Fault prediction method and device for driving control detection board of aging test equipment

Abstract

The embodiment of the invention provides a fault prediction method and device for an aging test equipment drive control detection board. The fault prediction method for the aging test equipment drive control detection board comprises the steps of obtaining historical signal values corresponding to analog quantity signals of the aging test equipment drive control detection board in a plurality of historical time sequences; the similarity between different degradation paths of the aging test equipment driving control detection board is calculated, and the different degradation paths are composed of historical signal values corresponding to different historical time sequences; clustering the different degradation paths based on the similarity to generate at least two clustering results; taking historical signal values corresponding to the degradation paths contained in different clustering results as training data, inputting the training data into a corresponding to-be-trained fault prediction model for training, and obtaining a trained fault prediction model; the number of the to-be-trained fault prediction models is equal to the number of the at least two clustering results, and the to-be-trained fault prediction models are in one-to-one correspondence with the clustering results.

Description

Technical Field

[0001] The embodiments of the present specification relate to the technical field of non-destructive reliability screening of integrated circuits, and more particularly to a method for predicting faults of a drive control detection board of an aging test device. Background Art

[0002] Integrated circuit high temperature aging test equipment accelerates various physical and chemical reaction processes inside components by continuously applying a certain amount of electrical stress to components over a long period of time, prompting various potential faults inside components to be exposed early, thereby eliminating early failed products and allowing electronic components to enter a period of low failure rate and relative stability from the beginning of use.

[0003] The current high-temperature aging test bench for integrated circuits can achieve long-term monitoring of the test environment by adding long-term monitoring in the machine and overstress protection mechanisms, and can respond in time when the machine fails, realizing post-maintenance based on fault data. However, due to the lack of active protection technology for high-temperature aging test benches for integrated circuits, it is difficult to achieve the integrity of the test process and the consistency of the stress of the test environment, 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 adverse effects such as the introduction of additional stress during the test due to the degradation of machine performance, resulting in the aging test being identified as a failure test, 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, 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.

[0004] Since IC high temperature aging test equipment operates under harsh conditions such as high temperature for a long time, the risk of failure of its key equipment is high. Therefore, the failure prediction and health management of key equipment of IC high temperature aging test equipment has become an important research direction. Effective health assessment and failure prediction can promote the development of reliable maintenance plans, thereby preventing potential failures.

[0005] Key equipment of integrated circuit high temperature aging test equipment, such as the drive control detection board, is mainly used for the generation of secondary power supply and voltage and current detection, digital signal generation and drive, analog signal generation and drive, temperature signal feedback circuit, etc. Due to the core role of drive control detection in the system, once it fails, it will have a serious impact on the entire system, not only causing test failure, but also causing equipment damage and triggering safety accidents. Therefore, how to predict the fault of drive control detection has become an urgent problem to be solved. Summary of the invention

[0006] In view of this, an embodiment of this specification provides a method for predicting a fault of a drive control detection board of an aging test device. One or more embodiments of this specification also involve a device for predicting a fault of a drive control detection board of an aging test device, a computing device, a computer-readable storage medium, and a computer program to solve the technical defects existing in the prior art.

[0007] According to a first aspect of an embodiment of this specification, a method for predicting a fault of a drive control detection board of an aging test device is provided, comprising: Obtain historical signal values ​​corresponding to multiple historical time series of analog signals of a drive control detection board of an aging test device; Calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment, wherein the different degradation paths are composed of historical signal values ​​corresponding to different historical time series; Clustering different degradation paths based on the similarity to generate at least two clustering results; The historical signal values ​​corresponding to the degradation paths contained in different clustering results are respectively used as training data input to the corresponding fault prediction model to be trained to obtain a trained fault prediction model; The number of the fault prediction models to be trained is equal to the number of the at least two clustering results, and each fault prediction model to be trained corresponds to each clustering result one by one.

[0008] Optionally, the fault prediction model to be trained is a multidimensional recurrent neural network model, including an input layer, an intermediate layer and an output layer, the intermediate layer includes a sequentially connected neighbor component analysis model structure and a multidimensional recurrent neural network model structure, and the multidimensional recurrent neural network model structure includes a fully connected layer, a bidirectional long short-term memory network layer, a bidirectional gated recurrent unit layer and a splicing layer.

[0009] Optionally, the calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment includes: The historical signal values ​​corresponding to different degradation paths of the drive control detection board of the aging test equipment are processed by the neighbor component analysis model structure to obtain the similarity between different degradation paths, wherein the neighbor component analysis model structure processes the historical signal values ​​corresponding to different degradation paths of the drive control detection board of the aging test equipment by the neighbor component analysis algorithm.

[0010] Optionally, the intermediate layer includes a neighbor component analysis model structure, a Gaussian mixture model structure, and a multidimensional recurrent neural network model structure that are sequentially connected; Accordingly, clustering different degradation paths based on the similarity includes: The different degradation paths are clustered based on the similarity by using the Gaussian mixture model structure, wherein the Gaussian mixture model structure clusters the different degradation paths based on the similarity by using a Gaussian mixture algorithm.

