Battery test system and test method for new energy automobile maintenance

Abstract

The invention relates to the technical field of battery testing, and discloses a battery testing system and method for new energy automobile maintenance, and the method comprises the steps: starting a battery testing device, building a safe connection with a to-be-tested new energy automobile battery management system through a standard communication protocol, and carrying out the equipment self-inspection and environment calibration; after system initialization is completed, data of multiple parameters such as voltage, current, temperature and internal resistance during battery operation are collected from a BMS, the data are stored in a local database and synchronously uploaded to a cloud server, meanwhile, the data are preliminarily filtered and cleaned, noise and abnormal values are removed, and a high-quality initial data set is obtained. According to the battery test system and test method for new energy automobile maintenance, the system establishes safe connection with a battery management system by using a CAN bus, and performs equipment self-inspection and environment calibration, so that the stability and reliability of data acquisition are ensured, and key parameters of a battery are monitored and recorded in real time through a high-precision sensor.

Description

Technical Field

[0001] The present invention relates to the technical field of battery testing, and in particular to a battery testing system and a testing method for new energy vehicle maintenance. Background Art

[0002] Battery testing refers to the process of comprehensively evaluating battery performance, aiming to ensure the safety and reliability of the battery under various operating conditions. However, in the existing technology, the connection between the battery testing equipment and the battery management system (BMS) may be unstable, the security of data transmission cannot be fully guaranteed, and the traditional battery state of health (SOH) and remaining capacity (SOC) estimation methods are based on simple linear models, which are difficult to handle complex nonlinear relationships. At the same time, the existing technology has limited capabilities in fault identification and location, making it difficult to provide detailed fault reports and targeted maintenance suggestions. Summary of the invention

[0003] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0004] To achieve the above object, the present invention provides the following technical solutions: First, a battery testing system and method for new energy vehicle maintenance, including: starting the battery testing equipment, establishing a secure connection with the battery management system of the new energy vehicle to be tested through a standard communication protocol, and performing equipment self-test and environmental calibration at the same time; after the system initialization is completed, collecting data on multiple parameters such as voltage, current, temperature and internal resistance during battery operation from the BMS, the data is stored in the local database and uploaded to the cloud server simultaneously, and the data is preliminarily filtered and cleaned to remove noise and outliers to obtain a set of high-quality initial data sets; based on the high-quality initial data sets obtained from the above preliminary analysis, a pre-trained multi-parameter comprehensive evaluation model is used to estimate the battery health status and remaining power. The model uses a machine learning algorithm to process complex nonlinear relationships, dynamically adjusts the prediction results, and finally outputs the battery status information; uses an intelligent diagnostic algorithm to perform Perform in-depth analysis to identify potential faults or abnormal modes, generate detailed fault reports, point out the specific fault location and possible causes, and provide targeted maintenance suggestions; execute maintenance suggestions through intelligent diagnostic algorithms, maintain a continuous data stream for remote monitoring of battery status, immediately notify relevant personnel when warning conditions are detected, and provide emergency response guidelines, and regularly send users reports containing the latest battery health status; through the latest battery health status report, combined with the user's usage habits and driving conditions, formulate the best maintenance plan, personalize the maintenance plan to extend the battery life, and continuously improve the test algorithm and model through the feedback mechanism to obtain test records, diagnostic results and maintenance actions, and encrypt and archive the test records, diagnostic results and maintenance actions, follow the privacy policy to protect user information security, and understand customer satisfaction through regular return visits to optimize service processes.

[0005] As a further solution of the present invention: the battery testing device is started to establish a safe connection with the battery management system of the new energy vehicle to be tested through a standard communication protocol, and at the same time, the device self-test and environmental calibration are performed. The specific steps are: first, the CAN bus is used as the standard communication protocol to establish a safe connection with the battery management system of the new energy vehicle to be tested; the device automatically executes a series of self-test programs to check the functional integrity of hardware components, including the power module, sensor interface and communication interface, and calibrates the environmental conditions.

