Health Status Assessment Method and Device for High-Temperature Aging Test Chamber

Abstract

The present invention discloses a method and device for evaluating the health status of a high-temperature aging test chamber. The method includes: collecting nine-point temperature measurement signals, compressor vibration signals, and fan speed signals of the high-temperature aging test chamber to be evaluated; extracting features from the above monitoring signals to obtain a multi-dimensional feature sequence; inputting the multi-dimensional feature sequence into a pre-trained temporal convolutional network model to obtain the degradation feature state of the high-temperature aging test chamber; in the case where the high-temperature aging test chamber is in a degraded state, determining the state degradation curve of the high-temperature aging test chamber to be evaluated based on the probability space points after mapping of the multi-dimensional feature sequence and the health baseline in the temporal convolutional network model, so as to determine the health status of the high-temperature aging test chamber. The method for evaluating the health status of the high-temperature aging test chamber provided by this application can accurately evaluate the health status of the high-temperature aging test chamber.

Description

Technical Field

[0001] The present invention relates to the technical field of non-destructive reliability screening of integrated circuits, and particularly to a method and device for evaluating the health status of a high-temperature aging test chamber. Background Art

[0002] Existing high-temperature aging products can achieve long-term monitoring of the test environment by means of increasing in-machine long-term monitoring, overstress protection mechanisms, etc., and can respond in a timely manner when a product fails, realizing after-sales maintenance based on failure data. However, due to the lack of active guarantee technologies for high-temperature aging products, it is difficult for related products to achieve the integrity of the test process and the consistency of the test environment stress, which is extremely likely to lead to major property losses such as the destruction of millions of test devices (also known as test pieces to be detected) due to the forced interruption of the test process caused by product failures, or the aging test being recognized as a failed test due to adverse effects such as additional stress introduced during the test period caused by 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 of integrated circuits, greatly reduce the failure rate of integrated circuits, and avoid large-scale electronic system failures and outages such as new energy vehicles, civil airliners, and energy storage substations caused by integrated circuit failures.

[0003] High-temperature aging products such as aging platforms (also known as aging test platforms) simulate various actual use environments and working conditions, enabling products to experience state changes similar to those after long-term use in a short period of time. Aging tests usually require long-term power-on operation of test equipment to simulate the aging process of products in actual use. Among them, the high-temperature test chamber heats the air inside the chamber to reach a set high-temperature environment, realizing the high-temperature aging test of test pieces.

[0004] High-temperature aging test chambers need to accurately create a high-temperature environment to simulate the product aging process in various scientific research and production tests. After long-term use, key components such as heating elements and temperature sensors may experience performance degradation, affecting the accuracy of test results. In addition, once there is a problem with the air circulation system inside the chamber during use, it will destroy the original uniform temperature field, making the actual temperatures of samples at different positions inconsistent, affecting the aging test. Conducting real-time health assessment of high-temperature aging test chambers can help testers timely grasp the current state of the test chamber, discover potential hidden dangers that may exist in high-temperature aging test chambers in advance, and repair or replace relevant components in advance to ensure that the subsequent aging tests can be completed as planned.

[0005] It can be seen that there is an urgent need for those skilled in the art to provide a health status assessment scheme for high-temperature aging test chambers. Summary of the Invention

[0006] The purpose of the embodiments of the present invention is to provide a method and device for evaluating the health status of a high-temperature aging test chamber and an electronic device, which can solve the above problems existing in the prior art.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] The embodiments of the present invention provide a method for evaluating the health status of a high-temperature aging test chamber. Among them, the method includes:

[0009] Collect the monitoring signals of the high-temperature aging test chamber to be evaluated. Among them, the monitoring signals include: the nine-point temperature measurement signals of the high-temperature aging test chamber, the compressor vibration signals, and the fan speed signals;

[0010] Extract features from the monitoring signals to obtain a multi-dimensional feature sequence;

[0011] Input the multi-dimensional feature sequence into a pre-trained time convolutional network model to obtain the degradation feature state of the high-temperature aging test chamber. Among them, the degradation feature state includes: a healthy state and a degradation state;

[0012] In the case where the high-temperature aging test chamber is in a degradation state, based on the probability space points after mapping of the multi-dimensional feature sequence and the health baseline in the time convolutional network model, determine the state degradation curve of the high-temperature aging test chamber to be evaluated. Among them, the state degradation curve can characterize the health status of the high-temperature aging test chamber.

[0013] Optionally, the extracted features include at least two of the following: temperature fluctuation degree, temperature control accuracy, temperature uniformity, temperature overshoot, heating and cooling rate, vibration signal time and frequency domain features, and fan speed time domain features.

[0014] Optionally, the time convolutional network model is trained in the following manner:

[0015] Obtain the training time series degradation feature samples of the high-temperature aging test chamber; each training time series degradation feature sample is marked with a degradation feature state; input the training time series degradation feature samples into a pre-established time convolutional network model to obtain the first probability space points after mapping;

[0016] Discriminate the degradation starting point of the high-temperature aging test chamber according to the two-dimensional first probability space points and generate the health baseline of the high-temperature aging test chamber.

[0017] Optionally, the method further includes:

[0018] Obtain the test time series degradation feature samples of the high-temperature aging test chamber;

[0019] Input the sample of the test timing degradation characteristics into the time convolutional network model being trained to obtain the mapped second probability space points;

[0020] Calculate the distance between the second probability space and the healthy baseline based on a preset multi-distance metric algorithm.

[0021] Optionally, the step of calculating the distance between the second probability space and the healthy baseline based on a preset multi-distance metric algorithm includes:

[0022] Calculate the distances between the second probability space and the healthy baseline based on the Mahalanobis distance algorithm, cosine similarity algorithm, and Manhattan distance algorithm respectively to obtain the first distance, second distance, and third distance;

[0023] Perform a weighted sum of the first distance, second distance, and third distance to obtain the corresponding health degree.

