Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the technical solution of the present application and are not intended to limit the present application.
For a better understanding of the technical solution of the present application, the following detailed description will be given with reference to the drawings and the specific embodiments.
The main solution of the embodiment of the application is that at least one sensor data is preprocessed, standardized data corresponding to each sensor data is determined, linear dimension reduction operation is carried out on the standardized data, dimension reduction data is determined, a machine learning model is trained by using the dimension reduction data, the dimension reduction data is mapped to a low-dimension space, a low-dimension data graph is determined, data point distribution is checked according to the low-dimension data graph, abnormal points are identified, and a fault detection result is determined.
At present, a manual detection method is mostly adopted for detecting welding faults, and identification and perception are performed manually. The manual welding fault detection process has high requirements on the proficiency and experience of workers, the manual detection efficiency is not high enough, no unified standard exists in the manual detection process, indexes are difficult to quantify, and the detection accuracy is low.
The application provides a solution, which is characterized in that the accuracy and consistency of data are ensured by preprocessing at least one sensor data, further standardized data corresponding to each sensor data are determined, linear dimension reduction operation is carried out on the standardized data, dimension reduction data are generated, a machine learning model is trained by using the dimension reduction data, the dimension reduction data are mapped to a low-dimension space through the model, a low-dimension data graph which is easy to observe and analyze is generated, and finally abnormal points are accurately identified according to the distribution condition of data points in the low-dimension data graph, so that a fault detection result is determined, and the efficiency and accuracy of welding fault detection are improved.
It should be noted that, the execution body of the embodiment may be a computing service device with functions of data processing, network communication and program running, such as a tablet computer, a personal computer, a mobile phone, or an electronic device, a welding fault detector, or the like, which can implement the above functions. The present embodiment and the following embodiments will be described below with reference to a welding failure detector as an example.
Example 1
The embodiment of the application discloses a welding fault detection method, and referring to fig. 1, the welding fault detection method comprises the following steps:
step S110, preprocessing at least one sensor data, and determining standardized data corresponding to each sensor data.
In this embodiment, the sensor data is measured or observed values generated by the sensor, including data such as temperature, pressure, vibration, welding speed, etc., the preprocessing is to perform operations such as cleaning and noise reduction on the data, and the standardized data is data converted into standard dimensions.
As an alternative embodiment, the abnormal value or missing value due to sensor failure, transmission error, etc. is deleted or repaired, a filter is used to reduce noise caused by the environment or the sensor itself, smoothing is performed on time series data, the maximum value and the minimum value of the data are found by traversing the data set, and the data is normalized to a standard scale using a normalization formula. Wherein the filter comprises a moving average filter, a Kalman filter, and the like.
Optionally, step S110 includes, before:
step S111, at least one sensor is installed at a key position of the welding machine.
In this embodiment, the welder is an apparatus for welding that melts and bonds the contact surfaces of two or more workpieces into a single body by means of heat and/or pressure.
As an alternative embodiment, the key position of the sensor to be installed is determined according to the structure and the function of the welding machine, and the sensor is installed by selecting a proper sensor type according to the parameter to be monitored. Wherein the monitored parameters include temperature, pressure, current, voltage, etc.
Step S112, recording the sensor data in real time and storing the sensor data.
In this embodiment, real-time recording refers to a process of capturing, recording, or saving data immediately while it is being generated.
As an alternative embodiment, the sensor sends data through its interface to a data acquisition system or controller, which periodically or continuously reads the data sent by the sensor and writes the sensor data stored in the memory or buffer to the long-term storage medium periodically or on demand. The sensor interface comprises analog signals, digital signals, wireless transmission and the like, and the long-term storage medium comprises a hard disk, a flash memory, a database, cloud storage and the like.
And step S120, performing linear dimension reduction operation on the standardized data, and determining dimension reduction data.
In this embodiment, linear dimension reduction is a data preprocessing technique for projecting high-dimensional data into a low-dimensional space while preserving as much as possible the original structure and information of the data, and dimension reduction data is a low-dimensional representation extracted from the original high-dimensional data by a dimension reduction technique including principal component analysis PCA, t-SNE, UMAP, and the like.
