A battery full life cycle management method, system and storage medium
Through the AI-based battery diagnosis system, the AI cloud platform analyzes battery failure data and provides the optimal solution, solving the problem that battery failure diagnosis relies on manual experience in the existing technology, realizing automated diagnosis and efficient battery failure management.
Patent Information
- Application Number
- CN202411080708.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-08
AI Technical Summary
In the prior art, battery fault diagnosis relies on manual experience, resulting in the inability to accurately determine the type of fault in the first time, which may lead to unnecessary waste and safety hazards.
Using an AI-based battery diagnosis system, data is transmitted to the AI cloud platform through detection equipment, AI is used to analyze battery material characteristics and detection data, confirm the fault type, and provide the best solution and corresponding costs to achieve automated diagnosis.
It realizes battery fault diagnosis without artificial dependencies, provides the best solution, reduces waste, and improves the safety and management efficiency of the battery system.
Smart Images

Figure CN118626938B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of battery detection, and in particular to a battery full life cycle management method, system and storage medium. Background Art
[0002] With the rapid development of distributed batteries, people have higher and higher requirements for distributed safety performance. Its safety issues are the bottleneck restricting the rapid development of distributed batteries. Due to its poor anti-abuse performance, the external environment and the use conditions, the battery system may have various faults, causing the power battery to degrade faster, and even electrolyte leakage, fire, explosion and other safety accidents. Therefore, fault diagnosis research is crucial to improve the safety of battery systems.
[0003] The existing battery testing generally uses manual on-site testing equipment to test various battery data to determine the type of battery failure, and then the corresponding maintenance personnel determine the battery maintenance method based on their own experience. This method cannot confirm the faulty battery in the first time, and the experience of different operation and maintenance personnel is different. The diagnosis of battery failure may result in some over-diagnosis, such as replacing the battery, which causes great waste.
[0004] Based on the above problems, there is an urgent need for a battery life cycle management system that can independently determine the type of fault and provide the best solution without relying on manual labor. Summary of the invention
[0005] With regard to the current manual diagnosis method of batteries, it is easy for maintenance personnel to fail to provide the best solution due to their lack of experience, resulting in unnecessary waste. This application solves the above problem by providing an AI-based battery diagnosis system and diagnosis method.
[0006] To achieve the above object, the present invention is implemented through the following technical solutions:
[0007] The present application embodiment discloses a battery life cycle management method, including:
[0008] S1: The detection equipment detects various parameters of the battery at different time periods and transmits them to the AI cloud platform;
[0009] S2: The AI cloud platform analyzes and confirms the fault type based on the data detected by the detection equipment in different time periods and the battery material characteristics stored in the AI cloud platform;
[0010] S3: The AI cloud platform matches different solutions according to the confirmed fault type;
[0011] S4: The AI cloud platform matches the costs of different solutions according to the matching solutions, selects the best solution and provides a diagnostic report;
[0012] S5: The AI cloud platform detects the repaired data, analyzes the repaired data and the data at the time of the failure, and evaluates the diagnosis results;
[0013] S6: Store the optimal solution in the storage unit of the AI cloud platform for analysis and optimization by the AI cloud platform.
[0014] Adopting the above technical solution: This solution can determine the type of fault based on the data detected by the detection equipment through the AI cloud platform, and provide a solution to the fault and the cost of the solution based on the type of fault.
[0015] Preferably, S4 includes:
[0016] S41: Confirm the solution benefits of different solutions based on the data recovery degree achieved by the solutions;
[0017] S42: Based on the calculation of the AI cloud platform, confirm the costs required for different solutions;
[0018] S43: Determine the evaluation scores based on the benefits and costs of different solutions, and determine the optimal solution based on the evaluation scores.
[0019] Adopt the above technical solution: The above solution can be analyzed according to the solution benefits of the provided solution and the cost required for the solution to confirm the optimal solution.
[0020] Further preferably, in S4, the calculation formula of the evaluation score is:
[0021] ;
[0022] in: For the solution benefits of the current solution, is the measured value of the ith data item, The optimal value of the i-th data, is the solution benefit coefficient of the i-th data; is the evaluation score of the ith solution, To solve the evaluation coefficient of benefit, is the cost of the i solutions, is the assessment coefficient for the assessment fee.
