Feature extraction method and system for self-healing voltage information of metallized film capacitors

Abstract

The present invention relates to the technical field of equipment performance testing, and discloses a method and system for extracting features of the self-healing voltage information of a metallized film capacitor. The method comprises: obtaining voltage measurement information corresponding to a target capacitor to be analyzed, where the target capacitor is a metallized film capacitor; using the voltage measurement information to determine the self-healing information of the target capacitor; performing target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information; wherein the target data processing includes at least signal decomposition of the voltage measurement information and feature extraction based on a preset feature extraction function; and the target data processing result includes self-healing feature information corresponding to the target capacitor. It can be seen that implementing the present invention can improve the efficiency and accuracy of feature extraction of the self-healing information corresponding to the capacitor.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment performance testing, and in particular to a method and system for extracting features of self-healing voltage information of a metallized film capacitor. Background Art

[0002] Metallized film capacitors are widely used in power electronics systems due to their high-frequency characteristics, high energy density, and excellent self-healing ability. This self-healing ability refers to the ability of the metallized film coating to instantly evaporate when the capacitor is subjected to overvoltage or partial breakdown, forming an insulating path, thereby automatically restoring the capacitor's insulation properties and preventing permanent damage to the equipment. This characteristic greatly improves the capacitor's reliability and service life, and is particularly important under harsh operating conditions such as high voltage and high pulses.

[0003] However, the self-healing process of capacitors is often accompanied by complex electrical signal changes. These signals contain valuable information about the self-healing state. However, effectively extracting and analyzing this information to accurately evaluate and predict the self-healing performance of capacitors has always been a technical challenge in the power electronics field. Traditional monitoring methods mostly rely on simple voltage or current threshold judgments. This method not only has limited accuracy but also has difficulty capturing subtle characteristic changes during the self-healing process, failing to meet the high reliability and intelligent maintenance requirements of modern electronic equipment. Summary of the Invention

[0004] The present invention provides a method and system for extracting features of the self-healing voltage information of a metallized film capacitor, which can improve the feature extraction efficiency and feature extraction accuracy of the self-healing information corresponding to the capacitor.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a method for extracting features of self-healing voltage information of a metallized film capacitor, the method comprising:

[0006] Obtaining voltage measurement information corresponding to a target capacitor to be analyzed, where the target capacitor is a metallized film capacitor; the voltage measurement information is used to determine self-healing information of the target capacitor;

[0007] performing target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information;

[0008] The target data processing includes at least signal decomposition of the voltage measurement information and feature extraction based on a preset feature extraction function; and the target data processing result includes self-healing feature information corresponding to the target capacitor.

[0009] As an optional implementation manner, in the first aspect of the present invention, performing target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information includes:

[0010] performing signal decomposition on the voltage measurement signal according to a preset feature extraction function to obtain a signal decomposition result corresponding to the voltage measurement signal, the signal decomposition result including low-frequency feature information and high-frequency feature information corresponding to the voltage measurement signal;

[0011] According to a preset feature extraction requirement and in combination with a preset target threshold, feature extraction is performed on the signal decomposition result to obtain a feature extraction result corresponding to the signal decomposition result as a target data processing result corresponding to the voltage measurement information;

[0012] Among them, the feature extraction requirements include at least two characteristic parameters, which are characteristic parameters corresponding to the self-healing information of the target capacitor; the two characteristic parameters are amplitude and pulse width respectively; the target threshold is used to perform denoising and / or signal screening on the signal decomposition result.

[0013] As an optional implementation manner, in the first aspect of the present invention, the preset target threshold value includes a sub-threshold value corresponding to each of the characteristic parameters;

[0014] The step of performing feature extraction on the signal decomposition result according to a preset feature extraction requirement and in combination with a preset target threshold to obtain a feature extraction result corresponding to the signal decomposition result includes:

[0015] Based on the two characteristic parameters included in the preset feature extraction requirements, data analysis is performed on the signal decomposition result to obtain parameter data corresponding to each of the characteristic parameters;

[0016] For each of the characteristic parameters, performing noise determination and noise filtering on the parameter data corresponding to the characteristic parameter according to the sub-threshold value corresponding to the characteristic parameter, to obtain a noise filtering result corresponding to the parameter data corresponding to the characteristic parameter;

[0017] According to the noise filtering results corresponding to all the characteristic parameters, taking the non-zero interval of the signal as a reference, and combining the two characteristic parameters, determining the pulse interval corresponding to the self-healing discharge pulse of the target capacitor;

[0018] The noise filtering results and the pulse intervals corresponding to all the characteristic parameters are determined as feature extraction results corresponding to the signal decomposition results.

[0019] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0020] Performing a performance evaluation on the target data processing result according to a preset self-healing performance evaluation process to obtain self-healing performance evaluation information for the target capacitor;

[0021] determining whether the self-healing performance evaluation information indicates that a preset parameter adjustment condition is met, and generating parameter adjustment information for the target capacitor when it is determined that the self-healing performance evaluation information indicates that the parameter adjustment condition is met;

[0022] The feature extraction process is updated according to the parameter adjustment information, and the preset feature extraction process is re-executed to perform target data processing on the voltage measurement information to obtain a target data processing result corresponding to the voltage measurement information. The preset self-healing performance evaluation process is then executed to perform performance evaluation on the target data processing result to obtain an operation corresponding to the self-healing performance evaluation information of the target capacitor. When it is determined that a certain piece of self-healing performance evaluation information does not meet the parameter adjustment condition, it is determined that the self-healing information feature extraction for the target capacitor is completed.

[0023] As an optional embodiment, in the first aspect of the present invention, performing a performance evaluation on the target data processing result according to a preset self-healing performance evaluation process to obtain self-healing performance evaluation information for the target capacitor includes:

[0024] Obtaining device model information of the target capacitor, and determining a reference parameter value corresponding to each characteristic parameter according to the device model information;

[0025] According to the reference parameter value corresponding to each characteristic parameter and taking all the characteristic parameters as evaluation benchmarks, a self-healing performance evaluation is performed on the target data processing result to obtain self-healing performance evaluation information for the target capacitor.

[0026] As an optional implementation manner, in the first aspect of the present invention, determining whether the self-healing performance evaluation information indicates that a preset parameter adjustment condition is met includes:

[0027] collecting actual self-healing information of the target capacitor;

[0028] Calculating a data difference between the actual self-healing information and the self-healing performance evaluation result, where the data difference is used to indicate a matching degree between the self-healing performance evaluation result and the actual self-healing information;

[0029] Determining, based on the data difference, whether a matching degree between the self-healing performance evaluation result and the actual self-healing information is lower than a set matching threshold;

[0030] When the degree of matching between the self-healing performance evaluation result and the actual self-healing information is lower than the matching threshold, it is determined that the self-healing performance evaluation information meets the preset parameter adjustment condition.

