Lithium battery anomaly detection method and system based on trend thermodynamic diagram
By using a trend heat map-based method, big data and deep learning technology to monitor the battery parameters of lithium batteries in real time, the problem of lithium battery anomalies being difficult to detect in existing technologies is solved, and early warning of faults and reduction of failure rates are achieved.
Patent Information
- Application Number
- CN202510868870.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-26
- Publication Date
- 2025-09-16
AI Technical Summary
Existing technologies make it difficult to detect potential battery anomalies by analyzing the original characteristics of lithium batteries such as voltage flow, resulting in the inability to detect and warn early when faults occur.
Through a trend heat map-based method, the big data cloud platform is used to obtain battery parameters, perform preprocessing and sliding window slicing, calculate the trend value matrix and draw a heat map, and combine it with a deep learning network for identification and detection to achieve early detection of lithium battery anomalies.
It realizes real-time monitoring of lithium batteries, reduces the occurrence of serious failures, improves user experience and reduces maintenance costs.
Smart Images
Figure CN120652297A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure belongs to the field of battery detection technology, and in particular relates to a lithium battery anomaly detection method and system based on a trend heat map. Background Art
[0002] Lithium batteries must maintain a safe range of potential characteristics, including voltage and temperature, during operation and storage. However, battery packs are subject to numerous unpredictable internal and external factors during manufacturing, post-production operation, and storage. These factors can severely impact the battery's safety limits, leading to battery failure.
[0003] The trends of battery voltage, temperature, and other time series characteristics during normal charging, discharging, or resting states are generally consistent. Therefore, by analyzing the trends of these characteristics during charging, discharging, or resting, we can identify power battery failures and detect potential battery anomalies early. However, if the cause of the failure is more complex, relying solely on raw voltage flow characteristics may not reveal the underlying connection.
[0004] Therefore, it is necessary to provide a new lithium battery anomaly detection method and system based on trend heat map to solve the above technical problems. Summary of the Invention
[0005] The purpose of the present disclosure is to provide a lithium battery anomaly detection method and system based on trend heat map in order to solve the above problems.
[0006] The present disclosure achieves the above objectives through the following technical solutions: A lithium battery anomaly detection method based on a trend heat map includes the following steps: Preprocess the acquired battery parameters to obtain valid time series data; Setting a window length parameter, performing sliding window slicing on the time series data to obtain samples; Calculating the trend value of the sample and drawing a trend value heat map; The trend value heat map is identified and detected using a trained deep learning network.
[0007] As a further optimization solution of the present disclosure, the battery parameters include voltage, temperature, insulation resistance and current.
[0008] As a further optimization solution of the present disclosure, the acquired battery parameters are preprocessed to obtain effective time series data, including: The battery parameters are obtained through the data cloud platform, and abnormal point detection is performed on the battery parameters. If an abnormal point is detected, the abnormal point is processed using the forward and backward mean method to obtain valid time series data.
[0009] As a further optimization solution of the present disclosure, the trend value of the sample is calculated and a trend value heat map is drawn, including: The slopes of the voltage, current, temperature and insulation resistance in the sample are calculated to obtain a trend value matrix, and a trend value heat map is drawn according to the trend value matrix.
[0010] A lithium battery anomaly detection system based on a trend heat map, comprising: The data preprocessing module is used to preprocess the acquired battery parameters to obtain valid time series data; A sliding window slicing module is used to set a window length parameter and perform sliding window slicing on the time series data to obtain samples; A heat map drawing module, used to calculate the trend value of the sample and draw a heat map of the trend value; The recognition and detection module is used to use the trained deep learning network to recognize and detect the trend value heat map.
[0011] As a further optimization solution of the present disclosure, the battery parameters include voltage, temperature, insulation resistance and current.
[0012] As a further optimization solution of the present disclosure, the data preprocessing module preprocesses the acquired battery parameters to obtain valid time series data, including: The battery parameters are obtained through the data cloud platform, and abnormal point detection is performed on the battery parameters. If an abnormal point is detected, the abnormal point is processed using the forward and backward mean method to obtain valid time series data.
[0013] As a further optimization solution of the present disclosure, the heat map drawing module calculates the trend value of the sample and draws a heat map of the trend value, including: The slopes of the voltage, current, temperature and insulation resistance in the sample are calculated to obtain a trend value matrix, and a trend value heat map is drawn according to the trend value matrix.
