New energy automobile battery health state assessment method and system

Abstract

The invention provides a new energy automobile battery health state assessment method and system, and relates to the technical field of automobile battery management. According to the invention, the data acquisition frequency is adjusted in real time according to the driving habits and states of the vehicle, so that more dense and detailed data can be obtained at a critical moment or in a high-load state, more subtle changes which may influence the health state of the battery can be captured, and meanwhile, the accuracy of the data acquisition is improved. According to the dynamic adjustment of the verification level, verification of different degrees is carried out on various types of data according to the importance of the data and the influence degree on an evaluation result, error and abnormal data are effectively eliminated, the quality and reliability of the data are further improved, and the dual adjustment mechanisms act together to improve the accuracy and reliability of the data. The extracted features associated with the health degree of the battery are more accurate and comprehensive, and a firmer data basis is provided for a subsequent evaluation model.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile battery management, and in particular to a method and system for evaluating the health status of a battery in a new energy automobile. Background Art

[0002] With the rapid development of the new energy vehicle industry, the accurate assessment of the health status of batteries as their core components has become a crucial technical issue. However, in practical applications, the assessment of the health status of new energy vehicle batteries often faces many challenges:

[0003] First, traditional evaluation methods usually use a fixed data collection frequency and cannot adjust the data collection strategy in real time according to the dynamic changes in the actual driving process of the vehicle (such as acceleration, deceleration, high-speed driving, long-term parking, etc.). This results in the inability to obtain sufficiently dense and detailed data at critical moments or under high load conditions, thereby missing subtle changes that may affect the health status of the battery, limiting the accuracy of the evaluation results.

[0004] Secondly, the existing evaluation system often uses a unified verification standard to process all data, ignoring the differences in the importance of different data categories in the evaluation and their different impacts on the results. This rigid verification method is difficult to effectively eliminate errors and abnormal data, which reduces the quality and reliability of the data and thus affects the accuracy of the evaluation results.

[0005] Due to the limitations of data collection frequency and data verification standards, the extracted features associated with battery health are often not comprehensive and accurate. This results in a lack of a solid data foundation when building the evaluation model, making it difficult to fully reflect the actual health status of the battery, limiting the accuracy and credibility of the evaluation results.

[0006] Therefore, it is necessary to provide a new energy vehicle battery health status assessment method and system to solve the above technical problems. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a new energy vehicle battery health status assessment method and system for solving the problems of data collection frequency limitation, rigid data verification standards and lack of assessment accuracy in existing battery health status assessment methods.

[0008] The present invention provides a method for evaluating the health status of a new energy vehicle battery, comprising the following steps:

[0009] Extract the charge and discharge data of the battery raw data and preprocess it, and extract the related features that affect the battery health;

[0010] Detect the battery health and obtain the test results. The extracted mapping relationship between the associated features affecting the battery health and the test results is used as a training set, and the evaluation model is obtained through machine learning algorithm training.

[0011] Based on the extraction of related features that affect battery health and the vehicle's driving habits and status, the frequency of current battery charge and discharge data collection is dynamically adjusted to collect current battery charge and discharge data;

[0012] Based on the vehicle's driving habits and status, dynamically adjust the verification level of each category of data in the current battery charging and discharging data, verify the collected current battery charging and discharging data, and obtain verified data of each category;

[0013] Remove the erroneous data in the verified data of each category and sort them out to obtain the data set to be extracted;

[0014] The obtained data set to be extracted is received, and the associated features affecting the battery health are extracted and input into the evaluation model to output the evaluation result of the battery health status.

[0015] Preferably, the specific steps of extracting the charging and discharging data of the battery raw data and preprocessing it, and extracting the associated features that affect the battery health are:

[0016] Collect the charge and discharge data of the battery raw data recorded by the battery management system, including voltage, current, temperature, and charge and discharge time;

[0017] Remove noise, outliers, missing values ​​and normalize the battery raw data to obtain pre-processed data;

[0018] Feature extraction parameters are set based on professional knowledge of battery health, and features closely related to battery health are extracted from preprocessed data through feature extraction algorithms.

[0019] Preferably, the battery health is detected and the detection results are obtained, and the mapping relationship between the extracted associated features affecting the battery health and the detection results is used as a training set, and the specific steps of obtaining the evaluation model through machine learning algorithm training are:

[0020] Use battery testing equipment to test the battery health and obtain the battery health test results;

[0021] By using statistical analysis methods, the corresponding relationship between the extracted features closely related to battery health and the battery health test results is identified, and the corresponding relationship is integrated into a training data set;

[0022] Select any one of the neural network or random forest in the machine learning algorithm as the model architecture, train it using the training data set, and obtain the evaluation model.

