Fault Diagnosis Method, System, Electronic Device and Storage Medium for New Energy Batteries

Abstract

The present invention discloses a fault diagnosis method, system, electronic device and storage medium for a new energy battery, relating to the technical field of battery fault diagnosis. For each battery, the original voltage signal is decomposed into a low-frequency voltage signal and a high-frequency voltage signal; a high-frequency feature vector is extracted from the high-frequency voltage signal, and a low-frequency feature vector is extracted from the low-frequency voltage signal; the high-frequency features and low-frequency features are combined to obtain the feature vector curve of the battery, and the average feature vector curve of the battery pack is determined; the curve distance between the feature vector curve of the battery and the average feature vector curve is calculated to determine whether the battery has a fault. This method reduces the interference between high-frequency information and low-frequency information, reduces noise interference, and respectively extracts feature parameters that can reflect battery faults and inconsistencies based on SAE and SVD, which helps to improve the accuracy of fault diagnosis and inconsistency detection.

Description

Technical Field

[0001] The present invention relates to the technical field of battery fault diagnosis, and particularly relates to a fault diagnosis method, system, electronic device and storage medium for new energy batteries. Background Art

[0002] Battery faults have always been a major hidden danger to the safety of new energy vehicles. Early fault diagnosis can reduce many safety accidents of new energy vehicles. Moreover, generally, the early fault short-circuit signals are very weak. Therefore, realizing the early warning of battery faults is still a major challenge at present.

[0003] Most of the existing fault diagnosis methods artificially extract characteristic parameters in the time domain, and the fault information is easily submerged in the battery inconsistency, affecting the accuracy of fault diagnosis. Summary of the Invention

[0004] The object of the present invention is to solve the problems in the above background art, and to propose a fault diagnosis method, system, electronic device and storage medium for new energy batteries.

[0005] The object of the present invention can be achieved by the following technical solutions:

[0006] In the first aspect of the embodiments of the present invention, a fault diagnosis method for new energy batteries is provided, and the method includes:

[0007] Obtain the original voltage signal of the new energy battery pack, and decompose the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack;

[0008] For each battery, preprocess the high-frequency voltage signal to remove signal noise to obtain a time-domain high-frequency voltage signal, and use a sparse autoencoder to extract the characteristic parameters of the time-domain high-frequency voltage signal as the high-frequency characteristic vector of the battery;

[0009] For each battery, perform singular value decomposition on the low-frequency voltage signal to extract the characteristic parameters of the low-frequency voltage signal as the low-frequency characteristic vector of the battery;

[0010] Combine the high-frequency characteristics and low-frequency characteristics to obtain the characteristic vector curve of the battery, and determine the average characteristic vector curve of the battery pack;

[0011] For each battery, calculate the curve distance between the characteristic vector curve of the battery and the average characteristic vector curve, and judge whether the battery has a fault according to the curve distance.

[0012] Optionally, decomposing the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack includes:

[0013] For each battery in the battery pack, perform four-layer wavelet packet decomposition on the original voltage signal to obtain a low-frequency voltage signal and a high-frequency voltage signal.

[0014] Optionally, for each battery, preprocess the high-frequency voltage signal to remove signal noise to obtain a time-domain high-frequency voltage signal, including:

[0015] For each battery, calculate the energy contained in each high-frequency subsequence in the high-frequency voltage signal;

[0016] Remove high-frequency subsequences with energy lower than a preset threshold;

[0017] Perform wavelet packet reconstruction on the filtered high-frequency subsequences to obtain a denoised time-domain high-frequency voltage signal.

[0018] Optionally, determine whether the battery has a fault according to the curve distance, including:

[0019] Pass the curve distance through an outlier filter based on Chauvenet's criterion to detect whether there is a fault in the curve distance; the dynamic threshold of the outlier filter is determined by the inverse normal distribution function.

