A detection method and system based on electronic component performance data

Through the combination of adaptive filtering and neural network model, the problem of low performance detection accuracy of electronic components is solved, and more efficient noise suppression and performance feature extraction is achieved, which significantly improves detection accuracy.

CN118245735BActive Publication Date: 2024-11-12LIMA OPTOELECTRONICS TECH (BEIJING) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410667013.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-27
Publication Date
2024-11-12
Estimated Expiration
2044-05-27

AI Technical Summary

Technical Problem

In the prior art, the performance detection accuracy of electronic components is not high, mainly due to the simple analysis of the detection data of the electronic components itself, the failure to effectively denoise and extract their performance characteristics.

Method used

Adaptive filtering method is used to perform multi-scale denoising processing, and a performance detection model is built in combination with convolutional neural networks and long-term memory networks to detect denoising performance data to improve detection accuracy.

Benefits of technology

Through multi-scale denoising processing, the detailed characteristics of different decomposition scales are highlighted, noise is suppressed, and the accuracy and reliability of electronic component performance detection are significantly improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118245735B_ABST
    Figure CN118245735B_ABST
Patent Text Reader

Abstract

The present disclosure provides a detection method and system based on electronic component performance data, wherein the method comprises: using a performance detection device to test the electronic component to be tested to obtain initial performance data; performing multi-scale denoising processing on the initial performance data based on an adaptive filtering method to obtain denoised performance data; and performing performance testing on the denoised performance data based on a trained performance detection model to obtain a detection result for the electronic component to be tested. The present disclosure can highlight the detailed features at different decomposition scales through multi-scale denoising processing, better suppress noise, and enhance the accuracy of data processing, thereby making the subsequent performance detection based on the performance detection model more accurate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a detection method and system based on electronic component performance data. Background Art

[0002] With the rapid development of electronic technology, the performance of electronic components directly affects the reliability and stability of the entire system. Therefore, it is of great significance to develop an accurate and efficient electronic component performance detection system.

[0003] In the prior art, generally, it is based on a simple analysis of the detection data of the electronic component itself, such as threshold comparison, to determine whether there is an abnormality in the performance of the electronic component. This leads to the problem that the accuracy of the performance detection of the electronic component is not high. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a detection method and system based on electronic component performance data to improve the performance detection accuracy of electronic components.

[0005] In a first aspect, an embodiment of the present disclosure provides a detection method based on electronic component performance data, comprising:

[0006] Use performance testing equipment to test the electronic components to obtain initial performance data;

[0007] Performing multi-scale denoising processing on the initial performance data based on an adaptive filtering method to obtain denoised performance data;

[0008] A performance test is performed on the denoised performance data based on the trained performance test model to obtain a test result for the electronic component to be tested.

[0009] In a possible implementation, the performing multi-scale denoising processing on the initial performance data based on an adaptive filtering method includes:

[0010] Performing wavelet decomposition on the initial performance data at multiple decomposition scales to obtain wavelet coefficients corresponding to each decomposition scale;

[0011] Constructing filtering thresholds at various decomposition scales according to the size of the initial performance data;

[0012] Constructing a data filtering model based on the filtering threshold and the wavelet coefficient;

[0013] Filtering the initial performance data based on the data filtering model to obtain filtered performance data;

[0014] The filtering performance data is cleaned to obtain the denoising performance data.

[0015] In a possible implementation, the filtering threshold at each decomposition scale is constructed according to the following formula:

[0016]

[0017] in, Indicated in j The filtering threshold at the decomposition scale is Indicated in j The standard deviation of noise at each decomposition scale is Indicated in j The length of the signal at the decomposition scale, j Indicates the decomposition scale.

[0018] In a possible implementation, the constructing a data filtering model based on the filtering threshold and the wavelet coefficient includes:

[0019] At each decomposition scale, the difference between the corresponding wavelet coefficient and the filtering threshold is calculated;

[0020] Determining the wavelet coefficients after filtering at each decomposition scale based on the difference corresponding to the decomposition scale;

[0021] The data filtering model is constructed based on the filtered wavelet coefficients at each decomposition scale.