[0023] Preferably, the frequency of collecting the current battery charge and discharge data is dynamically adjusted based on the extraction of the associated features affecting the battery health and the vehicle driving habits and status. The specific steps of collecting the current battery charge and discharge data are:

[0024] Analyze the historical driving data of the current vehicle, identify its driving mode, and preliminarily set the data collection frequency baseline in each mode based on the battery usage characteristics under different driving modes;

[0025] Real-time monitoring of the vehicle's battery status, including but not limited to power, temperature, voltage and current;

[0026] According to the vehicle's driving habits and current status, evaluate the impact of the vehicle's driving habits and battery status on the data collection frequency, and formulate dynamic adjustment rules for the data collection frequency and corresponding trigger conditions based on the evaluation results;

[0027] Use on-board sensors and control systems to monitor the vehicle's driving status and battery parameter data in real time, and evaluate the impact of current driving habits and battery status on data collection frequency, to obtain real-time monitoring data and evaluation results;

[0028] If the real-time monitoring data and evaluation results meet the trigger conditions, the data collection frequency is adjusted according to the established dynamic adjustment rules to collect the current battery charging and discharging data.

[0029] Preferably, the specific steps of dynamically adjusting the verification level of each category of data in the current battery charge and discharge data based on the vehicle driving habits and status, verifying the collected current battery charge and discharge data, and obtaining the verified data of each category are:

[0030] According to the importance of various types of battery charging and discharging data and the degree of influence on vehicle performance, different verification levels and corresponding verification methods are pre-set;

[0031] Based on different pre-set verification level standards, the verification level of each category of data in the current battery charging and discharging data is divided;

[0032] According to the verification level of each category of data in the current battery charging and discharging data, the corresponding verification method is matched for synchronous verification to obtain the verified data of each category.

[0033] Preferably, the presetting of different verification levels and verification methods corresponding to the verification levels specifically include:

[0034] The core parameter data of the battery is set to advanced verification. The corresponding verification method is to compare the battery voltage, current and temperature parameters with the preset safety range. If they are out of range, an alarm will be immediately issued and recorded. Secondly, the real-time data will be compared with the battery historical data to analyze whether there are abnormal fluctuations or trends.

[0035] For data that affects vehicle performance but is not core, it is set as intermediate verification. The corresponding verification method is to regularly test the battery's charging efficiency and discharge rate;

[0036] Auxiliary data that affects battery health is set to low-level verification, and the corresponding verification method is to perform basic format verification and logic verification on the data.

[0037] Preferably, the specific steps of receiving the data set to be extracted, extracting the associated features affecting the battery health, and inputting them into the evaluation model, and outputting the evaluation result of the battery health state are:

[0038] Extract features related to battery health from the data set to be extracted, and process them into feature data that conforms to the input format of the evaluation model;

[0039] The feature data processed to conform to the evaluation model input format is input into the evaluation model, and the evaluation model calculates and outputs the evaluation results of the battery health status, including but not limited to the battery remaining capacity percentage and health level information.

[0040] A new energy vehicle battery health status assessment system, the assessment system comprising:

[0041] The historical feature extraction module is used to extract the charge and discharge data of the battery raw data and pre-process it, and extract the related features that affect the battery health;

[0042] The model building module is used to detect the battery health and obtain the test results. The extracted mapping relationship between the associated features affecting the battery health and the test results is used as a training set to obtain an evaluation model through machine learning algorithm training.

[0043] A dynamic collection module is used to dynamically adjust the frequency of current battery charge and discharge data collection and collect current battery charge and discharge data based on the extraction of related features that affect battery health and the vehicle's driving habits and status;

[0044] A dynamic verification module is used to dynamically adjust the verification level of each category of data in the current battery charge and discharge data based on the vehicle's driving habits and status, verify the collected current battery charge and discharge data, and obtain verified data of each category;

[0045] The data cleaning module is used to remove the erroneous data in the verified data of each category and sort them out to obtain the data set to be extracted;

[0046] The evaluation and analysis module is used to receive the obtained data set to be extracted, extract the associated features that affect the battery health, input the evaluation model, and output the evaluation results of the battery health status.

