Battery life remote detection system and method based on charging data intelligent analysis

Abstract

The invention discloses a battery life remote detection system and method based on charging data intelligent analysis, and relates to the technical field of battery life analysis, data acquisition of the battery life remote detection system is realized based on push data of a charging pile platform, and battery charging order data pushed by the charging pile platform is received; and when the charging of the user at the charging pile is completed, a supplier of the charging pile platform pushes heartbeat data to the battery life remote detection system, and data and change trend of key information such as voltage, current and power in the charging process are obtained through the obtained battery charging order data. According to the method, before the battery life analysis process is entered, the validity of the order needs to be confirmed firstly, it is ensured that the charging data of each vehicle is accurately classified, the battery performance is accurately judged, the battery life is accurately predicted during charging, the battery life state can be more accurately evaluated from the macroscopic perspective, and the battery life analysis efficiency is improved. Therefore, the user experience is optimized and the service life of the battery is effectively prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of battery life analysis, and in particular to a battery life remote detection system and method based on intelligent analysis of charging data. Background Art

[0002] As electric bicycles become more and more popular, the reliability of their charging equipment and the durability of their batteries have become particularly important. At present, the common battery life methods on the market mostly rely on manual operations for detection and maintenance, which is not only inefficient, but also prone to omissions and misjudgments, and cannot meet the growing needs of users. In addition, the prediction of battery life is usually based on basic indicators such as the number of charging times, usage time, and charging time. These methods often cannot provide accurate information about the actual performance status of the battery, causing users to face uncertainty and potential safety risks during use. Therefore, the development of a more efficient and accurate battery life analysis system has become an urgent problem that the industry needs to solve. Summary of the invention

[0003] In order to solve the technical problem of analyzing the battery life of electric bicycles, the present invention provides a battery life remote detection system and method based on intelligent analysis of charging data. The following technical solutions are adopted:

[0004] The method for remotely detecting battery life based on intelligent analysis of charging data includes the following steps:

[0005] Step 1: Data collection: the battery life remote detection system receives the battery charging order data pushed by the charging pile platform;

[0006] Step 2, data validity check, the battery life remote detection system determines whether the collected battery charging order data is valid based on the set charging time threshold and the characteristics of the charging power curve in the historical battery charging order data;

[0007] Step 3, if it is determined in step 2 that the battery charging order data is valid, the battery charging order data is parsed, the battery characteristics are identified, and the pre-stored battery life rules are obtained based on the battery characteristic identification results, and the indicators required in the analysis process are obtained according to the battery life rules, and the indicators refer to the effective charging time and the effective charging power range;

[0008] Step 4, effective charging time calculation: based on the battery charging order data obtained in step 1 and the effective charging power range obtained in step 3, the charging time within the effective charging power range in all charging heartbeat data is determined in turn, and the total effective charging time of the battery charging order data is calculated cumulatively;

[0009] Step 5, battery life detection, based on the battery effective charging time in the battery life analysis rule in step 3 and the total effective charging time of the battery calculated in step 4, the battery life is determined.

[0010] Optionally, in step 1, the battery charging order data includes multiple charging heartbeat data based on a time series, and the charging heartbeat data includes performance parameters of the electric bicycle battery during charging, timestamp data of each data push, and identification information data of the device.

[0011] By adopting the above technical solution, the data collection of the battery life remote detection system is realized based on the push data of the charging pile platform. It can use the IoT sensing technology in the Internet of Things to receive the battery charging order data pushed by the charging pile platform, which comes from the charging process of the user's electric bicycle. The heartbeat data not only records the key performance parameters of the electric bicycle charging process, such as voltage, current, power value and the timestamp of each data push, but also includes the identification information of the user and the device, such as user ID, supplier ID and order number.

