Power battery operation process early warning method and early warning system

Abstract

The invention discloses a power battery operation process early warning method and system, and belongs to the technical field of vehicle early warning, and the method comprises the steps that a processing center receives first operation data collected by a collection module, and carries out the preprocessing of the first operation data; performing equivalent modeling on the preprocessed first operation data; generating a personalized feature report of the power battery, converting the generated personalized feature report into an identification signal, and monitoring the power battery in real time; and performing early warning according to a matching analysis result, and sending out an early warning signal. In the implementation process of the technical scheme, equivalent modeling is performed on the first operation data, the relationship between the operation characteristics and the health state of the power battery is established, and the personalized characteristic report of the power battery is generated, so that the characteristic information of the power battery under different working conditions is obtained; and early warning is carried out according to the recognition result of the feature information, so that the accuracy and response speed of the early warning result are improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle warning technology, and specifically to a power battery operation process warning method and warning system. Background Art

[0002] With the advancement of science and technology, the cost of new energy technology has gradually decreased, the market share of new energy vehicles has continued to increase, and more and more new energy vehicles have entered the market. New energy vehicles include pure electric vehicles, plug-in hybrid vehicles, extended-range vehicles, etc. These vehicles all require the use of power batteries to achieve direct or indirect power supply through power batteries.

[0003] During the driving of new energy vehicles, it is usually necessary to detect and warn the power battery. The operating parameters of the power battery are collected through battery management technology (BMS), and the health state (SOH) of the power battery is detected based on these parameters, so as to diagnose and warn of faults that occur during the operation of the power battery to ensure the safety of vehicle driving.

[0004] However, among the existing battery management technologies, most rely on the estimation of basic parameters, such as charging voltage, temperature, internal resistance, etc. Although these parameters can detect the health status of the battery, they cannot accurately obtain the specific source of potential problems. In addition, the existing technology usually adopts a relatively simple health status monitoring method, which is based on certain general parameters (such as increased internal resistance and temperature increase of the battery) to infer the battery status. This method takes less consideration of the individual differences of different batteries, resulting in limited accuracy of early warning and unable to meet the complex and changeable actual working conditions.

[0005] Therefore, it is necessary to provide a power battery operation process early warning method and early warning system to solve the above problems.

[0006] It should be noted that the above information disclosed in this background technology section is only for understanding the background technology of the present application concept, and therefore, it may contain information that does not constitute the prior art. Summary of the invention

[0007] Based on the above-mentioned problems existing in the prior art, the problem to be solved by the present application is: to provide a power battery operation process early warning method and early warning system, to improve the accuracy and response speed of the early warning results and reduce driving safety risks through equivalent modeling.

[0008] The technical solution adopted by the present application to solve the technical problem is: a power battery operation process early warning method, characterized in that it includes: The processing center receives the first operation data collected by the collection module and pre-processes the first operation data, wherein the first operation data includes data directly collected by the collection module and data indirectly calculated from the collected data; Performing equivalent modeling on the preprocessed first operating data to establish a relationship between the operating characteristics and health status of the power battery; Generate a personalized feature report of the power battery, which contains feature information of the power battery under different working conditions, and convert the generated personalized feature report into an identification signal. After receiving the identification signal, the processing center quickly performs matching analysis and monitors the power battery in real time. The personalized feature report is converted into an identification signal using a policy gradient mapping method. Through the policy gradient mapping method, the generated personalized feature report is converted into an identification signal that can be recognized by the processing center. An early warning is issued based on the matching analysis results and a warning signal is sent out.

[0009] During the implementation of the technical solution of the present application, by performing equivalent modeling on the first operating data, the relationship between the operating characteristics and the health status of the power battery is established, and a personalized characteristic report of the power battery is generated, so as to obtain the characteristic information of the power battery under different working conditions, and issue an early warning based on the recognition result of the characteristic information, thereby improving the accuracy of the early warning result and the response speed.

[0010] Furthermore, preprocessing the first operating data includes: filtering and denoising the first operating data, removing noise in the first operating data, and smoothing the first operating data; standardizing the first operating data after filtering and denoising; extracting features from the first operating data after standardization and generating a feature set; and optimizing the continuity of the first operating data so that each data has a time correlation.

