Fault detection and diagnosis method and device for front-end isolated switching power supply of aging table

Abstract

The embodiment of the invention provides a fault detection and diagnosis method and device for a front-end isolated switching power supply of an aging table. The fault detection and diagnosis method for the front-end isolated switching power supply of the aging table comprises the following steps: acquiring a plurality of historical signal values corresponding to analog quantity signals of the front-end isolated switching power supply of the aging table in a plurality of historical time sequences; determining signal parameters of the front-end isolated switching power supply of the aging station based on the plurality of historical signal values; performing binning processing on the signal parameters, and respectively constructing feature vectors of the front-end isolated switching power supply of the aging station based on at least two binning data sets contained in a binning processing result; a training sample set is constructed based on the feature vectors and the state labels corresponding to the feature vectors, a to-be-trained support vector machine diagnosis model is trained based on the training sample set, and the trained support vector machine diagnosis model is used for carrying out fault detection diagnosis on the aged table front-end isolated switching power supply.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of non-destructive reliability screening of integrated circuits, and more particularly to a method for detecting and diagnosing faults of isolated switching power supplies at the front end of a burn-in station. Background Art

[0002] The integrated circuit high temperature aging test bench accelerates various physical and chemical reaction processes inside the components by continuously applying a certain amount of electrical stress to the components over a long period of time, prompting various potential faults inside the components to be exposed early, thereby eliminating early failure products and making the electronic components enter a period of low failure rate and relative stability from the beginning of use. The current integrated circuit high temperature aging test bench can achieve long-term monitoring of the test environment by adding long-term monitoring in the machine and overstress protection mechanism, and can respond in time when the machine fails to achieve post-maintenance based on fault data. However, due to the lack of active protection technology for integrated circuit high temperature aging test benches, it is difficult to achieve the integrity of the test process and the consistency of the test environment stress, and it is very easy to cause the test process to be interrupted due to machine failure, resulting in major property losses such as damage to millions of test devices, or the aging test is identified as a failure test due to adverse effects such as the introduction of additional stress during the test due to machine performance degradation, resulting in ineffective waste of resources. At the same time, ensuring the quality of high-temperature aging tests can avoid over-aging and under-aging failures of integrated circuits, significantly reduce the failure rate of integrated circuits, and help avoid large-scale electronic system failures and shutdowns due to integrated circuit failures in new energy vehicles, civil airliners, energy storage and transmission stations, etc. that use the same integrated circuits.

[0003] The front-end isolated switching power supply provides the required power for the entire aging test bench to ensure that all parts of the test bench can work normally. As the core key equipment of the aging test bench, the front-end isolated switching power supply has a great impact on the overall reliability of the aging test bench. Once circuit degradation, failure or sudden failure occurs, the aging test bench test will stop and damage the object under test. In severe cases, the voltage will be overloaded, causing a fire, resulting in major property losses and safety hazards. Therefore, it is very necessary to perform fault detection and diagnosis on the front-end isolated switching power supply of the aging test bench. How to perform fault detection and diagnosis on the front-end isolated switching power supply of the aging test bench has become an urgent problem to be solved. Summary of the invention

[0004] In view of this, an embodiment of this specification provides a method for detecting and diagnosing a fault of an isolated switching power supply at the front end of a burn-in station. One or more embodiments of this specification also relate to a device for detecting and diagnosing a fault of an isolated switching power supply at the front end of a burn-in station, a computing device, a computer-readable storage medium, and a computer program to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a method for detecting and diagnosing faults of a front-end isolated switching power supply of a burn-in station is provided, comprising: Obtain multiple historical signal values ​​corresponding to multiple historical time series of the analog signal of the isolated switching power supply at the front end of the aging station; Based on the multiple historical signal values, determining the signal parameters of the isolated switching power supply at the front end of the aging station; Binning the signal parameters, and constructing feature vectors of the front-end isolated switching power supply of the aging station based on at least two binning data sets included in the binning processing results; A training sample set is constructed based on the feature vector and the state label corresponding to the feature vector, and a support vector machine diagnostic model to be trained is trained based on the training sample set, wherein the trained support vector machine diagnostic model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station.

[0006] Optionally, the step of constructing the feature vectors of the front-end isolated switching power supply of the aging station based on at least two binned data sets included in the binning processing result includes: Based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set, and a feature vector of the front-end isolated switching power supply of the aging station is constructed based on the feature extraction result, wherein the target binned data set is each of the at least two binned data sets.

[0007] Optionally, the extracting features of the target binned data set based on the target signal parameters contained in the target binned data set includes: Based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set to obtain the corresponding average value, standard deviation and peak value of the target signal parameters.

[0008] Optionally, the performing binning processing on the signal parameters includes: The signal parameters are binned using a K-means binning algorithm.

