所述运行数据包括振动数据、转速数据、转动扭矩数据、温度数据、电流稳定性数据；Collect historical fault data and operating data of the equipment; wherein the operating data includes vibration data, rotational speed data, rotational torque data, temperature data, and current stability data;
用神经网络算法训练传感器信号和失效模式之间的关系，进而根据采集信号和训练模型预测失效模式；Use neural network algorithms to train the relationship between sensor signals and failure modes, and then predict failure modes based on collected signals and training models;
其中，步骤收集设备的历史故障数据和运行数据包括：Among them, the steps to collect historical fault data and operating data of the equipment include:
收集设备的历史故障数据和运行数据，包括设备的各种传感器数据、操作记录；Collect historical fault data and operating data of the equipment, including various sensor data and operation records of the equipment;
步骤用神经网络算法训练传感器信号和失效模式之间的关系，进而根据采集信号和训练模型预测失效模式包括：The steps use a neural network algorithm to train the relationship between sensor signals and failure modes, and then predict the failure mode based on the collected signals and training model, including:
对收集的数据进行清洗和预处理，包括去除异常值、处理缺失值、标准化数据；Clean and preprocess the collected data, including removing outliers, processing missing values, and standardizing data;
对预处理后的数据进行特征提取；并利用提取的特征以及历史数据对神经网络模型进行训练，得到已训练的训练模型；Extract features from the preprocessed data; and use the extracted features and historical data to train the neural network model to obtain a trained training model;
将传感器检测到的电机运行参数输入至已训练的训练模型中，对电机本体的故障进行预测，进而定位和识别电机故障模式。Input the motor operating parameters detected by the sensor into the trained training model to predict the fault of the motor body, and then locate and identify the motor fault mode.
可选的，所述方法还包括：Optionally, the method also includes:
基于定位和识别电机故障模式，制定对所述电机本体的维护策略。Based on locating and identifying the motor failure mode, a maintenance strategy for the motor body is formulated.
可选的，电机本体停转状态下，配置目标检测策略；其中所述目标检测策略包括：Optionally, configure a target detection strategy when the motor body is stopped; the target detection strategy includes:
线路检测、电机过载检测、电机本体的机构卡死检测、电机转轴损坏检测、电机绕组烧毁检测、电机电容故障检测、控制电路故障检测。Line detection, motor overload detection, motor body mechanism stuck detection, motor shaft damage detection, motor winding burnt detection, motor capacitor fault detection, control circuit fault detection.
可选的，获取设备的历史故障数据，采用统计聚类算法分析所述历史数据，建立严酷度矩阵，确定故障模式的严酷度等级包括：Optionally, obtain historical fault data of the equipment, use a statistical clustering algorithm to analyze the historical data, establish a severity matrix, and determine the severity level of the failure mode, including:
基于所述严酷度等级的严重程度，为每一个所述严酷度等级配置权重；assigning a weight to each of said severity levels based on the severity of said severity levels;
基于每种故障类型发生的频次，表征某种故障模式发生的可能性；Based on the frequency of occurrence of each fault type, it represents the possibility of a certain fault mode occurring;
通过配置有权重的严酷度等级以及故障类型发生的频次，构建严酷度矩阵，基于严酷度矩阵确定故障模式的严酷度等级；By configuring the weighted severity level and the frequency of occurrence of the fault type, a severity matrix is constructed, and the severity level of the fault mode is determined based on the severity matrix;
根据故障模式的严酷度等级，为各同等级的故障模式配置相应的处理措施。According to the severity level of the failure mode, configure corresponding processing measures for each level of failure mode.
可选的，结合风险优先系数法和危害性矩阵法进行故障模式的危害性分析；Optionally, combine the risk priority coefficient method and the hazard matrix method to conduct hazard analysis of the failure mode;
RPN＝ESR×OPRRPN＝ESR×OPR
PRN等于该故障模式的严酷度等级ESR和故障模式的发生概率等级OPR的乘积，基于RPN值的高低，确定故障的危害性，RPN值越高，危害性越大。PRN is equal to the product of the severity level ESR of the failure mode and the occurrence probability level OPR of the failure mode. Based on the RPN value, the hazard of the fault is determined. The higher the RPN value, the greater the hazard.
可选的，确定设备原始故障类型的概率密度函数和平均故障时间MTBF。Optionally, determine the probability density function and mean time to failure MTBF of the original fault type of the equipment.
得到原故障概率密度函数的原函数，采样抽样统计的方法计算基本修复后故障概率密度函数；The original function of the original fault probability density function is obtained, and the fault probability density function after basic repair is calculated using sampling statistics;
计算第一次修复后的平均寿命和标准差，第二次，直到第n次......；Calculate the average life and standard deviation after the first repair, the second time, until the nth time...;
确定设备在实际运行情况时发生的第一次故障时间，设备继续运行的年限Y；通过将故障成本乘以故障发生的概率来估计故障的预期维修成本；其中，故障成本指在故障发生后造成的经济损失，故障维修成本与故障次数有关。Determine the time of the first failure of the equipment in actual operation and the number of years the equipment continues to operate Y; estimate the expected maintenance cost of the failure by multiplying the failure cost by the probability of the failure; where the failure cost refers to the damage caused after the failure occurs Economic losses, failure repair costs are related to the number of failures.