[0011] Furthermore, the method for equivalent modeling of the first operating data after preprocessing includes: establishing an equivalent circuit model, and using the model to simulate the charging and discharging process of the battery, so as to quantify the internal reaction and performance change of the power battery; establishing a thermal management model, simulating the temperature distribution of the power battery, and obtaining the temperature distribution and thermal effect change trend of the power battery; combining the equivalent circuit model with the thermal management model to dynamically simulate the power battery to simulate its comprehensive performance under different working conditions; according to the simulation results, adjusting the battery management strategy to optimize the response characteristics of the battery under complex working conditions.

[0012] Furthermore, the thermal management model is selected based on the physical and chemical properties of the battery and the heat conduction equation.

[0013] Furthermore, the analysis of the chemical properties of batteries can be achieved using electrochemical models, which simulate the performance of batteries by describing the chemical reaction processes at the molecular level inside the batteries.

[0014] Furthermore, when dynamically simulating the power battery, the temperature changes and electrochemical reactions under various working conditions are simulated, and the extreme working conditions of the power battery are simulated by changing parameters to obtain the response characteristics of the battery under extreme working conditions.

[0015] Furthermore, the identification signal is in a coded form, and converting the personalized feature report into the identification signal includes: establishing a state space, which represents the state set of each time node in the mapping process, and inputting the feature information in the personalized feature report into the state space; defining a discrete mapping operation set, which refers to the operations that the personalized feature report will involve in the mapping process; constructing a policy network, learning the state space and the operation set through the policy network, generating a mapping strategy, and selecting a mapping operation according to the current state; generating an identification signal through the policy network, which is Base64 encoded or URL encoded, and verifying the generated identification signal, wherein the verification process uses a hash check algorithm.

[0016] Furthermore, when performing power battery analysis, the power battery is analyzed in blocks, and the power battery is divided into multiple separate blocks.

[0017] A power battery operation process early warning system, comprising: A data preprocessing module, used for the processing center to receive the first operation data collected by the collection module and preprocess the first operation data; An equivalent modeling module, used to perform equivalent modeling on the preprocessed first operating data, and establish a relationship between the operating characteristics and health status of the power battery; The personalized feature report generation module is used to generate a personalized feature report of the power battery, which contains the feature information of the power battery under different working conditions, and converts the generated personalized feature report into an identification signal. After receiving the identification signal, the processing center quickly performs matching analysis and monitors the power battery in real time. The early warning module is used to issue early warnings based on the matching analysis results and send out early warning signals.

[0018] The beneficial effect of the present application is that the present application provides a power battery operation process early warning method and early warning system, which establishes the relationship between the operating characteristics and the health status of the power battery by equivalent modeling of the first operating data, generates a personalized characteristic report of the power battery, thereby obtaining the characteristic information of the power battery under different working conditions, and issues an early warning based on the recognition result of the characteristic information, thereby improving the accuracy of the early warning result and the response speed.