[0031] As an optional implementation, in the first aspect of the present invention, the feature extraction function includes a Haar wavelet function; the parameter adjustment information includes function adjustment information for the Haar wavelet function and / or threshold adjustment information for the target threshold;

[0032] The updating of the feature extraction process according to the parameter adjustment information includes:

[0033] When the parameter adjustment information includes the function adjustment information, performing parameter adjustment on the function parameters corresponding to the Haar wavelet function according to the function adjustment information;

[0034] When the parameter adjustment information includes the threshold adjustment information, performing a numerical adjustment on the target threshold according to the threshold adjustment information;

[0035] Among them, the function parameters include scale parameters, translation parameters, decomposition layers and filter parameters; the scale parameters are used to adjust the coarseness of the wavelet transform corresponding to the Haar wavelet function; the translation parameters are used to adjust the position of the Haar wavelet function on its current transformed signal; the decomposition layers are used to adjust the recursive depth of the Haar wavelet function; the filter parameters are used to adjust the filter coefficients of the filter used by the Haar wavelet function.

[0036] A second aspect of the present invention discloses a feature extraction system for self-healing voltage information of a metallized film capacitor, the system comprising:

[0037] an acquisition module, configured to acquire voltage measurement information corresponding to a target capacitor to be analyzed, wherein the target capacitor is a metallized film capacitor; the voltage measurement information is used to determine self-healing information of the target capacitor;

[0038] a data processing module, configured to perform target data processing on the voltage measurement information according to a preset feature extraction process, and obtain a target data processing result corresponding to the voltage measurement information;

[0039] The target data processing includes at least signal decomposition of the voltage measurement information and feature extraction based on a preset feature extraction function; and the target data processing result includes self-healing feature information corresponding to the target capacitor.

[0040] As an optional embodiment, in the second aspect of the present invention, the data processing module performs target data processing on the voltage measurement information according to a preset feature extraction process, and a method of obtaining a target data processing result corresponding to the voltage measurement information specifically includes:

[0041] performing signal decomposition on the voltage measurement signal according to a preset feature extraction function to obtain a signal decomposition result corresponding to the voltage measurement signal, the signal decomposition result including low-frequency feature information and high-frequency feature information corresponding to the voltage measurement signal;

[0042] According to a preset feature extraction requirement and in combination with a preset target threshold, feature extraction is performed on the signal decomposition result to obtain a feature extraction result corresponding to the signal decomposition result as a target data processing result corresponding to the voltage measurement information;

[0043] Among them, the feature extraction requirements include at least two characteristic parameters, which are characteristic parameters corresponding to the self-healing information of the target capacitor; the two characteristic parameters are amplitude and pulse width respectively; the target threshold is used to perform denoising and / or signal screening on the signal decomposition result.

[0044] As an optional implementation, in the second aspect of the present invention, the preset target threshold includes a sub-threshold corresponding to each of the characteristic parameters;

[0045] The data processing module performs feature extraction on the signal decomposition result according to a preset feature extraction requirement and a preset target threshold, and obtains a feature extraction result corresponding to the signal decomposition result in a manner specifically including:

[0046] Based on the two characteristic parameters included in the preset feature extraction requirements, data analysis is performed on the signal decomposition result to obtain parameter data corresponding to each of the characteristic parameters;

[0047] For each of the characteristic parameters, performing noise determination and noise filtering on the parameter data corresponding to the characteristic parameter according to the sub-threshold value corresponding to the characteristic parameter, to obtain a noise filtering result corresponding to the parameter data corresponding to the characteristic parameter;

[0048] According to the noise filtering results corresponding to all the characteristic parameters, taking the non-zero interval of the signal as a reference, and combining the two characteristic parameters, determining the pulse interval corresponding to the self-healing discharge pulse of the target capacitor;

[0049] The noise filtering results and the pulse intervals corresponding to all the characteristic parameters are determined as feature extraction results corresponding to the signal decomposition results.

[0050] As an optional embodiment, in the second aspect of the present invention, the system further includes:

[0051] a performance evaluation module, configured to perform a performance evaluation on the target data processing result according to a preset self-healing performance evaluation process, and obtain self-healing performance evaluation information for the target capacitor;

[0052] A judgment module, configured to judge whether the self-healing performance evaluation information indicates that a preset parameter adjustment condition is met;

[0053] a generating module, configured to generate parameter adjustment information for the target capacitor when the judging module determines that the self-healing performance evaluation information satisfies the parameter adjustment condition;

[0054] An updating module is configured to update the feature extraction process according to the parameter adjustment information, trigger the data processing module to re-execute the feature extraction process according to the preset configuration, perform target data processing on the voltage measurement information, and obtain a target data processing result corresponding to the voltage measurement information, and trigger the performance evaluation module to execute the self-healing performance evaluation process according to the preset configuration, perform performance evaluation on the target data processing result, and obtain an operation corresponding to the self-healing performance evaluation information of the target capacitor, until it is determined that a certain self-healing performance evaluation information does not meet the parameter adjustment condition, thereby determining that the self-healing information feature extraction for the target capacitor is completed.

[0055] As an optional embodiment, in the second aspect of the present invention, the performance evaluation module performs performance evaluation on the target data processing result according to a preset self-healing performance evaluation process, and the method of obtaining the self-healing performance evaluation information for the target capacitor specifically includes:

[0056] Obtaining device model information of the target capacitor, and determining a reference parameter value corresponding to each characteristic parameter according to the device model information;

[0057] According to the reference parameter value corresponding to each characteristic parameter and taking all the characteristic parameters as evaluation benchmarks, a self-healing performance evaluation is performed on the target data processing result to obtain self-healing performance evaluation information for the target capacitor.

[0058] As an optional implementation manner, in the second aspect of the present invention, the manner in which the judgment module judges whether the self-healing performance evaluation information indicates that the preset parameter adjustment condition is met specifically includes:

[0059] collecting actual self-healing information of the target capacitor;

[0060] Calculating a data difference between the actual self-healing information and the self-healing performance evaluation result, where the data difference is used to indicate a matching degree between the self-healing performance evaluation result and the actual self-healing information;

[0061] Determining, based on the data difference, whether a matching degree between the self-healing performance evaluation result and the actual self-healing information is lower than a set matching threshold;

[0062] When the degree of matching between the self-healing performance evaluation result and the actual self-healing information is lower than the matching threshold, it is determined that the self-healing performance evaluation information meets the preset parameter adjustment condition.

[0063] As an optional implementation, in the second aspect of the present invention, the feature extraction function includes a Haar wavelet function; the parameter adjustment information includes function adjustment information for the Haar wavelet function and / or threshold adjustment information for the target threshold;

[0064] The updating module updates the feature extraction process according to the parameter adjustment information in the following manner:

[0065] When the parameter adjustment information includes the function adjustment information, performing parameter adjustment on the function parameters corresponding to the Haar wavelet function according to the function adjustment information;

[0066] When the parameter adjustment information includes the threshold adjustment information, performing a numerical adjustment on the target threshold according to the threshold adjustment information;

[0067] Among them, the function parameters include scale parameters, translation parameters, decomposition layers and filter parameters; the scale parameters are used to adjust the coarseness of the wavelet transform corresponding to the Haar wavelet function; the translation parameters are used to adjust the position of the Haar wavelet function on its current transformed signal; the decomposition layers are used to adjust the recursive depth of the Haar wavelet function; the filter parameters are used to adjust the filter coefficients of the filter used by the Haar wavelet function.