本公开的在电机本体上设置有传感器，传感器实时采集电机运行参数，定位和识别电机故障模式；在所述电机本体的底部设置有振动传感器，所述振动传感器用于检测所述电机本体在运行过程中的振动数据；在所述电机本体上设置有用于检测所述电机本体的转轴转速数据的速度传感器，以及设置有用于检测电机本体转动扭矩数据的扭矩传感器，以及用于检测电机本体温度数据的温度传感器；在所述电机本体上还设置有用于检测电机输入电流稳定性数据的电流传感器；所述故障分析装置用于接收并基于所述振动数据、所述转速数据、所述转动扭矩数据、所述温度数据、所述电流稳定性数据分析所述电机故障的类型。通过将标准值输入到已训练的故障预测模型中，对故障类型以及故障类型的风险等级进行了预测，避免主观统计计算，不仅可以实现预测的功能，还能有效的规避主观统计计算的不科学性，可见，本申请的方案可以在一定程度上克服由于相关技术的限制和缺陷而导致的多为检查(遏制)而不是预防(控制)；其中的RPN为严重度S、频度O、探测度D三者的乘积，计算方法缺少科学性；S、O、D主观得分，没有可定义的距离度量的情况。In the present disclosure, a sensor is provided on the motor body, and the sensor collects the operating parameters of the motor in real time, and locates and identifies the motor failure mode; a vibration sensor is provided at the bottom of the motor body, and the vibration sensor is used to detect when the motor body is running. Vibration data during the process; the motor body is provided with a speed sensor for detecting the rotational speed data of the rotating shaft of the motor body, a torque sensor for detecting the rotational torque data of the motor body, and a torque sensor for detecting the temperature data of the motor body. temperature sensor; the motor body is also provided with a current sensor for detecting motor input current stability data; the fault analysis device is used to receive and base on the vibration data, the rotational speed data, and the rotational torque data , the temperature data and the current stability data analyze the type of motor failure. By inputting the standard values into the trained fault prediction model, the fault type and the risk level of the fault type are predicted to avoid subjective statistical calculations. Not only can the prediction function be realized, but also the unscientific subjective statistical calculations can be effectively avoided. It can be seen that the solution of this application can overcome to a certain extent the limitations and defects of related technologies that lead to inspection (containment) rather than prevention (control); where RPN is severity S, frequency O, detection The product of the three degrees D, the calculation method lacks scientificity; the subjective scores of S, O, and D have no definable distance measurement.
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and do not limit the present disclosure.
附图说明Description of the drawings
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。显而易见地，下面描述中的附图仅仅是本公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.
图1示意性示出本公开示例性实施例中一种电机故障分析装置的结构示意图；Figure 1 schematically shows a structural diagram of a motor fault analysis device in an exemplary embodiment of the present disclosure;
图2示意性示出本公开示例性实施例中一种开环前馈解耦算法的架构图；Figure 2 schematically shows an architectural diagram of an open-loop feedforward decoupling algorithm in an exemplary embodiment of the present disclosure;
图3示意性示出本公开示例性实施例中一种危害性矩阵示意图。Figure 3 schematically shows a hazard matrix diagram in an exemplary embodiment of the present disclosure.
图4示意性示出本公开示例性实施例中一种故障预测模型的训练示意图。FIG. 4 schematically shows a training diagram of a fault prediction model in an exemplary embodiment of the present disclosure.
图5示意性示出本公开示例性实施例中一种电机故障分析方法流程图。Figure 5 schematically shows a flow chart of a motor fault analysis method in an exemplary embodiment of the present disclosure.
具体实施方式Detailed ways
现在将参考附图更全面地描述示例实施方式。然而，示例实施方式能够以多种形式实施，且不应被理解为限于在此阐述的范例；相反，提供这些实施方式使得本公开将更加全面和完整，并将示例实施方式的构思全面地传达给本领域的技术人员。所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施方式中。Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concepts of the example embodiments. To those skilled in the art. The described features, structures or characteristics may be combined in any suitable manner in one or more embodiments.
此外，附图仅为本公开的示意性图解，并非一定是按比例绘制。图中相同的附图标记表示相同或类似的部分，因而将省略对它们的重复描述。附图中所示的一些方框图是功能实体，不一定必须与物理或逻辑上独立的实体相对应。可以采用软件形式来实现这些功能实体，或在一个或多个硬件模块或集成电路中实现这些功能实体，或在不同网络和/或处理器装置和/或微控制器装置中实现这些功能实体。Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor devices and/or microcontroller devices.
附图中所示的方框图仅仅是功能实体，不一定必须与物理上独立的实体相对应。即，可以采用软件形式来实现这些功能实体，或在一个或多个硬件模块或集成电路中实现这些功能实体，或在不同网络和/或处理器装置和/或微控制器装置中实现这些功能实体。The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor devices and/or microcontroller devices. entity.
附图中所示的流程图仅是示例性说明，不是必须包括所有的内容和操作/步骤，也不是必须按所描述的顺序执行。例如，有的操作/步骤还可以分解，而有的操作/步骤可以合并或部分合并，因此实际执行的顺序有可能根据实际情况改变。The flowcharts shown in the drawings are only illustrative, and do not necessarily include all contents and operations/steps, nor must they be performed in the order described. For example, some operations/steps can be decomposed, and some operations/steps can be merged or partially merged, so the actual order of execution may change according to the actual situation.