[0019] In addition to the above-described purposes, features and advantages, the present application also has other purposes, features and advantages. The present application will be further described in detail with reference to the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 This is a schematic diagram of the overall process of a power battery operation process early warning method in this application; Figure 2 This is a schematic diagram of the module structure of a power battery operation process early warning system in this application. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0023] Embodiment 1: Figure 1 As shown, the present application provides a power battery operation process early warning method, which is used to provide operation early warning for the power battery in the new energy vehicle, by collecting multi-dimensional electrochemical data (such as voltage, current, temperature, internal resistance, etc.) during the charging and discharging process, and identifying the change trend inside the power battery through these data, and providing early warning for the failure or performance degradation of the power battery, thereby achieving more accurate monitoring and early warning, the early warning method includes the following steps: Step 10: The processing center receives the first operation data collected by the collection module and pre-processes the first operation data; During the operation of the new energy vehicle, it is necessary to collect data on the operation of the power battery so as to obtain accurate data of the power battery. In this embodiment, the power battery is collected by a collection module, which includes sensor devices such as a voltage sensor, a thermocouple sensor, and a Hall sensor, respectively collecting voltage, temperature, and current data of the power battery, and sending the collected first operation data to a processing center for subsequent processing. The processing center may be an on-board processing center or a cloud processing center. It can be understood that in order to transmit the collected data to the processing center, there is a data exchange channel between the collection module and the processing center. In this embodiment, the channel is a wireless transmission channel, such as Bluetooth, wireless local area network, etc., to upload the first operation data to the processing center in real time; In addition to the data directly collected by the collection module, the first operation data also includes data indirectly calculated from the collected data, such as the open circuit voltage (OCV), dynamic internal resistance, electric power, power factor, etc. of the power battery. These indirectly calculated data can refer to existing formulas or calculation methods, which are not described in detail in this embodiment, as well as some auxiliary data, such as environmental data (vibration, ambient temperature, etc.) and the physical state of the power battery (appearance, deformation, etc.), so as to further supplement the operation process of the power battery; After receiving the first operation data, it is also necessary to preprocess it. Because during the operation process, the collected data is usually complex and contains noise, so the first operation data needs to be preprocessed before subsequent processing to improve the accuracy of the analysis result. Specifically, the preprocessing of the first operation data includes: First, the first operation data is filtered and denoised, the noise in the first operation data is removed, and the first operation data is smoothed; in the original data, since the acquisition process contains noise data, the first operation data will be affected by load fluctuations and environmental factors, so it is filtered and denoised, wherein the filtering and denoising of the first operation data can adopt a digital filtering algorithm, such as Kalman filtering, low-pass filtering, etc., so that the first operation data is smoother and convenient for subsequent processing; The first operating data after filtering and denoising is standardized; after filtering and denoising, the first operating data needs to be standardized, because the dimensions and numerical ranges of the operating parameters of different batteries are different, which will produce different scales, so it is standardized, wherein the standardization adopts the minimum-maximum standardization method to map the data to the [0,1] interval, eliminate the dimensional influence between different parameters, and achieve comparability between data, or adopt other methods, such as the Z-score standardization method, which is not described in detail in this embodiment, as long as the first operating data can be standardized; Perform feature extraction on the first operation data after the standardization process and generate a feature set; after completing the above operations, it is necessary to perform feature extraction on it to extract features with physical significance, such as the battery's charge and discharge curve, maximum current, average temperature, temperature change rate, etc. These features can reflect the battery's operating status and health, and are an important basis for subsequent battery status evaluation and analysis. The generation of feature sets can use principal component analysis, linear discriminant analysis and other methods to reduce feature dimensions and improve analysis efficiency. For details, refer to the prior art; The continuity of the first operation data is optimized to make the data temporally correlated. Since the sampling intervals may be uneven during the collection process, or there may be real data under some timestamps, the continuity of the first operation data will be affected. Therefore, it is also necessary to optimize its continuity and perform time series analysis during the connection optimization process to make the data temporally correlated. Therefore, even if there is missing data, it can be supplemented through interpolation and other methods to ensure the continuity and integrity of the data on the time axis, providing a basis for subsequent battery health status assessment.

[0024] Step 20: Perform equivalent modeling on the preprocessed first operating data to establish a relationship between the operating characteristics and health status of the power battery.