[0006] As a further solution of the present invention: after the system initialization is completed, data on multiple parameters such as voltage, current, temperature and internal resistance during battery operation are collected from the BMS, the data are stored in the local database and synchronously uploaded to the cloud server, and the data are preliminarily filtered and cleaned to remove noise and outliers to obtain a set of high-quality initial data sets. The specific steps are: using high-precision sensors to monitor and record the voltage, current, temperature and internal resistance data of each battery cell in real time; all collected data are first stored in the local database to ensure that the original data can be retained even when the network connection is unstable; the collected data are denoised and outliers are removed to obtain a set of high-quality initial data sets.

[0007] As a further solution of the present invention: the high-quality initial data set obtained based on the preliminary analysis is used to estimate the battery health status and remaining power by using a pre-trained multi-parameter comprehensive evaluation model. The model uses a machine learning algorithm to process complex nonlinear relationships, dynamically adjusts the prediction results, and finally outputs the battery status information. The specific steps are as follows: first, Each data point in is sorted according to the four dimensions of voltage, current, temperature and internal resistance to form a multidimensional feature vector ; Use the random forest model for each feature vector The evaluation is performed to identify the complex interactions between different features, thereby accurately estimating the battery's state of health and remaining capacity, expressed as: ; ; in, Indicates the battery health status. Indicates the remaining battery power. By voltage Current ,temperature and internal resistance The multidimensional feature vector composed of is the random forest function used to estimate SOH, is another random forest output calculated from the eigenvector, yes The adjustment coefficient, yes The offset of yes The adjustment coefficient, yes The offset of The function is used to map the prediction results to the [0,1] interval.

[0008] As a further solution of the present invention: the intelligent diagnosis algorithm is used to deeply analyze the obtained battery status information, identify potential faults or abnormal modes, generate a detailed fault report, point out the specific fault location and possible causes, and provide targeted maintenance suggestions. The specific steps are: the battery status information obtained from the multi-parameter comprehensive evaluation model and , as well as the previously collected high-dimensional feature vectors of voltage, current, temperature and internal resistance As input; use the pre-trained mixture model for each feature vector Analysis is performed to extract local features and capture long-term dependencies in time series. The expression is: ; in, is the failure probability index corresponding to the i-th eigenvector, It is feature vectors, is the convolutional neural network output, is the LSTM network output, is the adjustment coefficient of the convolutional neural network output, is the adjustment coefficient of the LSTM output, is the offset.

[0009] As a further solution of the present invention: the maintenance suggestions are executed through the intelligent diagnosis algorithm, a continuous data stream is maintained for remote monitoring of the battery status, relevant personnel are notified immediately when a warning condition is detected, and an emergency response guide is provided, and a report containing the latest battery health status is sent to the user regularly. The specific steps are: according to the maintenance suggestions in the fault report generated by the intelligent diagnosis algorithm, the technician takes specific maintenance actions, as follows: the report indicates that a certain battery module has an overheating risk, and it is recommended to replace the module or adjust its cooling system. After the maintenance is completed, the updated battery status information will be re-incorporated into the monitoring system to evaluate the maintenance effect; real-time remote monitoring is achieved, and the system maintains a stable and uninterrupted data transmission channel, including real-time collection of key parameters of voltage, current, temperature and internal resistance from the battery management system, and uploading them to the cloud server through a secure encryption protocol, and selecting MQTT as the communication protocol; the early warning system is run on the cloud server, and the system analyzes the incoming data in real time based on preset thresholds and pattern recognition algorithms, and the expression is: ; in, It is the early warning index. is the current voltage, is the current, is the current temperature, is the current internal resistance, is the reference voltage, is the reference current, is the reference temperature, is the reference internal resistance, is the standard deviation of the voltage, is the standard deviation of the current, is the standard deviation of temperature, is the standard deviation of the internal resistance.