[0014] An electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; The processor is used to execute the program stored in the memory to implement the lithium battery anomaly detection method based on the trend heat map.
[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the lithium battery anomaly detection method based on a trend heat map.
[0016] The beneficial effects of the present disclosure are: This disclosure obtains the original characteristics of the battery and the algorithm based on the big data cloud platform to obtain a trend heat map. The trend heat map can be used to determine whether there is a fault in the battery and prevent serious faults from occurring, thereby reducing the serious failure rate and maintenance costs and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 is a flow chart of a method in an embodiment of the present disclosure; Figure 2 is a schematic diagram comparing normal and abnormal thermal maps in an embodiment of the present disclosure; Figure 3 is a system structure block diagram in an embodiment of the present disclosure; Figure 4 It is a block diagram of the device structure in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0018] The present application will be described in further detail below in conjunction with the accompanying drawings. It is necessary to point out that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technicians in this field can make some non-essential improvements and adjustments to the present application based on the above application content.
[0019] like Figure 1 As shown, a lithium battery anomaly detection method based on a trend heat map includes the following steps: Preprocess the acquired battery parameters to obtain valid time series data; Setting a window length parameter, performing sliding window slicing on the time series data to obtain samples; Calculating the trend value of the sample and drawing a trend value heat map; The trend value heat map is identified and detected using a trained deep learning network.
[0020] In this embodiment, it specifically includes: Obtain battery-related data through the data cloud platform: The big data cloud platform refers to a cloud platform built using big data technology to process and store power battery information; the relevant data obtained includes battery-related information such as voltage, insulation resistance, temperature, and current.
[0021] Clean the data, remove invalid data and retain valid data: Perform outlier detection on the original data, use the previous and next mean method to calculate the true predicted value of the outlier, and process the outlier; if there are missing data features at the same moment, use the previous and next information to fill in the missing value; if two or more frames are missing, eliminate the value at that moment, including voltage, temperature, insulation resistance, and current, and finally obtain valid time series data.
[0022] Set the window length and slice the data to obtain samples: An appropriate window length is set. In this embodiment, the window length is set to 30. The acquired time series data is sliced to obtain sample segments.
[0023] Calculate the sample trend value: Trend value matrix calculation method:
[0024] v: voltage of all single cells, such as v 12 Refers to the second point in the first cell sequence; c: current; ir: insulation resistance; t: all temperature values, the subscript has the same meaning as v; V: voltage trend value, such as V 21 Refers to the first voltage trend value of the second cell; C: current trend value; IR: Insulation resistance trend value; T: Temperature trend value, the subscript has the same meaning as V; m: There are m time series features and the number of rows in the matrix; n: There are n timing points; The features in the matrix include battery parameters directly collected by sensors such as voltage, current, temperature, and insulation resistance.
[0025] The battery sample trend value matrix can be obtained by calculating the above formula.
[0026] Draw a heat map of trend values: The trend value heat map refers to the energy distribution of the trend value matrix, and the drawing algorithm is not required. Figure 2 The yellow color represents the matrix energy distribution, and the energy distribution in abnormal state is denser than that in normal state.
[0027] Use deep learning networks to classify, identify and detect heat maps; A deep learning network refers to a network built using a deep learning algorithm, with the network structure optimized and adjusted based on the results. This embodiment primarily uses a modified ResNet, processing samples in both abnormal and normal states into training, validation, and test sets. The validation and test sets are not homologous to the training set. The modified ResNet network is then adjusted to fit the sample inputs. After iterative optimization, a classification model is obtained, and the trained model is used to test new samples.
[0028] The present disclosure can monitor the health status of the vehicle battery in real time during the operation of the entire vehicle, realize early detection and early warning of serious faults, reduce the occurrence rate of serious faults, and enhance brand competitiveness.
[0029] like Figure 3 As shown, an embodiment of the present disclosure provides a lithium battery anomaly detection system based on a trend heat map, comprising: The data preprocessing module 11 is used to preprocess the acquired battery parameters to obtain valid time series data; A sliding window slicing module 12 is used to set a window length parameter and perform sliding window slicing on the time series data to obtain samples; A heat map drawing module 13 is used to calculate the trend value of the sample and draw a heat map of the trend value; The identification and detection module 14 is used to use the trained deep learning network to identify and detect the trend value heat map.
[0030] The implementation process of the functions and effects of each module in the above system is specifically described in the implementation process of the corresponding steps in the above method, which will not be repeated here.