[0025] After the first operating data is preprocessed, it is necessary to further analyze it. In the traditional analysis method, the relationship between various parameters is usually directly established based on the collected data, but this method cannot combine multiple data, and in each established relationship, the correlation between various parameters must be satisfied, resulting in the relationship between the operating characteristics and the health state finally obtained cannot truly reflect the actual situation. Therefore, in this embodiment, the relationship between the operating characteristics and the health state of the power battery is established by equivalent modeling. Specifically, the method of equivalent modeling the preprocessed first operating data includes: Step 201: Establish an equivalent circuit model, and use the model to simulate the charging and discharging process of the battery, so as to quantify the internal reaction and performance change of the power battery; The equivalent circuit model (ECM) is a model that fits the relationship between the terminal voltage and the open circuit voltage. Common equivalent circuit models include a first-order RC circuit model, a second-order RC circuit model, etc. By adjusting the parameters of the equivalent circuit model, it can more accurately reflect the actual working state of the battery. In this embodiment, after the equivalent circuit model is established, the pre-processed first operating data is input into the equivalent circuit model, so as to obtain the characteristics of various parameters of the power battery, such as the current change, voltage fluctuation, open circuit voltage fluctuation, etc. during the charging and discharging process, without repeated measurement. In addition, since the standardization process is performed during the pre-processing process, when applying the equivalent circuit model, there is no need to worry about the dimensions between different data, thereby improving the effectiveness of the model analysis results and accurately obtaining the change trend of each parameter. Step 202: Establish a thermal management model, simulate the temperature distribution of the power battery, and obtain the temperature distribution and thermal effect change trend of the power battery; During the operation of the power battery, temperature change is an extremely important parameter, because temperature not only affects the charge and discharge performance of the power battery, but also has a significant impact on the life of the battery. Since temperature data cannot be directly simulated by an equivalent circuit model, a thermal management model is used in this embodiment to simulate the temperature distribution and obtain the temperature distribution and thermal effect change trend of the power battery. Specifically, the thermal management model can be selected based on the physical and chemical properties of the battery and the heat conduction equation to simulate and analyze the temperature field of the battery under different working conditions, and combined with the material properties of the battery, to achieve the correlation analysis between temperature and battery aging rate; It should be noted that the analysis of the chemical characteristics of the battery can be achieved by using an electrochemical model method, which describes the chemical reaction process at the molecular level inside the battery, such as the migration of lithium ions between the negative electrode and the positive electrode in a lithium-ion battery, to more accurately simulate the performance of the battery. However, due to the complexity of the electrochemical model calculation and high data requirements, a simplified method is often used in practical applications. When using a cloud processing center or edge processing equipment with sufficient computing power, an electrochemical model can be used for accurate analysis, thereby achieving real-time monitoring and prediction of the battery health status. Among them, the electrochemical model includes an electrolyte diffusion model, a Nernst model, a P2D (Pseudo Two-Dimensional) model, etc., which are not described in detail in this embodiment; Step 203: combining the equivalent circuit model and the thermal management model to dynamically simulate the power battery to simulate its comprehensive performance under different working conditions; After establishing the equivalent circuit model and thermal management model, it is also necessary to combine the analysis data of the two to perform dynamic simulation on the power battery, because the two models analyze different types of data, but different data types will have an impact on each other, such as excessive temperature leading to reduced charging and discharging current and reduced battery life. Therefore, it is necessary to combine the analysis results of the two models for dynamic simulation, taking the impact between the input data into account during the analysis process, thereby improving the dynamic responsiveness and accuracy of the analysis results; When dynamically simulating a power battery, the overall performance and health of the power battery can be more comprehensively evaluated by simulating temperature changes and electrochemical reactions under various operating conditions. In addition, the dynamic simulation process can also predict the battery life under different usage conditions, thereby optimizing the battery's efficiency and extending its service life. The extreme operating conditions of the power battery can be simulated by changing parameters to obtain the response characteristics of the battery under extreme conditions. For example, the introduction of the dendrite growth control method of zinc-ion batteries in the dynamic simulation process can improve the performance of the power battery under complex conditions. The addition of sodium dodecylbenzene sulfonate additives to the electrolyte not only improves the battery's cycle stability and coulombic efficiency, but also reduces the risk of battery life reduction due to temperature changes through the optimization of the thermal management model. Therefore, in the dynamic simulation process, changing parameters can improve the battery life while simulating extreme conditions of the power battery.

[0026] Step 204: According to the simulation results, the battery management strategy is adjusted to optimize the response characteristics of the battery under complex working conditions.

[0027] After the simulation, the battery management strategy needs to be adjusted according to the simulation results to ensure that the battery management strategy matches the actual operating conditions and improve the safety and reliability of the battery system. At the same time, the battery aging mechanism can be analyzed in combination with the simulation data to determine the battery aging mechanism. In traditional analysis methods, since there is a gap between the various data and the impact of temperature on various data is not considered, inaccurate battery life prediction often occurs. In this embodiment, the equivalent modeling method is used to not only connect different types of data, but also improve the accuracy of battery life prediction, thereby facilitating early warning.