[0047] Compared with the related art, the method and system for evaluating the health status of a new energy vehicle battery provided by the present invention have the following beneficial effects:

[0048] The present invention can ensure that more intensive and detailed data are obtained at critical moments or under high load conditions by adjusting the data collection frequency in real time according to the vehicle's driving habits and status, thereby capturing more subtle changes that may affect the battery's health status. At the same time, the dynamic adjustment of the verification level performs different degrees of verification on each category of data according to the importance of the data and the degree of influence on the evaluation results, effectively eliminating errors and abnormal data, and further improving the quality and reliability of the data. This dual adjustment mechanism works together to make the extracted features associated with the battery health more accurate and comprehensive, providing a more solid data foundation for the subsequent evaluation model. Therefore, the accuracy of the evaluation results is significantly improved, which can more accurately reflect the actual health status of the battery, and provide a more reliable decision-making basis for car owners and manufacturers. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of a method for evaluating the health status of a battery of a new energy vehicle according to the present invention;

[0050] Figure 2 is a flow chart of step S300 in an embodiment of the present invention;

[0051] Figure 3 is a flow chart of step S400 in an embodiment of the present invention;

[0052] Figure 4 The system block diagram of a new energy vehicle battery health status assessment system of the present invention. DETAILED DESCRIPTION

[0053] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0054] Embodiment 1

[0055] like Figure 1 As shown, a method for evaluating the health status of a new energy vehicle battery comprises the following steps:

[0056] S100, extracting charging and discharging data of the battery raw data and preprocessing it, and extracting the associated features that affect the health of the battery;

[0057] In the specific implementation process, the steps of step S100 are specifically as follows:

[0058] S101, collecting charging and discharging data of battery raw data recorded by a battery management system (BMS), including voltage, current, temperature, and charging and discharging time;

[0059] Specifically, ensure that the interface connection between the BMS system and the data collection system is normal. After confirmation, extract the battery charge and discharge data from the BMS system through the interface, including voltage (V), current (A), temperature (℃), and the start and end time (timestamp) of each charge and discharge. Then store the collected data in an appropriate storage medium, such as a database, file system, etc.

[0060] S102, removing noise, outliers, missing values ​​and normalizing the charge and discharge data of the battery raw data to obtain pre-processed data;

[0061] Specifically, filtering technology is used to remove high-frequency noise in the charging and discharging data of the battery raw data, and outliers (such as extremely high values ​​or low values) in the charging and discharging data of the battery raw data are identified and processed. Usually, thresholds are set or statistical methods are used to identify and replace or delete outliers. Then, for missing values ​​in the charging and discharging data of the battery raw data, linear interpolation and polynomial interpolation in the interpolation method are used to fill in the missing values. Finally, all data are scaled to the same dimension to obtain preprocessed data.

[0062] S103, setting feature extraction parameters based on professional knowledge of battery health, and extracting features closely related to battery health from the preprocessed data through a feature extraction algorithm;

[0063] Specifically, based on the professional knowledge in the field of battery health, determine which features have an important impact on the battery health assessment, including but not limited to the number of charge and discharge cycles, capacity decay rate, internal resistance change, temperature distribution, etc., and use this to set the specific parameters of the feature extraction algorithm, specifically the window size, step size, threshold and other parameters, and use statistical methods and algorithms to extract features closely related to battery health from the preprocessed data.

[0064] S200, detecting the battery health and obtaining the detection results, extracting the mapping relationship between the associated features affecting the battery health and the detection results as a training set, and obtaining an evaluation model through machine learning algorithm training;

[0065] In the specific implementation process, the specific steps of step S200 are:

[0066] S201, using a battery testing device to perform a battery health test on the battery and obtain a battery health test result;

[0067] S202, identifying the correspondence between the extracted features closely related to the battery health and the battery health detection results through a statistical analysis method, and integrating the correspondence into a training data set;

[0068] S203. Select any one of the neural network or random forest in the machine learning algorithm as the model architecture, use the training data set for training, and obtain an evaluation model.