本公开提供了一种电机故障分析装置，参见图1所示，包括：电机本体、故障分析装置；在所述电机本体的底部设置有振动传感器，所述振动传感器用于检测所述电机本体在运行过程中的振动数据；在所述电机本体上设置有用于检测所述电机本体的转轴转速数据的速度传感器，以及设置有用于检测电机本体转动扭矩数据的扭矩传感器，以及用于检测电机本体温度数据的温度传感器；在所述电机本体上还设置有用于检测电机输入电流稳定性数据的电流传感器；所述故障分析装置用于接收并基于所述振动数据、所述转速数据、所述转动扭矩数据、所述温度数据、所述电流稳定性数据分析所述电机故障的类型。The present disclosure provides a motor fault analysis device, as shown in Figure 1, which includes: a motor body and a fault analysis device; a vibration sensor is provided at the bottom of the motor body, and the vibration sensor is used to detect when the motor body Vibration data during operation; the motor body is provided with a speed sensor for detecting the rotational speed data of the rotating shaft of the motor body, a torque sensor for detecting the rotational torque data of the motor body, and a temperature sensor for detecting the temperature of the motor body The temperature sensor of the data; the motor body is also provided with a current sensor for detecting the motor input current stability data; the fault analysis device is used to receive and based on the vibration data, the rotational speed data, the rotation torque The data, the temperature data, and the current stability data analyze the type of motor failure.
本示例实施方式中，本公开提供了一种电机故障分析方法，包括：在电机本体上设置有传感器，传感器实时采集电机运行参数，定位和识别电机故障模式；在所述电机本体的底部设置有振动传感器，所述振动传感器用于检测所述电机本体在运行过程中的振动数据；在所述电机本体上设置有用于检测所述电机本体的转轴转速数据的速度传感器，以及设置有用于检测电机本体转动扭矩数据的扭矩传感器，以及用于检测电机本体温度数据的温度传感器；在所述电机本体上还设置有用于检测电机输入电流稳定性数据的电流传感器；所述故障分析装置用于接收并基于所述振动数据、所述转速数据、所述转动扭矩数据、所述温度数据、所述电流稳定性数据分析所述电机故障的类型。In this example embodiment, the present disclosure provides a motor fault analysis method, which includes: a sensor is provided on the motor body, and the sensor collects motor operating parameters in real time, locates and identifies the motor failure mode; and is provided with a sensor at the bottom of the motor body. Vibration sensor, the vibration sensor is used to detect the vibration data of the motor body during operation; a speed sensor for detecting the rotation speed data of the rotating shaft of the motor body is provided on the motor body, and a speed sensor for detecting the motor body is provided. A torque sensor for body rotation torque data, and a temperature sensor for detecting motor body temperature data; a current sensor for detecting motor input current stability data is also provided on the motor body; the fault analysis device is used to receive and The type of the motor fault is analyzed based on the vibration data, the rotation speed data, the rotation torque data, the temperature data, and the current stability data.
在一种具体实施方式中，确定导致的电机故障的多个变量；利用智能解耦算法将多个变量系统转化为多个独立的单变量系统映射；系统解耦成若干个子系统，再进行独立分析和诊断，实现单一故障或多故障下的失效原因追溯。In a specific implementation, multiple variables causing motor failure are determined; an intelligent decoupling algorithm is used to convert multiple variable systems into multiple independent single-variable system mappings; the system is decoupled into several subsystems, and then independently Analysis and diagnosis enable traceability of failure causes under single or multiple faults.
具体而言：针对多变量导致的电机故障，利用智能解耦算法将多变量系统转化为多个独立的单变量系统映射，系统解耦成若干个子系统，再进行独立分析和诊断，实现单一故障或多故障下的失效原因追溯。Specifically: for motor failures caused by multivariables, an intelligent decoupling algorithm is used to convert the multivariable system into multiple independent single-variable system mappings. The system is decoupled into several subsystems, and then independent analysis and diagnosis are performed to achieve a single fault. Or trace the cause of failure under multiple faults.
参见图2所示，以2输入，2输出对象为例，采用基于神经网络的开环前馈解耦算法，对于某一通道，将其余通道对它的影响当做干扰信号，用前馈补偿的方法进行消除。As shown in Figure 2, taking a 2-input, 2-output object as an example, an open-loop feedforward decoupling algorithm based on neural networks is used. For a certain channel, the impact of other channels on it is regarded as an interference signal, and feedforward compensation is used. method to eliminate.
如图2所示，图中，f11,f12,f21,f22为对象特性，N12，N21为神经网络解耦环节，对于第一个主通道f11和输出y1(k+1)，可将第二通道的输入u2(k)看成一个可测干扰，通过引入前馈补偿环节N12进行消除，即N12＝f21·f22-1。As shown in Figure 2, in the figure, f11 , f12 , f21 , f22 are object characteristics, N12 , N21 are neural network decoupling links. For the first main channel f11 and output y1 (k +1), the input u2 (k) of the second channel can be regarded as a measurable interference, which can be eliminated by introducing the feedforward compensation link N12 , that is, N12 = f21 · f22-1 .