[0011] Optionally, the calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment includes: Determine at least two signal parameters of the aging test equipment drive control detection board based on the historical signal value; Performing feature extraction on the at least two signal parameters to obtain feature vectors corresponding to different degradation paths; The similarity is calculated for the characteristic vector corresponding to each degradation path to obtain the similarity between different degradation paths of the drive control detection board of the aging test equipment.

[0012] Optionally, the at least two signal parameters include: mean, standard deviation, variance, skewness, and peak-to-peak value.

[0013] Optionally, the fault prediction method of the aging test equipment drive control detection board further includes: Obtaining the signal value corresponding to the target time series of the analog signal of the drive control detection board of the aging test equipment; Determine, according to the signal value, a target clustering result to which the target degradation path composed of the signal value belongs; A target fault prediction model corresponding to the target clustering result is determined, the signal value is input into the target fault prediction model, and a fault prediction result of the drive control detection board of the aging test equipment output by the target fault prediction model is obtained.

[0014] According to a second aspect of the embodiments of this specification, a fault prediction device for a drive control detection board of an aging test device is provided, comprising: An acquisition module is configured to acquire historical signal values ​​corresponding to multiple historical time series of analog signals of a drive control detection board of an aging test device; A calculation module is configured to calculate the similarity between different degradation paths of the drive control detection board of the aging test equipment, wherein different degradation paths are composed of historical signal values ​​corresponding to different historical time series; A clustering module, configured to cluster different degradation paths based on the similarity to generate at least two clustering results; The training module is configured to respectively use the historical signal values ​​corresponding to the degradation paths included in different clustering results as training data input into the corresponding fault prediction model to be trained to obtain a trained fault prediction model; The number of the fault prediction models to be trained is equal to the number of the at least two clustering results, and each fault prediction model to be trained corresponds to each clustering result one by one.

[0015] 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 fault prediction method for the drive control detection board of the aging test equipment.

[0016] 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 predicting a fault of a drive control detection board of an aging test device.

[0017] 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 predicting the fault of the drive control detection board of the aging test equipment.

[0018] The fault prediction method of the drive control detection board of the aging test equipment provided in the embodiment of this specification is obtained by obtaining the historical signal values ​​corresponding to the analog signal of the drive control detection board of the aging test equipment in multiple historical time series; calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment, wherein different degradation paths are composed of historical signal values ​​corresponding to different historical time series; clustering different degradation paths based on the similarity to generate at least two clustering results; respectively inputting the historical signal values ​​corresponding to the degradation paths contained in different clustering results as training data into the corresponding fault prediction model to be trained to obtain the trained fault prediction model; wherein the number of fault prediction models to be trained is equal to the number of the at least two clustering results, and each fault prediction model to be trained corresponds to each clustering result one by one. Through this processing method, the fault mode is taken into consideration, the different degradation paths of the drive control detection board of the aging test equipment are identified, and the historical signal values ​​of the analog signal corresponding to the drive control detection board of the aging test equipment of the same type of degradation path are brought into the same model for training and prediction, which is conducive to improving the accuracy of the fault prediction results of the drive control detection board of the aging test equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of a fault prediction method of a drive control detection board of an aging test equipment provided by an embodiment of this specification; Figure 2is a processing flow chart of a training process of a fault prediction model to be trained provided by an embodiment of this specification; Figure 3 is a process flow chart of a fault prediction model provided by an embodiment of this specification; Figure 4 It is a structural schematic diagram of a fault prediction device for a drive control detection board of an aging test equipment provided by an embodiment of this specification; Figure 5 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0020] 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.

[0021] 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.

[0022] 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".

[0023] First, the terms involved in one or more embodiments of this specification are explained.

[0024] Neighborhood Component Analysis (NCA): It is a supervised learning method mainly used for metric learning and dimensionality reduction. Its core idea is to maximize the average leave-one-out classification effect in the new transformation space by learning a linear space transformation matrix.

[0025] Bidirectional Long Short-Term Memory (BiLSTM): is a special recurrent neural network structure that combines two directional LSTM layers, one for processing the forward direction of the time series (from the past to the future) and the other for processing the reverse direction of the time series (from the future to the past), so that the context information can be obtained simultaneously when processing sequence data.

[0026] Remaining Useful Life (RUL): Mainly refers to the remaining service life of a system after it has run for a period of time. Accurately predicting the remaining service life of a system can greatly reduce the losses caused by system downtime and improve the operating reliability of the system.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] In addition, for high-temperature aging test benches for integrated circuits, current fault prediction is mainly carried out based on individual differences and degradation characteristics of equipment or systems, while there is little research on the impact of different degradation paths of the drive control detection board on the prediction results. However, since the drive control detection board generally has multiple degradation paths and other unstable conditions, the current prediction method will have two problems: (1) Multiple degradation paths: The drive control detection board has multiple degradation paths, which is reflected in the aging test bench as having multiple performance degradation paths. The impact of different performance degradation paths on the remaining service life of the equipment is different, which will affect the prediction results; (2) The voltage parameter time series of the drive control detection board is long, and the degradation information in the series is difficult to capture and learn, which will also affect the prediction results. Due to the existence of the above two problems, it is currently impossible to carry out accurate fault prediction for the drive control detection board of the aging test equipment.