[0020] In the second aspect of the embodiments of the present invention, a fault diagnosis system for new energy batteries is further provided. The system includes a preprocessing module, a first feature extraction module, a second feature extraction module, a feature vector curve module, and a fault judgment module:

[0021] The preprocessing module is used to obtain the original voltage signal of the new energy battery pack and decompose the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack;

[0022] The first feature extraction module is used to, for each battery, preprocess the high-frequency voltage signal to remove signal noise to obtain a time-domain high-frequency voltage signal, and extract the characteristic parameters of the time-domain high-frequency voltage signal using a sparse autoencoder as the high-frequency feature vector of the battery;

[0023] The second feature extraction module is used to, for each battery, perform singular value decomposition on the low-frequency voltage signal to extract the characteristic parameters of the low-frequency voltage signal as the low-frequency feature vector of the battery;

[0024] The feature vector curve module is used to combine the high-frequency features and low-frequency features to obtain the feature vector curve of the battery and determine the average feature vector curve of the battery pack;

[0025] The fault judgment module is used to, for each battery, calculate the curve distance between the feature vector curve of the battery and the average feature vector curve, and determine whether the battery has a fault according to the curve distance.

[0026] Optionally, the preprocessing module is configured to perform four-layer wavelet packet decomposition on the original voltage signal for each battery in the battery pack to obtain a low-frequency voltage signal and a high-frequency voltage signal.

[0027] Optionally, the first feature extraction module includes a calculation module, a filtering module, and a reconstruction module:

[0028] The calculation module is configured to calculate the energy contained in each high-frequency subsequence in the high-frequency voltage signal for each battery;

[0029] The filtering module is configured to remove high-frequency subsequences with energy lower than a preset threshold;

[0030] The reconstruction module is configured to perform wavelet packet reconstruction on the filtered high-frequency subsequences to obtain a denoised high-frequency voltage signal in the time domain.

[0031] Optionally, the reconstruction module is configured to pass the curve distance through an outlier filter based on the Chauvenet criterion to detect whether there is a fault in the curve distance; the dynamic threshold of the outlier filter is determined by the inverse normal distribution function.

[0032] In a third aspect of the embodiments of the present invention, there is also provided an electronic device, which is characterized in that it includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete mutual communication through the communication bus;

[0033] The memory is used to store a computer program;

[0034] The processor is configured to implement the method steps described in any one of the above when executing the program stored on the memory.

[0035] In a fourth aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, which is characterized in that the computer-readable storage medium stores a computer program, and the computer program implements the method steps described in any one of the above when executed by a processor.

[0036] Advantages of the present invention:

[0037] An embodiment of the present invention provides a method for fault diagnosis of a new energy battery. The method includes: obtaining an original voltage signal of a new energy battery pack, and decomposing the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack; for each battery, preprocessing the high-frequency voltage signal to remove signal noise to obtain a time-domain high-frequency voltage signal, and using a sparse autoencoder to extract characteristic parameters of the time-domain high-frequency voltage signal as the high-frequency characteristic vector of the battery; for each battery, performing singular value decomposition on the low-frequency voltage signal to extract characteristic parameters of the low-frequency voltage signal as the low-frequency characteristic vector of the battery; combining the high-frequency characteristics and the low-frequency characteristics to obtain a characteristic vector curve of the battery, and determining an average characteristic vector curve of the battery pack; for each battery, calculating a curve distance between the characteristic vector curve of the battery and the average characteristic vector curve, and determining whether the battery has a fault according to the curve distance. By preprocessing the original voltage data through WPD, separating the high-frequency subsequence containing fault information and the low-frequency subsequence containing inconsistent information, the interference between the high-frequency information and the low-frequency information is reduced, and the high-frequency components are denoised by the wavelet packet energy denoising method to reduce the interference of noise. Based on SAE and SVD, characteristic parameters that can reflect battery faults and inconsistencies are extracted respectively, which helps to improve the accuracy of fault diagnosis and inconsistency detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described below with reference to the accompanying drawings.