As an optional implementation manner, a covariance matrix of the standardized data is calculated, eigenvalue decomposition is carried out on the covariance matrix to obtain eigenvalues and corresponding eigenvectors, the eigenvectors corresponding to larger eigenvalues are selected as new basis vectors according to the magnitude of the eigenvalues, and the standardized data is projected onto the new basis vectors to obtain the dimensionality-reduced data.
Illustratively, according to the standardized data, calculating a covariance matrix among all features, decomposing the covariance matrix to obtain a group of feature values and corresponding feature vectors, selecting the feature vector corresponding to the largest feature value of the previous k (k represents the target dimension to be reduced) as a main component according to the size of the feature values, constructing a projection matrix by using the selected main component (feature vector), and projecting the standardized data onto the matrix to obtain the dimension-reduced data.
And step S130, training a machine learning model by using the reduced-dimension data, mapping the reduced-dimension data to a low-dimension space, and determining a low-dimension data graph.
In this embodiment, the machine learning model is a data-based algorithm or method for learning from data and making predictions or decisions, including decision trees, random forests, support vector machines, neural networks, and the like.
As an alternative embodiment, a suitable machine learning model is selected, a reduced dimension data is used as input features, the machine learning model is trained using the reduced dimension data, a suitable visualization tool is selected, a suitable pattern type is selected according to the dimensions and properties of the reduced dimension data, a reduced dimension data pattern is drawn using the visualization tool, and a low dimension data pattern is determined. Wherein the visualization tools include matplotlib, seaborn, plotly, etc., and the graphic types include scatter plots, thermodynamic diagrams, etc.
And step S140, checking data point distribution according to the low-dimensional data graph, identifying abnormal points and determining a fault detection result.
In this embodiment, the data point distribution is the arrangement and aggregation of data points in the visualization, and the outlier is a point in the data set that is significantly different from other data points.
As an alternative implementation mode, the arrangement and aggregation conditions of data points in the low-dimensional data graph are observed, possible abnormal points are initially identified according to the distribution conditions of the data points, and whether a fault detection result exists is judged by comprehensively considering association factors. The association factors comprise the number, the position, the distribution condition of abnormal points, the association with an actual business scene and the like.
In this embodiment, the accuracy and consistency of the data are ensured by preprocessing at least one sensor data, so as to determine standardized data corresponding to each sensor data, perform linear dimension reduction operation on the standardized data, generate dimension reduction data, train a machine learning model by using the dimension reduction data, map the dimension reduction data to a low-dimension space by the model, generate a low-dimension data graph easy to observe and analyze, and finally accurately identify abnormal points according to the distribution condition of data points in the low-dimension data graph, thereby determining a fault detection result and improving the efficiency and accuracy of welding fault detection.
Based on the first embodiment, a second embodiment of the present application provides a welding fault detection method, referring to fig. 2, step S110 includes:
step S210, checking the data integrity of each sensor data, processing the missing values, and determining the complete data.
In this embodiment, the data integrity refers to the state of the data in the process of collecting the data, where the data is complete, not damaged or not lost, and the missing value is a data point that is missing or cannot be obtained in the data set.
As an alternative embodiment, the data is read from the sensor, the integrity of the data is checked, missing values in the data set are identified, the missing values are deleted, filled or replaced, and the complete data is determined.
Illustratively, raw data is read from a sensor or storage medium, whether the data is recorded in an expected format and frequency is checked, which data points in the data set are missing, if there are few data points with missing values or the effect of missing values on data analysis is small, the data row or data column containing missing values can be deleted directly, the data points before and after the missing values are found, the size of the missing values is estimated using a linear interpolation formula, and the data set is filled with the size. After interpolation filling, a complete data set is obtained.
And step S220, removing noise in each complete data through a filter, and determining denoising data.
In this embodiment, the filter is a device or algorithm for removing unwanted components or noise from a signal, and the filter types include a low-pass filter, a high-pass filter, a band-stop filter, a digital filter, and the like.
As an alternative implementation manner, a proper filter type is selected, parameters of the filter are determined according to the characteristics and the data quality of the sensor, the complete data is input into the filter, denoising processing is carried out, and denoising data is determined. The parameters of the filter include cut-off frequency, window size, iteration number and the like.
Illustratively, a Moving average filter (Moving AVERAGE FILTER) is selected to remove noise of the temperature data, a Window Size (Window Size) is determined according to the noise level and the required smoothness degree of the temperature data, the whole temperature data sequence is traversed, an average value of each data point and two data points (5 data points in total) is calculated, the calculated average value is taken as a data point after denoising, and all the data points after denoising are combined into a new data sequence, namely denoising data.