[0031] In response to the above problems, the embodiments of this specification utilize a large language model for fault diagnosis and prediction of integrated circuit high-temperature aging equipment to ensure that the technology has the ability to process and analyze multi-source heterogeneous data, and the ability to dynamically mine degradation and fault characteristics, so as to solve the problems of fault feature annihilation, failure path ambiguity and inaccurate degradation trend prediction caused by environmental stress fluctuations under the coupling interference of thermal-electric multi-physical fields, realize system self-diagnosis and self-warning, and thus solve the problem that performance degradation trends at different levels under multiple structural levels of the product are difficult to calculate in real time.

[0032] The embodiments of this specification provide a method for predicting faults of a drive control detection board of an aging test device under multiple degradation paths, so as to solve the problem that accurate fault prediction of the drive control detection board cannot be performed.

[0033] In this specification, a fault prediction method for a drive control detection board of an aging test equipment is provided. This specification also involves a fault prediction device for a drive control detection board of an aging test equipment, a computing device, a computer-readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.

[0034] Figure 1 A flow chart of a method for predicting a fault of a drive control detection board of an aging test device provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0035] Step 102: Obtain historical signal values ​​corresponding to multiple historical time series of analog signals of the aging test equipment drive control detection board.

[0036] Specifically, the aging test equipment 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 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 drive control detection board is mainly used to provide the following functions: secondary power supply generation and voltage and current detection, digital signal generation and drive, analog signal generation and drive, and temperature signal feedback circuit.

[0037] Since the drive control detection board of the aging test equipment generates a voltage monitoring signal during operation, the analog signal described in the embodiment of this specification can be a voltage signal.

[0038] In addition, each historical time series described in the embodiments of this specification may be composed of time points in a time period corresponding to each complete use process of the drive control detection board.

[0039] Step 104: Calculate the similarity between different degradation paths of the drive control detection board of the aging test equipment, wherein different degradation paths are composed of historical signal values ​​corresponding to different historical time series.

[0040] In an optional implementation, the calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment includes: Determine at least two signal parameters of the aging test equipment drive control detection board based on the historical signal value; Performing feature extraction on the at least two signal parameters to obtain feature vectors corresponding to different degradation paths; The similarity is calculated for the characteristic vector corresponding to each degradation path to obtain the similarity between different degradation paths of the drive control detection board of the aging test equipment.

[0041] The at least two signal parameters include: mean, standard deviation, variance, skewness, and peak-to-peak value.

[0042] In addition, the embodiment of the present specification trains the fault prediction model to be trained by acquiring historical signal values, and the fault prediction model to be trained is a multidimensional recurrent neural network model, including an input layer, an intermediate layer and an output layer, the intermediate layer includes a sequentially connected neighbor component analysis model structure and a multidimensional recurrent neural network model structure, and the multidimensional recurrent neural network model structure includes a fully connected layer, a bidirectional long short-term memory network layer, a bidirectional gated recurrent unit layer and a splicing layer.

[0043] Among them, the bidirectional long short-term memory network (BiLSTM) is used to process multi-sensor monitoring signals, the splicing layer is used to fuse the outputs of the bidirectional long short-term memory network and the bidirectional gated recurrent unit (BiGRU), and the output layer is a fully connected layer, namely the Dense layer, which is used to predict the remaining service life RUL. Therefore, the multidimensional recurrent neural network uses the bidirectional LSTM (BiLSTM layer) and bidirectional GRU (BiGRU layer) layers to extract time series features, and then splices the outputs of the two to finally output the predicted remaining service life.

[0044] Accordingly, the calculating of the similarity between different degradation paths of the drive control detection board of the aging test equipment includes: The historical signal values ​​corresponding to different degradation paths of the drive control detection board of the aging test equipment are processed by the neighbor component analysis model structure to obtain the similarity between different degradation paths, wherein the neighbor component analysis model structure processes the historical signal values ​​corresponding to different degradation paths of the drive control detection board of the aging test equipment by the neighbor component analysis algorithm.

[0045] The processing flow chart of a training process of a fault prediction model to be trained provided in the embodiment of this specification is as follows: Figure 2 shown.

[0046] Specifically, during the actual operation of the aging test equipment drive control detection board, its usable time does not decrease linearly with the degradation process (use process), but after being used for a period of time and reaching its life limit, the remaining usable time gradually decreases. Therefore, when predicting the fault (usable time prediction) of the aging test equipment drive control detection board, it can be considered that the initial degradation of the aging test equipment drive control detection board can be ignored, and during the initial degradation process, its remaining usable time is a constant value, and after reaching the critical value of the life, its remaining usable time decreases linearly.

[0047] Based on this, according to the principle of piecewise linear degradation, after obtaining the historical signal values ​​corresponding to multiple historical time series, the embodiments of this specification can also determine at least two signal parameters of the aging test equipment drive control detection board based on the historical signal values, specifically, the mean, standard deviation, variance, skewness, peak-to-peak value, etc. corresponding to the analog signal, so as to train the neighbor component analysis model structure in the fault prediction model to be trained based on the signal parameters.