[0010] As a further solution of the present invention: the report on the latest battery health status is combined with the user's usage habits and driving conditions to formulate the best maintenance plan, personalize the maintenance plan to extend the battery life, and continuously improve the test algorithm and model through the feedback mechanism to obtain test records, diagnostic results and maintenance actions, and encrypt and archive the test records, diagnostic results and maintenance actions, follow the privacy policy to protect user information security, and understand customer satisfaction through regular return visits to optimize the service process. The specific steps are: based on the data in the battery health status report sent to the user the most recent time, including the historical trend chart and current status of the key parameters of battery health status, remaining power, voltage, current, temperature and internal resistance, in-depth analysis is performed; the user's usage habits and driving conditions are collected and combined with the battery health status data, and the expression is: ; in, is the battery life index, is the number of days of use, It is The intensity of daily use, is the average usage intensity, is the number of charging times, It is Energy input per charge, is the average charging energy, is the number of environmental factors, It is The weight of the impact of environmental factors, is the average environmental impact weight; based on the above analysis results, formulate the optimal maintenance plan and personalized maintenance plan.

[0011] In a second aspect, the present invention provides a battery testing system for new energy vehicle maintenance, including a safety connection and self-test module, a data acquisition and preliminary processing module, a multi-parameter comprehensive evaluation module, an intelligent diagnosis module, a remote monitoring and early warning module, a personalized maintenance plan module, and a data encryption and customer feedback module; the safety connection and self-test module is used to start the battery testing equipment, establish a safety connection with the battery management system of the new energy vehicle to be tested through a standard communication protocol, and automatically execute a series of self-test programs to check the functional integrity of the hardware components and calibrate the environmental conditions; the data acquisition and preliminary processing module is used to collect data on voltage, current, temperature and internal resistance parameters of the battery during operation from the BMS in real time after the system initialization is completed, store the data in a local database and upload it to a cloud server synchronously, and at the same time perform preliminary filtering and cleaning on the data to remove noise and outliers to obtain a set of high-quality initial data sets; the multi-parameter comprehensive evaluation module is used to estimate the battery health status and remaining power based on the high-quality initial data set obtained by the above preliminary analysis, and the model adopts a machine learning algorithm for processing The intelligent diagnosis module is used to use the intelligent diagnosis algorithm to deeply analyze the obtained battery status information, identify potential faults or abnormal modes, generate detailed fault reports, point out the specific fault location and possible causes, and provide targeted maintenance suggestions; the remote monitoring and early warning module is used to execute maintenance suggestions through the intelligent diagnosis algorithm, maintain a continuous data stream for remote monitoring of the battery status, immediately notify relevant personnel when early warning conditions are detected, and provide emergency response guidelines, and regularly send reports containing the latest battery health status to users; the personalized maintenance plan module is used to formulate the best maintenance plan based on the user's usage habits and driving conditions, personalize the maintenance plan to extend the battery life, and continuously improve the test algorithm and model through the feedback mechanism to obtain test records, diagnostic results and maintenance actions; the data encryption and customer feedback module is used to encrypt and archive the test records, diagnostic results and maintenance actions, follow the privacy policy to protect user information security, and understand customer satisfaction through regular return visits to further optimize the service process.

[0012] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the new energy vehicle maintenance battery testing method as described in the first aspect of the present invention is implemented.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for testing batteries for repairing new energy vehicles as described in the first aspect of the present invention is implemented.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The system uses the CAN bus to establish a secure connection with the battery management system, and performs equipment self-test and environmental calibration to ensure the stability and reliability of data collection. It monitors and records the key parameters of the battery in real time through high-precision sensors. The data is not only stored in the local database, but also uploaded to the cloud server simultaneously. After preliminary filtering and cleaning, a high-quality initial data set is formed. The system formulates personalized maintenance plans based on the user's usage habits and driving conditions to extend the battery life, and continuously improves the test algorithms and models through feedback mechanisms. All test records, diagnostic results and maintenance actions are encrypted and archived to strictly protect user information security. Through regular return visits to understand customer satisfaction, the service process is further optimized, which not only improves the accuracy of battery status assessment, but also improves user experience and service quality, providing strong technical support for the efficient maintenance of new energy vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of the battery testing method for new energy vehicle maintenance; Figure 2 This is a schematic diagram of the battery testing system for new energy vehicle maintenance. DETAILED DESCRIPTION