[0024] An embodiment of the present invention also provides a device for evaluating the health state of a high-temperature aging test chamber. Among them, the device includes:

[0025] A collection module for collecting monitoring signals of the high-temperature aging test chamber to be evaluated. Among them, the monitoring signals include: nine-point temperature measurement signals of the high-temperature aging test chamber, compressor vibration signals, and fan speed signals;

[0026] An extraction module for extracting features from the monitoring signals to obtain a multi-dimensional feature sequence;

[0027] A prediction module for inputting the multi-dimensional feature sequence into a pre-trained time convolutional network model to obtain the degradation feature state of the high-temperature aging test chamber. Among them, the degradation feature state includes: a healthy state and a degradation state;

[0028] A determination module for determining the state degradation curve of the high-temperature aging test chamber to be evaluated based on the probability space points mapped from the multi-dimensional feature sequence and the healthy baseline in the time convolutional network model when the high-temperature aging test chamber is in a degradation state. Among them, the state degradation curve can characterize the health state of the high-temperature aging test chamber.

[0029] Optionally, the extracted features include at least two of the following: temperature fluctuation degree, temperature control accuracy, temperature uniformity, temperature overshoot, heating and cooling rate, vibration signal time and frequency domain features, and fan speed time domain features.

[0030] Optionally, the device further includes a model training module for training the time convolutional network model; the model training module includes:

[0031] The first sub-module is used to obtain the training time-series degradation feature samples of the high-temperature aging test chamber; each training time-series degradation feature sample is marked with a degradation feature state.

[0032] The second sub-module is used to input the training time-series degradation feature samples into a pre-established temporal convolutional network model to obtain the first probability space points after mapping.

[0033] The third sub-module is used to discriminate the degradation starting point of the high-temperature aging test chamber according to the two-dimensional first probability space points and generate a health baseline for the high-temperature aging test chamber.

[0034] Optionally, the model training module further includes:

[0035] The fourth sub-module is used to obtain the test time-series degradation feature samples of the high-temperature aging test chamber.

[0036] The fifth sub-module is used to input the test time-series degradation feature samples into the temporal convolutional network model under training to obtain the second probability space points after mapping.

[0037] The sixth sub-module is used to calculate the distance between the second probability space and the health baseline based on a preset multi-distance metric algorithm.

[0038] Optionally, the sixth sub-module is specifically used for:

[0039] Calculating the distances between the second probability space and the health baseline based on the Mahalanobis distance algorithm, the cosine similarity algorithm, and the Manhattan distance algorithm respectively to obtain a first distance, a second distance, and a third distance.

[0040] Performing a weighted sum of the first distance, the second distance, and the third distance to obtain the corresponding health degree.

[0041] An embodiment of the present invention further provides an electronic device, which includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus; the memory is used to store a computer program; when the processor executes the program stored on the memory, it implements the process of any one of the above-mentioned high-temperature aging test chamber health status evaluation methods.

[0042] The health status evaluation scheme for the high-temperature aging test chamber disclosed in the embodiments of the present invention collects monitoring signals such as nine-point temperature measurement signals, compressor vibration signals, and fan speed signals of the high-temperature aging test chamber to be evaluated; extracts features from the monitoring signals to obtain a multi-dimensional feature sequence; inputs the multi-dimensional feature sequence into a pre-trained time convolutional network model to obtain the degradation feature state of the high-temperature aging test chamber; in the case where the high-temperature aging test chamber is in a degraded state, based on the probability space points after mapping of the multi-dimensional feature sequence and the health baseline in the time convolutional network model, determines the state degradation curve of the high-temperature aging test chamber to be evaluated, so as to determine the health status of the high-temperature aging test chamber. The health status evaluation scheme for the high-temperature aging test chamber provided by the embodiments of the present invention collects the monitoring signals of the test chamber and extracts the multi-dimensional feature sequence, and predicts the multi-dimensional feature sequence based on the trained time convolutional network model, and can determine the state degradation curve of the high-temperature aging test chamber to be evaluated, so as to accurately determine the health status of the high-temperature aging test chamber. Since the health status of the high-temperature aging test chamber can be accurately determined, it is possible to process it in time when the high-temperature aging test chamber has health problems, thereby avoiding damage to the test piece during the aging test due to the failure of the high-temperature aging test chamber. Description of the Drawings

[0043] Figure 1 is a flowchart showing the steps of a method for evaluating the health status of a high-temperature aging test chamber according to an embodiment of the present application;

[0044] Figure 2 is a flowchart showing the steps of a method for evaluating the health status of a high-temperature aging test chamber according to an embodiment of the present application;

[0045] Figure 3 is a flowchart showing the steps of a method for predicting the life of a switching power supply according to an embodiment of the present application;

[0046] Figure 4 is a structural block diagram showing an apparatus for evaluating the health status of a high-temperature aging test chamber according to an embodiment of the present application. Detailed Embodiments

[0047] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0048] The following will describe in detail the method for evaluating the health status of a high-temperature aging test chamber provided by the embodiments of the present application with reference to the accompanying drawings, through specific embodiments and their application scenarios.

[0049] As shown in the attached Figure 1 figures, the method for evaluating the health status of a high-temperature aging test chamber according to the embodiments of the present application includes the following steps:

[0050] Step 101: Collect monitoring signals of the high-temperature aging test chamber to be evaluated.

[0051] Among them, the monitoring signals include: nine-point temperature measurement signals of the high-temperature aging test chamber, compressor vibration signals, and fan speed signals.

[0052] The method for evaluating the health status of the high-temperature aging test chamber (also known as the aging high-temperature test chamber) provided by the implementation of this application can be applied to electronic devices. In the electronic device, a computer program for evaluating the health status of the high-temperature aging test chamber is set. When the computer program is executed by a processor, the method for evaluating the health status of the high-temperature aging test chamber in the embodiments of this application is realized.