[0048] In practical applications, after determining at least two signal parameters, feature extraction can be performed on the at least two signal parameters to obtain feature vectors corresponding to different degradation paths, and then similarity calculation is performed on the feature vectors corresponding to each degradation path to obtain the similarity between different degradation paths of the drive control detection board of the aging test equipment.

[0049] Specifically, multiple historical signal values ​​included in the same degradation path may be determined first, then the signal parameters corresponding to the multiple historical signal values ​​may be determined, and then the feature vector corresponding to the degradation path may be constructed based on the parameter values ​​corresponding to the signal parameters, thereby achieving dimensionality reduction feature extraction for the multiple historical signal values.

[0050] After feature extraction is completed, the healthy state features and the degraded state features can be divided based on the feature extraction results, and the healthy state features (including mean, standard deviation, variance, skewness, peak-to-peak value) can be regarded as the original input of the healthy set of the nearest component analysis model structure, and the degraded state features (including mean, standard deviation, variance, skewness, peak-to-peak value) can be regarded as the original input of the degraded set, and the healthy and degraded labels can be used as the model output.

[0051] Among them, the degradation state characteristics can be expressed as ,in, , i is the number of cycles of use of the aging test equipment test board, j is the dimension of the drive control characteristic of the degradation state (each time the drive control test board is used, its dimension of the degradation state characteristic is fixed, but the value of the degradation state characteristic will change with the number of cycles of use).

[0052] If the first 10% of the features in the feature extraction results of the aging test equipment drive control detection board are taken as the healthy set, and the last 90% of the features are taken as the degraded set, then the healthy set and degenerate sets It can be expressed as:

[0053]

[0054] in, and are the processed features.

[0055]

[0056]

[0057] Based on the division of healthy set and degraded set, the labels are set. The state label can be expressed as ,in is the status label corresponding to the health status, is the state label corresponding to the degradation state, and each degradation feature of the aging test equipment drive control detection board corresponds to a state label. Therefore, the state labels corresponding to the healthy set and the degradation set can be expressed as:

[0058]

[0059] Characterized by healthy set and degraded set As the input of the nearest component analysis model, the state label corresponding to the feature As the model output, by setting the maximum number of model iterations, the model parameters of the nearest component analysis model are optimized, so as to effectively divide and identify the healthy and degraded states of the drive control detection board of the aging test equipment, and obtain the learned optimized Mahalanobis distance matrix Q.

[0060] Among them, in the adaptive mapping of degradation features, the core is to adaptively map the input features to a new space that conforms to the feature state according to the nearest component analysis model, thereby reducing the aliasing of health and fault features caused by data fluctuations or changes in working conditions, making the measurement calculation between health and degradation more stable and robust, and the distance representation more accurate.

[0061] The training sample set and test sample set The one-dimensional mapping feature of the aging test equipment drive control detection board can be expressed as:

[0062]

[0063] Among them, the mapping features of the drive control detection board of each aging test equipment can be expressed as a collection of healthy mapping features and degradation mapping features: , .

[0064] The similarity of characteristic time series trajectories such as mean, standard deviation, variance, skewness, peak-to-peak value, etc. between different degradation paths is calculated through the nearest component analysis algorithm. Subsequently, the clustering of the time series trajectories can be achieved through the clustering method, so that the drive control detection board of the aging test equipment can be classified according to the performance degradation trajectory.

[0065] The embodiment of this specification takes advantage of the nearest component analysis (NCA) algorithm based on the mean, standard deviation, variance, skewness, peak-to-peak value and other performance parameters extracted by dimensionality reduction of the voltage timing signal of the drive control detection board, and scales the time axis of the unknown sequence to be consistent with the length of the template sequence, so as to better grasp the similarity between the sample performance degradation paths.

[0066] Step 106: Clustering different degradation paths based on the similarity to generate at least two clustering results.

[0067] In an optional embodiment, the aforementioned fault prediction model to be trained is a multidimensional recurrent neural network model, and the model includes an input layer, an intermediate layer and an output layer, and the intermediate layer includes a neighbor component analysis model structure, a Gaussian mixture model structure and a multidimensional recurrent neural network model structure connected in sequence; Accordingly, clustering different degradation paths based on the similarity includes: The different degradation paths are clustered based on the similarity by using the Gaussian mixture model structure, wherein the Gaussian mixture model structure clusters the different degradation paths based on the similarity by using a Gaussian mixture algorithm.

[0068] Specifically, the embodiment of this specification takes advantage of the time used for cluster centroid selection in Gaussian mixture and the complexity of cluster overlap space, and uses the optimal point that actually exists in the data set as its centroid, so that the trajectory corresponding to the centroid can be found.

[0069] Among them, the implementation process of the Gaussian mixture algorithm is as follows: Algorithm principle: Assume a point in a high-dimensional space (dimension n) If the distribution of these points is approximately an ellipsoid, a single Gaussian density function can be used To describe the probability density function that produces these data:

[0070] in is the mean, the center point of the density function; is the covariance matrix of the density function.