[0069] S300, based on the extraction of correlation features affecting battery health and the vehicle driving habits and status, dynamically adjust the frequency of current battery charge and discharge data collection, and collect current battery charge and discharge data;

[0070] In the specific implementation process, the specific steps of step S300 are:

[0071] S301, analyzing the historical driving data of the current vehicle, identifying its driving mode, and preliminarily setting the data collection frequency baseline in each mode according to the battery usage characteristics of the vehicle in different driving modes;

[0072] Specifically, Python in the data analysis tool is used to mine historical data to identify typical driving modes, including urban commuting mode (low speed, frequent starts and stops), long-distance high-speed mode (high speed, stable speed), mountain climbing mode (high load, frequent acceleration and deceleration), etc. For each driving mode, the battery usage characteristics in these modes are analyzed, including power consumption rate, temperature change trend, voltage stability, etc. Based on the above analysis, a baseline value of the data collection frequency in each driving mode is preliminarily set. In this embodiment, in the urban commuting mode, the data collection frequency baseline is set to once every 5 seconds; in the long-distance high-speed mode, the data collection frequency baseline is specifically set to once every 10 seconds; and in the mountain climbing mode, the data collection frequency baseline is specifically set to once every 5 seconds.

[0073] S302, real-time monitoring of the battery status of the vehicle, including but not limited to power, temperature, voltage and current;

[0074] Specifically, key parameters such as battery power, temperature, voltage and current are obtained in real time through the vehicle's onboard battery management system (BMS).

[0075] S303, based on the vehicle driving habits and the current battery status, evaluate the impact of the vehicle driving habits and the battery status on the data collection frequency, and formulate a dynamic adjustment rule for the data collection frequency and a corresponding trigger condition based on the evaluation result;

[0076] Specifically, evaluate driving habits: the city commuting mode requires a higher data collection frequency, the long-distance high-speed mode needs to appropriately reduce the data collection frequency to save resources, and the mountain climbing mode needs to increase the data collection frequency to monitor battery performance and potential safety issues; evaluate battery status: when the battery power is below a certain threshold (such as 20%), the data collection frequency needs to be increased to monitor the remaining battery life and avoid over-discharge; when the battery temperature exceeds or falls below the normal range (such as exceeding 45°C or below 0°C), the data collection frequency needs to be increased; according to the results of evaluating driving habits and the results of evaluating battery status, formulate dynamic data collection frequency The specific state adjustment rules are as follows: in this embodiment, in the city commuting mode, the data collection frequency baseline is set to once every 3 seconds; in the long-distance high-speed mode, the data collection frequency baseline is specifically set to once every 5 seconds, and in the mountain climbing mode, the data collection frequency baseline is specifically set to once per second; the trigger conditions are: the adjustment of the data collection frequency is triggered when the vehicle enters a different driving mode based on the GPS data and the acceleration sensor data, and the adjustment of the data collection frequency is triggered when the battery management system (BMS) reports that the battery power is lower than the set threshold, the battery temperature exceeds the normal range, or the voltage / current fluctuations are abnormal.

[0077] S304, using the vehicle-mounted sensors and control system to monitor the vehicle's driving status and battery parameter data in real time, and evaluating the impact of current driving habits and battery status on data collection frequency, and obtaining real-time monitoring data and evaluation results;

[0078] S305: If it is determined that the real-time monitoring data and the evaluation results meet the triggering conditions, the data collection frequency is adjusted according to the formulated dynamic adjustment rules to collect the current battery charging and discharging data.

[0079] S400, dynamically adjusting the verification level of each category of data in the current battery charge and discharge data based on the vehicle's driving habits and status, verifying the collected current battery charge and discharge data, and obtaining verified data of each category;

[0080] In the specific implementation process, the specific steps of step S400 are:

[0081] S401, presetting different verification levels and verification methods corresponding to the verification levels according to the importance of various types of data in the battery charging and discharging data and the degree of influence on vehicle performance;

[0082] Specifically, the various types of data in the battery charging and discharging data are classified in detail, specifically classified into power data, voltage data, current data, temperature data, internal resistance data, etc. Then, the importance of each type of data for battery health status assessment and vehicle performance is evaluated, and different verification levels and corresponding verification methods are set as follows:

[0083] The core parameter data of the battery (power data, voltage data, current data, temperature data) is set to advanced verification. The corresponding verification method is to compare the voltage, current and temperature parameters of the battery with the preset safety range. If they are out of range, an alarm will be immediately issued and recorded. Secondly, the real-time data will be compared with the battery historical data to analyze whether there are abnormal fluctuations or trends.

[0084] For data that affects vehicle performance but is not core (charging efficiency and discharge rate data), set it as intermediate verification. The corresponding verification method is to regularly test the charging efficiency and discharge rate of the battery.