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0018] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0019] Example 1 See also Figure 1-2, which is the first embodiment of the present invention, provides a battery testing system and a testing method for new energy vehicle maintenance, including: S1. Start the battery test equipment, establish a secure connection with the battery management system of the new energy vehicle to be tested through the standard communication protocol, and perform equipment self-test and environmental calibration at the same time; Specifically, start the battery testing equipment, establish a secure connection with the battery management system of the new energy vehicle to be tested through the standard communication protocol, and perform equipment self-test and environmental calibration at the same time. The specific steps are: first, use the CAN bus as the standard communication protocol to establish a secure connection with the battery management system of the new energy vehicle to be tested; the equipment automatically executes a series of self-test procedures to check the functional integrity of hardware components, including the power module, sensor interface and communication interface, and calibrates the environmental conditions.

[0020] It should be noted that the use of CAN bus as the standard communication protocol ensures the stability and efficiency of establishing a secure connection with the battery management system (BMS) of new energy vehicles. The self-test program not only checks the functional integrity of the hardware components, but also compensates for the influence of external factors such as temperature and humidity on sensor accuracy through environmental calibration, thereby ensuring the accuracy of subsequent data collection.

[0021] S2. After the system is initialized, the voltage, current, temperature and internal resistance data of the battery during operation are collected from the BMS. The data is stored in the local database and uploaded to the cloud server simultaneously. At the same time, the data is initially filtered and cleaned to remove noise and outliers to obtain a set of high-quality initial data sets. Specifically, after the system is initialized, data on multiple parameters such as voltage, current, temperature and internal resistance during battery operation are collected from the BMS, stored in the local database and uploaded to the cloud server synchronously, and the data is preliminarily filtered and cleaned to remove noise and outliers to obtain a set of high-quality initial data sets. The specific steps are: use high-precision sensors to monitor and record the voltage, current, temperature and internal resistance data of each battery cell in real time; all collected data are first stored in the local database to ensure that the original data can be retained even when the network connection is unstable; the collected data is denoised and outliers are removed to obtain a set of high-quality initial data sets.

[0022] It should be noted that the application of high-precision sensors ensures the accuracy and reliability of data collection. The dual storage mechanism of local database and cloud server ensures that the original data can be retained even in the case of unstable network to prevent data loss. The preliminary filtering and cleaning steps effectively remove noise and outliers, improve data quality, and provide a reliable basis for subsequent analysis.

[0023] S3. Based on the high-quality initial data set obtained from the above preliminary analysis, a pre-trained multi-parameter comprehensive evaluation model is applied to estimate the battery health status and remaining power. The model uses a machine learning algorithm to handle complex nonlinear relationships, dynamically adjusts the prediction results, and finally outputs the battery status information; Specifically, based on the high-quality initial data set obtained from the preliminary analysis above, a pre-trained multi-parameter comprehensive evaluation model is used to estimate the battery health status and remaining power. The model uses a machine learning algorithm to process complex nonlinear relationships, dynamically adjusts the prediction results, and finally outputs the battery status information. The specific steps are as follows: First, Each data point in is sorted according to the four dimensions of voltage, current, temperature and internal resistance to form a multidimensional feature vector ; Use the random forest model for each feature vector The evaluation is performed to identify the complex interactions between different features, thereby accurately estimating the battery's state of health and remaining capacity, expressed as: ; ; in, Indicates the battery health status. Indicates the remaining battery power. By voltage Current ,temperature and internal resistance The multidimensional feature vector composed of is the random forest function used to estimate SOH, is another random forest output calculated from the eigenvector, yes The adjustment coefficient, yes The offset of yes The adjustment coefficient, yes The offset of The function is used to map the prediction results to the [0,1] interval.

[0024] It should be noted that the random forest model was chosen based on its ability to handle nonlinear relationships and capture complex interactions. The model has been trained with a large amount of historical data and can dynamically adjust the prediction results to provide more accurate battery state of health (SOH) and remaining capacity (SOC) estimates. The application of the hyperbolic tangent function enables the output results to be smoothly mapped to the [0,1] interval, enhancing the interpretability and stability of the prediction results.