[0071] However, if the distribution of these points is not ellipsoidal, it is not appropriate to use a single Gaussian probability density function to describe the probability density function of the distribution of these points. At this time, a workaround can be used to express it by the weighted average of several single Gaussian probability density functions, that is, the Gaussian mixture model (GMM). The Gaussian mixture model is defined as follows:

[0072] Where m is the mixing number of the model; is the weight coefficient of the mixed model, and ; is the i-th single Gaussian probability density function.

[0073] The unknown parameters in the mixed Gaussian distribution can usually be evaluated by the expectation maximization EM algorithm (Expectation Maximization), and the main steps are divided into two stages: E and M.

[0074] The Gaussian mixture method is used to cluster system samples through the performance degradation path similarity matrix of the aging test equipment drive control detection board, so that the aging test equipment drive control detection board can be identified according to the performance degradation trajectory time series.

[0075] Step 108: inputting the historical signal values ​​corresponding to the degradation paths included in different clustering results as training data into the corresponding fault prediction model to be trained, thereby obtaining a trained fault prediction model.

[0076] The number of the fault prediction models to be trained is equal to the number of the at least two clustering results, and each fault prediction model to be trained corresponds to each clustering result one by one.

[0077] Specifically, after clustering different degradation paths to generate at least two clustering results, the number of clustering results can be determined first, and then a corresponding number of fault prediction models to be trained can be constructed, and the historical signal values ​​corresponding to the degradation paths contained in each clustering result can be used to train the multidimensional recurrent neural network model structure in each fault prediction model to be trained; wherein the historical signal values ​​corresponding to the degradation paths contained in each clustering result are used to train a fault prediction model to be trained, and the fault prediction models to be trained by the historical signal values ​​corresponding to the degradation paths contained in each clustering result are different.

[0078] For example, if two clustering results are generated, two fault prediction models to be trained are constructed, and the multidimensional recurrent neural network model structure in one fault prediction model to be trained can be trained by the historical signal values ​​corresponding to the degradation path contained in the first clustering result, and the multidimensional recurrent neural network model structure in the other fault prediction model to be trained can be trained by the historical signal values ​​corresponding to the degradation path contained in the second clustering result.

[0079] In practical applications, the multidimensional recurrent neural network model structure uses momentum and adaptive learning rate to speed up convergence, and has been proven to be superior to the classic stochastic gradient descent optimizer to achieve higher processing efficiency and prediction quality.

[0080] The specific implementation process is as follows: 1) Establish at least two fault prediction models to be trained, corresponding to multiple performance degradation paths. According to the performance degradation paths, the historical signal values ​​corresponding to different degradation paths of the drive control detection board are used as the input of the multidimensional recurrent neural network model structure in the fault prediction model to be trained.

[0081] In practical applications, after determining at least two signal parameters of the drive control detection board of the aging test equipment, the at least two signal parameters can also be used as model input. , where K is the number of training samples, Represents the input data matrix obtained from the monitoring data time series by time window, with a size of N, where are the sensor measurements of the s selected sensors at time t.

[0082] 2) The operating condition data Connect to In the above example, we construct a high-order vector Then, the vector Feed it into the stacked BiLSTM and BiGRU layers to obtain hidden feature maps of different dimensions.

[0083] 3) Set the number of BiLSTM layers and BiGRU layers to be the same, that is, the total number of stacked BiGRU layers is also M. For the last BiLSTM layer and BiGRU layer, the output of the last BiLSTM layer and BiGRU layer at the last time is used as the final output of the last BiLSTM layer and BiGRU layer.

[0084] 4) The hidden feature vectors are concatenated into a merged feature vector. Finally, the merged feature vector is fed into two more linear regression dense layers to generate the predicted RUL.

[0085] 5) The error between the RUL predicted value and the RUL actual value is used as the loss function to calculate the loss, and the relevant parameters in the network are updated through back propagation. The training is repeated until the loss reaches the required level. The prediction accuracy is used to evaluate the performance of the fault prediction model. In the embodiments of this specification, the prediction accuracy is defined as follows:

[0086] Among them, RUL is the actual RUL (actual remaining usable time), The predicted RUL (predicted remaining usable time) and TUL estimated by the fault prediction model It is the actual total usage time of the target circuit, which is defined as the total number of test cycles when the aging test equipment drives the control detection board to reach the failure threshold.

[0087] In an optional implementation, the method for predicting a fault of a drive control detection board of the aging test equipment further includes: Obtaining the signal value corresponding to the target time series of the analog signal of the drive control detection board of the aging test equipment; Determine, according to the signal value, a target clustering result to which the target degradation path composed of the signal value belongs; A target fault prediction model corresponding to the target clustering result is determined, the signal value is input into the target fault prediction model, and a fault prediction result of the drive control detection board of the aging test equipment output by the target fault prediction model is obtained.