Step S230, synchronizing the time of each denoising data, and determining the synchronization data.
In this embodiment, the synchronization data time is aligned by a time stamp that is used to record the time each data point was collected.
As an alternative embodiment, the time stamps in the de-noised data are identified, all time stamps are converted to a uniform format, the data are ordered by time stamp, and a consolidated data set is created that contains all data source data, determining the synchronized data.
Step S240, determining standardized data based on each of the synchronous data.
In this embodiment, the standardized data refers to converting the original data according to a certain standard or specification, so that the original data has a unified format, unit and metric, so as to be capable of performing comparison and analysis across sensors, platforms or time.
As an alternative embodiment, for each feature in the dataset, the mean and standard deviation are calculated, and a normalization formula is applied to each data point in the dataset to generate a new dataset, i.e., normalized data.
For example, a data set of synchronized data, which contains two features of temperature and pressure, the original dimensions of which are different (temperature may be in degrees celsius and pressure may be in pascals) and thus their dimensions may also be different, the mean and standard deviation of the temperature and pressure data, respectively, are calculated, the Z-score normalization is applied, and for each temperature and pressure data point in the data set, their Z-score is calculated, and the normalized data is determined.
In the embodiment, through cleaning, denoising and unifying formats of the original data of the sensor, redundant information and interference factors in the data can be eliminated, so that subsequent analysis is more focused and accurate. By converting the data of different sensors to the same scale, it can be ensured that the various data have the same weight and importance in subsequent analysis. This helps the machine learning model better understand and identify patterns in the data, thereby improving the accuracy of fault detection.
Based on the first embodiment, a third embodiment of the present application provides a welding fault detection method, referring to fig. 3, step S120 includes:
step S310, calculating a covariance matrix based on the normalized data.
In this embodiment, the covariance matrix is a square matrix whose elements are the covariance between the ith and jth random variables, and describes the linear relationship, in particular the correlation, between the random variables.
Illustratively, an n×n zero matrix C is initialized for storing elements of the covariance matrix, for each element c_ij of the covariance matrix (i=1, 2,.,; j=1, 2,..n.), calculating the covariance between the ith and jth columns in Z, i.e. c_ij=Σ_k= 1^m (z_ki- μ_i) × (z_kj- μ_j)/(m-1), where mu i and mu j are the mean of the ith and jth columns in Z respectively (since it has been normalized, so μ_i=μ_j=0), filling the calculated c_ij into the j-th column of the i-th row of the matrix C, and the resulting matrix C is the covariance matrix of the normalized data.
And step S320, carrying out eigenvalue decomposition according to the covariance matrix to determine eigenvalues and eigenvectors.
In this embodiment, eigenvalue decomposition is a method of decomposing a matrix into a set of eigenvectors and eigenvalues, the eigenvalues describing the extent to which the matrix stretches or compresses the eigenvectors, the eigenvectors being non-zero vectors that make the transformation of the matrix a simple telescopic transformation.
As an alternative embodiment, the covariance matrix is decomposed with eigenvalues by using a function provided by a numerical computation library, so as to obtain eigenvalues and corresponding eigenvectors. The numerical calculation library includes NumPy, MATLAB, and the like.
And step S330, taking the characteristic vector with the corresponding larger characteristic value in the characteristic vectors as a main component.
In this embodiment, the principal component (PRINCIPAL COMPONENT) is a concept in Principal Component Analysis (PCA), which refers to the direction of the greatest change in the dataset, and the direction corresponding to the eigenvector with the larger eigenvalue is the principal component, which represents the most dominant direction of change in the dataset.
As an alternative embodiment, the feature values and the feature vectors are ordered according to the sizes of the feature values, the feature values are ensured to be arranged from large to small, the order of the feature vectors is adjusted accordingly, and the first k feature vectors with larger feature values are selected as main components. Wherein k is a super parameter, and needs to be selected according to practical situations.
And step S340, projecting the standardized data to the main component, and determining the dimension reduction data.
In this embodiment, projection refers to a process of mapping a point, line or pattern from one space to another space, and in this embodiment, projection refers to mapping normalized data onto a principal component, thereby obtaining dimension-reduced data.