[0022] In a possible implementation manner, the wavelet coefficients after filtering at the decomposition scale are determined according to the following formula:

[0023]

[0024] in, Indicated in j After filtering at the decomposition scale k wavelet coefficients, Indicated in j The first k wavelet coefficients, Indicated in j The filtering threshold at the decomposition scale is sign is the symbolic function, is the first preset coefficient, b is the second preset coefficient.

[0025] In a possible implementation, the performance detection model is composed of a convolutional neural network sub-model and a long short-term memory network sub-model, and the performance detection of the denoised performance data based on the trained performance detection model includes:

[0026] Inputting the denoised performance data into the convolutional neural network sub-model for feature extraction to obtain component performance characteristics;

[0027] The component performance characteristics are input into the long short-term memory network sub-model for prediction to obtain a test result for the electronic component to be tested.

[0028] In a possible implementation, the value range of the Sigmoid function in the convolutional neural network sub-model and the long short-term memory network sub-model is [0, 1];

[0029] The value range of the tanh activation function in the convolutional neural network sub-model and the long short-term memory network sub-model is [-1, 1].

[0030] In a possible implementation manner, after obtaining the detection result for the electronic component to be tested, the method further includes:

[0031] Data analysis is performed on the detection results of the electronic component to be tested to determine analysis results, wherein the analysis results include at least one of data chart display results, performance evaluation results and life prediction results.

[0032] In a possible implementation manner, the performance detection device includes one or more of the following devices:

[0033] Voltage source, current source, frequency generator, oscilloscope, multi-channel measurement switch and data acquisition card.

[0034] In a second aspect, the present disclosure further provides a detection system based on electronic component performance data, comprising:

[0035] A test module, used to test the electronic component to be tested using a performance testing device to obtain initial performance data;

[0036] A denoising module, used for performing multi-scale denoising processing on the initial performance data based on an adaptive filtering method to obtain denoised performance data;

[0037] The detection module is used to perform performance detection on the denoised performance data based on the trained performance detection model to obtain a detection result for the electronic component to be tested.

[0038] By adopting the above-mentioned detection method and system based on electronic component performance data, when using performance detection equipment to test the electronic component to be tested, initial performance data can be obtained, and then the initial performance data is subjected to multi-scale denoising processing based on the adaptive filtering method, and finally the denoised performance data obtained by the processing is subjected to performance detection based on the trained performance detection model, thereby obtaining the detection result for the electronic component to be tested. The present disclosure can highlight the detailed features at different decomposition scales through multi-scale denoising processing, better suppress noise, and enhance the accuracy of data processing, so that the accuracy of subsequent performance detection based on the performance detection model is higher.

[0039] Other advantages of the present disclosure will be explained in more detail in conjunction with the following description and drawings.

[0040] It should be understood that the above description is only an overview of the technical solution of the present disclosure, so that the technical means of the present disclosure can be generally understood and then implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are specifically described below by example. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the drawings only illustrate certain embodiments of the present disclosure and therefore should not be regarded as limiting the scope of protection. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work. Moreover, the same reference numerals are used to represent the same components throughout the drawings. In the drawings:

[0042] Figure 1 A flow chart of a detection method based on electronic component performance data provided by an embodiment of the present disclosure is shown;

[0043] Figure 2 A schematic diagram of a detection system based on electronic component performance data provided by an embodiment of the present disclosure is shown;

[0044] Figure 3 A schematic diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0045] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] In the description of the embodiments of the present disclosure, it should be understood that terms such as "including" or "having" are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or a combination thereof in the specification, and do not exclude the possibility of the presence of one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof.

[0047] Unless otherwise specified, “ / ” means or. For example, A / B can mean A or B. The “and / or” in this article is merely a way to describe the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0048] The terms "first", "second", etc. are used only to distinguish the same or similar technical features for the convenience of description, and should not be understood as indicating or implying the relative importance or quantity of these technical features. Thus, the features defined by "first", "second", etc. may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise specified, the term "plurality" means two or more than two.