引入N12,N21后，y1(k+1)只受r1(k)的控制，且两者之间的映射关系为f11，y2(k+1)只受r2(k)的控制，且两者之间的映射关系为f22，即解耦以后的单变量系统具有原对象主通道的特性。After introducing N12 and N21 , y1 (k+1) is only controlled by r1 (k), and the mapping relationship between the two is f11 , y2 (k+1) is only controlled by r2 (k ), and the mapping relationship between the two is f22 , that is, the single-variable system after decoupling has the characteristics of the main channel of the original object.
在一种具体实施方式中，包括：收集设备的历史故障数据和运行数据；其中，所述运行数据包括振动数据、转速数据、转动扭矩数据、温度数据、电流稳定性数据；用神经网络算法训练传感器信号和失效模式之间的关系，进而根据采集信号和训练模型预测失效模式；其中，步骤收集设备的历史故障数据和运行数据包括：收集设备的历史故障数据和运行数据，包括设备的各种传感器数据、操作记录；步骤用神经网络算法训练传感器信号和失效模式之间的关系，进而根据采集信号和训练模型预测失效模式包括：对收集的数据进行清洗和预处理，包括去除异常值、处理缺失值、标准化数据；对预处理后的数据进行特征提取；并利用提取的特征以及历史数据对神经网络模型进行训练，得到已训练的训练模型；将传感器检测到的电机运行参数输入至已训练的训练模型中，对电机本体的故障进行预测，进而定位和识别电机故障模式。In a specific implementation, it includes: collecting historical fault data and operating data of the equipment; wherein the operating data includes vibration data, rotational speed data, rotational torque data, temperature data, and current stability data; training with a neural network algorithm The relationship between the sensor signal and the failure mode, and then predict the failure mode based on the collected signal and the training model; among them, the step of collecting historical fault data and operating data of the equipment includes: collecting historical fault data and operating data of the equipment, including various types of equipment Sensor data and operation records; the steps use neural network algorithms to train the relationship between sensor signals and failure modes, and then predict failure modes based on the collected signals and training models, including: cleaning and preprocessing the collected data, including removing outliers and processing Missing values and standardized data; extract features from the preprocessed data; and use the extracted features and historical data to train the neural network model to obtain a trained training model; input the motor operating parameters detected by the sensor into the trained In the training model, the fault of the motor body is predicted, and then the motor fault mode is located and identified.
具体而言：收集设备的历史故障数据和运行数据，利用神经网络算法训练传感器信号和失效模式之间的关系，进而根据采集信号和训练模型预测失效模式，为工业生产中设备预测性维护提供依据，包含以下步骤：Specifically: collect historical fault data and operating data of equipment, use neural network algorithms to train the relationship between sensor signals and failure modes, and then predict failure modes based on the collected signals and training models, providing a basis for predictive maintenance of equipment in industrial production. , including the following steps:
①数据收集：收集设备的历史故障数据和运行数据，包括设备的各种传感器数据、操作记录等。①Data collection: Collect historical fault data and operating data of the equipment, including various sensor data and operation records of the equipment.
②数据清洗和预处理：对收集的数据进行清洗和预处理，包括去除异常值、处理缺失值、标准化数据等。②Data cleaning and preprocessing: Clean and preprocess the collected data, including removing outliers, processing missing values, standardizing data, etc.
③特征提取：从预处理后的数据中提取有用的特征，例如设备的振动频率、温度变化、电流变化等。③Feature extraction: Extract useful features from the preprocessed data, such as the vibration frequency of the device, temperature changes, current changes, etc.
④神经网络模型构建：选择合适的神经网络模型进行构建，例如多层感知机(MLP)、卷积神经网络(CNN)等。④Neural network model construction: Select an appropriate neural network model to build, such as multi-layer perceptron (MLP), convolutional neural network (CNN), etc.
⑤模型训练：使用历史数据对神经网络模型进行训练，包括设置合适的学习率、迭代次数等参数。训练以多传感器数据为节点输入、故障类型为节点输出的算法模型，实现对传感器采集到的多源数据(如电流、电压、温度、压力、速度等信号)的综合分析与诊断。⑤Model training: Use historical data to train the neural network model, including setting appropriate parameters such as learning rate and number of iterations. Train an algorithm model that uses multi-sensor data as node input and fault types as node output to achieve comprehensive analysis and diagnosis of multi-source data (such as current, voltage, temperature, pressure, speed and other signals) collected by sensors.
预测模型对“多因一果”、“多因多果”的故障类型能够实现精准预测和诊断。The prediction model can accurately predict and diagnose fault types such as "multiple causes and one effect" and "multiple causes and multiple effects".
本实施例中，参见图4所示，预测模型利用训练数据集训练得到，具体的：训练方法包括：In this embodiment, as shown in Figure 4, the prediction model is trained using the training data set. Specifically, the training method includes:
基于所述训练数据集中回顾性队列的目标数据的类型、目标数据发生的时间、目标数据持续的时间，确定特征样本集。Based on the type of target data of the retrospective queue in the training data set, the time when the target data occurs, and the duration of the target data, a characteristic sample set is determined.
对所述获取的特征样本集进行预处理得到所述特征对应的特征向量。The obtained feature sample set is preprocessed to obtain a feature vector corresponding to the feature.