[0009] Optionally, the training sample set includes a training sample subset and a test sample subset, and the state label includes a healthy state label and a fault state label; Accordingly, the training of the support vector machine diagnostic model to be trained based on the training sample set includes: Training the to-be-trained support vector machine diagnostic model using the training sample subset to generate a trained support vector machine diagnostic model; Evaluating the support vector machine diagnostic model through the test sample subset and generating a score value corresponding to the support vector machine diagnostic model; The support vector machine diagnosis model is iteratively updated according to the score value until the score value of the support vector machine diagnosis model meets the score requirement or reaches a preset number of iterations.

[0010] Optionally, the performing binning processing on the signal parameters includes: Obtaining reference information on the value range and change rule corresponding to the signal parameter; Determine the abnormal value interval corresponding to the signal parameter according to the fault information of the isolated switching power supply at the front end of the aging station; Determine the binning interval corresponding to the signal parameter based on the value range reference information, the change rule reference information and the abnormal value interval; The signal parameters are binned according to the binning intervals.

[0011] Optionally, the aging station front-end isolated switching power supply fault detection and diagnosis method further includes: Acquire multiple real-time simulation monitoring signal values ​​of the analog signal of the isolated switching power supply at the front end of the aging station; Inputting the real-time simulation monitoring signal value into the support vector machine diagnosis model, and obtaining the target state label generated by the support vector machine diagnosis model by processing the real-time simulation monitoring signal value; In the case where the target state tag is a fault state tag, a target protection strategy of the isolated switching power supply at the front end of the aging station is triggered and executed.

[0012] According to a second aspect of the embodiments of this specification, a device for detecting and diagnosing faults of an isolated switching power supply at the front end of a burn-in station is provided, comprising: An acquisition module is configured to acquire multiple historical signal values ​​corresponding to multiple historical time series of the analog signal of the isolated switching power supply at the front end of the aging station; A determination module, configured to determine a signal parameter of the front-end isolated switching power supply of the aging station based on the multiple historical signal values; A construction module is configured to perform binning processing on the signal parameters, and to respectively construct feature vectors of the front-end isolated switching power supply of the aging station based on at least two binning data sets included in the binning processing results; The training module is configured to construct a training sample set based on the feature vector and the state label corresponding to the feature vector, and to train the support vector machine diagnostic model to be trained based on the training sample set, wherein the trained support vector machine diagnostic model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station.

[0013] According to a third aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement any step of the method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station.

[0014] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, which, when executed by a processor, implement the steps of any one of the methods for detecting and diagnosing faults of isolated switching power supplies at the front end of an aging station.

[0015] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station.

[0016] The embodiments of this specification obtain multiple historical signal values ​​corresponding to the analog signal of the isolated switching power supply at the front end of the aging station in multiple historical time series; determine the signal parameters of the isolated switching power supply at the front end of the aging station based on the multiple historical signal values; bin the signal parameters, and construct the feature vectors of the isolated switching power supply at the front end of the aging station based on at least two binned data sets contained in the binning processing results; construct a training sample set based on the feature vector and the state label corresponding to the feature vector, and train the support vector machine diagnosis model to be trained based on the training sample set, wherein the trained support vector machine diagnosis model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station. The embodiments of this specification group the signal parameters according to certain rules through binning processing, so that the grouped signal parameters become more discrete, and then construct a training sample set through the grouped signal parameters, and train the support vector machine diagnosis model to be trained, which can be beneficial to enhancing the stability of the trained support vector machine diagnosis model and avoiding overfitting of the trained support vector machine diagnosis model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for detecting and diagnosing faults of a front-end isolated switching power supply of a burn-in station provided by one embodiment of this specification; Figure 2 It is a structural schematic diagram of a front-end isolated switching power supply fault detection and diagnosis device for a burn-in station provided by an embodiment of this specification; Figure 3 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0018] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0019] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0020] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0021] First, the terms involved in one or more embodiments of this specification are explained.

[0022] Generalized Sequential Pattern (GSP) Mining: GSP is mainly used to process sequence data sets to find frequent sequences that meet the minimum support. The GSP algorithm uses a prefix search tree structure to organize candidate sequences through layer-by-layer mining, and reduces the search space through pruning technology to improve efficiency.