[0088] Specifically, after the model training is completed, the signal value corresponding to the analog signal of the aging test equipment drive control detection board in the target time series can be obtained, and the signal value can be input into the fault prediction model to process the signal value through the nearest component analysis model structure in the fault prediction model, and determine the characteristic vector corresponding to the target degradation path constituted by the signal value according to the processing result, and then calculate the similarity between the target degradation path and the aforementioned multiple different degradation paths according to the characteristic vector; then determine the target clustering result to which the target degradation path belongs according to the similarity through the Gaussian mixture model structure in the fault prediction model, wherein the target clustering result belongs to one of the aforementioned at least two clustering results; then determine the target fault prediction model corresponding to the target clustering result, input the signal value into the target fault prediction model, and process the signal value or the mean, standard deviation, variance, skewness, and peak-to-peak value determined based on the signal value through the multidimensional recurrent neural network model structure in the target fault prediction model to generate a fault prediction result of the aging test equipment drive control detection board.

[0089] When it is determined that the drive control detection board of the aging test equipment is in a degraded state according to the fault prediction results, the health state of the signal value is quantitatively calculated using the multi-distance metric fusion method with automatic weight optimization 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 drive control detection board of the aging test equipment.

[0090] In an optional implementation, the health status of the signal value is quantitatively calculated using a multi-distance metric fusion method with automatic weight optimization to obtain the health status of the degradation state at the current moment, including: respectively calculating the Mahalanobis distance, cosine similarity and Manhattan distance between the 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.

[0091] Among them, the health baseline data is constructed based on the historical signal values ​​corresponding to all fault types.

[0092] 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:

[0093] in, Indicates the health of the degradation state at the current moment, represents the Mahalanobis distance; represents cosine similarity; represents Manhattan distance; , and denote weights, and + + =1.

[0094] Alternatively, when it is determined that the aging test equipment drive control detection board is in a degraded state according to the fault prediction results, the state degradation curve of the aging test equipment drive control detection board is determined based on the probability space points after the multi-dimensional feature sequence is mapped and the health baseline in the residual convolutional neural network model, wherein the state degradation curve can characterize the health state of the aging test equipment drive control detection board; the multi-dimensional feature sequence is generated by extracting features from historical signal values.

[0095] In an optional implementation, the residual convolutional neural network model is trained in the following manner: Acquire training timing degradation feature samples of the drive control detection board of the aging test equipment; 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 drive control detection board of the aging test equipment is judged according to the two-dimensional first probability space point, and the health baseline of the drive control detection board of the aging test equipment is generated.

[0096] In the actual implementation process, the training timing degradation feature samples of the aging test equipment drive control detection board can be expressed as , the maximum number of iterations max_iter. Mark the degradation characteristic state corresponding to the driver control detection board of the training aging test equipment , including healthy and degraded states.

[0097] A processing flow chart of a fault prediction model provided in the embodiment of this specification is as follows: Figure 3 As shown, the specific steps include the following steps.

[0098] Step 302: Obtain historical signal values.

[0099] Step 304: construct a fault prediction model to be trained.

[0100] Step 306: Initialize network parameters.

[0101] Step 308: Calculate the loss function.

[0102] Step 310: Model training.

[0103] Step 312: Determine whether a training cycle is completed.

[0104] Specifically, after the model is trained, it can be determined whether a training cycle is completed; if so, step 314 is executed; if not, the process returns to step 308.

[0105] Step 314: Determine whether all training cycles are completed.

[0106] Specifically, after determining that one training cycle is completed, it may be further determined whether all training cycles are completed; if so, execute step 318; if not, return to execute step 308.

[0107] Step 316: Obtain the target signal value.

[0108] Step 318: Complete model training.

[0109] After obtaining the target signal value, the target signal value can be input into the trained fault prediction model for processing. The target signal value is the signal value corresponding to the analog signal of the drive control detection board of the aging test equipment in the target time series.

[0110] Step 320: Predict the remaining usage time.

[0111] Step 322: Real data of remaining usage time.

[0112] Step 324: Calculate the model prediction error.

[0113] Specifically, after processing the target signal value through the fault prediction model and obtaining the predicted remaining usage time output by the fault prediction model, the actual remaining usage time of the aging test equipment drive control detection board (i.e., the real data of the remaining usage time) can also be obtained, and then the prediction error of the fault prediction model is calculated based on the predicted remaining usage time and the actual remaining usage time.

[0114] Step 326: Evaluate the model prediction results.

[0115] The embodiments of this specification use a nearest component analysis algorithm to evaluate the similarity between different degradation paths of the drive control detection board of aging test equipment with multiple different decay rates and different fault initiation degrees, and on this basis introduce a Gaussian mixture clustering algorithm to achieve fast and accurate classification of different degradation paths of the drive control detection board of the aging test bench; in addition, the embodiments of this specification propose a fault prediction model for the drive control detection board of aging test equipment based on a multidimensional recurrent neural network model, which achieves high-precision fault prediction by comprehensively considering the impact of the degradation path on the prediction result of the remaining usable time of the drive control detection board of the aging test equipment.

[0116] 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.

[0117] In addition, the embodiments of this specification utilize a large language model for fault diagnosis and prediction of integrated circuit high-temperature aging equipment to ensure that the technology has the ability to process and analyze multi-source heterogeneous data and the ability to dynamically mine degradation and fault characteristics, so as to solve the problems of fault feature annihilation, failure path ambiguity and inaccurate degradation trend prediction caused by environmental stress fluctuations under the interference of thermal-electric multi-physical field coupling, and realize system self-diagnosis and self-warning.