[0012] When the user completes charging at the charging pile, the supplier of the charging pile platform will push heartbeat data to the battery life remote detection system, which contains a specific flag that clearly indicates that the charging process has ended. Based on the user identification and order information carried in this heartbeat data, the battery life remote detection system retrieves all the time-series-based heartbeat data records accumulated since the battery charging order data was started in the back-end database, and constructs a complete battery charging order data. Through the obtained battery charging order data, the data and change trends of key information such as voltage, current, and power during the charging process can be obtained, thereby providing an information basis for subsequent judgments.

[0013] Before entering the battery life analysis process, the validity of the order must be confirmed first. The standard is defined as: the charging time of the battery charging order data must be greater than the set threshold. If the battery charging order data does not meet this validity standard, the program will be terminated and will not enter the subsequent judgment process; on the contrary, if the conditions are met, the system will continue to execute the subsequent battery life judgment logic.

[0014] At the same time, it is crucial to identify the situation where a single user owns multiple vehicles and classify the data, because the charging data of different vehicles may have significant differences. If these differences are not correctly distinguished, they may lead to confusion and misjudgment of the analysis results. Therefore, by analyzing the characteristics of the charging power curve in the user's historical battery charging order data, the system can effectively distinguish and identify the batteries of multiple electric bicycles owned by the user. This step ensures that the charging data of each vehicle is accurately classified, providing an accurate data basis for each specific order. Subsequently, these classified order data will be sent to the subsequent processing flow for detailed analysis to accurately judge the battery performance. In this way, we can avoid data confusion caused by users owning multiple vehicles and ensure the accuracy and reliability of battery life analysis.

[0015] Optionally, step 2 includes the following sub-steps:

[0016] Step 21, charging time threshold determination, assuming that the battery charging time obtained from the battery charging order data is T total , assuming the charging time threshold is T m , if T total >T m Then continue to judge;

[0017] Step 22, analyzing whether the characteristics of the battery charging power curve in the battery charging order data match the characteristics of the corresponding battery charging power curve in the historical battery charging order data of the corresponding user. If they match, the battery charging order data is judged to be valid, otherwise it is judged to be invalid.

[0018] Optionally, if the characteristics of the charging power curve of the battery in the battery charging order data in step 22 do not match the characteristics of the corresponding battery charging power curve in the historical battery charging order data of the corresponding user, and if there is no successful match in multiple battery charging order data of the corresponding user, a judgment result that the battery charging order data is invalid is output;

[0019] If there is a battery charging power curve feature match with one of the multiple battery charging order data in the historical battery charging order data of the corresponding user, step 3 uses the corresponding successfully matched battery data to obtain battery life rules.

[0020] By adopting the above technical solution, the specific charging time threshold T m Can be set to 3 hours, when the battery is charged for a long time T total If the time is greater than 3 hours, the curve feature matching judgment of step 22 will be continued;

[0021] The subsequent characteristic matching of the charging power curve can be achieved by the following specific methods:

[0022] Extract the statistical features of the charging power curve, such as the average, maximum, minimum, standard deviation, median, etc. Analyze the shape characteristics of the curve, such as the rising slope, falling slope, inflection point, peak and valley value, etc.

[0023] Analyze the time series dynamic characteristics of the power curve, such as the changing trend of the charging rate, the division of the charging stages, etc., and calculate the Euclidean distance between the two sets of power curve feature vectors. The smaller the distance, the higher the similarity. Cosine similarity: measures the directional similarity of the two sets of feature vectors. The closer the value is to 1, the more similar they are.

[0024] It is also possible to train historical data based on machine learning methods using supervised learning algorithms (such as support vector machines, random forests, neural networks, etc.), and classify new charging curves after building a model to determine whether they match historical data.

[0025] Optionally, in step 4, the method for calculating the total effective charging time is:

[0026] The maximum power during the charging process is multiplied by the effective charging power percentage to obtain the effective charging power range. The system traverses each charging heartbeat data of the battery charging order data to evaluate whether the power value in the charging heartbeat data falls within the effective charging power range. The duration of the qualified records will be accumulated to calculate the total effective charging time T of the entire order. effcient .