[0049] It has been found that in the prior art, generally, simple analysis of the detection data of the electronic component itself is performed to determine whether there is any abnormality in the performance of the electronic component, such as threshold comparison. This leads to the problem that the accuracy of the performance detection of the electronic component is not high.

[0050] In order to at least partially solve one or more of the above problems and other potential problems, the present disclosure at least provides a detection method and system based on electronic component performance data to improve the performance detection accuracy of electronic components.

[0051] To facilitate understanding of this embodiment, a detection method based on electronic component performance data disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the detection method provided in the embodiment of the present disclosure is generally an electronic device with certain computing capabilities, and the electronic device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (UE), a handheld device, a computing device, etc. In some possible implementations, the detection method based on electronic component performance data can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0052] See also Figure 1 , which shows a flow chart of a detection method based on electronic component performance data provided by an embodiment of the present disclosure, the method comprising the following steps S101 to S103:

[0053] S101: Testing the electronic component to be tested using a performance testing device to obtain initial performance data;

[0054] S102: performing multi-scale denoising processing on the initial performance data based on an adaptive filtering method to obtain denoised performance data;

[0055] S103: Performing performance testing on the denoised performance data based on the trained performance testing model to obtain a testing result for the electronic component to be tested.

[0056] In order to facilitate understanding of the detection method based on electronic component performance data provided by the embodiment of the present disclosure, the application scenarios of the detection method are briefly introduced below. The detection method provided by the embodiment of the present disclosure is mainly used in related scenarios where electronic component testing is required. The scenarios in which different electronic components may be used are also different, such as integrated circuits, consumer electronics, communication systems, photovoltaic power generation, lighting, high-power power conversion and other fields. After the production of electronic components is completed and before they are put on the market, it is usually necessary to test the performance of the electronic components to determine whether there are any abnormalities in the performance of the electronic components based on the test results. If there are any abnormalities, the corresponding electronic components can be destroyed or re-improved.

[0057] Taking into account that the relevant technology only performs a simple analysis on the detection data of the electronic components themselves, resulting in low accuracy in the performance detection of the electronic components, based on this, the embodiment of the present disclosure provides a high-precision detection solution based on multi-scale denoising processing, which evaluates the performance of the components through advanced data analysis technology, thereby improving the accuracy and reliability of the electronic component evaluation.

[0058] For different application scenarios, the corresponding electronic components to be tested are also different. The embodiments of the present disclosure can realize performance testing of relevant electronic components in various application scenarios, and no specific limitation is made here.

[0059] Regardless of the type of electronic component to be tested, the embodiments of the present disclosure can first use a performance testing device to test the electronic component to determine the initial performance data, and then perform multi-scale denoising processing on the initial performance data based on an adaptive filtering method, and perform performance testing on the denoised performance data obtained by the denoising processing based on a trained performance detection model to determine the final detection result.

[0060] The performance detection equipment here may be, for example, a voltage source, a current source, a frequency generator, an oscilloscope, a multi-channel measurement switch and a data acquisition card. In addition, it may also be other detection equipment, which is not specifically limited here.

[0061] In practical applications, one of the above-mentioned performance detection devices can be used to implement component testing. For example, the output voltage of the component can be determined by a voltage source, and the voltage can be used as initial performance data. Multiple of the above-mentioned performance detection devices can also be used to implement component testing. For example, while determining the output voltage by a voltage source, a current source is also used to determine the output current, and both the output current and the output voltage are used as initial performance data. That is, the initial performance data determined by the embodiment of the present disclosure can be the test results from one performance detection device, or the test results from multiple performance detection devices, and no specific restrictions are made here. In addition, the initial performance data here can also be multiple test results from the same performance detection device, and no specific restrictions are made here.

[0062] In practical applications, the embodiments of the present disclosure can first prepare the system components and obtain the electronic components to be tested, such as resistors, capacitors, transistors, etc. Secondly, prepare performance testing equipment, including voltage sources, current sources, frequency generators, oscilloscopes, multi-channel measurement switches, and data acquisition cards, etc. Finally, install a data processing unit, such as a computer or microprocessor, which can be a processing unit built into the electronic device, and is equipped with performance analysis software.