[0053] The high-temperature aging provided by this application can perform non-destructive aging detection on the test piece. The method for evaluating the health status of the high-temperature aging test chamber provided in the embodiments of this application can detect the health assessment status of the high-temperature aging test chamber, so as to ensure the safety of the test piece when the high-temperature aging detects the test piece.

[0054] In the actual implementation process, the directly measured temperature monitoring signal data of the high-temperature aging test chamber is large in quantity and contains a large amount of redundant information. Therefore, preliminary feature extraction is performed on the directly measured data to obtain a feature sequence with high information density. Step 102: Extract features from the monitoring signals to obtain a multi-dimensional feature sequence.

[0055] The extracted features include at least two of the following: temperature fluctuation degree, temperature control accuracy, temperature uniformity, temperature overshoot, heating and cooling rate, vibration signal time-domain and frequency-domain features, and fan speed time-domain features, etc. The specific features to be extracted can be flexibly set by those skilled in the art according to actual needs, as long as the extracted features can characterize the state of the test chamber.

[0056] Step 103: Input the multi-dimensional feature sequence into a pre-trained time convolutional network model to obtain the degradation feature state of the high-temperature aging test chamber.

[0057] Among them, the degradation feature state includes: healthy state and degradation state. If the degradation feature state of the high-temperature aging test chamber is the healthy state, step 104 and subsequent steps do not need to be executed. If the degradation feature state of the high-temperature aging test chamber is the degradation state, it means that the high-temperature aging test chamber has degraded. By performing adaptive analysis on the multi-dimensional feature sequence data through the time convolutional network model, the degradation progress of the high-temperature aging test chamber can be automatically identified.

[0058] In an optional embodiment, the training process of the time convolutional network model may include the following sub-steps:

[0059] Sub-step 1: Obtain the training time-series degradation feature samples of the high-temperature aging test chamber;

[0060] Among them, each training time-series degradation feature sample is labeled with a degradation feature state. The training time-series degradation feature sample of the high-temperature aging test chamber can be obtained by monitoring the temperature signal and the degradation feature state during the entire life cycle of a high-temperature aging test chamber.

[0061] In the actual implementation process, the training time-series degradation feature sample of the high-temperature aging test chamber can be expressed as , the maximum number of iterations max_iter. Mark the corresponding degradation feature state of the trained high-temperature aging test chamber , including the healthy state and the degraded state.

[0062] Sub-step 2: Input the training time-series degradation feature sample into the pre-established temporal convolutional network model to obtain the first probability space point after mapping;

[0063] In the actual implementation process, with as the input, as the output to train the TCN model (i.e., the temporal convolutional network model); obtain the TCN model parameters obtained by iterative learning. When the number of iterations reaches the maximum number of iterations max_iter, stop iterative learning.

[0064] In the actual implementation process, the maximum number of iterations max_iter can be flexibly set by those skilled in the art, and no specific limitation is made in the embodiments of the present application.

[0065] Sub-step 3: Discriminate the degradation starting point of the high-temperature aging test chamber according to the two-dimensional first probability space point, and generate a healthy baseline for the high-temperature aging test chamber.

[0066] In an optional embodiment, the training process of the temporal convolutional network model may further include the following process:

[0067] Obtain the test time-series degradation feature sample of the high-temperature aging test chamber; input the test time-series degradation feature sample into the training temporal convolutional network model to obtain the second probability space point after mapping; calculate the distance between the second probability space and the healthy baseline based on a preset multi-distance metric algorithm.

[0068] The test time-series degradation feature sample of the high-temperature aging test chamber can be expressed as: . During the training and testing of the temporal convolutional network model, with and as the input of the TCN algorithm model, obtain the probability space points after mapping and .

[0069] Automatically identify the degradation starting point based on the two-dimensional probability space results, and calculate the distances between the health space and the degradation space of the training and test high-temperature aging test chambers using a weighted fusion multi-distance metric algorithm. Traverse all failure modes to obtain the health assessment results corresponding to each failure mode. Finally, the trained temporal convolutional network model outputs and the health assessment curves corresponding to each high-temperature aging test chamber.

[0070] More specifically, based on the preset multi-distance metric algorithm, the way to calculate the distance between the second probability space and the health baseline can be as follows: Calculate the distances between the second probability space and the health baseline based on the Mahalanobis distance algorithm, cosine similarity algorithm, and Manhattan distance algorithm respectively to obtain the first distance, second distance, and third distance; Perform a weighted sum of the first distance, second distance, and third distance to obtain the corresponding health degree.

[0071] In the actual implementation process, it is not limited to using the above three distance algorithms to calculate the distance. It can also use any one of the above three distance algorithms, or use any two of the above three distance algorithms to obtain two distances and then perform a weighted sum of the two distances.

[0072] Introduce the high-temperature aging test chamber test time-series degradation feature samples during the training process of the temporal convolutional network model, and the accuracy of the prediction of the temporal convolutional network model can be tested through the prediction results. In the actual implementation process, when the prediction accuracy of the temporal convolutional network model reaches the accuracy threshold, it can be determined that the training of this temporal convolutional network model is completed. Subsequently, the trained temporal convolutional network model can be used to predict the state degradation curve of the high-temperature aging test chamber to be evaluated.

[0073] Step 104: In the case where the high-temperature aging test chamber is in a degraded state, determine the state degradation curve of the high-temperature aging test chamber to be evaluated based on the probability space points after mapping of the multi-dimensional feature sequences and the health baseline in the temporal convolutional network model.

[0074] Among them, the state degradation curve can characterize the health state of the high-temperature aging test chamber.

[0075] By analyzing the multi-dimensional features of the high-temperature aging test chamber to be evaluated through the temporal convolutional network model, the health degree of the test chamber at the current moment can be obtained, and at the same time, the state degradation curve (also known as the health degree degradation curve) up to this moment is output, providing reliable data support for the further research on the remaining service life prediction of the high-temperature aging test chamber.