[0027] Optionally, set the maximum power P during charging max , the maximum effective charging power percentage is a up , the minimum effective charging power percentage is a down , the maximum effective charging power in the effective charging power range is P up , the minimum effective charging power is P down ;

[0028] Then P up =P max ·a up ;P down =P max ·a down ;

[0029] The effective charging power range is P down —P up .

[0030] By adopting the above technical solution, it is important to note that when analyzing the duration within the maximum power range and the abnormal power range, since the power curve is essentially a scatter plot composed of heartbeat data points, at the code implementation level, the calculation of the duration is actually approximated by calculating the time difference between adjacent data points and accumulating them. This method of calculating the duration is an approximate calculation method, but it has been proven to be effective and practical in actual applications, and can provide reliable data support for battery life evaluation.

[0031] Optionally, in step 5, the specific method for determining the battery life is: after completing the traversal of all heartbeat data, compare the total effective charging time with the target effective charging time T in the indicator. target For comparison, if T effcient <T target , then it is judged that the battery corresponding to the battery charging order data has a normal life, and the accumulated days and order quantity within the evaluation period are reset; otherwise, it is judged that the battery corresponding to the battery charging order data has a battery life problem, and the days and order quantity are accumulated.

[0032] By adopting the above technical solution, the normal life standard of the battery is determined according to the type of battery and the data provided by the manufacturer. This usually includes the expected cycle life (such as 500 times, 1000 times, etc.), the expected calendar life (such as 5 years, 10 years, etc.), and the total effective charging time divided by the number of charges to obtain the average charging time per time. Estimated number of cycles: Divide the total effective charging time by the average charging time to obtain the approximate number of cycles of the battery. Compare the estimated number of cycles with the expected cycle life of the battery. If the estimated number of cycles is much lower than the expected cycle life, it may indicate that the battery life is abnormal (premature decay). If the estimated number of cycles is close to or slightly lower than the expected cycle life, the battery life may be normal.

[0033] A battery life remote detection system based on intelligent analysis of charging data is used to implement the battery life remote detection method based on intelligent analysis of charging data. The battery life remote detection system includes a charging data acquisition module and a charging data analysis module. The charging data acquisition module is communicatively connected to the charging pile platform to collect battery charging order data pushed by the charging pile platform. The charging data analysis module runs a detection program designed using the battery life remote detection method based on intelligent analysis of charging data, inputs the battery charging order data into the detection program, and the detection program outputs the battery life detection result.

[0034] Optionally, the charging data analysis module is connected to the charging pile platform for communication and the battery life test results output by the interactive detection program.

[0035] By adopting the above technical solution, the charging data acquisition module can directly communicate with the charging pile based on the Internet of Things technology to interact with the battery charging order data, and can also directly communicate with the charging pile platform to interact with the battery charging order data. The charging data analysis module is mainly implemented based on the server computer. The battery life test results of the server computer interact with the charging pile platform. The charging pile platform can communicate with the electric bicycle corresponding to the connected battery to feedback the battery life test results, thereby realizing accurate prediction of the battery life during charging.

[0036] In summary, the present invention includes at least one of the following beneficial technical effects:

[0037] The present invention can provide a remote detection system and method for battery life based on intelligent analysis of charging data. The data collection of the remote detection system for battery life is realized based on the push data of the charging pile platform, and the battery charging order data pushed by the charging pile platform is received. When the user completes charging at the charging pile, the supplier of the charging pile platform will push the heartbeat data to the remote detection system for battery life. Through the obtained battery charging order data, the data of key information such as voltage, current, power, etc. during the charging process and the change trend are obtained, thereby providing an information basis for subsequent judgments.

[0038] Before entering the battery life analysis process, the validity of the order must be confirmed first to ensure that the charging data of each vehicle is accurately classified, providing an accurate data basis for each specific order. Subsequently, these classified order data will be sent to the subsequent processing flow for detailed analysis, so as to accurately judge the battery performance and accurately predict the battery life during charging. It can more accurately evaluate the battery life status from a macro perspective, thereby optimizing the user experience and effectively extending the battery life. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of a method for remotely detecting battery life based on intelligent analysis of charging data of the present invention. DETAILED DESCRIPTION

[0040] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0041] The embodiment of the present invention discloses a battery life remote detection system and method based on intelligent analysis of charging data.