[0068] A third aspect of the present invention discloses a device for extracting characteristics of self-healing voltage information of a metallized film capacitor, the device comprising:

[0069] a memory storing executable program code;

[0070] a processor coupled to the memory;

[0071] The processor calls the executable program code stored in the memory to execute the feature extraction method of the self-healing voltage information of the metallized film capacitor disclosed in the first aspect of the present invention.

[0072] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the feature extraction method of the self-healing voltage information of the metallized film capacitor disclosed in the first aspect of the present invention.

[0073] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0074] In an embodiment of the present invention, a method for extracting feature information of self-healing voltage of a metallized film capacitor is provided. The method comprises: obtaining voltage measurement information corresponding to a target capacitor to be analyzed, wherein the target capacitor is a metallized film capacitor; using the voltage measurement information to determine self-healing information of the target capacitor; performing target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information; wherein the target data processing includes at least signal decomposition of the voltage measurement information and feature extraction based on a preset feature extraction function; and the target data processing result includes self-healing feature information corresponding to the target capacitor. It can be seen that after the voltage measurement information of the target capacitor is obtained, the present invention performs in-depth target data processing on the voltage measurement information by using a preset feature extraction process, especially multiple data processing of signal decomposition and feature extraction based on a preset feature extraction function, which is conducive to improving the accuracy of determining the self-healing information of the target capacitor. Furthermore, the accurately determined self-healing information realizes real-time monitoring and rapid diagnosis of the status of the metallized film capacitor, which is conducive to improving the speed of discovering and repairing capacitor faults through the self-healing information, and to a certain extent, is conducive to improving the service life of the capacitor. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0076] Figure 1 This is a flow chart of a method for extracting features of self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention;

[0077] Figure 2 This is a flow chart of another method for extracting characteristics of self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention;

[0078] Figure 3 This is a structural diagram of a feature extraction system for self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention;

[0079] Figure 4 This is a schematic structural diagram of another feature extraction system for self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention;

[0080] Figure 5 The present invention is a schematic structural diagram of a device for extracting characteristics of self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0081] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0082] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or end comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed therein, or may optionally include other steps or elements inherent to such process, method, product, or end.

[0083] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0084] The present invention discloses a method and system for extracting feature information of the self-healing voltage of a metallized film capacitor. After obtaining the voltage measurement information of a target capacitor, the method performs in-depth target data processing on the voltage measurement information by adopting a preset feature extraction process. In particular, multiple data processing is performed through signal decomposition and feature extraction based on a preset feature extraction function. This helps to improve the accuracy of determining the self-healing information of the target capacitor. Furthermore, the accurately determined self-healing information enables real-time monitoring and rapid diagnosis of the status of the metallized film capacitor, which in turn helps to improve the speed of discovering and repairing capacitor faults through the self-healing information, and to a certain extent helps to increase the service life of the capacitor. Detailed descriptions are given below.

[0085] Example 1

[0086] See also Figure 1 , Figure 1 This is a flow chart of a method for extracting the characteristics of the self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention. Figure 1 The method for extracting the feature of the self-healing voltage information of the metallized film capacitor described above can be applied to a system or device for extracting the feature of the self-healing voltage information of the metallized film capacitor, and the embodiment of the present invention does not limit this. Figure 1 As shown, the feature extraction method of the self-healing voltage information of the metallized film capacitor may include the following operations:

[0087] 101. Obtain voltage measurement information corresponding to a target capacitor to be analyzed, where the target capacitor is a metallized film capacitor; the voltage measurement information is used to determine self-healing information of the target capacitor.

[0088] In an embodiment of the present invention, in order to obtain voltage measurement information of a target capacitor, a test circuit for the target capacitor can be pre-constructed, and a data acquisition device such as an oscilloscope can be connected to the test circuit. Specifically, the oscilloscope is connected to both ends of the target capacitor to thereby acquire the voltage waveform across the target capacitor in real time. The real-time acquired voltage waveform is the voltage measurement information. Furthermore, the oscilloscope can be directly connected or communicatively connected to a data processing terminal (such as a PC), so that the data processing terminal can acquire or receive the voltage measurement information and perform relevant information processing on the voltage measurement information as actually needed.

[0089] 102. Perform target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information.

[0090] In an embodiment of the present invention, target data processing includes at least signal decomposition of voltage measurement information and feature extraction based on a preset feature extraction function; and the target data processing result includes self-healing feature information corresponding to the target capacitor.

[0091] It can be seen that implementation Figure 1The described method for extracting the feature information of the self-healing voltage of a metallized film capacitor, after obtaining the voltage measurement information of the target capacitor, performs in-depth target data processing on the voltage measurement information by adopting a preset feature extraction process, especially through multiple data processing of signal decomposition and feature extraction based on a preset feature extraction function, which is beneficial to improving the accuracy of determining the self-healing information of the target capacitor; furthermore, the accurately determined self-healing information realizes real-time monitoring and rapid diagnosis of the status of the metallized film capacitor, which is beneficial to improving the speed of discovering and repairing capacitor faults through the self-healing information, and to a certain extent, is beneficial to improving the service life of the capacitor.

[0092] In an optional embodiment, the method of obtaining the voltage measurement information corresponding to the target capacitor to be analyzed in step 101 specifically includes:

[0093] Determining test usage information corresponding to performing a self-healing performance test on a target capacitor; the test usage information includes boost information and voltage stabilization information, wherein the boost information indicates parameters required to set a boost operation on the target capacitor; and the voltage stabilization information indicates a corresponding maintenance time after completing the boost operation;

[0094] After determining that the test circuit for the target capacitor meets the preset test conditions, performing a target test operation on the target capacitor according to the test usage information to obtain test record data for the target capacitor as voltage measurement information;

[0095] The boost information includes a boost rate and a target voltage value. Specifically, the boost rate can be 200V / s. The target voltage value needs to be adjusted according to the actual device model of the target capacitor. Generally, the target voltage value is set to 1.6 times the rated voltage of the capacitor.

[0096] The voltage stabilization information includes a voltage stabilization time, which is generally set to [5, 10] in seconds.

[0097] In this optional embodiment, the test circuit of the target capacitor satisfies the preset test conditions, specifically including:

[0098] The test circuit of the target capacitor is correctly connected, each circuit component of the test circuit operates normally, and the waveform recorded by the oscilloscope for the target capacitor in the test circuit is consistent with the waveform recorded by the target capacitor in normal operating state.

[0099] It can be seen that in this optional embodiment, the process of obtaining the voltage measurement information of the target capacitor is refined, and the test accuracy and reliability of the voltage measurement information are improved through the intelligent determination and setting of the test usage information, the test condition judgment of the test circuit, and the execution of the target test operation.

[0100] In another optional embodiment, the above step 102 performs target data processing on the voltage measurement information according to a preset feature extraction process, and a method of obtaining a target data processing result corresponding to the voltage measurement information specifically includes:

[0101] Performing signal decomposition on the voltage measurement signal according to a preset feature extraction function to obtain a signal decomposition result corresponding to the voltage measurement signal, the signal decomposition result including low-frequency feature information and high-frequency feature information corresponding to the voltage measurement signal;

[0102] According to the preset feature extraction requirements and the preset target threshold, feature extraction is performed on the signal decomposition result to obtain a feature extraction result corresponding to the signal decomposition result as the target data processing result corresponding to the voltage measurement information;

[0103] Among them, the feature extraction requirements include at least two feature parameters, which are feature parameters corresponding to the self-healing information of the target capacitor; the two feature parameters are amplitude and pulse width respectively; the target threshold is used to perform denoising and / or signal screening on the signal decomposition result.