[0085] Auxiliary data that affects battery health (such as battery serial number, production date, number of cycles, etc.) is set as a low-level check, and the corresponding check method is to perform basic format check and logic check on the data.

[0086] S402, dividing the verification level of each category of data in the current battery charging and discharging data based on different pre-set verification level standards;

[0087] S403, according to the verification level of each category of data in the current battery charging and discharging data, matching the corresponding verification method for synchronous verification, and obtaining verified data of each category;

[0088] Specifically, according to the verification level, a suitable method is selected from the preset verification methods to verify each type of data, and the selected verification method is applied to the data, including data comparison, range check, anomaly detection, etc. The data confirmed to be correct or corrected during the verification process is saved as verified data, and the data with anomalies or that fails the verification is marked.

[0089] S500, removing the erroneous data in the verified data of each category, and sorting out the data set to be extracted;

[0090] Specifically, the data marked as abnormal or unable to pass verification in step S403 is removed by using existing data processing tools, and is sorted to obtain a data set to be extracted.

[0091] S600: Receive the obtained data set to be extracted, extract the associated features that affect the battery health, input them into the evaluation model, and output the evaluation result of the battery health status.

[0092] Embodiment 2

[0093] like Figure 4 As shown, a new energy vehicle battery health status assessment system applied to a new energy vehicle battery health status assessment method specifically includes:

[0094] The historical feature extraction module is used to extract the charge and discharge data of the battery raw data and pre-process it, and extract the associated features that affect the battery health;

[0095] The model building module is used to detect the battery health and obtain the test results. The extracted mapping relationship between the associated features affecting the battery health and the test results is used as a training set to obtain an evaluation model through machine learning algorithm training.

[0096] A dynamic collection module is used to dynamically adjust the frequency of current battery charge and discharge data collection and collect current battery charge and discharge data based on the extraction of related features that affect battery health and the vehicle's driving habits and status;

[0097] A dynamic verification module is used to dynamically adjust the verification level of each category of data in the current battery charge and discharge data based on the vehicle's driving habits and status, verify the collected current battery charge and discharge data, and obtain verified data of each category;

[0098] The data cleaning module is used to remove the erroneous data in the verified data of each category and sort them out to obtain the data set to be extracted;

[0099] The evaluation and analysis module is used to receive the obtained data set to be extracted, extract the associated features that affect the battery health, input the evaluation model, and output the evaluation results of the battery health status.

[0100] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0102] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A method for evaluating the health status of a new energy vehicle battery, characterized in that: The evaluation method comprises the following steps: Extract the charge and discharge data of the battery raw data and preprocess it, and extract the related features that affect the battery health; Detect the battery health and obtain the test results. The extracted mapping relationship between the associated features affecting the battery health and the test results is used as a training set, and the evaluation model is obtained through machine learning algorithm training. Based on the extraction of related features that affect battery health and the vehicle's driving habits and status, the frequency of current battery charge and discharge data collection is dynamically adjusted to collect current battery charge and discharge data; Based on the vehicle's driving habits and status, dynamically adjust the verification level of each category of data in the current battery charging and discharging data, verify the collected current battery charging and discharging data, and obtain verified data of each category; Remove the erroneous data in the verified data of each category and sort them out to obtain the data set to be extracted; The obtained data set to be extracted is received, and the associated features affecting the battery health are extracted and input into the evaluation model to output the evaluation result of the battery health status.

2. A method for evaluating the health status of a new energy vehicle battery according to claim 1, characterized in that: The specific steps of extracting the charging and discharging data of the battery raw data and preprocessing it, and extracting the associated features that affect the battery health are as follows: Collect the charge and discharge data of the battery raw data recorded by the battery management system, including voltage, current, temperature, and charge and discharge time; Remove noise, outliers, missing values ​​and normalize the battery raw data to obtain pre-processed data; Feature extraction parameters are set based on professional knowledge of battery health, and features closely related to battery health are extracted from preprocessed data through feature extraction algorithms.

3. A method for evaluating the health status of a new energy vehicle battery according to claim 1, characterized in that: The specific steps of detecting the battery health and obtaining the detection results, extracting the mapping relationship between the associated features affecting the battery health and the detection results as a training set, and obtaining the evaluation model through machine learning algorithm training are as follows: Use battery testing equipment to test the battery health and obtain the battery health test results; By using statistical analysis methods, the corresponding relationship between the extracted features closely related to battery health and the battery health test results is identified, and the corresponding relationship is integrated into a training data set; Select any one of the neural network or random forest in the machine learning algorithm as the model architecture, train it using the training data set, and obtain the evaluation model.