[0042] Reference Figure 1 , a battery life remote detection method based on intelligent analysis of charging data, comprising the following steps:

[0043] Step 1: Data collection: the battery life remote detection system receives the battery charging order data pushed by the charging pile platform;

[0044] Step 2, data validity check, the battery life remote detection system determines whether the collected battery charging order data is valid based on the set charging time threshold and the characteristics of the charging power curve in the historical battery charging order data;

[0045] Step 3, if it is determined in step 2 that the battery charging order data is valid, the battery charging order data is parsed, the battery characteristics are identified, and the pre-stored battery life rules are obtained based on the battery characteristic identification results, and the indicators required in the analysis process are obtained according to the battery life rules, and the indicators refer to the effective charging time and the effective charging power range;

[0046] Step 4, effective charging time calculation: based on the battery charging order data obtained in step 1 and the effective charging power range obtained in step 3, the charging time within the effective charging power range in all charging heartbeat data is determined in turn, and the total effective charging time of the battery charging order data is calculated cumulatively;

[0047] Step 5, battery life detection, based on the battery effective charging time in the battery life analysis rule in step 3 and the total effective charging time of the battery calculated in step 4, the battery life is determined.

[0048] In step 1, the battery charging order data includes multiple charging heartbeat data based on time series, and the charging heartbeat data includes performance parameters of the electric bicycle battery during charging, timestamp data of each data push, and identification information data of the device.

[0049] The data collection of the battery life remote detection system is based on the push data of the charging pile platform. It can use the IoT sensing technology in the Internet of Things to receive the battery charging order data pushed by the charging pile platform. These data come from the charging process of the user's electric bicycle. The heartbeat data not only records the key performance parameters of the electric bicycle charging process, such as voltage, current, power value and the timestamp of each data push, but also includes the identification information of the user and the device, such as user ID, supplier ID and order number.

[0050] When the user completes charging at the charging pile, the supplier of the charging pile platform will push heartbeat data to the battery life remote detection system, which contains a specific flag that clearly indicates that the charging process has ended. Based on the user identification and order information carried in this heartbeat data, the battery life remote detection system retrieves all the time-series-based heartbeat data records accumulated since the battery charging order data was started in the back-end database, and constructs a complete battery charging order data. Through the obtained battery charging order data, the data and change trends of key information such as voltage, current, and power during the charging process can be obtained, thereby providing an information basis for subsequent judgments.

[0051] Before entering the battery life analysis process, the validity of the order must be confirmed first. The standard is defined as: the charging time of the battery charging order data must be greater than the set threshold. If the battery charging order data does not meet this validity standard, the program will be terminated and will not enter the subsequent judgment process; on the contrary, if the conditions are met, the system will continue to execute the subsequent battery life judgment logic.

[0052] At the same time, it is crucial to identify the situation where a single user owns multiple vehicles and classify the data, because the charging data of different vehicles may have significant differences. If these differences are not correctly distinguished, they may lead to confusion and misjudgment of the analysis results. Therefore, by analyzing the characteristics of the charging power curve in the user's historical battery charging order data, the system can effectively distinguish and identify the batteries of multiple electric bicycles owned by the user. This step ensures that the charging data of each vehicle is accurately classified, providing an accurate data basis for each specific order. Subsequently, these classified order data will be sent to the subsequent processing flow for detailed analysis to accurately judge the battery performance. In this way, we can avoid data confusion caused by users owning multiple vehicles and ensure the accuracy and reliability of battery life analysis.

[0053] Step 2 includes the following sub-steps:

[0054] Step 21, charging time threshold determination, assuming that the battery charging time obtained from the battery charging order data is T total , assuming the charging time threshold is T m , if T total >T m Then continue to judge;

[0055] Step 22, analyzing whether the characteristics of the battery charging power curve in the battery charging order data match the characteristics of the corresponding battery charging power curve in the historical battery charging order data of the corresponding user. If they match, the battery charging order data is judged to be valid, otherwise it is judged to be invalid.