[0028] Step 30: Generate a personalized feature report of the power battery, which contains feature information of the power battery under different working conditions, and convert the generated personalized feature report into an identification signal. After receiving the identification signal, the processing center quickly performs matching analysis and monitors the power battery in real time. In actual scenarios, due to the continuous changes in environmental parameters and battery operating parameters, the working conditions of the power battery will continue to change. In this case, traditional analysis methods are difficult to apply to power batteries. Therefore, in this embodiment, a personalized feature report of the power battery is generated, and the report contains feature information of the power battery under different working conditions, such as voltage fluctuations during charging, changes in internal resistance, etc., and in order to facilitate the processing center to quickly identify and match the operating status of the battery, the personalized feature report is converted into an identification signal, wherein the personalized feature report is converted into an identification signal using a policy gradient mapping method. Through the policy gradient mapping method, the generated personalized feature report is converted into an identification signal that can be recognized by the processing center. Specifically, the personalized feature report is converted into an identification signal including: Establish a state space, which represents the state set of each time node in the mapping process, and input the feature information in the personalized feature report into the state space; when converting the personalized feature report, it is first necessary to build a state set that can cover all time nodes, and input the feature information in the personalized feature report into the state space, so as to facilitate subsequent retrieval and analysis; Define a discrete mapping operation set, which refers to the operations involved in the mapping process of the personalized feature report, such as the screening of feature information, weight allocation, etc., to ensure that each operation can accurately reflect the changes in feature information. The mapping operation set is discrete, so as to facilitate the refined management of feature information during the mapping process; Construct a policy network, learn the state space and operation set through the policy network, generate a mapping strategy, and select a mapping operation according to the current state; the policy network can be a fully connected network, a convolutional neural network, a recurrent neural network, etc., to ensure the accuracy and efficiency of the mapping strategy, and ultimately achieve accurate conversion from personalized feature reports to recognition signals; An identification signal is generated through a policy network. The identification signal is Base64 encoded or URL encoded, and the generated identification signal is verified. The verification process uses a hash verification algorithm to ensure the integrity and consistency of the identification signal.

[0029] After the policy network is constructed, it can be updated by calculating the gradient of each mapping operation, and calculated according to the policy gradient algorithm, and the result is converted into a Base64-encoded or URL-encoded identification signal, wherein the policy gradient algorithm can use the REINFORCE algorithm or the PPO algorithm, and its calculation process can refer to the existing technology, which is not described in detail in this embodiment. After the identification signal is generated, a hash check is performed on it to ensure the accuracy of data transmission, and finally the verified identification signal is transmitted to the processing center to realize real-time monitoring and optimization management of the battery status.

[0030] In order to further improve the accuracy of the power battery analysis results, the power battery can also be analyzed in blocks, and the power battery can be split into multiple separate blocks. When analyzing these blocks, the amount of instantaneous response data is smaller and the analysis results are more accurate. For example, for the battery pack on a new energy vehicle, it can be split according to the number of individual batteries in the battery pack, and then the same method can be used to analyze each split block separately, so as to quickly locate the fault location or abnormal location and improve the early warning efficiency. In the process of block analysis, the split data analysis can also reveal the imbalance inside the battery pack, which helps to adjust the battery management strategy in a targeted manner and optimize the performance of the entire battery pack.

[0031] Step 40: Issue an early warning based on the matching analysis results and send out an early warning signal.

[0032] After the matching analysis is completed, an early warning will be issued based on the analysis results. The early warning signal includes a fault prompt sent to the vehicle display terminal, and the fault location and fault cause prompt sent to the cloud platform. Maintenance suggestions are generated and corresponding response measures are triggered, such as reducing the charging and discharging current of the power battery, turning on auxiliary cooling, etc.

[0033] Embodiment 2: Figure 2 As shown, the present application proposes a power battery operation process early warning system, which runs the early warning method in the first embodiment. The system ensures that the power battery can maintain efficient and stable operation under complex and changeable working conditions through continuous data collection and real-time analysis, and provides early warning under different working conditions. The early warning system includes: A data preprocessing module, configured to receive the first operation data collected by the collection module from the processing center and preprocess the first operation data, wherein the first operation data includes data directly collected by the collection module and data indirectly calculated from the collected data; An equivalent modeling module, used to perform equivalent modeling on the preprocessed first operating data, and establish a relationship between the operating characteristics and health status of the power battery; A personalized feature report generation module is used to generate a personalized feature report of a power battery, which contains feature information of the power battery under different working conditions, and converts the generated personalized feature report into an identification signal. After receiving the identification signal, the processing center quickly performs matching analysis and monitors the power battery in real time. The personalized feature report is converted into an identification signal by using a policy gradient mapping method. Through the policy gradient mapping method, the generated personalized feature report is converted into an identification signal that can be recognized by the processing center. The early warning module is used to issue early warnings based on the matching analysis results and send out early warning signals.