[0039] Figure 1 is a flowchart of a method for fault diagnosis of a new energy battery provided by an embodiment of the present invention;

[0040] Figure 2 is a system block diagram of a fault diagnosis system for a new energy battery provided by an embodiment of the present invention;

[0041] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] An embodiment of the present invention provides a method for fault diagnosis of a new energy battery. Refer to Figure 1 , Figure 1 is a flowchart of a method for fault diagnosis of a new energy battery provided by an embodiment of the present invention. The method includes:

[0044] S101. Obtain the original voltage signal of the new energy battery pack, and decompose the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack.

[0045] S102. For each battery, preprocess the high-frequency voltage signal to remove signal noise to obtain the time-domain high-frequency voltage signal, and use a sparse autoencoder to extract the characteristic parameters of the time-domain high-frequency voltage signal as the high-frequency characteristic vector of the battery.

[0046] S103. For each battery, perform singular value decomposition on the low-frequency voltage signal to extract the characteristic parameters of the low-frequency voltage signal as the low-frequency characteristic vector of the battery.

[0047] S104. Combine the high-frequency characteristics and low-frequency characteristics to obtain the characteristic vector curve of the battery, and determine the average characteristic vector curve of the battery pack.

[0048] S105. For each battery, calculate the curve distance between the characteristic vector curve of the battery and the average characteristic vector curve, and determine whether the battery has a fault according to the curve distance.

[0049] Based on a fault diagnosis method for a new energy battery provided by an embodiment of the present invention, the original voltage data is preprocessed by WPD to separate the high-frequency subsequence containing fault information and the low-frequency subsequence containing inconsistent information, reducing the interference between high-frequency information and low-frequency information, and denoising the high-frequency component by the wavelet packet energy denoising method to reduce the interference of noise. The characteristic parameters that can reflect battery faults and inconsistencies are extracted based on SAE and SVD respectively, which helps to improve the accuracy of fault diagnosis and inconsistency detection.

[0050] In one embodiment, decomposing the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack includes:

[0051] For each battery in the battery pack, perform four-layer wavelet packet decomposition on the original voltage signal to obtain a low-frequency voltage signal and a high-frequency voltage signal.

[0052] In one embodiment, preprocessing the high-frequency voltage signal to remove signal noise to obtain the time-domain high-frequency voltage signal for each battery includes:

[0053] For each battery, calculate the energy contained in each high-frequency subsequence in the high-frequency voltage signal;

[0054] Remove the high-frequency subsequences with energy lower than a preset threshold;

[0055] Perform small wavelet reconstruction on the filtered high-frequency subsequences to obtain the denoised time-domain high-frequency voltage signal.

[0056] In one embodiment, determining whether the battery has a fault based on the curve distance includes:

[0057] Passing the curve distance through an outlier filter based on Chauvenet's criterion to detect whether there is a fault in the curve distance; the dynamic threshold of the outlier filter is determined by the inverse normal distribution function.

[0058] Based on the same inventive concept, an embodiment of the present invention also provides a fault diagnosis system for a new energy battery. Refer to Figure 2 , Figure 2 which is the system block diagram of a fault diagnosis system for a new energy battery provided by an embodiment of the present invention. The system includes a preprocessing module, a first feature extraction module, a second feature extraction module, a feature vector curve module, and a fault judgment module:

[0059] The preprocessing module is used to obtain the original voltage signal of the new energy battery pack, and decompose the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack;

[0060] The first feature extraction module is used to, for each battery, preprocess the high-frequency voltage signal to remove signal noise to obtain the time-domain high-frequency voltage signal, and use a sparse autoencoder to extract the characteristic parameters of the time-domain high-frequency voltage signal as the high-frequency feature vector of the battery;

[0061] The second feature extraction module is used to, for each battery, perform singular value decomposition on the low-frequency voltage signal to extract the characteristic parameters of the low-frequency voltage signal as the low-frequency feature vector of the battery;

[0062] The feature vector curve module is used to combine the high-frequency feature and the low-frequency feature to obtain the feature vector curve of the battery, and determine the average feature vector curve of the battery pack;

[0063] The fault judgment module is used to, for each battery, calculate the curve distance between the feature vector curve of the battery and the average feature vector curve, and determine whether the battery has a fault according to the curve distance.