[0063] After the preparation work is completed, the embodiment of the present disclosure then proceeds to build the system, connecting the electronic components to the performance testing equipment to ensure that the connections between all devices are correct and the data paths are unobstructed.

[0064] Here, you can set the test parameters in the performance analysis software, such as test voltage, current, frequency, temperature and other conditions, and set the data collection frequency and test duration.

[0065] After completing the setting of the test parameters, the embodiment of the present disclosure can start the performance detection device to test the electronic component according to the preset parameters. Here, a data acquisition card can be used to record the response data of the electronic component under different working conditions in real time as the initial performance data.

[0066] On the premise of determining the initial performance data, the embodiment of the present disclosure will perform multi-scale denoising on the initial performance data based on an adaptive filtering method. The multi-scale denoising here means that for signals decomposed in different frequency ranges, denoising with different thresholds can be performed, thereby highlighting the detailed features of the signals at different decomposition scales, suppressing noise, and enhancing the accuracy of data processing, so that the subsequent performance detection of the denoised performance data based on the trained performance detection model not only has a faster detection speed, but also has a higher detection accuracy.

[0067] Considering the key role of multi-scale denoising processing in achieving high-precision detection in the embodiments of the present disclosure, the process of implementing the multi-scale denoising processing will be described in detail below.

[0068] In the embodiment of the present disclosure, the initial performance data is subjected to multi-scale denoising processing according to the following steps:

[0069] Step 1: Perform wavelet decomposition on the initial performance data at multiple decomposition scales to obtain wavelet coefficients corresponding to each decomposition scale;

[0070] Step 2: construct filtering thresholds at each decomposition scale according to the size of the initial performance data;

[0071] Step 3: construct a data filtering model based on filtering threshold and wavelet coefficients;

[0072] Step 4: Filter the initial performance data based on the data filtering model to obtain filtered performance data;

[0073] Step 5: Clean the filtering performance data to obtain denoising performance data.

[0074] The embodiment of the present disclosure implements wavelet decomposition of initial performance data at multiple decomposition scales. As a signal processing technology with multi-resolution analysis as its core concept, wavelet transform uses the scaling and translation characteristics of wavelet basis functions to fit different frequency components of the measured signal and locate these frequency components in the time series. The decomposition scale here can be understood as the frequency range where different frequency components are located.

[0075] In addition, the disclosed embodiment also constructs filtering thresholds at each decomposition scale. In this way, the data filtering model constructed based on the filtering thresholds and wavelet coefficients can perform self-adjusting threshold transformation on the wavelet coefficients at each decomposition scale, thereby highlighting the detailed features of the signal at different decomposition scales.

[0076] The construction method of the data filtering model can be implemented in the following steps:

[0077] Step 1: At each decomposition scale, calculate the difference between the corresponding wavelet coefficient and the filtering threshold;

[0078] Step 2: Based on the difference corresponding to each decomposition scale, determine the wavelet coefficient after filtering at the decomposition scale;

[0079] Step 3: Construct a data filtering model based on the filtered wavelet coefficients at each decomposition scale.

[0080] Here, we can first determine the difference between the corresponding wavelet coefficient and the filtering threshold at each decomposition scale. The larger the difference, the more it indicates that a higher intensity filtering process is required at the decomposition scale. Similarly, the smaller the difference, the more it indicates that a lower intensity filtering process is required at the decomposition scale. In this way, the constructed data filtering model will be more suitable for the filtering needs of the initial performance data, so that the filtering performance data obtained by the filtering process and the denoising performance data obtained by the subsequent cleaning have higher processing accuracy.

[0081] In order to further understand the above filtering process, a specific formula will be used for explanation.

[0082] In the embodiment of the present disclosure, the filtering threshold at each decomposition scale can be constructed according to the following formula:

[0083]

[0084] in, Indicated in j The filtering threshold at the decomposition scale is Indicated in j The standard deviation of noise at each decomposition scale is Indicated in j The length of the signal at the decomposition scale, j Indicates the decomposition scale.