[0023] Current high-temperature aging products can achieve long-term monitoring of the test environment by adding long-term in-machine monitoring and overstress protection mechanisms, and can respond promptly when a product fails, achieving post-maintenance based on fault data. However, due to the lack of active protection technology for high-temperature aging products, existing aging products are difficult to achieve the integrity of the test process and the consistency of the test environment stress. It is very easy to cause the test process to be interrupted due to product failure, resulting in major property losses such as damage to millions of test devices, or the aging test is identified as a failure test due to adverse effects such as additional stress introduced during the test due to product performance degradation, resulting in ineffective waste of resources. At the same time, ensuring the quality of high-temperature aging tests can avoid over-aging and under-aging failures in integrated circuits, greatly reduce the failure rate of integrated circuits, and avoid large-scale electronic system failures such as new energy vehicles, civil airliners, and energy storage transmission stations due to integrated circuit failures.

[0024] Therefore, developing an intelligent test quality assurance system not only has important economic value, but also can help my country's high-end test equipment move to the forefront of the world.

[0025] Currently, active protection technology is difficult to adapt to high-temperature aging products. The key difficulties include: (1) inconsistent test environment makes it difficult to determine the health benchmark; (2) the multiple structural levels of the product make it difficult to calculate the performance degradation trends of different levels; (3) the complex composition of fault sources makes it difficult to construct fault self-healing strategies.

[0026] In addition, during the aging test, the front-end isolated switching power supply of the integrated circuit high-temperature aging test bench will generate monitoring signals such as voltage and current. The amount of monitoring signal data collected directly is large and contains a lot of redundant information.

[0027] In response to the above problems, and in view of the urgent need to independently ensure the performance of high-end test equipment in key areas, the characteristic parameters of high-temperature aging products are accurately monitored, and the characteristic vector of the isolated switching power supply at the front end of the aging station is constructed based on the monitored characteristic parameters. The model is trained based on the characteristic vector and its corresponding label, and the trained model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station to ensure the quality of the long-term operating environment of the test and meet the needs of large-scale integrated circuit batch aging. The relevant technical system can be effectively expanded to the same type of aging system to enhance the key scientific and technological strength of the integrated circuit testing industry.

[0028] The embodiment of this specification first extracts the performance parameters of ripple voltage from these monitoring data, and then uses the binning discretization method to perform feature processing on the extracted multiple performance parameters and convert them into a feature matrix with high information density. After binning, the value of the feature is more stable, and the tolerance of the model to abnormal values ​​is enhanced. Binning groups data according to certain rules to make the data more discrete, so as to enhance the stability of the model and avoid overfitting.

[0029] Based on the support vector machine diagnostic model, the feature matrix is ​​learned and classified to complete the fault detection and diagnosis of the primary switching power supply of the aging test bench. In addition, the overvoltage protection and overcurrent protection mechanisms are combined to achieve real-time response and ensure the normal progress of the aging test.

[0030] In this specification, a method for detecting and diagnosing faults of an isolated switching power supply at the front end of an aging station is provided. This specification also relates to a device for detecting and diagnosing faults of an isolated switching power supply at the front end of an aging station, a computing device, a computer-readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.

[0031] Figure 1 A flow chart of a method for detecting and diagnosing faults of an isolated switching power supply at the front end of a burn-in station provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0032] Step 102: Acquire multiple historical signal values ​​corresponding to multiple historical time series of the analog signal of the isolated switching power supply at the front end of the aging station.

[0033] Specifically, the aging bench is an integrated circuit high-temperature aging test bench, which accelerates various physical and chemical reaction processes inside the components by continuously applying a certain amount of electrical stress to the components for a long time, prompting various potential faults inside the components to be exposed early, thereby eliminating early failure products and making the electronic components enter a period of low failure rate and relative stability from the beginning of use. The front-end isolated switching power supply is used to provide the required power for the entire aging test bench.

[0034] Since the isolated switching power supply at the front end of the aging test bench will generate monitoring signals such as current and voltage during operation, the analog signal described in the embodiment of this specification may include an output voltage signal and a current accuracy signal.

[0035] In addition, the multiple historical signal values ​​described in the embodiments of this specification may be historical time series data of analog signals. Each historical time series may be composed of time points in a time period corresponding to each complete use process of the front-end isolated switching power supply.

[0036] In practical applications, the historical signal values ​​corresponding to the analog signals of the primary switching power supply can be obtained through simulation. In the simulation environment, by setting the input parameters (mains input voltage, load conditions, etc.) and working characteristics of the primary switching power supply, the signal values ​​of the corresponding voltage and current signals can be generated and output. The simulation system can simulate a variety of actual operating conditions (different load changes, component aging status, etc.), so as to generate monitoring signal data covering normal operation and fault status.

[0037] The signal data generated by simulation has high controllability and diversity, and can provide reliable data support for performance parameter extraction and fault diagnosis.

[0038] Step 104: Based on the multiple historical signal values, determine the signal parameters of the isolated switching power supply at the front end of the aging station.

[0039] Specifically, based on the aforementioned analog signal being a voltage signal, the signal parameter may be a ripple voltage.