[0104] In this optional embodiment, in actual application, a low-pass filter and a high-pass filter can be used to decompose the voltage measurement signal; and the signal decomposition result includes an approximate coefficient and a detail coefficient corresponding to the voltage measurement signal; wherein the approximate coefficient corresponds to the low-frequency feature information and is used to reflect the overall trend of the voltage measurement signal; the detail coefficient corresponds to the high-frequency feature information and is used to describe the local detail features of the voltage measurement signal, such as spikes, pulses, etc.

[0105] It can be seen that in this optional embodiment, the voltage measurement signal is decomposed by using a preset feature extraction function, which can accurately decompose the voltage signal into low-frequency feature information and high-frequency feature information; further, on the basis of the limited decomposition, the decomposition result can be combined with the preset feature extraction requirements and target threshold to perform feature extraction. Specifically, by selecting the amplitude and pulse width, two characteristic parameters closely related to the self-healing information of the target capacitor, it can be beneficial to improve the extraction efficiency and accuracy of the self-healing information of the target capacitor; in addition, by setting the target threshold, the interference of noise and irrelevant signals can be effectively removed, further ensuring the effectiveness and accuracy of the extracted features.

[0106] In yet another optional embodiment, the preset target threshold includes a sub-threshold corresponding to each characteristic parameter;

[0107] According to the preset feature extraction requirements and the preset target threshold, feature extraction is performed on the signal decomposition result. The method of obtaining the feature extraction result corresponding to the signal decomposition result specifically includes:

[0108] Based on the two characteristic parameters included in the preset feature extraction requirements, data analysis is performed on the signal decomposition results to obtain parameter data corresponding to each characteristic parameter;

[0109] For each characteristic parameter, performing noise determination and noise filtering on parameter data corresponding to the characteristic parameter according to the sub-threshold value corresponding to the characteristic parameter, to obtain a noise filtering result corresponding to the parameter data corresponding to the characteristic parameter;

[0110] Based on the noise filtering results corresponding to all characteristic parameters, taking the non-zero interval of the signal as a reference and combining the two characteristic parameters, the pulse interval corresponding to the self-healing discharge pulse of the target capacitor is determined;

[0111] The noise filtering results and pulse intervals corresponding to all characteristic parameters are determined as feature extraction results corresponding to the signal decomposition results.

[0112] In this optional embodiment, the voltage value of the target capacitor during self-healing is generally 500V or higher. Correspondingly, for the characteristic parameter of amplitude, the corresponding sub-threshold can be set to 500V, so that the amplitude below 500V is determined as noise; and, when the target capacitor self-heals, the conventional time measurement unit is microseconds. For the characteristic parameter of pulse width, the corresponding sub-threshold can be set to 1μs, and noise can be determined for a pulse width less than 1μs.

[0113] It can be seen that in this optional embodiment, a corresponding sub-threshold is set for each characteristic parameter (such as amplitude and pulse width) to accurately identify and filter out noise during the feature extraction process, effectively reduce the interference of noise signals on the characteristic parameters, and improve the accuracy and reliability of the extracted characteristic information; and, on the basis of data analysis of the signal decomposition results, the parameter data corresponding to each characteristic parameter is analyzed in detail based on the preset feature extraction requirements (including two characteristic parameters of amplitude and pulse width). On the basis of improving the degree of refinement of the feature extraction process, the extraction accuracy of key characteristic information directly related to the self-healing information of the target capacitor (corresponding to the above-mentioned feature extraction results) is further improved; in addition, in addition to the conventional amplitude and pulse width, the pulse interval feature is also introduced, which is beneficial not only to improve the dimension of the characteristic information, but also to improve the integrity of the characteristic information.

[0114] Example 2

[0115] See also Figure 2 , Figure 2 This is a flow chart of another method for extracting the characteristic of the self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention. Figure 2 The method for extracting the feature of the self-healing voltage information of the metallized film capacitor described above can be applied to a system or device for extracting the feature of the self-healing voltage information of the metallized film capacitor, and the embodiment of the present invention does not limit this. Figure 2 As shown, the feature extraction method of the self-healing voltage information of the metallized film capacitor may include the following operations:

[0116] 201. Obtain voltage measurement information corresponding to a target capacitor to be analyzed, where the target capacitor is a metallized film capacitor; the voltage measurement information is used to determine self-healing information of the target capacitor.

[0117] 202. Perform target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information.

[0118] In the embodiment of the present invention, for other descriptions of step 201-step 202, please refer to other specific descriptions of step 101-step 102 in embodiment 1, and the embodiment of the present invention will not be repeated here.

[0119] 203. Perform performance evaluation on the target data processing result according to a preset self-healing performance evaluation process to obtain self-healing performance evaluation information for the target capacitor.

[0120] 204. Determine whether the self-healing performance evaluation information indicates that a preset parameter adjustment condition is met.

[0121] In the embodiment of the present invention, when the judgment result of step 204 is yes, step 205 is triggered to be executed; when the judgment result of step 204 is no, step 206 is triggered to be executed.

[0122] 205. Generate parameter adjustment information for the target capacitor.

[0123] 205. Update the feature extraction process according to the parameter adjustment information.

[0124] In the embodiment of the present invention, before it is determined that a certain piece of self-healing performance evaluation information does not meet the parameter adjustment condition, the above steps 202 and 203 are repeatedly performed.

[0125] In the embodiment of the present invention, when it is determined that a certain self-healing performance evaluation information does not meet the parameter adjustment condition, step 206 is triggered.

[0126] 206. Determine whether the self-healing information feature extraction for the target capacitor is completed.

[0127] It can be seen that implementation Figure 2 The described feature extraction method for the self-healing voltage information of the metallized film capacitor introduces a self-healing performance evaluation process. Specifically, by performing performance evaluation on the target data processing results, the self-healing performance evaluation information of the target capacitor can be obtained in real time and accurately; and after obtaining the self-healing performance evaluation information, it can be compared and judged with the preset parameter adjustment conditions, and after determining that the parameter adjustment conditions are met, the corresponding parameter adjustment information can be intelligently generated, thereby realizing dynamic adjustment and iterative optimization of the feature extraction process, thereby continuously approaching the optimal feature extraction parameters and processes, while improving the accuracy and effectiveness of feature extraction, and also enhancing the adaptability and robustness of the overall method.

[0128] In an optional embodiment, the above step 203 performs performance evaluation on the target data processing result according to a preset self-healing performance evaluation process, and the method of obtaining the self-healing performance evaluation information for the target capacitor specifically includes:

[0129] Obtaining device model information of the target capacitor, and determining a reference parameter value corresponding to each characteristic parameter based on the device model information;

[0130] According to the reference parameter value corresponding to each characteristic parameter and taking all characteristic parameters as the evaluation benchmark, a self-healing performance evaluation is performed on the target data processing result to obtain self-healing performance evaluation information for the target capacitor.