[0076] The method for evaluating the health status of a high-temperature aging test chamber disclosed in the embodiments of the present invention collects the monitoring signals of the high-temperature aging test chamber to be evaluated; extracts features from the monitoring signals to obtain a multi-dimensional feature sequence; inputs the multi-dimensional feature sequence into a pre-trained temporal convolutional network model to obtain the degradation feature state of the high-temperature aging test chamber; in the case where the high-temperature aging test chamber is in a degraded state, based on the probability space points after mapping of the multi-dimensional feature sequence and the health baseline in the temporal convolutional network model, determines the state degradation curve of the high-temperature aging test chamber to be evaluated, so as to determine the health status of the high-temperature aging test chamber. The method for evaluating the health status of a high-temperature aging test chamber provided by the embodiments of the present invention collects the nine-point temperature measurement signals, compressor vibration signals, and fan speed signals of the test chamber and extracts a multi-dimensional feature sequence, and predicts the multi-dimensional feature sequence based on the trained temporal convolutional network model, and can determine the state degradation curve of the high-temperature aging test chamber to be evaluated, thereby accurately determining the health status of the high-temperature aging test chamber.

[0077] The following combines Figure 2 With a specific example, the high-temperature aging test chamber health status evaluation solution provided by this application is described.

[0078] The high-temperature aging test chamber health status evaluation method provided in this specific example is based on the identification of degradation points of a temporal convolutional network and the fusion of multiple distance metrics. The core is: during the aging test process, monitor the temperature of the high-temperature aging test chamber. The directly measured monitoring signal data is large and contains a lot of redundant information. First, perform preliminary feature extraction on the directly measured data, including features such as temperature fluctuation degree, temperature control accuracy, temperature uniformity, temperature overshoot, heating and cooling rate, time-frequency domain features of vibration signals, and time-domain features of fan speed, to obtain a feature sequence with high information density; use a temporal convolutional network to perform adaptive analysis on the feature sequence data to automatically identify the degradation starting point of the high-temperature aging test chamber. Use a distance metric algorithm to quantitatively calculate the health status of the feature sequence in the degradation stage to complete the health assessment of the high-temperature aging test chamber.

[0079] The process of the high-temperature aging test chamber health status evaluation method based on the identification of degradation points of a temporal convolutional network and the fusion of multiple distance metrics can specifically include the following processes:

[0080] S1: Temperature monitoring of the high-temperature aging test chamber:

[0081] The high-temperature aging test chamber is Figure 2 The old temperature aging table test chamber shown in. During the aging test process, monitor the nine-point temperature measurement signals, compressor vibration signals, and fan speed signals of the high-temperature aging test chamber through sensors to obtain a large amount of monitoring data for the state evaluation of the test chamber.

[0082] S2: Preliminary feature extraction.

[0083] Since the directly measured monitoring signal data is large in volume and contains a large amount of redundant information, it is first necessary to extract features from the directly monitored data, including temperature fluctuation degree, temperature control accuracy, temperature uniformity, temperature overshoot, heating and cooling rate, time-domain and frequency-domain characteristics of vibration signals, and time-domain characteristics of fan speed, etc., to obtain a feature sequence with high information density, that is, the multi-dimensional degradation characteristics of the high-temperature aging test chamber.

[0084] S3: Input the multi-dimensional degradation characteristics of the high-temperature aging test chamber into the temporal convolutional network model to automatically identify the degradation starting point and obtain the health baseline and degradation characteristics.

[0085] On the basis of the extracted feature sequence, the health assessment process is further realized: First, use the TCN (Temporal Convolutional Network) model to judge the degradation starting point of the temperature data and its characteristic data of the high-temperature aging test chamber, and eliminate the instability caused by artificially setting the health baseline to construct health indicators. The TCN model is based on causal convolution, strictly ensuring that the output of each time step depends only on the input before that time step. Then, dilated convolution is introduced on this basis. By inserting intervals between the convolutional kernel elements and increasing the receptive field according to a specific rule, it can effectively capture the long-term dependence relationships existing in the time series data. The TCN model stacks multiple modules containing causal convolution, dilated convolution, and residual connections reasonably, so that after the time series data is processed layer by layer, rich and valuable feature information can be extracted. Then, a fully connected layer is connected, and this layer will integrate the features extracted previously and map them to a two-dimensional space to realize the judgment of the degradation starting point of the high-temperature aging test chamber. Among them, Figure 2 DilatedCausal Convolution in it is dilated causal convolution, WeightNorm is the weight normalization layer, ReLU is the activation function, and Dropuot is dropout.

[0086] Specifically, in the training stage of the TCN model, input the training data with health status labels (that is, the training time series degradation feature samples and the degradation feature status labels marked for each sample) , where is the feature sample, is the corresponding label, 0 and 1 represent the healthy state and the degraded state respectively, and n is the number of feature samples obtained by resampling the entire degradation curve with a sliding window. In this process, the TCN model continuously optimizes the mapping parameters of the input data to the low-dimensional feature space, strengthens the classification ability of the healthy state data and the degraded state data, and enables the TCN model to obtain the ability to automatically segment the health baseline of the test data.