4. A method for evaluating the health status of a new energy vehicle battery according to claim 1, characterized in that: The specific steps of dynamically adjusting the frequency of current battery charge and discharge data collection based on extracting the associated features affecting battery health and the vehicle driving habits and status are as follows: Analyze the historical driving data of the current vehicle, identify its driving mode, and preliminarily set the data collection frequency baseline in each mode based on the battery usage characteristics under different driving modes; Real-time monitoring of the vehicle's battery status, including but not limited to power, temperature, voltage and current; According to the vehicle's driving habits and current status, evaluate the impact of the vehicle's driving habits and battery status on the data collection frequency, and formulate dynamic adjustment rules for the data collection frequency and corresponding trigger conditions based on the evaluation results; Use on-board sensors and control systems to monitor the vehicle's driving status and battery parameter data in real time, and evaluate the impact of current driving habits and battery status on data collection frequency, to obtain real-time monitoring data and evaluation results; If the real-time monitoring data and evaluation results meet the trigger conditions, the data collection frequency is adjusted according to the established dynamic adjustment rules to collect the current battery charging and discharging data.

5. A method for evaluating the health status of a new energy vehicle battery according to claim 1, characterized in that: The specific steps of dynamically adjusting the verification level of each category of data in the current battery charge and discharge data based on the vehicle driving habits and status, verifying the collected current battery charge and discharge data, and obtaining the verified data of each category are as follows: According to the importance of various types of data in the battery charging and discharging data and the degree of influence on vehicle performance, different verification levels and corresponding verification methods are pre-set; Based on different pre-set verification level standards, the verification level of each category of data in the current battery charging and discharging data is divided; According to the verification level of each category of data in the current battery charging and discharging data, the corresponding verification method is matched for synchronous verification to obtain the verified data of each category.

6. A method for evaluating the health status of a new energy vehicle battery according to claim 5, characterized in that: The presetting of different verification levels and verification methods corresponding to the verification levels specifically includes: The core parameter data of the battery is set to advanced verification. The corresponding verification method is to compare the battery voltage, current and temperature parameters with the preset safety range. If they are out of range, an alarm will be immediately issued and recorded. Secondly, the real-time data will be compared with the battery historical data to analyze whether there are abnormal fluctuations or trends. For data that affects vehicle performance but is not core, it is set as intermediate verification. The corresponding verification method is to regularly test the battery's charging efficiency and discharge rate; Auxiliary data that affects battery health is set to low-level verification, and the corresponding verification method is to perform basic format verification and logic verification on the data.

7. A method for evaluating the health status of a new energy vehicle battery according to claim 1, characterized in that: The specific steps of receiving the data set to be extracted, extracting the associated features affecting the battery health, and inputting them into the evaluation model, and outputting the evaluation result of the battery health state are as follows: Extract features related to battery health from the data set to be extracted, and process them into feature data that conforms to the input format of the evaluation model; The feature data processed to conform to the evaluation model input format is input into the evaluation model, and the evaluation model calculates and outputs the evaluation results of the battery health status, including but not limited to the battery remaining capacity percentage and health level information.

8. A new energy vehicle battery health status assessment system, applied to a new energy vehicle battery health status assessment method as claimed in any one of claims 1 to 7, characterized in that: The evaluation system comprises: The historical feature extraction module is used to extract the charge and discharge data of the battery raw data and pre-process it, and extract the related features that affect the battery health; The model building module is used to detect the battery health and obtain the test results. The extracted mapping relationship between the associated features affecting the battery health and the test results is used as a training set to obtain an evaluation model through machine learning algorithm training. A dynamic collection module is used to dynamically adjust the frequency of current battery charge and discharge data collection and collect current battery charge and discharge data based on the extraction of related features that affect battery health and the vehicle's driving habits and status; A dynamic verification module is used to dynamically adjust the verification level of each category of data in the current battery charge and discharge data based on the vehicle's driving habits and status, verify the collected current battery charge and discharge data, and obtain verified data of each category; The data cleaning module is used to remove the erroneous data in the verified data of each category and sort them out to obtain the data set to be extracted; The evaluation and analysis module is used to receive the obtained data set to be extracted, extract the associated features that affect the battery health, input the evaluation model, and output the evaluation results of the battery health status.

Images