[0085] It can be known that different filtering thresholds will be determined for different decomposition scales, and the filtering threshold is positively correlated with the length of the signal and the noise standard deviation under the corresponding decomposition scale. In this way, when the signal length is longer and / or the noise standard deviation is larger, a larger filtering threshold can be determined. Conversely, when the signal length is shorter and / or the noise standard deviation is smaller, a smaller filtering threshold can be determined.

[0086] Based on the constructed filtering thresholds at each decomposition scale and the wavelet coefficients before filtering at each decomposition scale, the wavelet coefficients after filtering at each decomposition scale can be determined here, which can be determined specifically according to the following disclosure:

[0087]

[0088] in, Indicated in j After filtering at the decomposition scale k wavelet coefficients, Indicated in j The first k wavelet coefficients, sign is the symbolic function, is the first preset coefficient, b is the second preset coefficient.

[0089] It can be seen that the embodiment of the present disclosure implements a multi-scale filtering scheme based on the comparative relationship between the wavelet coefficients and the filtering threshold at the same decomposition scale. In this way, each decomposition scale will correspond to one or more filtered wavelet coefficients, and when such wavelet coefficients are used for filtering, the detailed characteristics of the signal at the current decomposition scale will be highlighted to a greater extent, which significantly improves the accuracy of data processing.

[0090] The detection method based on electronic component performance data provided by the embodiment of the present disclosure performs performance detection on the denoised performance data based on a trained performance detection model. In order to achieve higher precision performance detection, the embodiment of the present disclosure uses a combined neural network to train the performance detection model.

[0091] The performance detection model here can be composed of a Convolutional Neural Networks (CNN) sub-model and a Long Short-Term Memory (LSTM) sub-model. The two sub-models (i.e., the CNN sub-model and the LSTM sub-model) can be integrated through a tensor processing layer.

[0092] Among them, the CNN sub-model in the embodiment of the present disclosure includes multiple stacked convolutional layers, ReLU activation functions and pooling layers arranged in sequence. The CNN sub-model is used to output the component performance characteristics after performance feature extraction; the LSTM sub-model is used to receive the component performance characteristics after performance feature extraction, and obtains the predicted detection results through the update and transmission process of the LSTM unit and the linear layer conversion process, which can accurately predict the performance of electronic components.

[0093] Preferably, the value range of the Sigmoid function in the two sub-models is [0, 1], and the value range of the tanh activation function is [-1, 1].

[0094] The detection results predicted by the embodiments of the present disclosure may be, for example, component performance presented by specific data such as resistance, capacitance, inductance, frequency response, signal gain, and noise level, which are used to intuitively reflect the performance of the component and further include the current working status, such as whether there are problems such as overheating, aging, and damage. Further analysis can reflect the reliability and life expectancy of the component.

[0095] Here, by performing data analysis on the test results of the electronic component to be tested, the analysis results can be determined, wherein the analysis results include at least one of a data chart display result, a performance evaluation result, and a life prediction result. It can be seen that the detection method provided by the embodiment of the present disclosure can realize a richer performance analysis solution, thereby better meeting the actual needs of users and being more applicable.

[0096] In the description of this specification, the description with reference to the terms "some possible embodiments", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure, and the above terms do not necessarily represent the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0097] About the method flow chart of the embodiment of the present disclosure, some operations are described as different steps performed in a certain order. Such a flow chart is illustrative and not restrictive. Some steps described in this article can be grouped together and performed in a single operation, or some steps can be divided into multiple sub-steps, and some steps can be performed in an order different from that shown in this article. The various steps shown in the flow chart can be implemented in any way by any circuit structure and / or tangible mechanism (for example, by software running on a computer device, hardware (for example, a logical function implemented by a processor or a chip), etc., and / or any combination thereof).

[0098] Those skilled in the art will appreciate that, in the method described in the above specific implementation, the writing order of each step does not mean a strict execution order, and the specific execution order of each step should be determined by its function and possible internal logic.