[0056] If the characteristics of the charging power curve of the battery in the battery charging order data in step 22 do not match the characteristics of the corresponding battery charging power curve in the historical battery charging order data of the corresponding user, and if there is no successful match in the multiple battery charging order data of the corresponding user, then a judgment result that the battery charging order data is invalid is output;

[0057] If there is a battery charging power curve feature match with one of the multiple battery charging order data in the historical battery charging order data of the corresponding user, step 3 uses the corresponding successfully matched battery data to obtain battery life rules.

[0058] Specific charging time threshold T mCan be set to 3 hours, when the battery is charged for a long time T total If the time is greater than 3 hours, the curve feature matching judgment of step 22 will be continued;

[0059] The subsequent characteristic matching of the charging power curve can be achieved by the following specific methods:

[0060] Extract the statistical features of the charging power curve, such as the average, maximum, minimum, standard deviation, median, etc. Analyze the shape characteristics of the curve, such as the rising slope, falling slope, inflection point, peak and valley value, etc.

[0061] Analyze the time series dynamic characteristics of the power curve, such as the changing trend of the charging rate, the division of the charging stages, etc., and calculate the Euclidean distance between the two sets of power curve feature vectors. The smaller the distance, the higher the similarity. Cosine similarity: measures the directional similarity of the two sets of feature vectors. The closer the value is to 1, the more similar they are.

[0062] It is also possible to train historical data based on machine learning methods using supervised learning algorithms (such as support vector machines, random forests, neural networks, etc.), and classify new charging curves after building a model to determine whether they match historical data.

[0063] In step 4, the method for calculating the total effective charging time is:

[0064] The maximum power during the charging process is multiplied by the effective charging power percentage to obtain the effective charging power range. The system traverses each charging heartbeat data of the battery charging order data to evaluate whether the power value in the charging heartbeat data falls within the effective charging power range. The duration of the qualified records will be accumulated to calculate the total effective charging time T of the entire order. effcient .

[0065] Assume the maximum power P during charging max , the maximum effective charging power percentage is a up , the minimum effective charging power percentage is a down , the maximum effective charging power in the effective charging power range is P up , the minimum effective charging power is P down ;

[0066] Then P up =P max ·a up ;P down =P max ·a down ;

[0067] The effective charging power range is P down —P up .

[0068] It is important to note that when analyzing the duration within the maximum power range and the abnormal power range, since the power curve is essentially a scatter plot consisting of heartbeat data points, the duration calculation is actually approximated by calculating the time difference between adjacent data points and accumulating them at the code implementation level. This method of calculating duration is an approximate calculation method, but it has been proven to be effective and practical in actual applications, and can provide reliable data support for battery life evaluation.

[0069] In step 5, the specific method for determining the battery life is: after completing the traversal of all heartbeat data, the total effective charging time is compared with the target effective charging time T in the indicator. target For comparison, if T effcient <T target , then it is judged that the battery corresponding to the battery charging order data has a normal life, and the accumulated days and order quantity within the evaluation period are reset; otherwise, it is judged that the battery corresponding to the battery charging order data has a battery life problem, and the days and order quantity are accumulated.

[0070] Based on the type of battery and the data provided by the manufacturer, determine the normal life standard of the battery. This usually includes the expected cycle life (such as 500 times, 1000 times, etc.), the expected calendar life (such as 5 years, 10 years, etc.), and the total effective charging time divided by the number of charges to obtain the average charging time per charge. Estimated number of cycles: Divide the total effective charging time by the average charging time to obtain the approximate number of cycles of the battery. Compare the estimated number of cycles with the expected cycle life of the battery. If the estimated number of cycles is much lower than the expected cycle life, it may indicate that the battery life is abnormal (premature decay). If the estimated number of cycles is close to or slightly lower than the expected cycle life, the battery life may be normal.