[0034] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A power battery operation process early warning method, characterized in that: include: The processing center receives the first operation data collected by the collection module and pre-processes the first operation data, wherein the first operation data includes data directly collected by the collection module and data indirectly calculated from the collected data; Performing equivalent modeling on the preprocessed first operating data to establish a relationship between the operating characteristics and health status of the power battery; Generate a personalized feature report of the power battery, which contains feature information of the power battery under different working conditions, and convert the generated personalized feature report into an identification signal. After receiving the identification signal, the processing center quickly performs matching analysis and monitors the power battery in real time. The personalized feature report is converted into an identification signal using a policy gradient mapping method. Through the policy gradient mapping method, the generated personalized feature report is converted into an identification signal that can be recognized by the processing center. An early warning is issued based on the matching analysis results and a warning signal is sent out.

2. A power battery operation process early warning method according to claim 1, characterized in that: Preprocessing the first operating data includes: filtering and denoising the first operating data, removing noise in the first operating data, and smoothing the first operating data; standardizing the first operating data after filtering and denoising; extracting features from the first operating data after standardization and generating a feature set; and optimizing the continuity of the first operating data so that each data has a time correlation.

3. The power battery operation process early warning method according to claim 1, characterized in that: The method for equivalent modeling of the first operating data after preprocessing includes: establishing an equivalent circuit model, using the model to simulate the charging and discharging process of the battery, so as to quantify the internal reaction and performance change of the power battery; establishing a thermal management model, simulating the temperature distribution of the power battery, and obtaining the temperature distribution and thermal effect change trend of the power battery; combining the equivalent circuit model with the thermal management model to dynamically simulate the power battery to simulate its comprehensive performance under different working conditions; according to the simulation results, adjusting the battery management strategy to optimize the response characteristics of the battery under complex working conditions.

4. A power battery operation process early warning method according to claim 3, characterized in that: The thermal management model is selected based on the physical and chemical characteristics of the battery and the heat conduction equation.

5. A power battery operation process early warning method according to claim 4, characterized in that: The chemical property analysis of the battery is implemented using the electrochemical model method, which simulates the battery performance by describing the chemical reaction process at the molecular level inside the battery.

6. A power battery operation process early warning method according to claim 3, characterized in that: When dynamically simulating a power battery, the temperature changes and electrochemical reactions under various operating conditions are simulated, and the extreme operating conditions of the power battery are simulated by changing parameters to obtain the response characteristics of the battery under extreme conditions.

7. The power battery operation process early warning method according to claim 1, characterized in that: Converting a personalized feature report into an identification signal includes: establishing a state space, which represents a set of states at each time node in a mapping process, and inputting feature information in the personalized feature report into the state space; defining a discrete mapping operation set, which refers to the operations that the personalized feature report will involve in the mapping process; constructing a policy network, learning the state space and the operation set through the policy network, generating a mapping strategy, and selecting a mapping operation according to the current state; generating an identification signal through the policy network, which is Base64 encoded or URL encoded, and verifying the generated identification signal, wherein the verification process uses a hash check algorithm.

8. The power battery operation process early warning method according to claim 1, characterized in that: When performing power battery analysis, the power battery is analyzed in blocks and divided into multiple separate blocks.

9. A power battery operation process early warning system, characterized in that: include: A data preprocessing module, configured to receive the first operation data collected by the collection module from the processing center and preprocess the first operation data, wherein the first operation data includes data directly collected by the collection module and data indirectly calculated from the collected data; An equivalent modeling module, used to perform equivalent modeling on the preprocessed first operating data, and establish a relationship between the operating characteristics and health status of the power battery; A personalized feature report generation module is used to generate a personalized feature report of a power battery, which contains feature information of the power battery under different working conditions, and converts the generated personalized feature report into an identification signal. After receiving the identification signal, the processing center quickly performs matching analysis and monitors the power battery in real time. The personalized feature report is converted into an identification signal by using a policy gradient mapping method. Through the policy gradient mapping method, the generated personalized feature report is converted into an identification signal that can be recognized by the processing center. The early warning module is used to issue early warnings based on the matching analysis results and send out early warning signals.

10. A power battery operation process warning system according to claim 9, characterized in that: Used to implement the power battery operation process early warning method as described in any one of claims 1 to 8.

Images