[0025] S4. Use intelligent diagnostic algorithms to deeply analyze the obtained battery status information, identify potential faults or abnormal modes, generate detailed fault reports, point out the specific fault location and possible causes, and provide targeted maintenance suggestions; Specifically, the intelligent diagnosis algorithm is used to deeply analyze the obtained battery status information, identify potential faults or abnormal modes, generate a detailed fault report, point out the specific fault location and possible causes, and provide targeted maintenance suggestions. The specific steps are as follows: the battery status information obtained from the multi-parameter comprehensive evaluation model and , as well as the previously collected high-dimensional feature vectors of voltage, current, temperature and internal resistance As input; use the pre-trained mixture model for each feature vector Analysis is performed to extract local features and capture long-term dependencies in time series. The expression is: ; in, is the failure probability index corresponding to the i-th eigenvector, It is feature vectors, is the convolutional neural network output, is the LSTM network output, is the adjustment coefficient of the convolutional neural network output, is the adjustment coefficient of the LSTM output, is the offset.

[0026] It should be noted that the hybrid model combines convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), which can not only extract local features, but also capture long-term dependencies in time series, thereby more comprehensively identifying potential faults or abnormal patterns. The calculation method of the fault probability index quantifies the possibility of faults corresponding to each feature vector, thereby improving the accuracy and reliability of fault diagnosis.

[0027] S5. Execute maintenance recommendations through intelligent diagnostic algorithms, maintain a continuous data stream for remote monitoring of battery status, immediately notify relevant personnel when warning conditions are detected, provide emergency response guidance, and regularly send reports to users containing the latest battery health status; Specifically, maintenance recommendations are implemented through intelligent diagnostic algorithms, and a continuous data stream is maintained for remote monitoring of battery status. When warning conditions are detected, relevant personnel are notified immediately, and emergency response guidelines are provided. Reports containing the latest battery health status are sent to users regularly. The specific steps are as follows: Based on the maintenance recommendations in the fault report generated by the intelligent diagnostic algorithm, technicians take specific maintenance actions, as follows: The report indicates that a battery module is at risk of overheating, and it is recommended to replace the module or adjust its cooling system. After the maintenance is completed, the updated battery status information will be re-incorporated into the monitoring system to evaluate the maintenance effect; Real-time remote monitoring is achieved, and the system maintains a stable and uninterrupted data transmission channel, including real-time collection of key parameters such as voltage, current, temperature and internal resistance from the battery management system, and uploads them to the cloud server through a secure encryption protocol, and selects MQTT as the communication protocol; The early warning system runs on the cloud server. The system analyzes the incoming data in real time based on preset thresholds and pattern recognition algorithms. The expression is: ; in, It is the early warning index. is the current voltage, is the current, is the current temperature, is the current internal resistance, is the reference voltage, is the reference current, is the reference temperature, is the reference internal resistance, is the standard deviation of the voltage, is the standard deviation of the current, is the standard deviation of temperature, is the standard deviation of the internal resistance.

[0028] It should be noted that the choice of MQTT protocol ensures low latency and high reliability of real-time data transmission. The introduction of the early warning system realizes real-time analysis of incoming data, timely detection and response to early warning conditions, and ensures the safe operation of the vehicle. The emergency response guide and regular report sending functions enhance the user's understanding and control of the battery status.