[0064] Based on the fault diagnosis system for a new energy battery provided by an embodiment of the present invention, the original voltage data is preprocessed by WPD to separate the high-frequency subsequence containing fault information and the low-frequency subsequence containing inconsistent information, reducing the interference between high-frequency information and low-frequency information, and denoising the high-frequency component by the wavelet packet energy denoising method to reduce the interference of noise. The characteristic parameters that can reflect battery faults and inconsistencies are extracted based on SAE and SVD respectively, which helps to improve the accuracy of fault diagnosis and inconsistency detection.

[0065] In one embodiment, the preprocessing module is configured to perform four-layer wavelet packet decomposition on the original voltage signal for each battery in the battery pack to obtain a low-frequency voltage signal and a high-frequency voltage signal.

[0066] In one embodiment, the first feature extraction module includes a calculation module, a filtering module, and a reconstruction module:

[0067] The calculation module is configured to calculate the energy contained in each high-frequency subsequence in the high-frequency voltage signal for each battery;

[0068] The filtering module is configured to remove high-frequency subsequences with energy lower than a preset threshold;

[0069] The reconstruction module is configured to perform wavelet packet reconstruction on the filtered high-frequency subsequences to obtain a denoised time-domain high-frequency voltage signal.

[0070] In one embodiment, the reconstruction module is configured to pass the curve distance through an outlier filter based on Chauvenet's criterion to detect whether there is a fault in the curve distance; the dynamic threshold of the outlier filter is determined by the inverse normal distribution function.

[0071] An embodiment of the present invention also provides an electronic device, as Figure 3 shown, including a processor 301, a communication interface 302, a memory 303, and a communication bus 304. Among them, the processor 301, the communication interface 302, and the memory 303 complete mutual communication through the communication bus 304,

[0072] The memory 303 is used to store a computer program;

[0073] When the processor 301 is configured to execute the program stored in the memory 303, the following steps are implemented:

[0074] Obtain the original voltage signal of the new energy battery pack, and decompose the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack;

[0075] For each battery, preprocess the high-frequency voltage signal to remove signal noise to obtain a time-domain high-frequency voltage signal, and use a sparse autoencoder to extract the characteristic parameters of the time-domain high-frequency voltage signal as the high-frequency feature vector of the battery;

[0076] For each battery, perform singular value decomposition on the low-frequency voltage signal to extract the characteristic parameters of the low-frequency voltage signal as the low-frequency feature vector of the battery;

[0077] Combine the high-frequency features and low-frequency features to obtain the characteristic vector curve of the battery, and determine the average characteristic vector curve of the battery pack;

[0078] For each battery, calculate the curve distance between the characteristic vector curve of the battery and the average characteristic vector curve, and determine whether the battery has a fault according to the curve distance.

[0079] The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0080] The communication interface is used for communication between the above electronic device and other devices.

[0081] The memory may include a Random Access Memory (RAM), or may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0082] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0083] In another embodiment provided by the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned fault diagnosis method for any new energy battery are implemented.

[0084] In another embodiment provided by the present invention, there is also provided a computer program product containing instructions, which when running on a computer, causes the computer to execute the fault diagnosis method for any new energy battery in the above embodiment.

[0085] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0086] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0087] Each embodiment in this specification is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, electronic device, computer-readable storage medium, and computer program product, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0088] The above has described in detail an embodiment of the present invention, but the above content is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made in accordance with the scope of the application of the present invention shall still fall within the scope covered by the patent of the present invention.