As an alternative embodiment, the normalized data is projected onto the selected principal component to obtain reduced-dimension data.
Illustratively, each sample in the high-dimensional normalized data is subjected to dot product operation with each selected principal component (i.e., feature vector), so as to obtain a 2-dimensional or 3-dimensional vector, which is the data after the dimension is reduced.
In this embodiment, the high-dimensional data is mapped to the low-dimensional space by the dimension reduction technique while key information in the data is retained. The method not only reduces the calculation complexity, but also is convenient for intuitively observing and analyzing the distribution and the mode of the data, and improves the efficiency of the welding fault detection method.
Based on the first embodiment, a fourth embodiment of the present application provides a welding fault detection method, referring to fig. 4, step S130 includes:
step S410, setting parameters of the machine learning model.
In this embodiment, the machine learning model is a model that is obtained by training through a machine learning algorithm and can predict or classify input data, and in the machine learning model, parameters are adjustable variables inside the model and are used to determine the behavior of the model.
As an alternative embodiment, parameters of the machine learning model are initialized and an appropriate learning rate is selected. The initialization method comprises random initialization, constant initialization, normal distribution initialization and the like, and the learning rate is an important super parameter in machine learning and determines the step length of the model when the parameters are updated each time in the training process.
Illustratively, a t-SNE algorithm is used to reduce the dimension of a high-dimensional dataset for visualization, a perplexity parameter (the number of neighboring points considered in deciding the conditional probability distribution in the high-dimensional space) is set to 30, a learning rate parameter (the speed at which the algorithm updates the parameters in the optimization process) is set to 'auto', an n_iter parameter (the number of iterations that decide the optimization process) is set to 1000 iterations, and an early_ exaggeration parameter (the distance between points that will be amplified in the initial stage of the optimization, helping the algorithm to better capture the local structure of the data) is set to 4.
And step S420, inputting the dimensionality reduction data into the machine learning model, mapping the dimensionality reduction data into a low-dimensional space, and determining low-dimensional data.
In this embodiment, the low-dimensional data is the result of a dimension reduction process, which is a representation of the original high-dimensional data in the low-dimensional space. These data typically have fewer features or dimensions, but still reflect the primary features or structure of the original data.
As an alternative embodiment, dimension-reduced data is input into a selected machine learning model, the machine learning model is trained using dimension-reduced data, the dimension-reduced data is mapped to a low-dimensional space, and the low-dimensional data is determined to reflect the structure of the high-dimensional data.
Step S430, visualizing the low-dimensional data, and determining a low-dimensional data graph.
In this embodiment, visualization is a process of converting data or information into graphics, images or animations, so that people can more easily understand, analyze and interpret patterns and trends in the data, and the visualization mode includes a scatter diagram, a thermodynamic diagram, a parallel coordinate diagram and the like, and the low-dimensional data graph refers to a result of displaying the low-dimensional data in the form of graphics or images, including a scatter diagram, a thermodynamic diagram, a line diagram and the like, for visually representing patterns and relationships in the data.
As an alternative embodiment, a visualization tool is used to draw the low-dimensional data into a graphic. Wherein the visualization tools include Matplotlib, seaborn, plotly, tableau, etc.
Illustratively, a scatter plot is drawn using visualization tool Matplotlib, a sufficiently large graphic area is determined to reveal all data points, a unique color is selected for each handwritten numerical category, the data points for each numerical category are traversed, the scatter plot is drawn in the graphic area, each data point corresponds to a two-dimensional coordinate (resulting from the t-SNE dimension reduction) and is represented by the color of the corresponding category, a legend is added to the graphic, the legend should contain each numerical category and its corresponding color, a header is added to the top or bottom of the graphic, and a low-dimensional data graphic is determined.
In the embodiment, the machine learning model is trained by using the dimension reduction data, when in real-time detection, the model can quickly identify abnormal data points and give accurate fault detection results, the data distribution and the mode of the welding process become visual by the visual output results, and in the subsequent analysis process, the visual results are displayed in a graph, so that the analysis time of the fault detection results can be saved, and the accuracy of the analysis of the fault detection results can be improved.