[0131] It can be seen that in this optional embodiment, by obtaining the device model information of the target capacitor and determining the benchmark parameter value corresponding to each characteristic parameter based on this, it is possible to ensure that the benchmark used in the evaluation process is consistent with the actual characteristics of the capacitor, which is conducive to improving the accuracy and pertinence of the subsequent self-healing performance evaluation; in addition, this evaluation method is not only applicable to standard capacitors, but can also flexibly respond to the evaluation needs of capacitors of different models and specifications, which is conducive to enhancing the versatility and practicality of the evaluation method.

[0132] In this optional embodiment, further, the above-mentioned method of performing self-healing performance evaluation on the target data processing result based on the reference parameter value corresponding to each characteristic parameter and taking all characteristic parameters as the evaluation benchmark to obtain self-healing performance evaluation information for the target capacitor specifically includes:

[0133] For each characteristic parameter, the parameter data corresponding to the characteristic parameter is compared with the corresponding reference parameter value to obtain the difference information between the two;

[0134] According to the difference information corresponding to the feature parameter, combined with the set scoring mechanism, the feature parameter is scored to obtain a scoring result corresponding to the feature parameter;

[0135] According to the scoring mechanism, a preset numerical calculation is performed on the scoring results corresponding to all characteristic parameters to obtain a comprehensive numerical calculation result corresponding to all characteristic parameters;

[0136] Determining the scoring result corresponding to each characteristic parameter and the comprehensive numerical calculation result as self-healing performance evaluation information for the target capacitor;

[0137] The preset numerical value calculation includes weighted average calculation, sum calculation, or weighted sum calculation.

[0138] In this optional embodiment, the characteristic parameters may further include three characteristic parameters: capacitance change rate, loss tangent, and self-healing time; wherein, the smaller the corresponding values ​​of the capacitance change rate, loss tangent, and self-healing time, the better the self-healing performance of the target capacitor;

[0139] Then, assuming that the preset numerical calculation adopts a weighted summation calculation method, and the score of the capacitance change rate is determined to be 85, the score of the loss tangent is determined to be 90, and the score of the self-healing time is determined to be 75, and the score weights of the three characteristic parameters are set to 0.4, 0.3, and 0.3 respectively;

[0140] Correspondingly, the comprehensive numerical calculation result = capacitance change rate score × capacitance change rate weight + loss tangent score × loss tangent weight + self-healing time score × self-healing time weight

[0141] Substituting the above values ​​into the corresponding calculation formula is:

[0142] The result of the comprehensive numerical calculation = 85 × 0.4 + 90 × 0.3 + 75 × 0.3 = 83.5 points

[0143] Furthermore, corresponding classification levels can be set for the comprehensive numerical calculation results, for example: 90 points or above: excellent; 80-89 points: good; 70-79 points: fair; 60-69 points: poor; and below 60 points: poor. Accordingly, the above score of 83.5 can be determined to belong to the good classification level.

[0144] It can be seen that in this optional embodiment, a complete scoring mechanism is set up for the self-healing performance information of the target capacitor, which can not only refine the consideration and scoring results of each characteristic parameter, but also comprehensively consider and determine the rating results of all characteristic parameters, thereby improving the determination precision, accuracy and reliability of the self-healing performance evaluation information of the target capacitor.

[0145] In another optional embodiment, the method of determining whether the self-healing performance evaluation information indicates that the preset parameter adjustment condition is met in step 204 specifically includes:

[0146] Collecting actual self-healing information of the target capacitor;

[0147] Calculating the data difference between the actual self-healing information and the self-healing performance evaluation result. The data difference is used to indicate the matching degree between the self-healing performance evaluation result and the actual self-healing information.

[0148] Determine whether the matching degree between the self-healing performance evaluation result and the actual self-healing information is lower than the set matching threshold based on the data difference;

[0149] When the degree of matching between the self-healing performance evaluation result and the actual self-healing information is lower than a matching threshold, it is determined that the self-healing performance evaluation information meets the preset parameter adjustment condition.

[0150] In this optional embodiment, the actual self-healing information of the target capacitor can specifically be the actual self-healing quantity of the capacitor core; by comparing it with the self-healing performance evaluation result, if the data difference is lower than the matching threshold, it means that the calculated result deviates too much from the actual situation and the feature needs to be re-extracted.

[0151] It can be seen that in this optional embodiment, by calculating the data difference between the actual self-healing information and the self-healing performance evaluation results, a quantitative analysis of the evaluation error is achieved, and the difference between the healing performance evaluation results and the actual situation is intuitively displayed through numerical values, which is conducive to improving the convenience of relevant responsible personnel in reviewing the feature extraction situation; and when it is judged that the matching degree is lower than the set matching threshold, the subsequent parameter adjustment process can be automatically triggered to ensure the accuracy and effectiveness of the evaluation results. This step not only improves the flexibility of the evaluation, but also enhances the adaptability and robustness of the method.

[0152] In yet another optional embodiment, the feature extraction function includes a Haar wavelet function; the parameter adjustment information includes function adjustment information for the Haar wavelet function and / or threshold adjustment information for a target threshold;

[0153] The above-mentioned step 205 specifically includes the following steps to update the feature extraction process according to the parameter adjustment information:

[0154] When the parameter adjustment information includes function adjustment information, performing parameter adjustment on the function parameters corresponding to the Haar wavelet function according to the function adjustment information;

[0155] When the parameter adjustment information includes threshold adjustment information, performing a numerical adjustment on the target threshold according to the threshold adjustment information;

[0156] Among them, the function parameters include scale parameter, translation parameter, decomposition layer number and filter parameter; the scale parameter is used to adjust the coarseness of the wavelet transform corresponding to the Haar wavelet function; the translation parameter is used to adjust the position of the Haar wavelet function on its current transformed signal; the decomposition layer number is used to adjust the recursive depth of the Haar wavelet function; the filter parameter is used to adjust the filter coefficient of the filter used by the Haar wavelet function.

[0157] In this optional embodiment, adjusting the scale parameter enables fine control of the coarseness of the Haar wavelet transform, thereby more accurately capturing key features in the capacitor performance data. Adjusting the translation parameter ensures that feature extraction can be performed on specific regions of the capacitor performance data, avoiding interference from irrelevant information. Adjusting the number of decomposition levels enables feature extraction to penetrate the multi-scale structure of the data, extracting richer feature information. Adjusting the filter parameters further optimizes the filtering effect and improves the accuracy and stability of feature extraction.

[0158] It can be seen that in this optional embodiment, by introducing function adjustment information, the scale parameters, translation parameters, number of decomposition layers and filter parameters of the Haar wavelet function can be adjusted in multiple dimensions in a personalized and targeted manner. This flexibility not only allows customized feature extraction according to the characteristics of the target capacitor, but also enables the feature extraction process to better adapt to different application scenarios and performance evaluation requirements, greatly improving the pertinence and effectiveness of feature extraction; in addition, by introducing threshold adjustment information, the target threshold can be intelligently adjusted according to the matching of the self-healing performance evaluation results with the actual self-healing information. This intelligent adjustment not only helps to optimize the threshold selection of feature extraction, but also can reduce the feature extraction error caused by improper threshold, further improving the reliability and robustness of feature extraction.