[0031] For the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can be referred to the partial description of the method embodiment. The system embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. Those of ordinary skill in the art can understand and implement it without paying any creative work.
[0032] In the above embodiments, any number of all modules can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in one module. At least one of all modules can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuit, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in an appropriate combination of any of them. Alternatively, at least one of all modules can be at least partially implemented as a computer program module, which can perform the corresponding function when the computer program module is executed.
[0033] See also Figure 3The electronic device provided by an embodiment of the present disclosure includes a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 communicate with each other through the communication bus 1140; Memory 1130, for storing computer programs; The processor 1110 is configured to implement the above-mentioned lithium battery abnormality detection method based on trend heat map when executing the program stored in the memory 1130 . The communication bus 1140 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the figure shows only one thick line, but this does not mean that there is only one bus or only one type of bus.
[0034] The communication interface 1120 is used for communication between the electronic device and other devices.
[0035] The memory 1130 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk storage. Alternatively, the memory 1130 may be at least one storage device located away from the processor 1110.
[0036] The above-mentioned processor 1110 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can 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.
[0037] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned lithium battery anomaly detection method based on a trend heat map.
[0038] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus. The computer-readable storage medium carries one or more programs that, when executed, implement the lithium battery anomaly detection method based on a trend heat map according to the embodiments of the present disclosure.
[0039] According to embodiments of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as, but not limited to, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0040] The above-described embodiments merely represent several implementation methods of the present disclosure. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present disclosure. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the scope of the present disclosure, all of which fall within the scope of protection of the present disclosure.
Claims
1. A lithium battery anomaly detection method based on trend heat map, characterized in that: The following steps are involved: Preprocess the acquired battery parameters to obtain valid time series data; Setting a window length parameter, performing sliding window slicing on the time series data to obtain samples; Calculating the trend value of the sample and drawing a trend value heat map; The trend value heat map is identified and detected using a trained deep learning network.
2. The method for detecting anomalies in lithium batteries based on a trend heat map according to claim 1, wherein: The battery parameters include voltage, temperature, insulation resistance and current.
3. The method for detecting anomalies in lithium batteries based on a trend heat map according to claim 1, wherein: The acquired battery parameters are preprocessed to obtain valid time series data, including: The battery parameters are obtained through the data cloud platform, and abnormal point detection is performed on the battery parameters. If an abnormal point is detected, the abnormal point is processed using the forward and backward mean method to obtain valid time series data.
4. The method for detecting anomalies in lithium batteries based on a trend heat map according to claim 1, wherein: Calculate the trend value of the sample and draw a trend value heat map, including: The slopes of the voltage, current, temperature and insulation resistance in the sample are calculated to obtain a trend value matrix, and a trend value heat map is drawn according to the trend value matrix.
5. A lithium battery anomaly detection system based on trend heat map, characterized in that: include: The data preprocessing module is used to preprocess the acquired battery parameters to obtain valid time series data; A sliding window slicing module is used to set a window length parameter and perform sliding window slicing on the time series data to obtain samples; A heat map drawing module, used to calculate the trend value of the sample and draw a heat map of the trend value; The recognition and detection module is used to use the trained deep learning network to recognize and detect the trend value heat map.
6. The lithium battery anomaly detection system based on trend heat map according to claim 5, characterized in that: The battery parameters include voltage, temperature, insulation resistance and current.
7. The lithium battery anomaly detection system based on trend heat map according to claim 5, characterized in that: The data preprocessing module preprocesses the acquired battery parameters to obtain valid time series data, including: The battery parameters are obtained through the data cloud platform, and abnormal point detection is performed on the battery parameters. If an abnormal point is detected, the abnormal point is processed using the forward and backward mean method to obtain valid time series data.
8. The lithium battery anomaly detection system based on trend heat map according to claim 5, characterized in that: The heat map drawing module calculates the trend value of the sample and draws a trend value heat map, including: The slopes of the voltage, current, temperature and insulation resistance in the sample are calculated to obtain a trend value matrix, and a trend value heat map is drawn according to the trend value matrix.
9. An electronic device, characterized in that: The processor, the communication interface, the memory and the communication bus are connected to each other via the communication bus. Memory for storing computer programs; A processor is used to execute a program stored in a memory to implement the lithium battery anomaly detection method based on a trend heat map according to any one of claims 1 to 4.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the lithium battery abnormality detection method based on a trend heat map according to any one of claims 1 to 4 is implemented.