[0023] Adopt the above technical solution: In the above solution, by providing an algorithm, the solution benefits and the cost of the solution are analyzed, and the best solution can be predicted more intuitively through data calculation.
[0024] Further preferably, the data measured by the detection equipment include: battery supply current, battery supply voltage, battery capacity, battery charging efficiency, battery temperature and battery internal resistance.
[0025] Adopt the above technical solution: The above solution can detect the data of different batteries and provide them to the AI cloud platform, which analyzes the data and confirms the type of fault.
[0026] Further preferably, the S3 further includes:
[0027] S31: The operator analyzes the fault type and solution to determine whether the solution can be implemented and eliminates the unfeasible solution.
[0028] Adopting the above technical solution: After the AI system analyzes the fault type and provides a solution, the corresponding operator can then judge the different solutions provided, eliminate unnecessary solutions, and prevent unfeasible solutions from affecting the evaluation of the final optimal solution.
[0029] Further preferably, the S2 comprises:
[0030] S21: The AI cloud platform calculates the time when different data falls into different fault types in different time periods;
[0031] S22: The AI cloud platform predicts the fault assessment value based on the time when different data falls into different fault types;
[0032] S23: Compare the fault assessment value with different fault thresholds in the AI cloud platform to confirm the type of fault.
[0033] Adopting the above technical solution: the above technical solution can realize the prediction of data of the battery in different time periods, predict the fault assessment value, and further confirm the fault type.
[0034] A battery life cycle management system, applied to any of the above-mentioned diagnostic methods, is characterized by comprising:
[0035] Data detection unit: The data detection unit is used to detect various data of the battery and upload them;
[0036] AI analysis unit: used to analyze and confirm the fault type, the solution required for the fault type, and the cost of the solution based on the data detected by the data detection unit.
[0037] Storage unit: used to store data for analysis by the AI analysis unit, including storage calculation methods, fault thresholds of different faults, solutions corresponding to different fault types, and costs corresponding to different solutions;
[0038] Communication unit: used for data transmission between the data detection unit and the storage unit, the communication unit includes a 485 communication module, a LoRa communication module and a mobile communication module.
[0039] Positioning alarm unit: When the battery is away from the set position for too long, the positioning alarm unit on the battery will sound an alarm.
[0040] Adopting the above-mentioned technical solution: the above-mentioned AI analysis unit can receive the data detected by the data detection unit and retrieve the data stored in the storage unit, analyze the data stored in the storage unit and the actually measured data, so as to further determine the fault type, confirm the fault cost according to the fault type, and finally select the best solution.
[0041] Further preferably, the AI analysis unit includes:
[0042] Fault analysis module: The fault analysis module is used to confirm the fault type according to the data detected by the data detection unit;
[0043] Solution providing module: used to provide different solutions according to the fault type;
[0044] Solution determination module: Determine the optimal solution based on different solutions and the costs required to resolve them.
[0045] Adopt the above technical solution: the above solution can analyze the fault type according to the detected data, provide corresponding solutions according to the fault type, and select the best solution according to the solution and the cost required for the solution.
[0046] Further preferably, it also includes a data writing unit, which is used to write various data of different types of batteries under stable working conditions and parameters of the batteries themselves for analysis by the AI analysis unit.
[0047] Adopting the above technical solution: when a new type of battery needs to be tested, the writing unit provided by the above technical solution can directly write the battery data manually and provide it to the AI cloud platform for detection and analysis.
[0048] A storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to execute any one of the diagnostic methods described above. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0050] Figure 1 This is a flow chart of the battery diagnostic method for this application;
[0051] Figure 2 For this application Figure 1 Flowchart of step 4 in ;
[0052] Figure 3 For this application Figure 1 Flowchart of step 2 in ;
[0053] Figure 4 This is the circuit connection block diagram of the battery diagnostic system of this application.