[0029] S6. Develop the best maintenance plan based on the latest battery health report, combined with the user's usage habits and driving conditions, and customize the maintenance plan to extend the battery life. Through the feedback mechanism, the test algorithm and model are continuously improved to obtain test records, diagnostic results and maintenance actions. The test records, diagnostic results and maintenance actions are encrypted and archived, and the privacy policy is followed to protect the user's information security. Regular return visits are conducted to understand customer satisfaction and optimize the service process. Specifically, through the latest battery health status report, combined with the user's usage habits and driving conditions, the optimal maintenance plan is formulated, and the maintenance plan is customized to extend the battery life. The test algorithm and model are continuously improved through the feedback mechanism to obtain test records, diagnostic results and maintenance actions. The test records, diagnostic results and maintenance actions are encrypted and archived, and the privacy policy is followed to protect user information security. Customer satisfaction is understood through regular return visits and the service process is optimized. The specific steps are: based on the data in the battery health status report sent to the user the most recent time, including the historical trend chart and current status of the key parameters of battery health status, remaining power, voltage, current, temperature and internal resistance, in-depth analysis is performed; the user's usage habits and driving conditions are collected and combined with the battery health status data. The expression is: ; in, is the battery life index, is the number of days of use, It is The intensity of daily use, is the average usage intensity, is the number of charging times, It is Energy input per charge, is the average charging energy, is the number of environmental factors, It is The weight of the impact of environmental factors, is the average environmental impact weight; based on the above analysis results, formulate the optimal maintenance plan and personalized maintenance plan.

[0030] It should be noted that by formulating personalized maintenance plans based on the user's usage habits and driving conditions, not only the battery life is extended, but also the user experience and service satisfaction are improved. The encrypted archiving measures follow a strict privacy policy and protect the security of user information. The regular follow-up mechanism helps to continuously optimize service processes and technical solutions, forming a closed-loop feedback system and promoting the system's self-evolution and improvement.

[0031] This embodiment also provides a computer device, which is applicable to the case of a battery testing method for new energy vehicle maintenance, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the battery testing method for new energy vehicle maintenance proposed in the above embodiment.

[0032] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0033] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for testing batteries for repairing new energy vehicles proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0034] In summary, the system uses the CAN bus to establish a secure connection with the battery management system, and performs equipment self-test and environmental calibration to ensure the stability and reliability of data collection. High-precision sensors are used to monitor and record key battery parameters in real time. The data is not only stored in the local database, but also uploaded to the cloud server simultaneously. After preliminary filtering and cleaning, a high-quality initial data set is formed. The system formulates personalized maintenance plans based on the user's usage habits and driving conditions to extend the battery life, and continuously improves the test algorithms and models through feedback mechanisms. All test records, diagnostic results and maintenance actions are encrypted and archived to strictly protect user information security. Through regular return visits, customer satisfaction is understood and service processes are further optimized, which not only improves the accuracy of battery status assessment, but also improves user experience and service quality, providing strong technical support for the efficient maintenance of new energy vehicles.

[0035] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A battery testing method for new energy vehicle maintenance, characterized in that: include: Start the battery test equipment, establish a secure connection with the battery management system of the new energy vehicle to be tested through the standard communication protocol, and perform equipment self-test and environmental calibration at the same time; After the system is initialized, the voltage, current, temperature and internal resistance data of multiple parameters during battery operation are collected from the BMS. The data is stored in the local database and uploaded to the cloud server simultaneously. At the same time, the data is initially filtered and cleaned to remove noise and outliers to obtain a set of high-quality initial data sets. Based on the high-quality initial data set obtained from the preliminary analysis above, a pre-trained multi-parameter comprehensive evaluation model is used to estimate the battery health status and remaining power. The model uses a machine learning algorithm to handle complex nonlinear relationships, dynamically adjusts the prediction results, and finally outputs the battery status information; Use intelligent diagnostic algorithms to deeply analyze the obtained battery status information, identify potential faults or abnormal modes, generate detailed fault reports, point out the specific fault location and possible causes, and provide targeted maintenance suggestions; Execute maintenance recommendations through intelligent diagnostic algorithms, maintain a continuous data stream for remote monitoring of battery status, immediately notify relevant personnel when warning conditions are detected, provide emergency response guidance, and regularly send users reports containing the latest battery health status; Through the latest battery health status report, combined with the user's usage habits and driving conditions, the optimal maintenance plan is formulated, and the maintenance plan is personalized to extend the battery life. The test algorithm and model are continuously improved through the feedback mechanism to obtain test records, diagnostic results and maintenance actions. The test records, diagnostic results and maintenance actions are encrypted and archived, and the privacy policy is followed to protect the security of user information. Through regular return visits, we understand customer satisfaction and optimize service processes.