[0071] A battery life remote detection system based on intelligent analysis of charging data is used to implement a battery life remote detection method based on intelligent analysis of charging data. The battery life remote detection system includes a charging data acquisition module and a charging data analysis module. The charging data acquisition module is communicated with the charging pile platform to collect battery charging order data pushed by the charging pile platform. The charging data analysis module runs a detection program designed for a battery life remote detection method based on intelligent analysis of charging data, inputs the battery charging order data into the detection program, and the detection program outputs the battery life detection result.

[0072] The charging data analysis module is connected to the charging pile platform for communication and the battery life test results output by the interactive detection program.

[0073] The charging data acquisition module can be based on the Internet of Things technology to directly communicate with the charging pile to interact with the battery charging order data, and can also directly communicate with the charging pile platform to interact with the battery charging order data. The charging data analysis module is mainly implemented based on the server computer. The battery life test results of the server computer interact with the charging pile platform. The charging pile platform can communicate with the electric bicycle corresponding to the connected battery to feedback the battery life test results, thereby realizing accurate prediction of the battery life during charging.

[0074] The following is an explanation of the principle of a remote battery life detection system and method based on intelligent analysis of charging data based on specific embodiments:

[0075] When a customer's electric bicycle is connected to a charging pile for charging, the supplier of the charging pile platform will push heartbeat data to the charging data acquisition module, which contains a specific flag that clearly indicates that the charging process has ended. Based on the user identification and order information carried in this heartbeat data, the server computer retrieves all the time-series-based heartbeat data records accumulated since the start of the battery charging order data in the back-end database, and constructs a complete battery charging order data. The obtained battery charging order data is used to obtain key information such as voltage, current, power, and change trends during the charging process.

[0076] First, determine the order validity and charging time threshold. Suppose the battery charging time obtained from the battery charging order data is T. total = 5 hours, assuming the charging time threshold is T m = 3 hours, T total >T m Continue to judge;

[0077] Analyze whether the characteristics of the battery charging power curve in the battery charging order data match the characteristics of the corresponding battery charging power curve in the historical battery charging order data of the corresponding user. Based on the machine learning method, use the supervised learning algorithm to train the historical data. After the model is established, classify the new charging curve. If the similarity with the battery charging power curve of the electric bicycle with the corresponding number in the historical data is greater than the set value, it is judged that it matches the historical data, and thus the order is determined to be valid;

[0078] The process for calculating the total effective charging time is as follows:

[0079] The maximum power during the charging process is multiplied by the effective charging power percentage to obtain the effective charging power range. The system traverses each charging heartbeat data of the battery charging order data to evaluate whether the power value in the charging heartbeat data falls within the effective charging power range. The duration of the qualified records will be accumulated to calculate the total effective charging time T of the entire order. effcient =1050 hours.

[0080] The recommended life of the battery of the corresponding numbered electric bicycle is estimated to be 1000 cycles (that is, 1000 full charges). The recommended time for each full charge is 6-8 hours. Taking 7 hours, the estimated target effective charging time T target =7000 hours, T effcient <T target , it is judged that the battery life of the electric bicycle corresponding to the current battery charging order data is normal.

[0081] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A remote battery life detection method based on intelligent analysis of charging data, characterized in that: The following steps are involved: Step 1: Data collection: the battery life remote detection system receives the battery charging order data pushed by the charging pile platform; Step 2, data validity check, the battery life remote detection system determines whether the collected battery charging order data is valid based on the set charging time threshold and the characteristics of the charging power curve in the historical battery charging order data; Step 3, if it is determined in step 2 that the battery charging order data is valid, the battery charging order data is parsed, the battery characteristics are identified, and the pre-stored battery life rules are obtained based on the battery characteristic identification results, and the indicators required in the analysis process are obtained according to the battery life rules, and the indicators refer to the effective charging time and the effective charging power range; Step 4, effective charging time calculation: based on the battery charging order data obtained in step 1 and the effective charging power range obtained in step 3, the charging time within the effective charging power range in all charging heartbeat data is determined in turn, and the total effective charging time of the battery charging order data is calculated cumulatively; Step 5, battery life detection, based on the battery effective charging time in the battery life analysis rule in step 3 and the total effective charging time of the battery calculated in step 4, the battery life is determined.