[0054] Reference numerals:
[0055] 1. Data detection unit; 2. AI analysis unit; 3. Storage unit; 4. Communication unit; 5. 485 communication module; 6. LoRa communication module; 7. Mobile communication module; 8. Fault analysis module; 9. Solution providing module; 10. Solution determination module; 11. Data writing unit; 12. Positioning alarm unit. DETAILED DESCRIPTION
[0056] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0057] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0058] See also Figure 1-Figure 4For example, the original method of detecting and processing batteries is that maintenance personnel use corresponding detection equipment to detect the relevant data of the batteries one by one, and then the operators evaluate their own experience and judge the battery failure according to the data. This method may result in different solutions due to the different experiences of the operators, and the management effect of the batteries is not good, which may cause financial losses or the final solution is not the best solution. Based on the above problems, the embodiment of the present application discloses a battery life cycle management method, including:
[0059] S1: The detection equipment detects various parameters of the battery at different time periods and transmits them to the AI cloud platform;
[0060] S2: The AI cloud platform analyzes and confirms the fault type based on the data detected by the detection equipment in different time periods and the battery material characteristics stored in the AI cloud platform;
[0061] S3: The AI cloud platform matches different solutions according to the confirmed fault type;
[0062] S4: The AI cloud platform matches the costs of different solutions according to the matching solutions, selects the best solution and provides a diagnostic report;
[0063] S5: The AI cloud platform detects the repaired data, analyzes the repaired data and the data at the time of the failure, and evaluates the diagnosis results;
[0064] S6: Store the optimal solution in the storage unit of the AI cloud platform for analysis and optimization by the AI cloud platform.
[0065] In the above solution, the detection equipment is composed of various data detection modules and is also installed on the battery during the battery installation process. When the battery is running, it can detect various data of the battery in real time and upload it to the AI cloud platform, which will perform real-time analysis. When the detection data is abnormal, the fault type is judged. At the same time, the AI cloud platform will provide the best solutions based on the fault type and the battery's own capacity, model, voltage, power and other data. In addition, the AI cloud platform will analyze and calculate the solution benefits achieved by the analyzed best solutions and the funds required to obtain a solution that can ultimately guarantee the solution benefits and funds.
[0066] In addition, after the battery diagnosis is completed, the corresponding testing equipment will test the repaired data, compare and analyze the data with the data at the time of failure, and make an evaluation. The solution analyzed by the AI cloud platform will be provided to the storage module of the AI cloud platform for analysis, automatically establish the edge algorithm and battery big data model, continuously optimize the accuracy of the testing equipment, shorten the testing time of the testing equipment, and provide the best remediation plan and evaluation report in the shortest time.
[0067] Preferably, S4 includes:
[0068] S41: Confirm the solution benefits of different solutions based on the data recovery degree achieved by the solutions;
[0069] S42: Based on the calculation of the AI cloud platform, confirm the costs required for different solutions;
[0070] S43: Determine the evaluation scores based on the benefits and costs of different solutions, and determine the optimal solution based on the evaluation scores.
[0071] The above solutions can be analyzed based on the solution benefits of the solutions provided and the costs required for the solutions to confirm the optimal solution.
[0072] Further preferably, in S4, the calculation formula of the evaluation score is:
[0073] ;
[0074] in: For the solution benefits of the current solution, is the measured value of the ith data item, The optimal value of the i-th data, is the solution benefit coefficient of the i-th data; is the evaluation score of the ith solution, To solve the evaluation coefficient of benefit, is the cost of the i solutions, is the assessment coefficient for the assessment fee.
[0075] The above are various standard data provided to the AI cloud platform when the battery is in normal operating state. They are measured data. The difference calculation can be used to obtain the degree of deviation of the solution from the normal operating state after maintenance. This is the proportion of different data recovery degrees in the solution benefit. In other words, the larger E is, the better the final solution benefit. However, we cannot only consider the solution benefit, but also the cost of the solution. Therefore, in the second set of formulas, the solution benefit and the evaluation coefficient of the solution benefit are used as the numerator, and the cost of the solution and the evaluation coefficient of the cost are used as the denominator. Calculation is performed to obtain the maximum value. In other words, the better the solution benefit and the lower the predicted cost, the better solution we want.
[0076] Further preferably, the data measured by the detection device include: battery supply current, battery supply voltage, battery capacity, battery charging efficiency, battery temperature and battery internal resistance. The above scheme can detect the data of different batteries and provide them to the AI cloud platform, which analyzes the data and confirms the type of fault.