[0118] The fault prediction method of the drive control detection board of the aging test equipment provided in the embodiment of this specification is obtained by obtaining the historical signal values ​​corresponding to the analog signal of the drive control detection board of the aging test equipment in multiple historical time series; calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment, wherein different degradation paths are composed of historical signal values ​​corresponding to different historical time series; clustering different degradation paths based on the similarity to generate at least two clustering results; respectively inputting the historical signal values ​​corresponding to the degradation paths contained in different clustering results as training data into the corresponding fault prediction model to be trained to obtain the trained fault prediction model; wherein the number of fault prediction models to be trained is equal to the number of the at least two clustering results, and each fault prediction model to be trained corresponds to each clustering result one by one. Through this processing method, the fault mode is taken into consideration, the different degradation paths of the drive control detection board of the aging test equipment are identified, and the historical signal values ​​of the analog signal corresponding to the drive control detection board of the aging test equipment of the same type of degradation path are brought into the same model for training and prediction, which is conducive to improving the accuracy of the fault prediction results of the drive control detection board of the aging test equipment.

[0119] Corresponding to the above method embodiment, this specification also provides an embodiment of a fault prediction device for a drive control detection board of an aging test device, Figure 4 FIG. 1 is a schematic diagram showing a structure of a fault prediction device for a drive control detection board of an aging test device provided by an embodiment of the present specification. Figure 4 As shown, the device comprises: The acquisition module 402 is configured to acquire historical signal values ​​corresponding to multiple historical time series of the analog signal of the drive control detection board of the aging test equipment; The calculation module 404 is configured to calculate the similarity between different degradation paths of the drive control detection board of the aging test equipment, wherein different degradation paths are composed of historical signal values ​​corresponding to different historical time series; A clustering module 406 is configured to cluster different degradation paths based on the similarity to generate at least two clustering results; The training module 408 is configured to respectively input the historical signal values ​​corresponding to the degradation paths included in different clustering results as training data into the corresponding fault prediction model to be trained to obtain a trained fault prediction model; The number of the fault prediction models to be trained is equal to the number of the at least two clustering results, and each fault prediction model to be trained corresponds to each clustering result one by one.

[0120] Optionally, the fault prediction model to be trained is a multidimensional recurrent neural network model, including an input layer, an intermediate layer and an output layer, the intermediate layer includes a sequentially connected neighbor component analysis model structure and a multidimensional recurrent neural network model structure, and the multidimensional recurrent neural network model structure includes a fully connected layer, a bidirectional long short-term memory network layer, a bidirectional gated recurrent unit layer and a splicing layer.

[0121] Optionally, the calculation module 404 is further configured to: The historical signal values ​​corresponding to different degradation paths of the drive control detection board of the aging test equipment are processed by the neighbor component analysis model structure to obtain the similarity between different degradation paths, wherein the neighbor component analysis model structure processes the historical signal values ​​corresponding to different degradation paths of the drive control detection board of the aging test equipment by the neighbor component analysis algorithm.

[0122] Optionally, the intermediate layer includes a neighbor component analysis model structure, a Gaussian mixture model structure, and a multidimensional recurrent neural network model structure that are sequentially connected; Accordingly, the clustering module is further configured as follows: The different degradation paths are clustered based on the similarity by using the Gaussian mixture model structure, wherein the Gaussian mixture model structure clusters the different degradation paths based on the similarity by using a Gaussian mixture algorithm.

[0123] Optionally, the calculation module 404 is further configured to: Determine at least two signal parameters of the aging test equipment drive control detection board based on the historical signal value; Performing feature extraction on the at least two signal parameters to obtain feature vectors corresponding to different degradation paths; The similarity is calculated for the characteristic vector corresponding to each degradation path to obtain the similarity between different degradation paths of the drive control detection board of the aging test equipment.

[0124] Optionally, the at least two signal parameters include: mean, standard deviation, variance, skewness, and peak-to-peak value.

[0125] Optionally, the fault prediction device for the aging test equipment drive control detection board further includes a processing module 410 configured to: Obtaining the signal value corresponding to the target time series of the analog signal of the drive control detection board of the aging test equipment; Determine, according to the signal value, a target clustering result to which the target degradation path composed of the signal value belongs; A target fault prediction model corresponding to the target clustering result is determined, the signal value is input into the target fault prediction model, and a fault prediction result of the drive control detection board of the aging test equipment output by the target fault prediction model is obtained.

[0126] The above is a schematic scheme of a fault prediction device for a drive control detection board of an aging test device in this embodiment. It should be noted that the technical scheme of the fault prediction device for the drive control detection board of the aging test device and the technical scheme of the fault prediction method for the drive control detection board of the aging test device mentioned above belong to the same concept. For details not described in detail in the technical scheme of the fault prediction device for the drive control detection board of the aging test device, please refer to the description of the technical scheme of the fault prediction method for the drive control detection board of the aging test device mentioned above.

[0127] Figure 5 The structure block diagram of a computing device 500 provided according to an embodiment of the present specification is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0128] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. 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 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is 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.

[0129] In one embodiment of the present specification, the above components of the computing device 500 and Figure 5 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 5 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.