将得到的特征向量划分为训练数据集以及验证数据集。The obtained feature vectors are divided into training data sets and validation data sets.
利用所述训练数据集训练所述故障预测模型，并利用所述验证数据集验证训练后的故障预测模型，得到已训练的故障预测模型。The training data set is used to train the fault prediction model, and the verification data set is used to verify the trained fault prediction model to obtain a trained fault prediction model.
其中，所述已训练的故障预测模型中包括信号输入端、隐含处理端、故障类型输出端。Wherein, the trained fault prediction model includes a signal input terminal, an implicit processing terminal, and a fault type output terminal.
本示例实施方式中，本申请的故障预测模型是基于人工神经网络算法的多传感器耦合技术，训练以多传感器数据为节点输入、故障类型为节点输出的算法模型，实现对传感器采集到的多源数据(如电流、电压、温度、压力、速度等信号)的综合分析与诊断，尤其是对“多因一果”、“多因多果”的故障类型实现精准预测。In this example implementation, the fault prediction model of this application is based on multi-sensor coupling technology of artificial neural network algorithm. It trains an algorithm model with multi-sensor data as node input and fault type as node output, so as to realize the multi-source data collected by the sensor. Comprehensive analysis and diagnosis of data (such as current, voltage, temperature, pressure, speed and other signals), especially to achieve accurate prediction of "multiple causes and one effect" and "multiple causes and multiple effects" fault types.
参见图4所示，X1、X2、X3......Xn分别表示电流表、电压表、温度传感器......速度传感器等一系列传感设备采集的数据经过预处理后的标准值，n为传感设备测点总数；Y1、Y2、Y3......Ym分别表示断裂、磨损、腐蚀......变形等一系列故障类型，m为故障类型总数；f1、f2、f3......fv分别表示各个隐含层。0≤X1、X2、X3......Xn≤1，当Xn为0时，表示该类型传感器检测到的信号和故障类型无关，例如烟雾传感器采集到的数据和转轴断裂的故障类型无关。As shown in Figure 4, X1, X2, X3... value, n is the total number of measuring points of the sensing equipment; Y1, Y2, Y3...Ym respectively represent a series of fault types such as breakage, wear, corrosion...deformation, etc., m is the total number of fault types; f1 , f2, f3...fv represent each hidden layer respectively. 0≤X1, .
在一种具体实施方式中，所述方法还包括：基于定位和识别电机故障模式，制定对所述电机本体的维护策略。In a specific implementation, the method further includes: formulating a maintenance strategy for the motor body based on locating and identifying the motor fault mode.
具体而言：以安全性、可靠性、维护成本为约束条件，上述预测结果为依据，制定并推荐预防性和恢复性措施。根据系统的使用情况和历史故障情况选择合适的预防性措施，并根据实际情况对其进行调整和优化；并根据故障类型和影响程度选择恢复性措施，避免过度维修和浪费资源。Specifically: taking safety, reliability, and maintenance costs as constraints and the above prediction results as a basis, we formulate and recommend preventive and restorative measures. Select appropriate preventive measures based on the system usage and historical fault conditions, and adjust and optimize them according to the actual situation; and select restorative measures based on the fault type and impact to avoid excessive maintenance and waste of resources.
在一种具体实施方式中，电机本体停转状态下，配置目标检测策略；其中所述目标检测策略包括：线路检测、电机过载检测、电机本体的机构卡死检测、电机转轴损坏检测、电机绕组烧毁检测、电机电容故障检测、控制电路故障检测。In a specific implementation, when the motor body is in a stalled state, a target detection strategy is configured; wherein the target detection strategy includes: line detection, motor overload detection, mechanism jamming detection of the motor body, motor shaft damage detection, motor winding detection Burnout detection, motor capacitor fault detection, control circuit fault detection.
根据工程实践和经验总结出常用的检测方法、检测工具和测量值，建立检测方法、检测工具和测量值数据库，根据设备类型和失效模式进行选择，推荐对应的检测方法、检测工具和测量值。Summarize commonly used detection methods, detection tools and measurement values based on engineering practice and experience, establish a database of detection methods, detection tools and measurement values, select based on equipment type and failure mode, and recommend corresponding detection methods, detection tools and measurement values.
针对传感元件不足或故障的情况下，需要多步筛查才能确定失效模式的情况，在推荐算法中引入了概率和逻辑判断，以便快速筛查失效原因。In view of the situation where the sensing element is insufficient or faulty and requires multi-step screening to determine the failure mode, probability and logical judgment are introduced in the recommendation algorithm to quickly screen the cause of the failure.
例如，电机停转时，系统生成以下策略作为推荐，直至成功检测出失效原因。For example, when the motor stalls, the system generates the following strategies as recommendations until the cause of the failure is successfully detected.
在一种具体实施方式中，获取设备的历史故障数据，采用统计聚类算法分析所述历史数据，建立严酷度矩阵，确定故障模式的严酷度等级包括：基于所述严酷度等级的严重程度，为每一个所述严酷度等级配置权重；基于每种故障类型发生的频次，表征某种故障模式发生的可能性；通过配置有权重的严酷度等级以及故障类型发生的频次，构建严酷度矩阵，基于严酷度矩阵确定故障模式的严酷度等级；根据故障模式的严酷度等级，为各同等级的故障模式配置相应的处理措施。In a specific implementation, obtaining historical fault data of the equipment, using a statistical clustering algorithm to analyze the historical data, establishing a severity matrix, and determining the severity level of the failure mode includes: based on the severity of the severity level, Configure a weight for each severity level; represent the possibility of a certain failure mode based on the frequency of each fault type; construct a severity matrix by configuring the weighted severity level and the frequency of the fault type, Determine the severity level of the fault mode based on the severity matrix; configure corresponding processing measures for each fault mode of the same level based on the severity level of the fault mode.