Claims

1. A fault diagnosis method for a new energy battery, characterized in that, The method includes: Obtain the original voltage signal of the new energy battery pack, and decompose the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack; For each battery, preprocess the high-frequency voltage signal to remove signal noise to obtain a time-domain high-frequency voltage signal, and use a sparse autoencoder to extract the characteristic parameters of the time-domain high-frequency voltage signal as the high-frequency characteristic vector of the battery; For each battery, perform singular value decomposition on the low-frequency voltage signal to extract the characteristic parameters of the low-frequency voltage signal as the low-frequency characteristic vector of the battery; Combine the high-frequency characteristics and low-frequency characteristics to obtain the characteristic vector curve of the battery, and determine the average characteristic vector curve of the battery pack; For each battery, calculate the curve distance between the characteristic vector curve of the battery and the average characteristic vector curve, and determine whether the battery has a fault according to the curve distance; Decomposing the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack includes: For each battery in the battery pack, perform four-layer wavelet packet decomposition on the original voltage signal to obtain a low-frequency voltage signal and a high-frequency voltage signal; Preprocessing the high-frequency voltage signal to remove signal noise to obtain a time-domain high-frequency voltage signal for each battery includes: For each battery, calculate the energy contained in each high-frequency subsequence in the high-frequency voltage signal; Remove the high-frequency subsequences with energy lower than the preset threshold; Perform small wave packet reconstruction on the filtered high-frequency subsequences to obtain a noise-reduced time-domain high-frequency voltage signal; Determining whether the battery has a fault according to the curve distance includes: Pass the curve distance through an outlier filter based on Chauvenet's criterion to detect whether there is a fault in the curve distance; the dynamic threshold of the outlier filter is determined by the inverse normal distribution function.

2. A fault diagnosis system for a new energy battery, characterized in that, The system includes a preprocessing module, a first feature extraction module, a second feature extraction module, a characteristic vector curve module, and a fault judgment module: The preprocessing module is used to obtain the original voltage signal of the new energy battery pack, and decompose the original voltage signal into a low-frequency voltage signal and a high-frequency voltage signal for each battery in the battery pack; The first feature extraction module is used to, for each battery, preprocess the high-frequency voltage signal to remove signal noise to obtain a time-domain high-frequency voltage signal, and use a sparse autoencoder to extract the characteristic parameters of the time-domain high-frequency voltage signal as the high-frequency characteristic vector of the battery; The second feature extraction module is used to, for each battery, perform singular value decomposition on the low-frequency voltage signal to extract the characteristic parameters of the low-frequency voltage signal as the low-frequency characteristic vector of the battery; The characteristic vector curve module is used to combine the high-frequency characteristics and low-frequency characteristics to obtain the characteristic vector curve of the battery, and determine the average characteristic vector curve of the battery pack; The fault judgment module is used to, for each battery, calculate the curve distance between the characteristic vector curve of the battery and the average characteristic vector curve, and determine whether the battery has a fault according to the curve distance; The preprocessing module is used to, for each battery in the battery pack, perform four-layer wavelet packet decomposition on the original voltage signal to obtain a low-frequency voltage signal and a high-frequency voltage signal; The first feature extraction module includes a calculation module, a filtering module, and a reconstruction module: The calculation module is configured to calculate the energy contained in each high-frequency subsequence in the high-frequency voltage signal for each battery; The filtering module is configured to remove the high-frequency subsequences with energy lower than a preset threshold; The reconstruction module is configured to perform wavelet packet reconstruction on the filtered high-frequency subsequences to obtain a denoised high-frequency voltage signal in the time domain; The reconstruction module is configured to pass the curve distance through an outlier filter based on Chauvenet's criterion to detect whether there is a fault in the curve distance; the dynamic threshold of the outlier filter is determined by the inverse normal distribution function.

3. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus; The memory is used to store computer programs; The processor is configured to implement the method steps described in claim 1 when executing the programs stored on the memory.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements the method steps described in claim 1.

Images