[0130] Computing device 500 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. Computing device 500 may also be a mobile or stationary server.

[0131] The processor 520 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the fault prediction method for the drive control detection board of the aging test equipment.

[0132] 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 fault prediction method of the above-mentioned aging test equipment drive control detection board 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 fault prediction method of the above-mentioned aging test equipment drive control detection board.

[0133] 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 predicting the fault of the drive control detection board of the aging test equipment.

[0134] 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 fault prediction method of the drive control detection board of the aging test equipment described above belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be found in the description of the technical scheme of the fault prediction method of the drive control detection board of the aging test equipment described above.

[0135] An embodiment of the present specification also provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for predicting the fault of the drive control detection board of the aging test equipment.

[0136] 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 fault prediction method of the above-mentioned aging test equipment drive control detection board belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be found in the description of the technical scheme of the fault prediction method of the above-mentioned aging test equipment drive control detection board.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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 predicting a fault of a drive control detection board of an aging test device, comprising: Obtain historical signal values ​​corresponding to multiple historical time series of analog signals of a drive control detection board of an aging test device; Calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment, wherein the different degradation paths are composed of historical signal values ​​corresponding to different historical time series; Clustering different degradation paths based on the similarity to generate at least two clustering results; The historical signal values ​​corresponding to the degradation paths contained in different clustering results are respectively used as training data input to the corresponding fault prediction model to be trained to obtain a trained fault prediction model; The number of the fault prediction models to be trained is equal to the number of the at least two clustering results, and each fault prediction model to be trained corresponds to each clustering result one by one.

2. According to the fault prediction method of the drive control detection board of the aging test equipment according to claim 1, the fault prediction model to be trained is a multidimensional recurrent neural network model, including an input layer, an intermediate layer and an output layer, the intermediate layer includes a sequentially connected neighbor component analysis model structure and a multidimensional recurrent neural network model structure, and the multidimensional recurrent neural network model structure includes a fully connected layer, a bidirectional long short-term memory network layer, a bidirectional gated recurrent unit layer and a splicing layer.

3. The fault prediction method for the drive control detection board of the aging test equipment according to claim 2, wherein the calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment comprises: The historical signal values ​​corresponding to different degradation paths of the drive control detection board of the aging test equipment are processed by the neighbor component analysis model structure to obtain the similarity between different degradation paths, wherein the neighbor component analysis model structure processes the historical signal values ​​corresponding to different degradation paths of the drive control detection board of the aging test equipment by the neighbor component analysis algorithm.

4. According to the fault prediction method of the drive control detection board of the aging test equipment according to claim 2 or 3, the intermediate layer includes a neighbor component analysis model structure, a Gaussian mixture model structure and a multidimensional recurrent neural network model structure connected in sequence; Accordingly, clustering different degradation paths based on the similarity includes: The different degradation paths are clustered based on the similarity by using the Gaussian mixture model structure, wherein the Gaussian mixture model structure clusters the different degradation paths based on the similarity by using a Gaussian mixture algorithm.

5. The fault prediction method for the drive control detection board of the aging test equipment according to claim 1, wherein the calculating the similarity between different degradation paths of the drive control detection board of the aging test equipment comprises: Determine at least two signal parameters of the aging test equipment drive control detection board based on the historical signal value; Performing feature extraction on the at least two signal parameters to obtain feature vectors corresponding to different degradation paths; The similarity is calculated for the characteristic vector corresponding to each degradation path to obtain the similarity between different degradation paths of the drive control detection board of the aging test equipment.

6. The fault prediction method for the drive control detection board of the aging test equipment according to claim 5, wherein the at least two signal parameters include: Mean, standard deviation, variance, skewness, peak-to-peak value.

7. The method for predicting a fault of a drive control detection board of an aging test device according to claim 1, further comprising: Obtaining the signal value corresponding to the target time series of the analog signal of the drive control detection board of the aging test equipment; Determine, according to the signal value, a target clustering result to which the target degradation path composed of the signal value belongs; A target fault prediction model corresponding to the target clustering result is determined, the signal value is input into the target fault prediction model, and a fault prediction result of the drive control detection board of the aging test equipment output by the target fault prediction model is obtained.

8. A fault prediction device for a drive control detection board of an aging test equipment, comprising: An acquisition module is configured to acquire historical signal values ​​corresponding to multiple historical time series of analog signals of a drive control detection board of an aging test device; A calculation module is configured to calculate the similarity between different degradation paths of the drive control detection board of the aging test equipment, wherein different degradation paths are composed of historical signal values ​​corresponding to different historical time series; A clustering module, configured to cluster different degradation paths based on the similarity to generate at least two clustering results; The training module is configured to respectively use the historical signal values ​​corresponding to the degradation paths included in different clustering results as training data input into the corresponding fault prediction model to be trained to obtain a trained fault prediction model; The number of the fault prediction models to be trained is equal to the number of the at least two clustering results, and each fault prediction model to be trained corresponds to each clustering result one by one.

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 fault prediction method for the drive control detection board of the aging test equipment 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 predicting a fault of a drive control detection board of an aging test device according to any one of claims 1 to 7.

Images