[0159] Example 3

[0160] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a feature extraction system for self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention. Figure 3 As shown, the feature extraction system of the self-healing voltage information of the metallized film capacitor may include an acquisition module 301 and a data processing module 302, wherein:

[0161] The acquisition module 301 is used to obtain voltage measurement information corresponding to the target capacitor to be analyzed, where the target capacitor is a metallized film capacitor; the voltage measurement information is used to determine self-healing information of the target capacitor.

[0162] The data processing module 302 is configured to perform target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information; wherein the target data processing includes at least signal decomposition of the voltage measurement information and feature extraction based on a preset feature extraction function; and the target data processing result includes self-healing feature information corresponding to the target capacitor.

[0163] It can be seen that implementation Figure 3 The described feature extraction system for the self-healing voltage information of the metallized film capacitor, after obtaining the voltage measurement information of the target capacitor, performs in-depth target data processing on the voltage measurement information by adopting a preset feature extraction process, especially through multiple data processing of signal decomposition and feature extraction based on a preset feature extraction function, which is conducive to improving the accuracy of determining the self-healing information of the target capacitor; further, the accurately determined self-healing information realizes real-time monitoring and rapid diagnosis of the status of the metallized film capacitor, which is conducive to improving the speed of discovering and repairing capacitor faults through the self-healing information, and to a certain extent, it is conducive to improving the service life of the capacitor.

[0164] In an optional embodiment, the data processing module 302 performs target data processing on the voltage measurement information according to a preset feature extraction process, and obtains a target data processing result corresponding to the voltage measurement information in the following manner:

[0165] Performing signal decomposition on the voltage measurement signal according to a preset feature extraction function to obtain a signal decomposition result corresponding to the voltage measurement signal, the signal decomposition result including low-frequency feature information and high-frequency feature information corresponding to the voltage measurement signal;

[0166] According to the preset feature extraction requirements and the preset target threshold, feature extraction is performed on the signal decomposition result to obtain a feature extraction result corresponding to the signal decomposition result as the target data processing result corresponding to the voltage measurement information;

[0167] Among them, the feature extraction requirements include at least two feature parameters, which are feature parameters corresponding to the self-healing information of the target capacitor; the two feature parameters are amplitude and pulse width respectively; the target threshold is used to perform denoising and / or signal screening on the signal decomposition result.

[0168] It can be seen that in this optional embodiment, the voltage measurement signal is decomposed by using a preset feature extraction function, which can accurately decompose the voltage signal into low-frequency feature information and high-frequency feature information; further, on the basis of the limited decomposition, the decomposition result can be combined with the preset feature extraction requirements and target threshold to perform feature extraction. Specifically, by selecting the amplitude and pulse width, two characteristic parameters closely related to the self-healing information of the target capacitor, it can be beneficial to improve the extraction efficiency and accuracy of the self-healing information of the target capacitor; in addition, by setting the target threshold, the interference of noise and irrelevant signals can be effectively removed, further ensuring the effectiveness and accuracy of the extracted features.

[0169] In another optional embodiment, the preset target threshold includes a sub-threshold corresponding to each characteristic parameter;

[0170] The data processing module 302 performs feature extraction on the signal decomposition result according to the preset feature extraction requirements and the preset target threshold. The method of obtaining the feature extraction result corresponding to the signal decomposition result specifically includes:

[0171] Based on the two characteristic parameters included in the preset feature extraction requirements, data analysis is performed on the signal decomposition results to obtain parameter data corresponding to each characteristic parameter;

[0172] For each characteristic parameter, performing noise determination and noise filtering on parameter data corresponding to the characteristic parameter according to the sub-threshold value corresponding to the characteristic parameter, to obtain a noise filtering result corresponding to the parameter data corresponding to the characteristic parameter;

[0173] Based on the noise filtering results corresponding to all characteristic parameters, taking the non-zero interval of the signal as a reference and combining the two characteristic parameters, the pulse interval corresponding to the self-healing discharge pulse of the target capacitor is determined;

[0174] The noise filtering results and pulse intervals corresponding to all characteristic parameters are determined as feature extraction results corresponding to the signal decomposition results.

[0175] It can be seen that in this optional embodiment, a corresponding sub-threshold is set for each characteristic parameter (such as amplitude and pulse width) to accurately identify and filter out noise during the feature extraction process, effectively reduce the interference of noise signals on the characteristic parameters, and improve the accuracy and reliability of the extracted characteristic information; and, on the basis of data analysis of the signal decomposition results, the parameter data corresponding to each characteristic parameter is analyzed in detail based on the preset feature extraction requirements (including two characteristic parameters of amplitude and pulse width). On the basis of improving the degree of refinement of the feature extraction process, the extraction accuracy of key characteristic information directly related to the self-healing information of the target capacitor (corresponding to the above-mentioned feature extraction results) is further improved; in addition, in addition to the conventional amplitude and pulse width, the pulse interval feature is also introduced, which is beneficial not only to improve the dimension of the characteristic information, but also to improve the integrity of the characteristic information.

[0176] In yet another alternative embodiment, see Figure 4 , Figure 4 This is a schematic diagram of the structure of a feature extraction system for self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention. Figure 4 As shown, the system further includes a performance evaluation module 303, a judgment module 304, a generation module 305 and an update module 306, wherein:

[0177] The performance evaluation module 303 is configured to perform a performance evaluation on the target data processing result according to a preset self-healing performance evaluation process to obtain self-healing performance evaluation information for the target capacitor;

[0178] The judgment module 304 is used to judge whether the self-healing performance evaluation information indicates that the preset parameter adjustment conditions are met;

[0179] A generating module 305 is configured to generate parameter adjustment information for a target capacitor when the judging module 304 judges that the self-healing performance evaluation information satisfies the parameter adjustment condition;

[0180] The updating module 306 is used to update the feature extraction process according to the parameter adjustment information, and trigger the data processing module 302 to re-execute the preset feature extraction process, perform target data processing on the voltage measurement information, and obtain the target data processing result corresponding to the voltage measurement information, and trigger the performance evaluation module 303 to execute the preset self-healing performance evaluation process, perform performance evaluation on the target data processing result, and obtain the operation corresponding to the self-healing performance evaluation information of the target capacitor, until it is determined that a certain self-healing performance evaluation information does not meet the parameter adjustment conditions, and it is determined that the self-healing information feature extraction for the target capacitor is completed.

[0181] It can be seen that in this optional embodiment, a self-healing performance evaluation process is introduced. Specifically, by performing performance evaluation on the target data processing results, the self-healing performance evaluation information of the target capacitor can be obtained in real time and accurately; and after obtaining the self-healing performance evaluation information, it can be compared and judged with the preset parameter adjustment conditions, and after determining that the parameter adjustment conditions are met, the corresponding parameter adjustment information is intelligently generated, thereby realizing dynamic adjustment and iterative optimization of the feature extraction process, thereby continuously approaching the optimal feature extraction parameters and processes, while improving the accuracy and effectiveness of feature extraction, it can also enhance the adaptability and robustness of the overall method.