[0077] Further preferably, the S3 further includes:
[0078] S31: The operator analyzes the fault type and solution to determine whether the solution can be implemented and eliminates the unimplementable solutions. Since the AI cloud platform only analyzes the detected data to obtain multiple better solutions, and the detection and maintenance of the battery still need to be considered according to the actual situation, after the AI system analyzes the fault type and provides a solution, the corresponding operator can judge the different solutions provided and eliminate unnecessary solutions to prevent the unimplementable solutions from affecting the evaluation of the final optimal solution.
[0079] Further preferably, the S2 comprises:
[0080] S21: The AI cloud platform calculates the time when different data falls into different fault types in different time periods;
[0081] S22: The AI cloud platform predicts the fault assessment value based on the time when different data falls into different fault types;
[0082] S23: Compare the fault assessment value with different fault thresholds in the AI cloud platform to confirm the type of fault.
[0083] In the above solution, the evaluation value can be calculated according to the time when different data falls into different fault types, so as to further judge the type of fault.
[0084] A battery life cycle management system, applied to any of the above-mentioned diagnostic methods, is characterized by comprising:
[0085] Data detection unit 1: The data detection unit 1 is used to detect various data of the battery and upload them;
[0086] AI analysis unit 2: used to analyze and confirm the fault type, the solution required for the fault type, and the cost required for the solution based on the data detected by the data detection unit 1.
[0087] Storage unit 3: used to store data for analysis by AI analysis unit 2, including storage calculation methods, fault thresholds of different faults, solutions corresponding to different fault types, and costs corresponding to different solutions;
[0088] Communication unit 4: used for data transmission between the data detection unit 1 and the storage unit 3, the communication unit 4 includes a 485 communication module 5, a LoRa communication module 6 and a mobile communication module 7.
[0089] Positioning alarm unit (12): When the battery is away from the corresponding device that needs to be powered for a longer period of time than a set distance, or when the positioning system on the battery shows that there is a significant change in the longitude and latitude between the battery and the device that needs to be powered, the positioning alarm unit on the battery will sound an alarm. For example, when a battery placed on an electric vehicle is stolen, an alarm will be immediately sent to the corresponding communication device to remind the user that the battery is away from the device being powered, and the real-time location of the battery will be displayed, so that the user can find the battery according to the location displayed on the communication device.
[0090] In the above-mentioned, the data detection unit 1 can detect various data of each battery and transmit different data in real time through the communication unit 4, which is stored in the storage unit 3. The AI analysis unit 2 retrieves the data in the storage unit 3, and compares and calculates with various standard data of the battery stored in the storage unit 3 to obtain the fault type, and provides multiple better solutions according to the fault type. The AI analysis unit 2 analyzes the benefits of solving the fault and the cost of solving the fault, and finally obtains the best solution.
[0091] Further preferably, the AI analysis unit 2 includes:
[0092] Fault analysis module 8: The fault analysis module 8 is used to confirm the fault type according to the data detected by the data detection unit 1;
[0093] Solution providing module 9: used to provide different solutions according to the fault type;
[0094] Solution determination module 10: Determine the optimal solution based on different solutions and the cost required for the solution. The above solution can analyze the fault type based on the detected data, and then provide corresponding solutions based on the fault type, and select the optimal solution based on the solution and the cost required for the solution.
[0095] Further preferably, a data writing unit 11 is included, and the data writing unit 11 is used to write various data of different types of batteries under stable working conditions and the parameters of the batteries themselves for analysis by the AI analysis unit 2. When a new type of battery needs to be tested, the writing unit provided by the above technical solution can directly write the battery data manually and provide it to the AI cloud platform for detection and analysis.
[0096] A storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to execute any one of the diagnostic methods described above.
[0097] Unless otherwise specified, the device components involved in the above embodiments are all conventional device components, and the connection methods and control methods involved are all conventional connection methods and control methods unless otherwise specified.
[0098] The present invention has been described in detail above in conjunction with the embodiments. However, those skilled in the art will appreciate that, without departing from the spirit of the present invention, the specific parameters in the above embodiments may be changed to form a plurality of specific embodiments, which are all within the common variation range of the present invention and will not be described in detail herein.