[0040] The embodiments of this specification can analyze the voltage signal generated by simulation and extract the key performance parameter, namely the ripple voltage. The ripple voltage is used to evaluate the AC component in the DC output voltage and is an important indicator of output quality. The AC part is retained by subtracting the DC component (average value).

[0041] Step 106: binning the signal parameters, and constructing feature vectors of the front-end isolated switching power supply of the aging station based on at least two binning data sets included in the binning processing results.

[0042] Specifically, the layer-by-layer frequent sequence mining algorithm (GSP) can be used to identify regular time series changes. By introducing time series patterns, fault modes that gradually change over a long period of time can be identified, rather than just relying on instantaneous data, thereby improving the accuracy of fault detection. Based on the acquired historical signal values, the changing patterns of voltage and current are analyzed to identify the characteristics of the load. By analyzing indicators such as voltage and current fluctuations and instantaneous changes, the type of load can be determined, such as resistive load, inductive load, or capacitive load.

[0043] In an optional implementation, the binning the signal parameters includes: The signal parameters are binned using a K-means binning algorithm.

[0044] Specifically, the embodiment of this specification adopts K-means binning algorithm (K-means Binning) and bins the signal parameters according to their data distribution rules. In addition, the signal parameters can also be binned with reference to the classification requirements of the support vector machine diagnostic model to ensure that the discrete data after binning can effectively reflect the differences between different operating states of the isolated switching power supply at the front end of the aging station.

[0045] In practical applications, the signal parameters are binned using the K-means binning algorithm. Specifically, the K-means model can be initialized first, and then the number of bins is selected as the number of clusters for the K-means binning. The K-means model is then trained using sample data, and the signal parameters are binned using the trained K-means model and the number of clusters to generate at least two corresponding binning intervals. The signal parameters contained in a binning interval constitute a binning data set.

[0046] In another optional implementation, the binning the signal parameters includes: Obtaining reference information on the value range and change rule corresponding to the signal parameter; Determine the abnormal value interval corresponding to the signal parameter according to the fault information of the isolated switching power supply at the front end of the aging station; Determine the binning interval corresponding to the signal parameter based on the value range reference information, the change rule reference information and the abnormal value interval; The signal parameters are binned according to the binning intervals.

[0047] Specifically, the basis for binning signal parameters in the embodiments of this specification mainly refers to the actual value range of the signal parameters in the aging station simulation data (i.e., the value range reference information) and its change law (i.e., the change law reference information), and is combined with the following considerations: 1) Based on the parameter distribution range of the front-end isolated switching power supply in the normal operating state (healthy state) in the aging bench simulation data, determine the normal range of the signal parameters; 2) Combined with the impact of possible fault scenarios on signal parameters during the simulation process, the abnormal range of signal parameters is defined to facilitate the distinction of fault types; 3) Consider the distribution characteristics of signal parameters and reasonably set the binning interval to reduce information loss.

[0048] Through the above binning and discretization processing, continuous performance parameters can be converted into discrete performance parameters, which improves the comparability of data and reduces the complexity of model training. The binning interval setting and discretization results provide efficient and accurate input features for the subsequent support vector machine diagnostic model to be trained.

[0049] In an optional implementation, the step of constructing the feature vectors of the front-end isolated switching power supply of the aging station based on at least two binned data sets included in the binning processing result includes: Based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set, and a feature vector of the front-end isolated switching power supply of the aging station is constructed based on the feature extraction result, wherein the target binned data set is each of the at least two binned data sets.

[0050] Furthermore, the step of extracting features from the target binned data set based on the target signal parameters contained in the target binned data set includes: Based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set to obtain the corresponding average value, standard deviation and peak value of the target signal parameters.

[0051] Specifically, the target binned data set is each of the at least two binned data sets, and the signal parameters included in the target binned data sets are the target signal parameters.

[0052] Before feature extraction, median filtering can be applied to the ripple voltage to reduce the impact of noise on feature extraction.

[0053] In practical applications, based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set. Specifically, three features can be extracted from the filtered ripple voltage: the average value of the ripple voltage, the standard deviation of the ripple voltage, and the peak value of the ripple voltage. After extracting these feature parameters, the feature vector of the isolated switching power supply at the front end of the aging station can be constructed based on these feature parameters to form a feature sequence with high information density, providing a basis for subsequent analysis.

[0054] Step 108: construct a training sample set based on the feature vector and the state label corresponding to the feature vector, and train the support vector machine diagnostic model to be trained based on the training sample set, wherein the trained support vector machine diagnostic model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station.

[0055] Specifically, after the feature vector is constructed, a training sample set can be constructed based on the feature vector and the state label corresponding to the feature vector, and the support vector machine diagnosis model to be trained can be trained based on the training sample set.