[0087] In the test phase of the TCN model, the test data (i.e., the time-series degradation feature samples of the test chamber) is input , and based on the model parameters optimized and learned during the training process, the TCN model can map the healthy baseline data and the degradation data into a two-dimensional probability space, complete the identification of the degradation starting point of the test data, and obtain , avoiding the blindness of manual segmentation of the healthy baseline

[0088] S4: Adopt a multi-distance metric fusion method to calculate the distance between the healthy baseline and the degradation features, and determine the state degradation curve and the current health of the high-temperature aging test chamber

[0089] To further evaluate the health state of the high-temperature aging test chamber at the current moment, a multi-distance metric fusion method is used to comprehensively consider the Mahalanobis distance, cosine similarity, and Manhattan distance between sample data and perform weighted fusion to obtain the health at the current moment. At the same time, the health degradation curve up to this moment is output, providing reliable data support for the further prediction of the remaining service life of the high-temperature aging test chamber

[0090] In the embodiments of the present application, a fault prediction method for the front-end isolated switching power supply of an aging platform considering multiple degradation paths is also provided. This method can be executed after the execution of the health state assessment process of the high-temperature aging test chamber, or before the execution of the health state assessment process of the high-temperature aging test chamber, or can be executed in parallel with it. The present application does not specifically limit the execution timing of the fault prediction method for the front-end isolated switching power supply of the aging platform considering multiple degradation paths

[0091] As shown in the appendix Figure 3 , the fault prediction method for the front-end isolated switching power supply of the aging platform considering multiple degradation paths in the embodiments of the present application includes the following steps

[0092] Step 301: Perform dimensionality reduction processing on the preset time-series signals of multiple aging platform switching power supplies and extract characteristic parameters

[0093] The fault prediction method for the front-end isolated switching power supply of the aging platform considering multiple degradation paths provided in the embodiments of the present application can be applied to electronic devices. An aging platform switching power supply life prediction computer program is set in the electronic device. When the computer program is executed by a processor, it implements the fault prediction method for the front-end isolated switching power supply of the aging platform considering multiple degradation paths in the embodiments of the present application to predict the remaining life of the switching power supply. The aging platform switch in the embodiments of the present application is a front-end isolated switch of the aging platform, and can also be called a primary switching power supply

[0094] Through the aging platform provided in the embodiments of the present application, non-destructive aging detection can be performed on the test piece to be detected. In the embodiments of the present application, the feature extraction and life prediction of the aging platform switching power supply are to ensure the safety of the test piece to be detected

[0095] Among them, the characteristic parameters include, but are not limited to: ripple voltage, average output voltage, peak-to-peak inductor current, peak inductor current, peak-to-peak capacitor current, peak capacitor current, circuit board temperature, heat flux density, heat flux rate, thermal conductivity, thermal diffusivity, etc.

[0096] The preset timing signal can be the current, voltage and other timing signals of the switching power supply. The multiple aging bench switching power supplies are aging bench switching power supplies with multiple different decay rates and different fault starting degrees.

[0097] Step 302: Calculate the similarity of the performance degradation paths of each aging bench switching power supply according to the characteristic parameters of each preset timing signal.

[0098] In the actual implementation process, the DTW (Dynamic Time Warping) method can be used to evaluate the similarity of the paths between the aging bench switching power supplies with multiple different decay rates and different fault starting degrees (i.e., the similarity of the performance degradation paths of each aging bench switching power supply). On this basis, the K-Means performance degradation path clustering method is introduced, and the rapid and accurate classification of the performance degradation paths of the aging bench (i.e., the aging test bench) switching power supply can be realized.

[0099] An optionally way to calculate the similarity of the performance degradation paths of each aging bench switching power supply according to the characteristic parameters of each preset timing signal may include the following sub-steps:

[0100] Sub-step 1: Construct parameter vectors for the characteristic parameters of each preset timing signal respectively;

[0101] Sub-step 2: Construct a matrix grid according to each of the parameter vectors;

[0102] For the performance parameter vector of the primary switching power supply sample of the aging bench , (a, b are sample numbers, m, n are corresponding running cycle numbers), after that, construct a matrix grid, and the matrix element represents and the distance between two points , and each matrix element represents aligned with .

[0103] Sub-step 3: Based on the preset path boundary constraint conditions, path continuity constraint conditions and path monotonicity constraint conditions, find the path with the minimum regularization cost passing through the matrix grid through multiple iterative adjustments.

[0104] Among them, the path with the minimum regularization cost can represent the similarity of the performance degradation paths of the switching power supplies on each aging bench.

[0105] When specifically implementing Sub-step 3, a regularized path passing through this grid can be found based on the path boundary constraint condition, the path continuity constraint condition, and the path monotonicity constraint condition, and it is represented by : 1. Then, based on these three constraint conditions, path regularization is performed iteratively multiple times until a path with the minimum regularization cost is obtained. The in the denominator is used to compensate for regularized paths of different lengths.

[0106] The path boundary condition constraint can be set as , , ensuring that the selected path must start from the common starting point of the sequence and end at the common ending point of the sequence.

[0107] The path continuity constraint condition can be set as: If , then for the next point of the path, it needs to satisfy and , ensuring that each coordinate in and appears in .

[0108] The path monotonicity constraint condition can be set as: If , then for the next point of the path, it needs to satisfy and , restricting that the points above must progress monotonically with time.

[0109] The similarity of the characteristic time series trajectories such as the ripple voltage, average output voltage, peak-to-peak inductor current, peak inductor current, peak-to-peak capacitor current, peak capacitor current, circuit board temperature, heat flux density, heat flux rate, thermal conductivity, and thermal diffusivity between the switching power supply samples (i.e., preset timing signals) on different aging benches is calculated through the DTW method. Subsequently, clustering of the time series trajectories can be achieved through the clustering method, so as to classify the switching power supplies on the aging benches according to the performance degradation trajectories.

[0110] Step 303: Cluster each degradation path based on the similarity of the performance degradation paths of the switching power supplies on each aging bench to obtain N degradation path sets.

[0111] N is a positive integer greater than or equal to 2. In the embodiments of the present application, N is taken as 2 for illustration.

[0112] In an alternative embodiment, the method of clustering each degradation path according to the similarity of the performance degradation paths of the switching power supplies on each aging bench to obtain N degradation path sets may include the following sub-steps:

[0113] Sub-step 1: Randomly select K points from the path with the minimum regularization cost as the centers of the initial clusters;

[0114] Sub-step 2: For each point in the path with the minimum regularization cost, assign each point to the cluster closest to the center point;

[0115] Sub-step 3: Update the center point of each cluster;

[0116] An exemplary way to update the center point of each cluster may be: for each cluster, calculate the average value of the points in the cluster; update the center point of the cluster to the position of the average value. The goal of updating the center point of the cluster is to minimize the within-cluster squared error.