[0099] Based on the same inventive concept, the embodiment of the present disclosure also provides a detection system corresponding to the detection method based on electronic component performance data. Since the principle of solving the problem by the system in the embodiment of the present disclosure is similar to the above-mentioned detection method in the embodiment of the present disclosure, the implementation of the system can refer to the implementation of the method, and the repeated parts will not be repeated.

[0100] Reference Figure 2 FIG. 2 is a schematic diagram of a detection system based on electronic component performance data provided by an embodiment of the present disclosure. The system includes: a test module 201, a denoising module 202, and a detection module 203; wherein:

[0101] The testing module 201 is used to test the electronic component to be tested by using the performance testing equipment to obtain initial performance data;

[0102] A denoising module 202, configured to perform multi-scale denoising processing on the initial performance data based on an adaptive filtering method to obtain denoised performance data;

[0103] The detection module 203 is used to perform performance detection on the denoised performance data based on the trained performance detection model to obtain a detection result for the electronic component to be tested.

[0104] By adopting the above-mentioned detection system based on electronic component performance data, when using the performance detection equipment to test the electronic component to be tested, initial performance data can be obtained, and then the initial performance data is subjected to multi-scale denoising processing based on the adaptive filtering method, and finally the denoised performance data obtained by the processing is subjected to performance testing based on the trained performance detection model, thereby obtaining the detection result for the electronic component to be tested. The present disclosure can highlight the detailed features at different decomposition scales through multi-scale denoising processing, better suppress noise, and enhance the accuracy of data processing, so that the accuracy of subsequent performance testing based on the performance detection model is higher.

[0105] In a possible implementation, the denoising module 202 is specifically configured to perform multi-scale denoising processing on the initial performance data based on an adaptive filtering method according to the following steps:

[0106] Perform wavelet decomposition on the initial performance data at multiple decomposition scales to obtain wavelet coefficients corresponding to each decomposition scale;

[0107] Construct filtering thresholds at each decomposition scale according to the size of the initial performance data;

[0108] Construct a data filtering model based on filtering threshold and wavelet coefficients;

[0109] Filtering the initial performance data based on the data filtering model to obtain filtered performance data;

[0110] The filtering performance data is cleaned to obtain denoising performance data.

[0111] In a possible implementation, the denoising module 202 is specifically configured to construct a filtering threshold at each decomposition scale according to the following formula:

[0112]

[0113] in, Indicated in j The filtering threshold at the decomposition scale is Indicated in j The standard deviation of noise at each decomposition scale is Indicated in j The length of the signal at the decomposition scale, j Indicates the decomposition scale.

[0114] In a possible implementation, the denoising module 202 is specifically configured to construct a data filtering model based on a filtering threshold and wavelet coefficients according to the following steps:

[0115] At each decomposition scale, the difference between the corresponding wavelet coefficient and the filtering threshold is calculated;

[0116] Based on the difference corresponding to each decomposition scale, determining the wavelet coefficient after filtering at the decomposition scale;

[0117] A data filtering model is constructed based on the filtered wavelet coefficients at each decomposition scale.

[0118] In a possible implementation, the denoising module 202 is specifically configured to determine the wavelet coefficients after filtering at the decomposition scale according to the following formula:

[0119]

[0120] in, Indicated in j After filtering at the decomposition scale k wavelet coefficients, Indicated in j The first k wavelet coefficients, Indicated in j The filtering threshold at the decomposition scale is sign is the symbolic function, is the first preset coefficient, b is the second preset coefficient.

[0121] In a possible implementation, the performance detection model is composed of a convolutional neural network sub-model and a long short-term memory network sub-model, and the detection module 203 is specifically used to perform performance detection on the denoised performance data based on the trained performance detection model according to the following steps:

[0122] The denoised performance data is input into the convolutional neural network sub-model for feature extraction to obtain component performance characteristics;

[0123] The component performance characteristics are input into the long short-term memory network sub-model for prediction to obtain the test results for the electronic component to be tested.

[0124] In a possible implementation, the value range of the Sigmoid function in the convolutional neural network sub-model and the long short-term memory network sub-model is [0, 1];

[0125] The value range of the tanh activation function in the convolutional neural network sub-model and the long short-term memory network sub-model is [-1, 1].