[0056] In the embodiments of the present specification, the support vector machine diagnostic model to be trained can be a particle swarm optimization support vector machine diagnostic model based on GSP. Therefore, particle swarm optimization (PSO) can be used to optimize the hyperparameters of the support vector machine diagnostic model to be trained, so that it can globally search for the optimal hyperparameter combination in a high-dimensional space to avoid the problem of local optimal solution.

[0057] In an optional implementation, the training sample set includes a training sample subset and a test sample subset, and the state label includes a healthy state label and a fault state label; Accordingly, the training of the support vector machine diagnostic model to be trained based on the training sample set includes: Training the to-be-trained support vector machine diagnostic model using the training sample subset to generate a trained support vector machine diagnostic model; Evaluating the support vector machine diagnostic model through the test sample subset and generating a score value corresponding to the support vector machine diagnostic model; The support vector machine diagnosis model is iteratively updated according to the score value until the score value of the support vector machine diagnosis model meets the score requirement or reaches a preset number of iterations.

[0058] Specifically, when constructing a training sample set based on feature vectors and state labels corresponding to feature vectors, the embodiments of this specification can divide the training sample set into two parts, one part is the training sample subset, which is used to train the support vector machine diagnostic model to be trained; the other part is the test sample subset, which is used to test the trained support vector machine diagnostic model.

[0059] Based on this, the support vector machine diagnosis model to be trained is trained based on the training sample set. Specifically, the support vector machine diagnosis model to be trained is trained by the feature vectors contained in the training sample subset and the state labels corresponding to the feature vectors, wherein the state labels can include two types, namely healthy state labels and fault state labels.

[0060] After the training is completed, the feature vector contained in the test sample subset and the state label corresponding to the feature vector can be input into the trained support vector machine diagnostic model to process the input data through the support vector machine diagnostic model and generate a corresponding output result. The output result may include the prediction result (healthy state or faulty state) generated by the model for fault prediction of the front-end isolated switching power supply based on the input feature vector, and may also include the score value corresponding to the output result.

[0061] Furthermore, after obtaining the scoring value, it can be determined whether the number of training iterations of the support vector machine diagnostic model to be trained reaches the preset number of iterations, and whether the scoring value is less than the preset scoring threshold; if the number of training iterations of the support vector machine diagnostic model to be trained does not reach the preset number of iterations, and the scoring value is less than the preset scoring threshold, the support vector machine diagnostic model needs to be iteratively updated according to the scoring value until the scoring value of the support vector machine diagnostic model is greater than or equal to the scoring threshold, or the number of training iterations reaches the preset number of iterations, then the training process is stopped to obtain the trained support vector machine diagnostic model.

[0062] In practical applications, multiple sets of data generated by simulation (including monitoring signals under normal operation and fault conditions) are used to train the support vector machine (SVM) diagnostic model. The training data includes feature matrices and state labels. The feature matrix is ​​the multi-performance signal parameter data after binning and discretization; the state label includes the normal state (healthy state) marked as "0" and the fault state marked as "1". SVM optimizes the classification boundary, learns the pattern relationship between different state features, and builds an accurate fault diagnosis model.

[0063] During the training process, the model performance can be evaluated through cross-validation, and the kernel function parameters of the model (RBF kernel) can be optimized using grid search. and regularization parameter C), making the training results of the model more accurate.

[0064] In an optional implementation, the method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station further includes: Acquire multiple real-time simulation monitoring signal values ​​of the analog signal of the isolated switching power supply at the front end of the aging station; Inputting the real-time simulation monitoring signal value into the support vector machine diagnosis model, and obtaining the target state label generated by the support vector machine diagnosis model by processing the real-time simulation monitoring signal value; In the case where the target state tag is a fault state tag, a target protection strategy of the isolated switching power supply at the front end of the aging station is triggered and executed.

[0065] Specifically, after the model training is completed, multiple real-time simulation monitoring signal values ​​of the analog signal of the isolated switching power supply at the front end of the aging station can be obtained, and the multiple real-time simulation monitoring signal values ​​can be input into the support vector machine diagnosis model to process the multiple real-time simulation monitoring signal values ​​through the support vector machine diagnosis model to generate corresponding target state labels. Among them, the target state label may be a healthy state label or a fault state label; and when the target state label is a fault state label, the target protection strategy of the isolated switching power supply at the front end of the aging station can be triggered and executed.