2. The method for testing a battery for maintenance of a new energy vehicle according to claim 1, characterized in that: The battery test equipment is started to establish a secure connection with the battery management system of the new energy vehicle to be tested through a standard communication protocol, and the equipment self-test and environmental calibration are performed at the same time. The specific steps are as follows: First, use the CAN bus as a standard communication protocol to establish a secure connection with the battery management system of the new energy vehicle to be tested; The device automatically performs a series of self-test procedures to check the functional integrity of hardware components, including the power module, sensor interfaces, and communication interfaces, and calibrate environmental conditions.

3. The method for testing a battery for maintenance of a new energy vehicle according to claim 1, characterized in that: After the system is initialized, the voltage, current, temperature and internal resistance of the battery are collected from the BMS during operation. The data is stored in the local database and uploaded to the cloud server simultaneously. At the same time, the data is initially filtered and cleaned to remove noise and outliers to obtain a set of high-quality initial data sets. The specific steps are as follows: Use high-precision sensors to monitor and record the voltage, current, temperature and internal resistance data of each battery cell in real time; All collected data is first stored in a local database to ensure that the original data is retained even when the network connection is unstable; The collected data is denoised and outliers are removed to obtain a set of high-quality initial data sets.

4. The method for testing a battery for maintenance of a new energy vehicle according to claim 1, characterized in that: Based on the high-quality initial data set obtained from the preliminary analysis, a pre-trained multi-parameter comprehensive evaluation model is used to estimate the battery health status and remaining power. The model uses a machine learning algorithm to process complex nonlinear relationships, dynamically adjusts the prediction results, and finally outputs the battery status information. The specific steps are as follows: First, Each data point in is sorted according to the four dimensions of voltage, current, temperature and internal resistance to form a multidimensional feature vector ; Use the random forest model to train each feature vector The evaluation is performed to identify the complex interactions between different features, thereby accurately estimating the battery's state of health and remaining capacity, expressed as: ; ; in, Indicates the battery health status. Indicates the remaining battery power. By voltage Current ,temperature and internal resistance The multidimensional feature vector composed of is the random forest function used to estimate SOH, is another random forest output calculated from the eigenvector, yes The adjustment coefficient, yes The offset of yes The adjustment coefficient, yes The offset of The function is used to map the prediction results to the [0,1] interval.

5. The method for testing batteries for new energy vehicle maintenance according to claim 1, characterized in that: The intelligent diagnosis algorithm is used to deeply analyze the obtained battery status information, identify potential faults or abnormal modes, generate a detailed fault report, point out the specific fault location and possible causes, and provide targeted maintenance suggestions. The specific steps are as follows: The battery status information obtained from the multi-parameter comprehensive evaluation model and , as well as the previously collected high-dimensional feature vectors of voltage, current, temperature and internal resistance As input; Use the pre-trained mixture model to train each feature vector Analysis is performed to extract local features and capture long-term dependencies in time series. The expression is: ; in, is the failure probability index corresponding to the i-th eigenvector, It is feature vectors, is the convolutional neural network output, is the LSTM network output, is the adjustment coefficient of the convolutional neural network output, is the adjustment coefficient of the LSTM output, is the offset.

6. The method for testing a battery for repairing a new energy vehicle according to claim 1, characterized in that: The maintenance recommendations are executed through intelligent diagnostic algorithms, a continuous data stream is maintained for remote monitoring of battery status, relevant personnel are notified immediately when warning conditions are detected, emergency response guidance is provided, and reports containing the latest battery health status are sent to users regularly. The specific steps are as follows: Based on the maintenance recommendations in the fault report generated by the intelligent diagnosis algorithm, the technician takes specific maintenance actions, as follows: The report indicates that a battery module is at risk of overheating and recommends replacing the module or adjusting its cooling system. After the repair is completed, the updated battery status information will be re-incorporated into the monitoring system to evaluate the repair effect; To achieve real-time remote monitoring, the system maintains a stable and uninterrupted data transmission channel, including real-time collection of key parameters such as voltage, current, temperature and internal resistance from the battery management system, and uploads them to the cloud server through a secure encryption protocol, selecting MQTT as the communication protocol; The early warning system runs on the cloud server. The system analyzes the incoming data in real time based on the preset threshold and pattern recognition algorithm. The expression is: ; in, It is the early warning index. is the current voltage, is the current, is the current temperature, is the current internal resistance, is the reference voltage, is the reference current, is the reference temperature, is the reference internal resistance, is the standard deviation of the voltage, is the standard deviation of the current, is the standard deviation of temperature, is the standard deviation of the internal resistance.