Claims
1. A battery life cycle management method, characterized in that: include: S1: The detection equipment detects various parameters of the battery at different time periods and transmits them to the AI cloud platform; S2: The AI cloud platform analyzes and confirms the fault type based on the data detected by the detection equipment in different time periods and the battery material characteristics stored in the AI cloud platform; S3: The AI cloud platform matches different solutions according to the confirmed fault type; S4: The AI cloud platform matches the costs of different solutions according to the matching solutions, selects the best solution and provides a diagnostic report; S5: The AI cloud platform detects the repaired data, analyzes the repaired data and the data at the time of the failure, and evaluates the diagnosis results; S6: storing the optimal solution in the storage unit of the AI cloud platform for analysis and optimization by the AI cloud platform; The S4 includes: S41: Confirm the solution benefits of different solutions based on the data recovery degree achieved by the solutions; S42: Based on the calculation of the AI cloud platform, confirm the costs required for different solutions; S43: According to the solution benefits and required costs of different solutions, an evaluation score is obtained, and the optimal solution is determined by the evaluation score; in S4, the calculation formula of the evaluation score is: ; ; in: For the solution benefits of the current solution, is the measured value of the ith data item, The optimal value of the i-th data item, is the solution benefit coefficient of the i-th data; is the evaluation score of the ith solution, To solve the evaluation coefficient of benefit, is the cost of the i solutions, is the assessment coefficient for the assessment fee.
2. A battery life cycle management method according to claim 1, characterized in that: The data measured by the detection device include: battery supply current, battery supply voltage, battery capacity, battery charging efficiency, battery temperature and battery internal resistance.
3. A battery life cycle management method according to claim 1, characterized in that: The S3 further includes: S31: The operator analyzes the fault type and solution to determine whether the solution can be implemented and eliminates the unfeasible solution.
4. A battery life cycle management method according to claim 1, characterized in that: The S2 includes: S21: The AI cloud platform calculates the time when different data falls into different fault types in different time periods; S22: The AI cloud platform predicts the fault assessment value based on the time when different data falls into different fault types; S23: Compare the fault assessment value with different fault thresholds in the AI cloud platform to confirm the type of fault.
5. A battery life cycle management system, applied to the management method according to any one of claims 1 to 4, characterized in that: include: Data detection unit (1): the data detection unit (1) is used to detect various data of the battery and upload them; AI analysis unit (2): used to analyze and confirm the fault type, the solution required for the fault type, and the cost of the solution based on the data detected by the data detection unit (1); Storage unit (3): used to store data for analysis by the AI analysis unit (2), including storage calculation methods, fault thresholds of different faults, solutions corresponding to different fault types, and costs corresponding to different solutions; A communication unit (4): used for performing data transmission between the data detection unit (1) and the storage unit (3), the communication unit (4) comprising a 485 communication module (5), a LoRa communication module (6) and a mobile communication module (7); Positioning alarm unit (12): When the battery is away from the set position for too long, the positioning alarm unit on the battery will sound an alarm.
6. A battery life cycle management system according to claim 5, characterized in that: The AI analysis unit (2) comprises: Fault analysis module (8): the fault analysis module (8) is used to confirm the fault type according to the data detected by the data detection unit (1); Solution providing module (9): used to provide different solutions according to the fault type; Solution determination module (10): determines the optimal solution based on different solutions and the costs required for the solutions.
7. A battery life cycle management system according to claim 5, characterized in that: It also comprises a data writing unit (11), wherein the data writing unit (11) is used to write various data of different types of storage batteries under stable working conditions and parameters of the storage batteries themselves for analysis by the AI analysis unit (2).
8. A storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to execute the management method described in any one of claims 1 to 4.
Citation Information
Patent Citations
Battery pack and battery management system matching testing central system
CN107202959A
Diagnosis method of battery heating performance, storage medium and vehicle
CN117885609A
Self-awakening diagnosis method and system for battery management
CN118169586A
Method, system and equipment for processing abnormal operation problem of power station and medium
CN118312649A
Advanced battery early warning and monitoring system
US20130135110A1