Based on the first embodiment, a fifth embodiment of the present application provides a welding fault detection method, referring to fig. 5, step S140 includes:
step S510, checking data point distribution through cluster analysis based on the low-dimensional data graph;
in this embodiment, cluster analysis is an unsupervised learning method for grouping similar data points into a set.
As an alternative implementation mode, a clustering algorithm is selected according to the characteristics and analysis targets of the data, low-dimensional data is taken as input, the selected clustering algorithm is operated, the algorithm divides the data points into different clusters according to the similarity among the data points, the clustering result is overlapped on the low-dimensional data graph, and the distribution and the clustering condition of the data points are displayed. The clustering algorithm comprises K-means clustering, hierarchical clustering, DBSCAN (spatial clustering based on density and noise application), spectral clustering and the like.
Step S520, setting a threshold value of fault detection, and marking the points exceeding the threshold value of the data points as abnormal points;
In this embodiment, the threshold is a threshold value that is used to distinguish between two or more different states or categories of data. In fault detection, a threshold is typically used to determine whether a data point is considered abnormal, which refers to data points that are significantly different from most data points, which may be atypical data due to various reasons.
As an alternative embodiment, a threshold is determined based on statistical properties of the data, each data point in the data set is traversed, whether its value exceeds a set threshold is checked, and each data point in the data set is analyzed and compared according to a set fault detection threshold to find outliers that exceed the threshold. The statistical characteristics of the data comprise mean, standard deviation, median absolute deviation and the like.
As another alternative embodiment, the threshold is determined based on the quartile, the median and the upper and lower quartiles of the data are used to determine the range of outliers, the range of outliers is used as the threshold, and the data points within the range of outliers are marked as outliers.
Illustratively, a distance threshold is determined based on the t-SNE visualization, and if the data point is above a certain threshold from the cluster center, the data point is marked as abnormal.
And step S530, determining a fault detection result through an alarm system according to the abnormal point.
In this embodiment, the alarm system is a mechanism for monitoring and detecting an abnormal situation and triggering an alarm notification when an abnormal situation is detected.
As an alternative implementation mode, the triggering condition of the alarm system is set, the notification mode of the alarm system is configured, and the alarm system determines a fault detection result according to preset rules and logic.
Optionally, step S530 includes:
Step S531, an alarm system is established, and when abnormal points are detected, an alarm signal is sent out and abnormal data corresponding to the abnormal points are recorded.
In this embodiment, the alarm signal is a notification or signal sent when the alarm system is triggered, and is used to inform relevant personnel that an abnormal situation occurs in the system or data.
As an alternative implementation manner, according to the service requirement and the data characteristics, the monitoring rule and the triggering condition of the alarm system are configured, the notification mode of the alarm system is configured, when an abnormal point is detected, the alarm system automatically triggers an alarm signal according to the preset configuration, and the alarm system records the abnormal data related to the abnormal point while sending the alarm signal. The recorded data may include, among other things, the original value of the outlier, a time stamp, related context information (e.g., device ID, sensor number, etc.), etc.
Step S532, determining a fault detection result based on the abnormal data.
In this embodiment, the failure detection result is a conclusion or evaluation result concerning whether or not there is a failure in the system or the device, based on analysis and processing of the abnormal data. This result may include information about the type, location, severity, etc. of the fault to guide subsequent troubleshooting and repair operations.
As an alternative embodiment, based on the analysis of the anomaly data, the type of possible fault is determined, the specific location or component at which the fault occurs is determined based on the context information of the anomaly data, and the severity of the fault is assessed based on the characteristics of the anomaly data and the analysis results.
Optionally, after step S530, the method includes:
In step S533, the accuracy of the fault detection result is verified by the actual state of the welding.
In the present embodiment, the actual state of the welding is the actual state during the welding process.
As an alternative implementation manner, actual state data of the welding piece is collected in the welding process, a fault detection result and the welding actual state data are subjected to comparison analysis, whether the detected fault type is consistent with the fault type in the actual state or not is compared, the comparison fault position is accurate or not, the evaluation of the severity of the comparison fault is accurate or not, and the accuracy of the fault detection method is evaluated according to the result of the comparison analysis.
Step S534, adjusting parameters of the machine learning model, and improving the welding fault detection method.
In this embodiment, the model parameters are internal values that the machine learning model needs to adjust during the training process, and these parameters determine how the model fits and predicts the data.