7. The method for testing a battery for repairing a new energy vehicle according to claim 1, characterized in that: The latest battery health status report is combined with the user's usage habits and driving conditions to develop the best maintenance plan, personalize the maintenance plan to extend the battery life, and continuously improve the test algorithm and model through the feedback mechanism to obtain test records, diagnostic results and maintenance actions. The test records, diagnostic results and maintenance actions are encrypted and archived, and the privacy policy is followed to protect user information security. Regular return visits are conducted to understand customer satisfaction and optimize service processes. The specific steps are as follows: Based on the data in the most recent battery health report sent to the user, including historical trend charts and current status of key parameters such as battery health status, remaining power, voltage, current, temperature and internal resistance, in-depth analysis is performed; Collect the user's usage habits and driving conditions and combine them with the battery health data to form the expression: ; in, is the battery life index, is the number of days of use, It is The intensity of daily use, is the average usage intensity, is the number of charging times, It is Energy input per charge, is the average charging energy, is the number of environmental factors, It is The weight of the impact of environmental factors, is the average environmental impact weight; Based on the above analysis results, formulate the optimal repair plan and personalized maintenance plan.

8. A battery testing system for new energy vehicle maintenance, based on the battery testing method for new energy vehicle maintenance according to any one of claims 1 to 7, characterized in that: It includes a secure connection and self-checking module, a data acquisition and preliminary processing module, a multi-parameter comprehensive evaluation module, an intelligent diagnosis module, a remote monitoring and early warning module, a personalized maintenance plan module, and a data encryption and customer feedback module; The safety connection and self-test module is used to start the battery test equipment, establish a safety connection with the battery management system of the new energy vehicle to be tested through a standard communication protocol, and automatically execute a series of self-test procedures to check the functional integrity of the hardware components and calibrate the environmental conditions; The data acquisition and preliminary processing module is used to collect data on voltage, current, temperature and internal resistance parameters of the battery during operation from the BMS in real time after the system initialization is completed, store the data in a local database and upload it to the cloud server synchronously, and perform preliminary filtering and cleaning on the data to remove noise and outliers to obtain a set of high-quality initial data sets; The multi-parameter comprehensive evaluation module is used to estimate the battery health status and remaining power based on the high-quality initial data set obtained by the preliminary analysis, using a pre-trained multi-parameter comprehensive evaluation model. The model uses a machine learning algorithm to process complex nonlinear relationships, dynamically adjusts the prediction results, and finally outputs the battery status information; The intelligent diagnosis module is used to use intelligent diagnosis algorithms to deeply analyze the obtained battery status information, identify potential faults or abnormal modes, generate detailed fault reports, point out the specific fault location and possible causes, and provide targeted maintenance suggestions; The remote monitoring and warning module is used to execute maintenance recommendations through intelligent diagnostic algorithms, maintain a continuous data stream for remote monitoring of battery status, immediately notify relevant personnel when warning conditions are detected, provide emergency response guidance, and regularly send reports to users containing the latest battery health status; The personalized maintenance plan module is used to formulate the best maintenance plan based on the user's usage habits and driving conditions, customize the maintenance plan to extend the battery life, and continuously improve the test algorithm and model through the feedback mechanism to obtain test records, diagnostic results and maintenance actions; The data encryption and customer feedback module is used to encrypt and archive test records, diagnostic results and maintenance actions, follow the privacy policy to protect user information security, and understand customer satisfaction through regular return visits to further optimize service processes.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the new energy vehicle maintenance battery testing method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the new energy vehicle maintenance battery testing method according to any one of claims 1 to 7 are implemented.

Images