[0066] In actual applications, multiple real-time simulation monitoring signal values ​​are input into the trained SVM diagnostic model for classification. The model outputs the operating status category and confidence level of the front-end isolated switching power supply. The normal state (value 0) indicates that all performance parameters of the front-end isolated switching power supply are within the normal range; the fault state (value 1) indicates that abnormal voltage parameters of the front-end isolated switching power supply are detected. When the operating status category output by the model is a fault state, the protection mechanism needs to be triggered according to the output result. When the ripple voltage exceeds the standard, the protection measures are activated.

[0067] In addition, when it is determined that the isolated switching power supply at the front end of the aging station is in a degraded state according to the fault status label, the multi-distance metric fusion method with automatic weight optimization is used to quantitatively calculate the health state of the real-time simulation monitoring signal value to obtain the health degree of the degraded state at the current moment, and the health degree of the degraded state at the current moment is used as the final fault detection result of the isolated switching power supply at the front end of the aging station.

[0068] In an optional implementation, a multi-distance metric fusion method with automatic weight optimization is used to quantitatively calculate the health status of the real-time simulation monitoring signal value, and the health status of the degradation state at the current moment is obtained, including: Respectively calculating the Mahalanobis distance, cosine similarity and Manhattan distance between the real-time simulation monitoring signal value and the pre-acquired health baseline data; The health of the degradation state at the current moment is obtained by fusing the multi-distance metrics by automatically optimizing the weights of the Mahalanobis distance, the cosine similarity and the Manhattan distance.

[0069] Among them, the health baseline data is constructed based on the historical signal values ​​corresponding to all fault status labels.

[0070] In an optional implementation, by performing multi-distance metric fusion on the Mahalanobis distance, the cosine similarity and the Manhattan distance, the health of the degradation state at the current moment is obtained, which includes:

[0071] in, Indicates the health of the degradation state at the current moment, represents the Mahalanobis distance; represents cosine similarity; represents the Manhattan distance; , and denote weights, and + + =1.

[0072] Alternatively, when it is determined that the front-end isolated switching power supply of the aging station is in a degraded state according to the fault prediction result, the state degradation curve of the front-end isolated switching power supply of the aging station is determined based on the probability space points after the multi-dimensional feature sequence mapping and the health baseline in the residual convolutional neural network model, wherein the state degradation curve can characterize the health state of the front-end isolated switching power supply of the aging station; the multi-dimensional feature sequence is generated by extracting features from historical signal values.

[0073] In an optional implementation, the residual convolutional neural network model is trained in the following manner: Obtaining a training timing degradation feature sample of the front-end isolated switching power supply of the aging station; wherein each training timing degradation feature sample is marked with a degradation feature state; Inputting the training time series degradation feature samples into a pre-established residual convolutional neural network model to obtain a mapped first probability space point; The degradation starting point of the front-end isolated switching power supply of the aging station is determined according to the two-dimensional first probability space point, and a health baseline of the front-end isolated switching power supply of the aging station is generated.

[0074] In the actual implementation process, the timing degradation feature samples of the isolated switching power supply training at the front end of the aging station can be expressed as , the maximum number of iterations max_iter. Mark the degradation characteristic state corresponding to the isolated switching power supply at the front end of the training aging station , including healthy and degraded states.

[0075] The embodiments of this specification provide active protection technology for high-temperature aging test benches for integrated circuits to achieve the integrity of the test process and the consistency of the test environment stress, and can reduce the significant property losses caused by the damage of millions of test devices due to forced interruption of the test process due to machine failure, or can reduce the adverse effects such as the introduction of additional stress during the test due to machine performance degradation, so as to avoid the aging test being identified as a failure test, thereby helping to avoid waste of resources. At the same time, ensuring the quality of high-temperature aging tests can avoid over-aging and under-aging failures of integrated circuits, greatly reduce the failure rate of integrated circuits, and help avoid the failure and shutdown of large-scale electronic systems such as new energy vehicles, civil airliners, energy storage and transmission stations using the same integrated circuits due to integrated circuit failures.

[0076] The embodiments of this specification obtain multiple historical signal values ​​corresponding to the analog signal of the isolated switching power supply at the front end of the aging station in multiple historical time series; determine the signal parameters of the isolated switching power supply at the front end of the aging station based on the multiple historical signal values; bin the signal parameters, and construct the feature vectors of the isolated switching power supply at the front end of the aging station based on at least two binned data sets contained in the binning processing results; construct a training sample set based on the feature vector and the state label corresponding to the feature vector, and train the support vector machine diagnosis model to be trained based on the training sample set, wherein the trained support vector machine diagnosis model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station. The embodiments of this specification group the signal parameters according to certain rules through binning processing, so that the grouped signal parameters become more discrete, and then construct a training sample set through the grouped signal parameters, and train the support vector machine diagnosis model to be trained, which can be beneficial to enhancing the stability of the trained support vector machine diagnosis model and avoiding overfitting of the trained support vector machine diagnosis model.