获取设备的历史故障数据，采用统计聚类算法分析所述历史数据，建立严酷度矩阵，确定故障模式的严酷度等级。Obtain historical fault data of the equipment, use a statistical clustering algorithm to analyze the historical data, establish a severity matrix, and determine the severity level of the fault mode.
故障类型可能产生的后果，包括物理损害、安全风险、环境问题、品质问题、可靠性问题等，根据这些后果的严重程度，为每一个后果赋予相应权重，越严重的后果，其权重越高。Possible consequences of the failure type include physical damage, safety risks, environmental problems, quality problems, reliability problems, etc. According to the severity of these consequences, each consequence is given a corresponding weight. The more serious the consequence, the higher the weight.
统计每种故障类型发生的频次，表征某种故障模式发生的可能性。Count the frequency of occurrence of each fault type to indicate the possibility of a certain fault mode occurring.
通过以上两维度建立严酷度矩阵，确定故障模式的严酷度等级。A severity matrix is established through the above two dimensions to determine the severity level of the failure mode.
根据故障模式的严酷度等级，分别对不同等级的故障模式采取不同的措施，来降低风险，比如对严酷度高的故障模式进行优先处理，采取更为严格的检验、测试等等。According to the severity level of the failure mode, different measures are taken for different levels of failure modes to reduce risks, such as prioritizing failure modes with high severity, adopting more stringent inspections, tests, etc.
本实施例中，获取设备的运行数据包括：In this embodiment, obtaining the operating data of the device includes:
确定待预测设备，并根据所述待预测设备的结构、尺寸、运行精度、运行数据的范围确定检测工具。Determine the equipment to be predicted, and determine a detection tool based on the structure, size, operating accuracy, and range of operating data of the equipment to be predicted.
采用确定后的检测工具对所述待预测设备进行检测。Use the determined detection tool to detect the device to be predicted.
在一种具体实施方式中，所述确定待预测设备，并根据所述待预测设备的结构、尺寸、运行精度、运行数据的范围确定检测工具包括：In a specific implementation, determining the equipment to be predicted and determining a detection tool based on the structure, size, operating accuracy, and range of operating data of the equipment to be predicted include:
构建目标预测设备与所述目标检测工具之间的关联关系，并存储，以建立检测工具数据库。Construct an association between the target prediction device and the target detection tool, and store it to establish a detection tool database.
确定目标待测设备，在所述检测工具数据库中基于所述目标待测设备与所述目标检测工具的关联关系索引目标检测工具。Determine the target device to be tested, and index the target detection tool in the detection tool database based on the association between the target device to be tested and the target detection tool.
调用所述目标检测工具，将所述目标检测工具作为所述检测工具。The target detection tool is called and used as the detection tool.
本示例实施方式中，完善故障检测方法模块，建立检测工具的专用数据库，分为通用工具和专用工具数据库，并推荐具体测量值。In this example implementation, the fault detection method module is improved, a special database of detection tools is established, divided into general tools and special tool databases, and specific measurement values are recommended.
数据库如下表所示：The database is shown in the following table:
在一种具体实施方式中，结合风险优先系数法和危害性矩阵法进行故障模式的危害性分析；In a specific implementation, the risk priority coefficient method and the hazard matrix method are combined to conduct hazard analysis of the failure mode;
RPN＝ESR×OPRRPN＝ESR×OPR
PRN等于该故障模式的严酷度等级ESR和故障模式的发生概率等级OPR的乘积，基于RPN值的高低，确定故障的危害性，RPN值越高，危害性越大。PRN is equal to the product of the severity level ESR of the failure mode and the occurrence probability level OPR of the failure mode. Based on the RPN value, the hazard of the fault is determined. The higher the RPN value, the greater the hazard.
具体而言：结合风险优先系数法(Risk Priority Number，RPN)和危害性矩阵法进行故障模式的危害性分析。Specifically: the risk priority coefficient method (Risk Priority Number, RPN) and the hazard matrix method are combined to conduct hazard analysis of the failure mode.
RPN＝ESR×OPRRPN＝ESR×OPR
PRN等于该故障模式的严酷度等级ESR和故障模式的发生概率等级OPR的乘积，RPN值越高，危害性越大，需要给予该故障模式更大的关注。PRN is equal to the product of the severity level ESR of the failure mode and the occurrence probability level OPR of the failure mode. The higher the RPN value, the greater the hazard, and greater attention needs to be given to the failure mode.
根据每种故障模式的严酷度和故障概率等级为指标，参见图3所示。The indicators are based on the severity and failure probability level of each failure mode, as shown in Figure 3.