As an alternative implementation mode, the detection result is different from the actual state, the reason is analyzed, parameters are adjusted based on the evaluation result of the model, the optimal parameter combination can be found by using a grid search method, a random search method or a Bayesian optimization method, and the processes of model training, evaluation and parameter adjustment are repeated until the performance of the model reaches a satisfactory level, so that the welding fault detection method is improved.
In this embodiment, the accuracy of the fault detection result is verified through the actual state of welding, and the parameters of the machine learning model are adjusted according to the verification result to improve the welding fault detection method, so that the accuracy of welding fault detection can be significantly improved.
It should be noted that the foregoing examples are only for understanding the present application, and are not meant to limit the welding fault detection method of the present application, and more forms of simple transformation based on the technical concept are all within the scope of the present application.
The application provides welding fault detection equipment, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the welding fault detection method in the first embodiment.
Referring now to fig. 6, a schematic diagram of a welding failure detection apparatus suitable for use in implementing embodiments of the present application is shown. The welding fault detection device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal DIGITAL ASSISTANT: personal digital assistants), PADs (Portable Application Description: tablet computers), PMPs (Portable MEDIA PLAYER: portable multimedia players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The welding fault detection apparatus shown in fig. 6 is only one example and should not be construed as limiting the functionality and scope of use of the embodiments of the present application.
As shown in fig. 6, the welding failure detection apparatus may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access Memory (RAM: random Access Memory) 1004. In the RAM1004, various programs and data required for the operation of the xxx device are also stored. The processing device 1001, the ROM1002, and the RAM1004 are connected to each other by a bus 1005. An input/output (I/O) interface 1006 is also connected to the bus. In general, a system including an input device 1007 such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc., an output device 1008 including a Liquid crystal display (LCD: liquid CRYSTAL DISPLAY), a speaker, a vibrator, etc., a storage device 1003 including a magnetic tape, a hard disk, etc., and a communication device 1009 may be connected to the I/O interface 1006. The communication means 1009 may allow the welding fault detection device to communicate wirelessly or by wire with other devices to exchange data. While a welding fault detection device having various systems is shown in the figures, it should be understood that not all of the illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. The above-described functions defined in the method of the disclosed embodiment of the application are performed when the computer program is executed by the processing device 1001.
The welding fault detection equipment provided by the application can solve the technical problem of welding fault detection by adopting the welding fault detection method in the embodiment. Compared with the prior art, the welding fault detection device has the same beneficial effects as the welding fault detection method provided by the embodiment, and other technical features in the welding fault detection device are the same as the features disclosed by the method of the previous embodiment, and are not described in detail herein.
It is to be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the description of the above embodiments, particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon for performing the welding fault detection method of the above-described embodiments.
The computer readable storage medium provided by the present application may be, for example, a U disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the foregoing. More specific examples of a computer-readable storage medium may include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access Memory (RAM: random Access Memory), a Read-Only Memory (ROM), an erasable programmable Read-Only Memory (EPROM: erasable Programmable Read Only Memory or flash Memory), an optical fiber, a portable compact disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this embodiment, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to electrical wiring, fiber optic cable, RF (Radio Frequency) and the like, or any suitable combination of the foregoing.
The computer readable storage medium may be included in the welding fault detection apparatus or may exist alone without being incorporated in the welding fault detection apparatus.
The computer readable storage medium carries one or more programs which, when executed by the welding fault detection device, cause the welding fault detection device to write computer program code for performing the operations of the present application in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++, and conventional procedural programming languages, such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of remote computers, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN: local Area Network) or a wide area network (WAN: wide Area Network), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present application may be implemented in software or in hardware. Wherein the name of the module does not constitute a limitation of the unit itself in some cases.
The readable storage medium provided by the application is a computer readable storage medium, and the computer readable storage medium stores computer readable program instructions (namely computer programs) for executing the welding fault detection method, so that the technical problem of welding fault detection can be solved. Compared with the prior art, the beneficial effects of the computer readable storage medium provided by the application are the same as those of the welding fault detection method provided by the embodiment, and are not repeated here.
The foregoing description is only a partial embodiment of the present application, and is not intended to limit the scope of the present application, and all the equivalent structural changes made by the description and the accompanying drawings under the technical concept of the present application, or the direct/indirect application in other related technical fields are included in the scope of the present application.