2. The method for remotely detecting battery life based on intelligent analysis of charging data according to claim 1, characterized in that: In step 1, the battery charging order data includes multiple charging heartbeat data based on time series, and the charging heartbeat data includes performance parameters of the electric bicycle battery during charging, timestamp data of each data push, and identification information data of the device.

3. The method for remotely detecting battery life based on intelligent analysis of charging data according to claim 2, characterized in that: Step 2 includes the following sub-steps: Step 21, charging time threshold determination, assuming that the battery charging time obtained from the battery charging order data is T total , assuming the charging time threshold is T m , if T total >T m Then continue to judge; Step 22, analyzing whether the characteristics of the battery charging power curve in the battery charging order data match the characteristics of the corresponding battery charging power curve in the historical battery charging order data of the corresponding user. If they match, the battery charging order data is judged to be valid, otherwise it is judged to be invalid.

4. The method for remotely detecting battery life based on intelligent analysis of charging data according to claim 3 is characterized in that: If the characteristics of the charging power curve of the battery in the battery charging order data in step 22 do not match the characteristics of the corresponding battery charging power curve in the historical battery charging order data of the corresponding user, and if there is no successful match in the multiple battery charging order data of the corresponding user, then a judgment result that the battery charging order data is invalid is output; If there is a battery charging power curve feature match with one of the multiple battery charging order data in the historical battery charging order data of the corresponding user, step 3 uses the corresponding successfully matched battery data to obtain battery life rules.

5. The method for remotely detecting battery life based on intelligent analysis of charging data according to claim 4, characterized in that: In step 4, the method for calculating the total effective charging time is: The maximum power during the charging process is multiplied by the effective charging power percentage to obtain the effective charging power range. The system traverses each charging heartbeat data of the battery charging order data to evaluate whether the power value in the charging heartbeat data falls within the effective charging power range. The duration of the qualified records will be accumulated to calculate the total effective charging time T of the entire order. effcient .

6. The method for remotely detecting battery life based on intelligent analysis of charging data according to claim 5, characterized in that: Assume the maximum power P during charging max , the maximum effective charging power percentage is a up , the minimum effective charging power percentage is a down , the maximum effective charging power in the effective charging power range is P up , the minimum effective charging power is P down ; Then P up = P max Δa up ; P down = P max ·a down ; The effective charging power range is P down —P up .

7. The method for remotely detecting battery life based on intelligent analysis of charging data according to claim 6, characterized in that: In step 5, the specific method for determining the battery life is: after completing the traversal of all heartbeat data, the total effective charging time is compared with the target effective charging time T in the indicator. target For comparison, if T effcient <T target , then the battery life corresponding to the battery charging order data is judged to be normal, and the accumulated days and order quantity in the evaluation period are reset; Otherwise, it is determined that the battery corresponding to the battery charging order data has a battery life problem, and the number of days and order quantity are accumulated.

8. A battery life remote detection system based on intelligent analysis of charging data, characterized by: For implementing the remote detection method of battery life based on intelligent analysis of charging data as described in claim 7, the remote detection system of battery life includes a charging data acquisition module and a charging data analysis module, the charging data acquisition module is communicatively connected with the charging pile platform, and collects battery charging order data pushed by the charging pile platform, the charging data analysis module runs a detection program designed using the remote detection method of battery life based on intelligent analysis of charging data as described in claim 7, the battery charging order data is input into the detection program, and the detection program outputs the battery life detection result.

9. The battery life remote detection system based on intelligent analysis of charging data according to claim 8, characterized in that: The charging data analysis module is connected to the charging pile platform for communication and the battery life test results output by the interactive detection program.

Images