[0117] Sub-step 4: For each point in the path with the minimum regularization cost, assign each point to the cluster closest to the updated center point;

[0118] Sub-step 5: Determine whether the clustering stop condition is reached. If not, return to execute the step of updating the center point of each cluster in Sub-step 3;

[0119] If not, return to execute Sub-step 3, Sub-step 4, and Sub-step 5, so as to update the center point again and cluster based on the updated center point.

[0120] The clustering stop condition can be flexibly set by those skilled in the art, and the embodiments of the present application do not make specific limitations in this regard. For example: the clustering stop condition can be set as: the change in the position of the cluster center point before and after the update is less than a preset value (the position of the cluster center point no longer changes significantly before and after the update), and it can also be set as reaching the upper limit of the set number of iterations.

[0121] This alternative degradation path clustering method utilizes the advantages of the time used for cluster centroid selection and the spatial complexity of cluster overlap in K-Means, and uses the optimal points actually existing in the dataset as its centroids. Therefore, it can find the characteristics of the trajectories corresponding to the centroids, and cluster the system samples through the similarity matrix of the performance degradation paths of the switching power supplies on the aging bench, so as to realize the identification of the switching power supplies on the aging bench according to the performance degradation trajectory time series (i.e., the preset timing signal).

[0122] Sub-step 6: If it has been reached, take the clusters obtained by clustering the updated center points as the N degradation path sets.

[0123] Step 304: Establish N switching power supply life prediction models, and train the N switching power supply life prediction models respectively according to the N degradation path sets.

[0124] Among them, the switching power supply life prediction model includes:

[0125] An input layer, a Dense layer (i.e., a dense layer), a BiLSTM layer (i.e., a bidirectional long short-term memory network layer) for processing multi-sensor monitoring signals, a BiGRU layer (i.e., a bidirectional gated recurrent layer) for processing the transformation result after the operation condition data (i.e., the hidden representation), a Concatenate layer (i.e., a feature concatenation layer) for fusing the outputs of the BiLSTM and BiGRU layers, a multi-dimensional feature map, and an output layer for outputting the RUL prediction value.

[0126] In an optional embodiment, the method for establishing N switching power supply life prediction models and training the N switching power supply life prediction models respectively according to N degradation path sets may include the following sub-steps:

[0127] Sub-step 1: Establish N switching power supply life prediction models.

[0128] When there are two performance degradation paths, two switching power supply life prediction models are established, and the switching power supply life prediction model is used to predict the remaining life of the switching power supply.

[0129] Sub-step 2: For each switching power supply life prediction model, use the characteristic parameters corresponding to the degradation paths in the corresponding degradation path set as the model input.

[0130] Sub-step 3: Perform a linear transformation on the input characteristic parameters in the fully connected layer and perform a hidden representation on the transformation result;

[0131] Among them, the input characteristic parameters can be regarded as multi-sensory monitoring data X i .

[0132] Sub-step 4: Construct a high-order vector based on the transformation result after the hidden representation, and send the high-order vector to the BiLSTM layer and the BiGRU layer to obtain hidden feature maps of different dimensions;

[0133] Among them, the stacking layers of the BiLSTM layer and the BiGRU layer are the same.

[0134] Sub-step 5: Input the feature vectors generated by combining the hidden features of different dimensions into two linear regression dense layers respectively to generate the RUL prediction value;

[0135] Sub-step 6: Use the error between the RUL prediction value and the actual RUL value as the loss function to calculate the loss;

[0136] Sub-step 7: Update the parameters of the switching power supply life prediction model according to the loss backpropagation;

[0137] Sub-step 8: Determine whether the switched-mode power supply life prediction model after updating the parameters meets the preset accuracy rate; if it meets, determine that the training of the switched-mode power supply life prediction model is completed; if it does not meet, return to execute the step of using the characteristic parameters corresponding to the degradation paths in the corresponding degradation path set as the model input.

[0138] The prediction accuracy rate is used to evaluate the performance of the prediction model. The accuracy rate of the switched-mode power supply life prediction model can be calculated by the following formula:

[0139]

[0140] where RUL is the actual RUL (remaining useful life); is the predicted RUL estimated by the prediction model; TUL is the actual total useful life of the target circuit, which is defined as the total number of test cycles when the switched-mode power supply on the aging platform reaches the failure threshold.

[0141] The switched-mode power supply life prediction model can be a multi-dimensional recurrent neural network (MDRNN) model. The multi-dimensional recurrent neural network uses momentum and an adaptive learning rate to accelerate the convergence speed and has been proven to be superior to the classical stochastic gradient descent optimizer, thus obtaining higher processing efficiency and prediction quality. The training process of the multi-dimensional recurrent neural network (MDRNN) model includes: S1: Extract the characteristic parameters of the switched-mode power supply on the aging platform; S2: Establish an MDRNN multi-dimensional recurrent neural network model; S3: Initialize the parameters of the MDRNN multi-dimensional recurrent neural network model; S4: Iteratively train the MDRNN multi-dimensional recurrent neural network model multiple times based on the characteristic parameters in S1, calculate the loss function after each training is completed, and adjust the model parameters based on the calculated loss function; after multiple rounds of forward propagation and backpropagation training, when reaching the stop state, the trained MDRNN multi-dimensional recurrent neural network model can be used to predict the remaining life of the switched-mode power supply.

[0142] Step 305: Based on the trained N switched-mode power supply life prediction models, predict the life of the switched-mode power supply on the aging platform to obtain the remaining life of the switched-mode power supply.