[0126] In a possible implementation, it further includes:

[0127] The analysis module 204 is used to perform data analysis on the test results of the electronic components to be tested after obtaining the test results, and determine the analysis results, which include at least one of data chart display results, performance evaluation results and life prediction results.

[0128] In a possible implementation, the performance detection device includes one or more of the following devices:

[0129] Voltage source, current source, frequency generator, oscilloscope, multi-channel measurement switch and data acquisition card.

[0130] It should be noted that the system in the embodiment of the present disclosure can implement each process of the embodiment of the aforementioned method and achieve the same effects and functions, which will not be repeated here.

[0131] The present disclosure also provides an electronic device, such as Figure 3 , which is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure, includes: a processor 301, a memory 302, and a bus 303. The memory 302 stores machine-readable instructions executable by the processor 301 (for example, Figure 2 The execution instructions corresponding to the test module 201, the denoising module 202, and the detection module 203 in the system, etc.), when the electronic device is running, the processor 301 communicates with the memory 302 through the bus 303, and the machine-readable instructions are executed by the processor 301 to perform the following processing:

[0132] Use performance testing equipment to test the electronic components to obtain initial performance data;

[0133] Perform multi-scale denoising on the initial performance data based on an adaptive filtering method to obtain denoised performance data;

[0134] Based on the trained performance test model, the denoised performance data is tested to obtain the test results for the electronic components to be tested.

[0135] The present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the detection method based on electronic component performance data described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0136] The embodiments of the present disclosure also provide a computer program product, which carries a program code. The instructions included in the program code can be used to execute the steps of the detection method based on electronic component performance data described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0137] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0138] Each embodiment in the present disclosure is described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system, device, and computer-readable storage medium embodiments, since they are basically similar to the method embodiments, their descriptions are simplified, and the relevant parts can be referred to the partial description of the method embodiments.

[0139] The system, device, and computer-readable storage medium provided in the embodiments of the present disclosure correspond one-to-one to the method. Therefore, the system, device, and computer-readable storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system, device, and computer-readable storage medium will not be repeated here.

[0140] It should be understood by those skilled in the art that the embodiments of the present disclosure can be implemented in the form of methods and systems (or devices), or computer-readable storage media. Therefore, the present disclosure can be implemented in a completely hardware implementation, a completely software implementation, or an implementation that combines software and hardware. Moreover, the present disclosure can be implemented in the form of a computer-readable storage medium implemented on one or more computer-usable storage media (including but not limited to disk storage, read-only compact disk storage (CD-ROM), optical storage, etc.) containing computer-usable program codes.

[0141] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, systems (or devices) and computer-readable storage media according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device are used to implement the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0142] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device, wherein the instruction device implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0143] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0144] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0145] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory (Flash RAM). Memory is an example of a computer-readable medium.

[0146] Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory, read-only memory, electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. In addition, although the operations of the disclosed method are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. In addition, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple sub-steps.

[0147] Although the spirit and principle of the present disclosure have been described above with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined. The present disclosure is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims.