[0182] In another optional embodiment, the performance evaluation module 303 performs performance evaluation on the target data processing result according to a preset self-healing performance evaluation process, and obtains the self-healing performance evaluation information for the target capacitor in a manner specifically including:

[0183] Obtaining device model information of the target capacitor, and determining a reference parameter value corresponding to each characteristic parameter based on the device model information;

[0184] According to the reference parameter value corresponding to each characteristic parameter and taking all characteristic parameters as the evaluation benchmark, a self-healing performance evaluation is performed on the target data processing result to obtain self-healing performance evaluation information for the target capacitor.

[0185] It can be seen that in this optional embodiment, by obtaining the device model information of the target capacitor and determining the benchmark parameter value corresponding to each characteristic parameter based on this, it is possible to ensure that the benchmark used in the evaluation process is consistent with the actual characteristics of the capacitor, which is conducive to improving the accuracy and pertinence of the subsequent self-healing performance evaluation; in addition, this evaluation method is not only applicable to standard capacitors, but can also flexibly respond to the evaluation needs of capacitors of different models and specifications, which is conducive to enhancing the versatility and practicality of the evaluation method.

[0186] In another optional embodiment, the determination module 304 determines whether the self-healing performance evaluation information satisfies the preset parameter adjustment condition in the following manner:

[0187] Collecting actual self-healing information of the target capacitor;

[0188] Calculating the data difference between the actual self-healing information and the self-healing performance evaluation result. The data difference is used to indicate the matching degree between the self-healing performance evaluation result and the actual self-healing information.

[0189] Determine whether the matching degree between the self-healing performance evaluation result and the actual self-healing information is lower than the set matching threshold based on the data difference;

[0190] When the degree of matching between the self-healing performance evaluation result and the actual self-healing information is lower than a matching threshold, it is determined that the self-healing performance evaluation information meets the preset parameter adjustment condition.

[0191] It can be seen that in this optional embodiment, by calculating the data difference between the actual self-healing information and the self-healing performance evaluation results, a quantitative analysis of the evaluation error is achieved, and the difference between the healing performance evaluation results and the actual situation is intuitively displayed through numerical values, which is conducive to improving the convenience of relevant responsible personnel in reviewing the feature extraction situation; and when it is judged that the matching degree is lower than the set matching threshold, the subsequent parameter adjustment process can be automatically triggered to ensure the accuracy and effectiveness of the evaluation results. This step not only improves the flexibility of the evaluation, but also enhances the adaptability and robustness of the method.

[0192] In another optional embodiment, the feature extraction function includes a Haar wavelet function; the parameter adjustment information includes function adjustment information for the Haar wavelet function and / or threshold adjustment information for a target threshold;

[0193] The updating module 306 updates the feature extraction process according to the parameter adjustment information in the following manner:

[0194] When the parameter adjustment information includes function adjustment information, performing parameter adjustment on the function parameters corresponding to the Haar wavelet function according to the function adjustment information;

[0195] When the parameter adjustment information includes threshold adjustment information, performing a numerical adjustment on the target threshold according to the threshold adjustment information;

[0196] Among them, the function parameters include scale parameter, translation parameter, decomposition layer number and filter parameter; the scale parameter is used to adjust the coarseness of the wavelet transform corresponding to the Haar wavelet function; the translation parameter is used to adjust the position of the Haar wavelet function on its current transformed signal; the decomposition layer number is used to adjust the recursive depth of the Haar wavelet function; the filter parameter is used to adjust the filter coefficient of the filter used by the Haar wavelet function.

[0197] It can be seen that in this optional embodiment, by introducing function adjustment information, the scale parameters, translation parameters, number of decomposition layers and filter parameters of the Haar wavelet function can be adjusted in multiple dimensions in a personalized and targeted manner. This flexibility not only allows customized feature extraction according to the characteristics of the target capacitor, but also enables the feature extraction process to better adapt to different application scenarios and performance evaluation requirements, greatly improving the pertinence and effectiveness of feature extraction; in addition, by introducing threshold adjustment information, the target threshold can be intelligently adjusted according to the matching of the self-healing performance evaluation results with the actual self-healing information. This intelligent adjustment not only helps to optimize the threshold selection of feature extraction, but also can reduce the feature extraction error caused by improper threshold, further improving the reliability and robustness of feature extraction.

[0198] Example 4

[0199] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a feature extraction device for self-healing voltage information of a metallized film capacitor disclosed in an embodiment of the present invention. Figure 5 As shown, the feature extraction device of the self-healing voltage information of the metallized film capacitor may include:

[0200] A memory 401 storing executable program code;

[0201] a processor 402 coupled to the memory 401;

[0202] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the method for extracting the feature of the self-healing voltage information of the metallized film capacitor described in the first embodiment or the second embodiment of the present invention.

[0203] Example 5

[0204] An embodiment of the present invention discloses a computer storage medium storing computer instructions. When the computer instructions are called, they are used to execute the steps of the method for extracting the feature of the self-healing voltage information of the metallized film capacitor described in the first embodiment or the second embodiment of the present invention.

[0205] Example 6

[0206] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the feature extraction method for self-healing voltage information of a metallized film capacitor described in Example 1 or Example 2.

[0207] The system and device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected based on actual needs to achieve the objectives of the present embodiments. Persons of ordinary skill in the art will be able to understand and implement the present embodiments without inventive effort.

[0208] Through the detailed description of the above embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer storage medium, such as a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0209] Finally, it should be noted that the method and system for extracting the feature of the self-healing voltage information of a metallized film capacitor disclosed in the embodiment of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions described in the aforementioned embodiments, or to replace some of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for extracting the characteristics of the self-healing voltage information of a metallized film capacitor, characterized in that: The method comprises: Obtaining voltage measurement information corresponding to a target capacitor to be analyzed, where the target capacitor is a metallized film capacitor; the voltage measurement information is used to determine self-healing information of the target capacitor; performing target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information; the target data processing result is obtained by performing feature extraction on the voltage measurement information according to a preset feature extraction requirement, the feature extraction requirement including at least two feature parameters, the two feature parameters being feature parameters corresponding to the self-healing information of the target capacitor; the two feature parameters being amplitude and pulse width, respectively; The target data processing includes at least signal decomposition of the voltage measurement information and feature extraction based on a preset feature extraction function; the target data processing result includes self-healing feature information corresponding to the target capacitor; The method further comprises: Performing a performance evaluation on the target data processing result according to a preset self-healing performance evaluation process to obtain self-healing performance evaluation information for the target capacitor; determining whether the self-healing performance evaluation information satisfies a preset parameter adjustment condition, and generating parameter adjustment information for the target capacitor when it is determined that the self-healing performance evaluation information satisfies the parameter adjustment condition; the feature extraction function includes a Haar wavelet function; and the parameter adjustment information includes function adjustment information for the Haar wavelet function and / or threshold adjustment information for a target threshold; updating the feature extraction process according to the parameter adjustment information, re-executing the preset feature extraction process, performing target data processing on the voltage measurement information to obtain a target data processing result corresponding to the voltage measurement information, and executing the preset self-healing performance evaluation process to perform performance evaluation on the target data processing result to obtain an operation corresponding to the self-healing performance evaluation information of the target capacitor, until it is determined that a certain piece of the self-healing performance evaluation information does not meet the parameter adjustment condition, and determining that the self-healing information feature extraction for the target capacitor is completed; The step of performing a performance evaluation on the target data processing result according to a preset self-healing performance evaluation process to obtain self-healing performance evaluation information for the target capacitor includes: Obtaining device model information of the target capacitor, and determining a reference parameter value corresponding to each characteristic parameter according to the device model information; According to the reference parameter value corresponding to each characteristic parameter and taking all the characteristic parameters as evaluation benchmarks, a self-healing performance evaluation is performed on the target data processing result to obtain self-healing performance evaluation information for the target capacitor.