[0077] Corresponding to the above method embodiment, this specification also provides an embodiment of a device for detecting and diagnosing faults of an isolated switching power supply at the front end of a burn-in station. Figure 2 FIG. 1 is a schematic diagram showing a structure of a device for detecting and diagnosing a fault of a front-end isolated switching power supply of a burn-in station provided by an embodiment of the present specification. Figure 2 As shown, the device comprises: The acquisition module 202 is configured to acquire multiple historical signal values ​​corresponding to multiple historical time series of the analog signal of the isolated switching power supply at the front end of the aging station; The determination module 204 is configured to determine the signal parameters of the front-end isolated switching power supply of the aging station based on the multiple historical signal values; A construction module 206 is configured to perform binning processing on the signal parameters, and to construct feature vectors of the front-end isolated switching power supply of the aging station based on at least two binning data sets included in the binning processing results; The training module 208 is configured to construct a training sample set based on the feature vector and the state label corresponding to the feature vector, and to train the support vector machine diagnostic model to be trained based on the training sample set, wherein the trained support vector machine diagnostic model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station.

[0078] Optionally, the construction module 206 is further configured to: Based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set, and a feature vector of the front-end isolated switching power supply of the aging station is constructed based on the feature extraction result, wherein the target binned data set is each of the at least two binned data sets.

[0079] Optionally, the construction module 206 is further configured to: Based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set to obtain the corresponding average value, standard deviation and peak value of the target signal parameters.

[0080] Optionally, the construction module 206 is further configured to: The signal parameters are binned using a K-means binning algorithm.

[0081] Optionally, the training sample set includes a training sample subset and a test sample subset, and the state label includes a healthy state label and a fault state label; Accordingly, the training module 208 is further configured to: Training the to-be-trained support vector machine diagnostic model using the training sample subset to generate a trained support vector machine diagnostic model; Evaluating the support vector machine diagnostic model through the test sample subset and generating a score value corresponding to the support vector machine diagnostic model; The support vector machine diagnosis model is iteratively updated according to the score value until the score value of the support vector machine diagnosis model meets the score requirement or reaches a preset number of iterations.

[0082] Optionally, the construction module 206 is further configured to: Obtaining reference information on the value range and change rule corresponding to the signal parameter; Determine the abnormal value interval corresponding to the signal parameter according to the fault information of the isolated switching power supply at the front end of the aging station; Determine the binning interval corresponding to the signal parameter based on the value range reference information, the change rule reference information and the abnormal value interval; The signal parameters are binned according to the binning intervals.

[0083] Optionally, the aging station front-end isolated switching power supply fault detection and diagnosis device further includes a processing module 210 configured to: Acquire multiple real-time simulation monitoring signal values ​​of the analog signal of the isolated switching power supply at the front end of the aging station; Inputting the real-time simulation monitoring signal value into the support vector machine diagnosis model, and obtaining the target state label generated by the support vector machine diagnosis model by processing the real-time simulation monitoring signal value; In the case where the target state tag is a fault state tag, a target protection strategy of the isolated switching power supply at the front end of the aging station is triggered and executed.

[0084] The above is a schematic scheme of a front-end isolated switch power supply fault detection and diagnosis device for an aging station of this embodiment. It should be noted that the technical scheme of the front-end isolated switch power supply fault detection and diagnosis device for the aging station and the technical scheme of the front-end isolated switch power supply fault detection and diagnosis method for the aging station mentioned above belong to the same concept. For details not described in detail in the technical scheme of the front-end isolated switch power supply fault detection and diagnosis device for the aging station, please refer to the description of the technical scheme of the front-end isolated switch power supply fault detection and diagnosis method for the aging station mentioned above.

[0085] Figure 3The block diagram of a computing device 300 according to an embodiment of the present specification is shown. The components of the computing device 300 include but are not limited to a memory 310 and a processor 320. The processor 320 is connected to the memory 310 via a bus 330, and the database 350 is used to store data.

[0086] The computing device 300 also includes an access device 340 that enables the computing device 300 to communicate via one or more networks 360. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 340 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0087] In one embodiment of the present specification, the above components of the computing device 300 and Figure 3 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 3 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0088] The computing device 300 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 300 may also be a mobile or stationary server.

[0089] The processor 320 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station.

[0090] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned aging station front-end isolated switching power supply fault detection and diagnosis method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned aging station front-end isolated switching power supply fault detection and diagnosis method.

[0091] An embodiment of the present specification also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station.

[0092] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned aging station front-end isolated switching power supply fault detection and diagnosis method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned aging station front-end isolated switching power supply fault detection and diagnosis method.

[0093] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is instructed to execute the steps of the above-mentioned method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station.