Claims

1. A detection method based on electronic component performance data, characterized in that: include: Use performance testing equipment to test the electronic components to obtain initial performance data; Performing multi-scale denoising processing on the initial performance data based on an adaptive filtering method to obtain denoised performance data; Performing a performance test on the denoised performance data based on the trained performance test model to obtain a test result for the electronic component to be tested; The multi-scale denoising process of the initial performance data based on the adaptive filtering method includes: Performing wavelet decomposition on the initial performance data at multiple decomposition scales to obtain wavelet coefficients corresponding to each decomposition scale; Constructing filtering thresholds at various decomposition scales according to the size of the initial performance data; Constructing a data filtering model based on the filtering threshold and the wavelet coefficient; Filtering the initial performance data based on the data filtering model to obtain filtered performance data; Performing data cleaning on the filtering performance data to obtain the denoising performance data; The specific calculation formula for constructing the filter threshold at each decomposition scale is: Among them, λ j represents the filtering threshold at the jth decomposition scale, σ j represents the standard deviation of the noise at the jth decomposition scale, N j represents the length of the signal at the jth decomposition scale, where j represents the decomposition scale; The step of constructing a data filtering model based on the filtering threshold and the wavelet coefficients includes: At each decomposition scale, the difference between the corresponding wavelet coefficient and the filtering threshold is calculated; Determining the wavelet coefficients after filtering at each decomposition scale based on the difference corresponding to the decomposition scale; Constructing the data filtering model based on the wavelet coefficients after filtering at each decomposition scale; The calculation formula for determining the wavelet coefficients after filtering at the decomposition scale is: in, represents the kth wavelet coefficient after filtering at the jth decomposition scale, ω j,k represents the kth wavelet coefficient at the jth decomposition scale, λ j represents the filtering threshold at the jth decomposition scale, sign is the sign function, a is the first preset coefficient, and b is the second preset coefficient.

2. The method according to claim 1, characterized in that The performance detection model is composed of a convolutional neural network sub-model and a long short-term memory network sub-model. The performance detection of the denoised performance data based on the trained performance detection model includes: Inputting the denoised performance data into the convolutional neural network sub-model for feature extraction to obtain component performance characteristics; The component performance characteristics are input into the long short-term memory network sub-model for prediction to obtain a test result for the electronic component to be tested.

3. The method according to claim 2, characterized in that The value range of the Sigmoid function in the convolutional neural network sub-model and the long short-term memory network sub-model is [0, 1]; The value range of the tanh activation function in the convolutional neural network sub-model and the long short-term memory network sub-model is [-1, 1].

4. The method according to claim 1, characterized in that After obtaining the test result for the electronic component to be tested, the method further includes: Data analysis is performed on the detection results of the electronic component to be tested to determine analysis results, wherein the analysis results include at least one of data chart display results, performance evaluation results and life prediction results.

5. The method according to claim 1, characterized in that The performance testing equipment includes one or more of the following equipment: Voltage source, current source, frequency generator, oscilloscope, multi-channel measurement switch and data acquisition card.

6. A detection system based on electronic component performance data, characterized in that: include: A test module, used to test the electronic component to be tested using a performance testing device to obtain initial performance data; A denoising module, used for performing multi-scale denoising processing on the initial performance data based on an adaptive filtering method to obtain denoised performance data; A detection module, used to perform performance detection on the denoised performance data based on a trained performance detection model to obtain a detection result for the electronic component to be tested; The denoising module specifically performs multi-scale denoising processing on the initial performance data based on an adaptive filtering method according to the following steps: Performing wavelet decomposition on the initial performance data at multiple decomposition scales to obtain wavelet coefficients corresponding to each decomposition scale; Constructing filtering thresholds at various decomposition scales according to the size of the initial performance data; Constructing a data filtering model based on the filtering threshold and the wavelet coefficient; Filtering the initial performance data based on the data filtering model to obtain filtered performance data; Performing data cleaning on the filtering performance data to obtain the denoising performance data; The specific calculation formula for constructing the filter threshold at each decomposition scale is: Among them, λ j represents the filtering threshold at the jth decomposition scale, σ j represents the standard deviation of the noise at the jth decomposition scale, N j represents the length of the signal at the jth decomposition scale, where j represents the decomposition scale; The step of constructing a data filtering model based on the filtering threshold and the wavelet coefficients includes: At each decomposition scale, the difference between the corresponding wavelet coefficient and the filtering threshold is calculated; Determining the wavelet coefficients after filtering at each decomposition scale based on the difference corresponding to the decomposition scale; Constructing the data filtering model based on the wavelet coefficients after filtering at each decomposition scale; The calculation formula for determining the wavelet coefficients after filtering at the decomposition scale is: in, represents the kth wavelet coefficient after filtering at the jth decomposition scale, ω j,k represents the kth wavelet coefficient at the jth decomposition scale, λ j represents the filtering threshold at the jth decomposition scale, sign is the sign function, a is the first preset coefficient, and b is the second preset coefficient.