2. The feature extraction method for self-healing voltage information of metallized film capacitors according to claim 1, characterized in that: The performing target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information includes: performing signal decomposition on the voltage measurement information according to a preset feature extraction function to obtain a signal decomposition result corresponding to the voltage measurement information, the signal decomposition result including low-frequency feature information and high-frequency feature information corresponding to the voltage measurement information; According to the feature extraction requirements and in combination with a preset target threshold, feature extraction is performed on the signal decomposition result to obtain a feature extraction result corresponding to the signal decomposition result as a target data processing result corresponding to the voltage measurement information; the target threshold is used to perform denoising and / or signal screening on the signal decomposition result.

3. The feature extraction method of the self-healing voltage information of the metallized film capacitor according to claim 2, characterized in that: The preset target threshold includes a sub-threshold corresponding to each of the characteristic parameters; The step of performing feature extraction on the signal decomposition result according to a preset feature extraction requirement and in combination with a preset target threshold to obtain a feature extraction result corresponding to the signal decomposition result includes: Based on the two characteristic parameters included in the preset feature extraction requirements, data analysis is performed on the signal decomposition result to obtain parameter data corresponding to each of the characteristic parameters; For each of the characteristic parameters, performing noise determination and noise filtering on the parameter data corresponding to the characteristic parameter according to the sub-threshold value corresponding to the characteristic parameter, to obtain a noise filtering result corresponding to the parameter data corresponding to the characteristic parameter; According to the noise filtering results corresponding to all the characteristic parameters, taking the non-zero interval of the signal as a reference, and combining the two characteristic parameters, determining the pulse interval corresponding to the self-healing discharge pulse of the target capacitor; The noise filtering results and the pulse intervals corresponding to all the characteristic parameters are determined as feature extraction results corresponding to the signal decomposition results.

4. The method for extracting the feature of the self-healing voltage information of the metallized film capacitor according to claim 1, characterized in that: The determining whether the self-healing performance evaluation information indicates that a preset parameter adjustment condition is met includes: collecting actual self-healing information of the target capacitor; Calculating a data difference between the actual self-healing information and the self-healing performance evaluation information, where the data difference is used to indicate a matching degree between the self-healing performance evaluation information and the actual self-healing information; Determining, based on the data difference, whether a matching degree between the self-healing performance evaluation information and the actual self-healing information is lower than a set matching threshold; When the degree of matching between the self-healing performance evaluation information and the actual self-healing information is lower than the matching threshold, it is determined that the self-healing performance evaluation information meets the preset parameter adjustment condition.

5. The feature extraction method of the self-healing voltage information of the metallized film capacitor according to claim 4, characterized in that: The updating of the feature extraction process according to the parameter adjustment information includes: When the parameter adjustment information includes the function adjustment information, performing parameter adjustment on the function parameters corresponding to the Haar wavelet function according to the function adjustment information; When the parameter adjustment information includes the threshold adjustment information, performing a numerical adjustment on the target threshold according to the threshold adjustment information; Among them, the function parameters include scale parameters, translation parameters, decomposition layers and filter parameters; the scale parameters are used to adjust the coarseness of the wavelet transform corresponding to the Haar wavelet function; the translation parameters are used to adjust the position of the Haar wavelet function on its current transformed signal; the decomposition layers are used to adjust the recursive depth of the Haar wavelet function; the filter parameters are used to adjust the filter coefficients of the filter used by the Haar wavelet function.

6. A feature extraction system for self-healing voltage information of metallized film capacitors, characterized in that: The system comprises: an acquisition module, configured to acquire voltage measurement information corresponding to a target capacitor to be analyzed, wherein the target capacitor is a metallized film capacitor; the voltage measurement information is used to determine self-healing information of the target capacitor; a data processing module, configured to perform target data processing on the voltage measurement information according to a preset feature extraction process to obtain a target data processing result corresponding to the voltage measurement information; the target data processing result is obtained by performing feature extraction on the voltage measurement information according to a preset feature extraction requirement, the feature extraction requirement including at least two feature parameters, the two feature parameters being feature parameters corresponding to the self-healing information of the target capacitor; the two feature parameters being amplitude and pulse width, respectively; The target data processing includes at least signal decomposition of the voltage measurement information and feature extraction based on a preset feature extraction function; the target data processing result includes self-healing feature information corresponding to the target capacitor; The system further comprises: a performance evaluation module, configured to perform a performance evaluation on the target data processing result according to a preset self-healing performance evaluation process, and obtain self-healing performance evaluation information for the target capacitor; A judgment module, configured to judge whether the self-healing performance evaluation information indicates that a preset parameter adjustment condition is met; a generating module configured to generate parameter adjustment information for the target capacitor when the judging module determines that the self-healing performance evaluation information satisfies the parameter adjustment condition; the feature extraction function includes a Haar wavelet function; and the parameter adjustment information includes function adjustment information for the Haar wavelet function and / or threshold adjustment information for a target threshold; an updating module, configured to update the feature extraction process according to the parameter adjustment information, trigger the data processing module to re-execute the preset feature extraction process, perform target data processing on the voltage measurement information, and obtain a target data processing result corresponding to the voltage measurement information, and trigger the performance evaluation module to execute the preset self-healing performance evaluation process, perform performance evaluation on the target data processing result, and obtain an operation corresponding to the self-healing performance evaluation information of the target capacitor, until it is determined that a certain self-healing performance evaluation information does not meet the parameter adjustment condition, and thus determine that the self-healing information feature extraction for the target capacitor is completed; The performance evaluation module performs performance evaluation on the target data processing result according to a preset self-healing performance evaluation process, and obtains the self-healing performance evaluation information for the target capacitor in a manner specifically including: Obtaining device model information of the target capacitor, and determining a reference parameter value corresponding to each characteristic parameter according to the device model information; According to the reference parameter value corresponding to each characteristic parameter and taking all the characteristic parameters as evaluation benchmarks, a self-healing performance evaluation is performed on the target data processing result to obtain self-healing performance evaluation information for the target capacitor.

7. A device for extracting characteristics of self-healing voltage information of a metallized film capacitor, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the feature extraction method for self-healing voltage information of a metallized film capacitor according to any one of claims 1 to 5.

8. A computer storage medium, characterized in that The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the feature extraction method for self-healing voltage information of a metallized film capacitor according to any one of claims 1 to 5.

Images