[0094] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station belong to the same concept. For details not described in detail in the technical scheme of the computer program, please refer to the description of the technical scheme of the above-mentioned method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station.

[0095] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0097] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0098] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0099] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A method for detecting and diagnosing faults of an isolated switching power supply at the front end of a burn-in station, comprising: Obtain multiple historical signal values ​​corresponding to multiple historical time series of the analog signal of the isolated switching power supply at the front end of the aging station; Based on the multiple historical signal values, determining the signal parameters of the isolated switching power supply at the front end of the aging station; Binning the signal parameters, and constructing feature vectors of the front-end isolated switching power supply of the aging station based on at least two binning data sets included in the binning processing results; A training sample set is constructed based on the feature vector and the state label corresponding to the feature vector, and a support vector machine diagnostic model to be trained is trained based on the training sample set, wherein the trained support vector machine diagnostic model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station.

2. The method for detecting and diagnosing faults of the front-end isolated switching power supply of the aging station according to claim 1, wherein the feature vectors of the front-end isolated switching power supply of the aging station are constructed based on at least two binning data sets contained in the binning processing result, respectively, including: Based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set, and a feature vector of the front-end isolated switching power supply of the aging station is constructed based on the feature extraction result, wherein the target binned data set is each of the at least two binned data sets.

3. The method for detecting and diagnosing faults of isolated switching power supplies at the front end of a burn-in station according to claim 2, wherein the step of extracting features of the target binned data set based on target signal parameters contained in the target binned data set comprises: Based on the target signal parameters contained in the target binned data set, feature extraction is performed on the target binned data set to obtain the corresponding average value, standard deviation and peak value of the target signal parameters.

4. According to the method for detecting and diagnosing faults of isolated switching power supplies at the front end of a burn-in station as claimed in claim 1, the step of binning the signal parameters comprises: The signal parameters are binned using a K-means binning algorithm.

5. The method for detecting and diagnosing faults of isolated switching power supplies at the front end of a burn-in station according to claim 1, wherein the training sample set comprises a training sample subset and a test sample subset, and the state label comprises a healthy state label and a fault state label; Accordingly, the training of the support vector machine diagnostic model to be trained based on the training sample set includes: Training the to-be-trained support vector machine diagnostic model using the training sample subset to generate a trained support vector machine diagnostic model; Evaluating the support vector machine diagnostic model through the test sample subset and generating a score value corresponding to the support vector machine diagnostic model; The support vector machine diagnosis model is iteratively updated according to the score value until the score value of the support vector machine diagnosis model meets the score requirement or reaches a preset number of iterations.

6. According to the method for detecting and diagnosing faults of isolated switching power supplies at the front end of a burn-in station as claimed in claim 1, the step of binning the signal parameters comprises: Obtaining reference information on the value range and change rule corresponding to the signal parameter; Determine the abnormal value interval corresponding to the signal parameter according to the fault information of the isolated switching power supply at the front end of the aging station; Determine the binning interval corresponding to the signal parameter based on the value range reference information, the change rule reference information and the abnormal value interval; The signal parameters are binned according to the binning intervals.

7. The method for detecting and diagnosing faults of the front-end isolated switching power supply of the burn-in station according to claim 1 further comprises: Acquire multiple real-time simulation monitoring signal values ​​of the analog signal of the isolated switching power supply at the front end of the aging station; Inputting the real-time simulation monitoring signal value into the support vector machine diagnosis model, and obtaining the target state label generated by the support vector machine diagnosis model by processing the real-time simulation monitoring signal value; In the case where the target state tag is a fault state tag, a target protection strategy of the isolated switching power supply at the front end of the aging station is triggered and executed.

8. A front-end isolated switching power supply fault detection and diagnosis device for a burn-in station, comprising: An acquisition module is configured to acquire multiple historical signal values ​​corresponding to multiple historical time series of the analog signal of the isolated switching power supply at the front end of the aging station; A determination module, configured to determine a signal parameter of the front-end isolated switching power supply of the aging station based on the multiple historical signal values; A construction module is configured to perform binning processing on the signal parameters, and to respectively construct feature vectors of the front-end isolated switching power supply of the aging station based on at least two binning data sets included in the binning processing results; The training module is configured to construct a training sample set based on the feature vector and the state label corresponding to the feature vector, and to train the support vector machine diagnostic model to be trained based on the training sample set, wherein the trained support vector machine diagnostic model is used to perform fault detection and diagnosis on the isolated switching power supply at the front end of the aging station.

9. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the method for detecting and diagnosing faults of the isolated switching power supply at the front end of the aging station as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for detecting and diagnosing faults of the isolated switching power supply at the front end of a burn-in station as claimed in any one of claims 1 to 7.

Images