图3中，标记的故障模式分布点向对角线(虚线OP)作垂线，以该垂线与对角线的交点到原点的距离作为度量故障模式(或产品)危害性的依据，距离越长，其危害性越大，越应尽快采取改进措施。在上图中，因O1距离比O2距离长，则故障模式M1比故障模式M2的危害性大。In Figure 3, the marked failure mode distribution points are drawn as a vertical line to the diagonal line (dashed line OP), and the distance from the intersection of the vertical line and the diagonal line to the origin is used as the basis for measuring the hazards of the failure mode (or product). The distance The longer it is, the more harmful it is, and improvement measures should be taken as soon as possible. In the above figure, because the distance O1 is longer than the distance O2, the fault mode M1 is more harmful than the fault mode M2.
在一种具体实施方式中，确定设备原始故障类型的概率密度函数和平均故障时间MTBF。得到原故障概率密度函数的原函数，采样抽样统计的方法计算基本修复后故障概率密度函数；计算第一次修复后的平均寿命和标准差，第二次，直到第n次......；确定设备在实际运行情况时发生的第一次故障时间，设备继续运行的年限Y；通过将故障成本乘以故障发生的概率来估计故障的预期维修成本；其中，故障成本指在故障发生后造成的经济损失，故障维修成本与故障次数有关。In a specific implementation, the probability density function of the original fault type of the equipment and the mean time to failure MTBF are determined. Obtain the original function of the original failure probability density function, and use sampling statistics to calculate the failure probability density function after basic repairs; calculate the average life and standard deviation after the first repair, the second time, until the nth time... .; Determine the first failure time of the equipment in actual operation conditions, and the number of years the equipment continues to operate Y; estimate the expected maintenance cost of the failure by multiplying the failure cost by the probability of the failure; where the failure cost refers to the time when the failure occurs The economic loss caused by the failure is related to the number of failures.
具体而言：可通过故障维修成本和故障概率密度评估故障成本。确定设备原始故障类型的概率密度函数和平均故障时间MTBF。得到原故障概率密度函数的原函数，采样抽样统计的方法计算基本修复后故障概率密度函数。计算第一次修复后的平均寿命和标准差，第二次，直到第n次......确定设备在实际运行情况时发生的第一次故障时间，各个解决方案中设备继续运行的年限Y。故障成本指在故障发生后造成的经济损失，故障维修成本与故障次数有关，通过将故障成本乘以故障发生的概率来估计故障的预期维修成本。Specifically: failure costs can be evaluated through failure repair costs and failure probability density. Determine the probability density function and mean time to failure MTBF of the original fault type of the equipment. The original function of the original fault probability density function is obtained, and the fault probability density function after basic repair is calculated using sampling statistics. Calculate the average life and standard deviation after the first repair, the second time, until the nth time... Determine the first failure time when the equipment is actually operating, and the equipment continues to operate in each solution Year Y. Failure cost refers to the economic loss caused after a failure occurs. Failure maintenance cost is related to the number of failures. The expected maintenance cost of a failure is estimated by multiplying the failure cost by the probability of failure.
本示例实施方式中，参见图5所示，本申请中的FMECA分析装置：包括电机故障数据采集模块、故障数据训练学习模块、计算模块、预测模块、决策模块、分析评估模块。In this example implementation, as shown in Figure 5, the FMECA analysis device in this application includes a motor fault data collection module, a fault data training and learning module, a calculation module, a prediction module, a decision-making module, and an analysis and evaluation module.
具体而言，参见图5所示，上述FMECA分析装置的运行原理如下：传感器实时监测电机状态，定位和识别电机故障模式；利用卡尔曼滤波算法解耦多源混合波形，独立分析和诊断；训练多传感器输入、故障类型输出的神经网络模型；预测单一或复杂因素影响下的故障类型；建立通用及专用工具数据库，并推荐测量工具和测量值；分配故障模式下故障原因权重，建立优先级排序；使用模糊综合评判方法量化故障模式的危害度；评估故障成本并提供维修方案；一键生成全流程分析报告。Specifically, as shown in Figure 5, the operating principle of the above-mentioned FMECA analysis device is as follows: the sensor monitors the motor status in real time, locates and identifies the motor failure mode; uses the Kalman filter algorithm to decouple multi-source mixed waveforms, independently analyzes and diagnoses; training Neural network model with multi-sensor input and fault type output; predicts fault types under the influence of single or complex factors; establishes a database of general and special tools, and recommends measurement tools and measured values; assigns the weight of fault causes in fault modes and establishes priority ranking ;Use fuzzy comprehensive evaluation method to quantify the hazard of failure modes; evaluate failure costs and provide maintenance plans; generate a full-process analysis report with one click.
此外，上述附图仅是根据本发明示例性实施例的方法所包括的处理的示意性说明，而不是限制目的。易于理解，上述附图所示的处理并不表明或限制这些处理的时间顺序。另外，也易于理解，这些处理可以是例如在多个模块中同步或异步执行的。Furthermore, the above-mentioned drawings are only schematic illustrations of processes included in methods according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal sequence of these processes. In addition, it is also easy to understand that these processes may be executed synchronously or asynchronously in multiple modules, for example.