[0143] When predicting the lifespan of the switching power supplies on the aging platform based on N switching power supply lifespan prediction models, the degradation path category to which the switching power supply to be predicted belongs can be determined based on the timing signal of the switching power supply to be predicted, and the switching power supply lifespan prediction model matching this category can be called for accurate prediction. The specific prediction process may include: determining the characteristic parameters of the timing signal of the switching power supply on the aging platform to be predicted; determining the degradation category to which the switching power supply on the aging platform to be predicted belongs; inputting the characteristic parameters into the switching power supply lifespan prediction model that matches the category to predict the remaining service life of this switching power supply. The result of this prediction can also be used as the basic data for evaluating the accuracy of the prediction model of the switching unit in the subsequent stage. Specifically, it can be: calculating the prediction error of the model based on the remaining service life obtained from this prediction and the true data of the remaining service life of this switching power supply; evaluating the accuracy of the model prediction result based on the prediction error.

[0144] The method for predicting the failure of the front-end isolated switching power supply of the aging platform considering multiple degradation paths provided by the embodiments of the present application performs dimensionality reduction processing on the preset timing signals of multiple switching power supplies on the aging platform and extracts characteristic parameters; calculates the similarity of the performance degradation paths of each switching power supply on the aging platform according to the characteristic parameters of each preset timing signal; clusters each degradation path according to the similarity of the performance degradation paths of each switching power supply on the aging platform to obtain N degradation path sets; establishes N switching power supply lifespan prediction models, and trains the N switching power supply lifespan prediction models respectively according to the N degradation path sets; predicts the lifespan of the switching power supply on the aging platform based on the N trained switching power supply lifespan prediction models to obtain the remaining lifespan of the switching power supply. For the method for predicting the failure of the front-end isolated switching power supply of the aging platform considering multiple degradation paths, on the one hand, the switching power supply lifespan prediction model of the aging platform based on the multi-dimensional recurrent neural network model comprehensively considers the influence of the performance degradation path on the prediction of the remaining service life of the switching power supply, and can achieve high-precision lifespan prediction; on the second hand, taking the failure mode as a consideration factor, identifying the performance degradation paths of the switching power supplies on the aging platform, and bringing the characteristic parameters of the switching power supplies on the aging platform with the same performance degradation path into the same model for training and prediction is beneficial to improving the prediction accuracy of the lifespan of the switching power supplies on the aging platform.

[0145] Figure 4 The structural block diagram of a device for evaluating the health status of a high-temperature aging test chamber for implementing the embodiments of the present application.

[0146] The device for evaluating the health status of the high-temperature aging test chamber provided by the embodiments of the present application includes the following functional modules:

[0147] The acquisition module 401 is used to acquire the monitoring signals of the high-temperature aging test chamber to be evaluated, where the monitoring signals include: the nine-point temperature measurement signals of the high-temperature aging test chamber, the compressor vibration signals, and the fan speed signals;

[0148] An extraction module 402, configured to extract features from the monitoring signal to obtain a multi-dimensional feature sequence;

[0149] A prediction module 403, configured to input the multi-dimensional feature sequence into a pre-trained temporal convolutional network model to obtain a degradation feature state of the high-temperature aging test chamber, where the degradation feature state includes: a healthy state and a degradation state; A determination module 404, configured to, when the high-temperature aging test chamber is in a degradation state, determine a state degradation curve of the to-be-evaluated high-temperature aging test chamber based on a probability space point after mapping of the multi-dimensional feature sequence and a health baseline in the temporal convolutional network model, where the state degradation curve can characterize the healthy state of the high-temperature aging test chamber.

[0150] Optionally, the apparatus further includes a model training module, configured to train the temporal convolutional network model; the model training module includes:

[0151] A first sub-module, configured to obtain a training time-series degradation feature sample of the high-temperature aging test chamber; where each training time-series degradation feature sample is labeled with a degradation feature state;

[0152] A second sub-module, configured to input the training time-series degradation feature sample into a pre-established temporal convolutional network model to obtain a first probability space point after mapping;

[0153] A third sub-module, configured to discriminate a degradation starting point of the high-temperature aging test chamber according to the two-dimensional first probability space point and generate a health baseline of the high-temperature aging test chamber.

[0154] Optionally, the extracted features include at least two of the following: temperature fluctuation degree, temperature control accuracy, temperature uniformity, temperature overshoot, heating and cooling rate, time-domain feature of vibration signal, frequency-domain feature of vibration signal, and time-domain feature of fan speed.

[0155] Optionally, the model training module further includes:

[0156] A fourth sub-module, configured to obtain a test time-series degradation feature sample of the high-temperature aging test chamber;

[0157] A fifth sub-module, configured to input the test time-series degradation feature sample into the temporal convolutional network model being trained to obtain a second probability space point after mapping;

[0158] A sixth sub-module, configured to calculate a distance between the second probability space and the health baseline based on a preset multi-distance metric algorithm.

[0159] Optionally, the sixth sub-module is specifically configured to:

[0160] Calculate the distances between the second probability space and the health baseline respectively based on the Mahalanobis distance algorithm, the cosine similarity algorithm, and the Manhattan distance algorithm, obtaining a first distance, a second distance, and a third distance;

[0161] Perform a weighted sum of the first distance, the second distance, and the third distance to obtain the corresponding health degree.

[0162] The Figure 4 high-temperature aging test chamber health status evaluation device shown in Figure 1 can implement each process implemented by the method embodiment. To avoid repetition, it will not be elaborated here.

[0163] The high-temperature aging test chamber health status evaluation device provided by the embodiments of the present application collects monitoring signals such as nine-point temperature measurement signals, compressor vibration signals, and fan speed signals of the high-temperature aging test chamber to be evaluated; performs feature extraction on the monitoring signals to obtain a multi-dimensional feature sequence; inputs the multi-dimensional feature sequence into a pre-trained temporal convolutional network model to obtain the degradation feature state of the high-temperature aging test chamber; in the case where the high-temperature aging test chamber is in a degraded state, based on the probability space points after mapping of the multi-dimensional feature sequence and the health baseline in the temporal convolutional network model, determine the state degradation curve of the high-temperature aging test chamber to be evaluated, so as to determine the health status of the high-temperature aging test chamber. The high-temperature aging test chamber health status evaluation device provided by the embodiments of the present invention collects the monitoring signals of the test chamber and extracts the multi-dimensional feature sequence, and predicts the multi-dimensional feature sequence based on the trained temporal convolutional network model, and can determine the state degradation curve of the high-temperature aging test chamber to be evaluated, thereby accurately determining the health status of the high-temperature aging test chamber.