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其他实施例。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由权利要求指出。Other embodiments of the disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure that follow the general principles of the disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the disclosure. . It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限。It is to be understood that the present disclosure is not limited to the precise structures described above and illustrated in the accompanying drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310684706.3ACN116720091A (en) | 2023-06-09 | 2023-06-09 | A motor fault analysis method |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310684706.3ACN116720091A (en) | 2023-06-09 | 2023-06-09 | A motor fault analysis method |
| Publication Number | Publication Date |
|---|---|
| CN116720091Atrue CN116720091A (en) | 2023-09-08 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310684706.3APendingCN116720091A (en) | 2023-06-09 | 2023-06-09 | A motor fault analysis method |
| Country | Link |
|---|---|
| CN (1) | CN116720091A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119125969A (en)* | 2024-11-12 | 2024-12-13 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | A method for detecting short-circuit faults in power transformer windings |
| CN119338077A (en)* | 2024-12-18 | 2025-01-21 | 四川省能投美姑新能源开发有限公司 | A prediction method and prediction system for wind turbine operating status |
| CN120494814A (en)* | 2025-07-15 | 2025-08-15 | 上海宇石能源集团有限公司 | A hydrogen fuel cell engine fault diagnosis system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850904A (en)* | 2015-05-12 | 2015-08-19 | 上海能策燃气轮机有限公司 | Analysis method for optimizing gas turbine overhaul and maintenance scheme |
| CN109255205A (en)* | 2018-11-16 | 2019-01-22 | 中国航空综合技术研究所 | A kind of complex mechanical system Design Method based on function robustness |
| CN113779890A (en)* | 2021-09-26 | 2021-12-10 | 中机国能电力工程有限公司 | A method of intercourse data mining and fault identification for photovoltaic modules |
| CN115856619A (en)* | 2022-11-25 | 2023-03-28 | 中国人民解放军陆军装甲兵学院 | Motor fault diagnosis method and device, electronic equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850904A (en)* | 2015-05-12 | 2015-08-19 | 上海能策燃气轮机有限公司 | Analysis method for optimizing gas turbine overhaul and maintenance scheme |
| CN109255205A (en)* | 2018-11-16 | 2019-01-22 | 中国航空综合技术研究所 | A kind of complex mechanical system Design Method based on function robustness |
| CN113779890A (en)* | 2021-09-26 | 2021-12-10 | 中机国能电力工程有限公司 | A method of intercourse data mining and fault identification for photovoltaic modules |
| CN115856619A (en)* | 2022-11-25 | 2023-03-28 | 中国人民解放军陆军装甲兵学院 | Motor fault diagnosis method and device, electronic equipment and storage medium |
| Title |
|---|
| 赵华全 等: "基于FMECA技术的振动筛可靠性分析", 《装备制造技术》, 15 April 2023 (2023-04-15), pages 71 - 73* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119125969A (en)* | 2024-11-12 | 2024-12-13 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | A method for detecting short-circuit faults in power transformer windings |
| CN119338077A (en)* | 2024-12-18 | 2025-01-21 | 四川省能投美姑新能源开发有限公司 | A prediction method and prediction system for wind turbine operating status |
| CN120494814A (en)* | 2025-07-15 | 2025-08-15 | 上海宇石能源集团有限公司 | A hydrogen fuel cell engine fault diagnosis system |
| Publication | Publication Date | Title |
|---|---|---|
| CN112785091B (en) | Method for carrying out fault prediction and health management on oil field electric submersible pump | |
| CN116720091A (en) | A motor fault analysis method | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN109186813A (en) | A temperature sensor self-checking device and method | |
| CN118261584B (en) | Transformer state evaluation method and system based on multi-parameter data | |
| JPH08234832A (en) | Plant monitoring and diagnostic apparatus and method | |
| CN119293664A (en) | A device operation evaluation method based on multi-source data fusion | |
| CN118653969B (en) | Real-time detection system and early warning method for lubrication system of wind power generation equipment | |
| CN117060409A (en) | Automatic detection and analysis method and system for power line running state | |
| KR20230125116A (en) | The method for fault detection without training data or diagnosis with prediction of remaining time until breakdown using clustering algorithm and statistical methods | |
| CN116295948B (en) | Abnormality detection method, system and storage medium of industrial temperature sensor in large temperature difference environment | |
| CN118690283A (en) | A method and system for diagnosing power equipment based on pattern recognition algorithm | |
| CN115081647A (en) | Industrial intelligent instrument fault pre-diagnosis method based on Bayesian network model | |
| CN118066934A (en) | Intelligent fault positioning system for weapon equipment | |
| CN117761423A (en) | Power distribution network fault prediction method | |
| CN115034094B (en) | A method and system for predicting the running state of a metal processing machine tool | |
| CN120045216A (en) | Visual equipment element configuration system | |
| KR102573254B1 (en) | System for predicting and analyzing trouble of mechanical equipment using federated learning | |
| CN119471552A (en) | A method and device for self-detecting fault of electric energy meter | |
| CN118965247A (en) | A power plant data management method and system based on multi-source data | |
| CN117827621B (en) | Embedded software automated testing platform system and method | |
| CN119062350A (en) | Fault detection and diagnosis method and system for shield machine hydraulic system | |
| CN118842734A (en) | Industrial switch fault prediction and health management system | |
| Chen et al. | BIM-and IoT-based data-driven decision support system for predictive maintenance of building facilities | |
| CN117591949A (en) | Equipment abnormality identification method, equipment and medium |
| 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 |