[0164] The embodiments of the present invention also provide an electronic device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus.

[0165] The memory is used to store a computer program;

[0166] The processor is used to implement the high-temperature aging test chamber health status evaluation method shown in the above method embodiment when executing the program stored in the memory.

[0167] The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0168] The communication interface is used for communication between the above-mentioned terminal and other devices.

[0169] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0170] In another embodiment provided by the present invention, there is also provided a computer-readable storage medium storing instructions, which, when running on an electronic device, enable the electronic device to implement the method for evaluating the health status of the high-temperature aging test chamber described in any one of the above embodiments.

[0171] In another embodiment provided by the present invention, there is also provided a computer program product containing instructions, which, when running on an electronic device, enable the electronic device to implement the method for evaluating the health status of the high-temperature aging test chamber described in any one of the above embodiments.

[0172] It should be noted that in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or device. Without further limitations, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the element.

[0173] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for evaluating the health status of a high temperature aging test chamber, characterized in that: The method comprises: Collect monitoring signals of the high-temperature aging test chamber to be evaluated; wherein the monitoring signals include: nine-point temperature measurement signals of the high-temperature aging test chamber, compressor vibration signals, and fan speed signals; Extracting features from the monitoring signal to obtain a multi-dimensional feature sequence; Inputting the multidimensional feature sequence into a pre-trained temporal convolutional network model to obtain the degradation feature state of the high temperature aging test chamber, wherein the degradation feature state includes: a healthy state and a degraded state; In the case where the high temperature aging test chamber is in a degraded state, based on the probability space points after the multi-dimensional feature sequence mapping and the health baseline in the time convolution network model, the state degradation curve of the high temperature aging test chamber to be evaluated is determined, wherein the state degradation curve can characterize the health state of the high temperature aging test chamber; Obtain samples of timing degradation characteristics tested in a high-temperature aging test chamber; Inputting the test time series degradation feature sample into the temporal convolutional network model in training to obtain a mapped second probability space point; Based on a preset multi-distance metric algorithm, calculating the distance between the second probability space and the health baseline; The temporal convolutional network model is trained in the following manner: obtaining a high-temperature aging test chamber training time series degradation feature sample; wherein each training time series degradation feature sample is marked with a degradation feature state; inputting the training time series degradation feature sample into a pre-established temporal convolutional network model to obtain a mapped first probability space point; judging the degradation starting point of the high-temperature aging test chamber according to the two-dimensional first probability space point, and generating a high-temperature aging test chamber health baseline.

2. The method according to claim 1, characterized in that: in, The extracted features include at least two of the following: temperature fluctuation, temperature control accuracy, temperature uniformity, temperature overshoot, heating and cooling rate, vibration signal time domain features, vibration signal frequency domain features, and fan speed time domain features.

3. The method according to claim 2, characterized in that The step of calculating the distance between the second probability space and the health baseline based on a preset multi-distance metric algorithm includes: Calculating the distance between the second probability space and the health baseline based on the Mahalanobis distance algorithm, the cosine similarity algorithm, and the Manhattan distance algorithm, respectively, to obtain a first distance, a second distance, and a third distance; The first distance, the second distance and the third distance are weightedly summed to obtain the corresponding health degree.

4. A high temperature aging test chamber health status assessment device, characterized in that: The device comprises: The acquisition module is used to acquire the monitoring signal of the high temperature aging test chamber to be evaluated; wherein the monitoring signal includes: the nine-point temperature measurement signal of the high temperature aging test chamber, the compressor vibration signal and the fan speed signal; An extraction module, used for extracting features from the monitoring signal to obtain a multi-dimensional feature sequence; A prediction module, used for inputting the multi-dimensional feature sequence into a pre-trained temporal convolutional network model to obtain the degradation feature state of the high temperature aging test chamber, wherein the degradation feature state includes: a healthy state and a degraded state; A determination module, configured to determine, when the high-temperature aging test chamber is in a degraded state, a state degradation curve of the high-temperature aging test chamber to be evaluated based on the probability space points mapped by the multidimensional feature sequence and the health baseline in the time convolution network model, wherein the state degradation curve can characterize the health state of the high-temperature aging test chamber; The device also includes a model training module for training the temporal convolutional network model; the model training module includes: The first submodule is used to obtain the high temperature aging test chamber training time series degradation feature samples; wherein each training time series degradation feature sample is marked with a degradation feature state; The second submodule is used to input the training temporal degradation feature sample into a pre-established temporal convolutional network model to obtain a mapped first probability space point; The third submodule is used to determine the degradation starting point of the high temperature aging test chamber according to the two-dimensional first probability space point, and generate a health baseline of the high temperature aging test chamber; The model training module also includes: The fourth submodule is used to obtain the timing degradation characteristic samples of the high temperature aging test chamber test; A fifth submodule is used to input the test time series degradation feature sample into the time convolution network model in training to obtain a mapped second probability space point; The sixth submodule is used to calculate the distance between the second probability space and the health baseline based on a preset multi-distance metric algorithm.

5. The device according to claim 4, characterized in that The sixth submodule is specifically used for: Calculating the distance between the second probability space and the health baseline based on the Mahalanobis distance algorithm, the cosine similarity algorithm, and the Manhattan distance algorithm, respectively, to obtain a first distance, a second distance, and a third distance; The first distance, the second distance and the third distance are weightedly summed to obtain the corresponding health degree.

6. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the high temperature aging test chamber health status assessment method as described in any one of claims 1 to 3 when executing the program stored in the memory.

Images