CN-121997136-A - Cell state identification method, device and storage medium based on sensing data

CN121997136ACN 121997136 ACN121997136 ACN 121997136ACN-121997136-A

Abstract

A battery core state identification method, device and storage medium based on sensing data relate to the technical field of battery management; the method comprises the steps of obtaining identity information of a battery cell to be identified, encoding the identity information through a two-dimensional code attached to a battery cell body, decoding the two-dimensional code, extracting first-class state information, synchronously collecting impedance response curves of the battery cell to be identified under current working conditions, inputting the first-class state information and the impedance response curves into a joint analysis model to generate a comprehensive evaluation result of the health state of the battery cell to be identified, and outputting a state conclusion of the battery cell based on the comprehensive evaluation result of the health state. The method aims to provide reliable technical support for each link of the full life cycle management of the battery.

Inventors

DU MINGYU
Luo Ruiqiao
ZHOU YI
ZHANG XINYONG
ZHAO YULONG
YAN ZHIFEI

Assignees

深圳市盛路物联通讯技术有限公司
深能源(深圳)创新技术有限公司
深能北方能源控股有限公司

Dates

Publication Date: 20260508
Application Date: 20260126

Claims (10)

1. A method for identifying a state of a battery cell based on sensing data, the method comprising: acquiring identity information of a battery cell to be identified, wherein the identity information is encoded through a two-dimensional code attached to a battery cell body; Decoding the two-dimensional code to extract first-class state information; synchronously collecting impedance response curves of the battery cells to be identified under the current working condition; inputting the first type of state information and the impedance response curve into a joint analysis model to generate a comprehensive evaluation result of the health state of the battery cell to be identified; And outputting a state conclusion of the battery cell based on the comprehensive health state evaluation result.
2. The method of claim 1, wherein the first type of status information includes at least nominal specifications of the cells, production lot information, and historical service records.
3. The method of claim 2, wherein inputting the first type of state information and the impedance response curve into a joint analysis model generates a comprehensive evaluation result of the health state of the cell to be identified, comprising: Calling a corresponding reference impedance evolution model according to the life model identifier analyzed from the first type of state information; Comparing the impedance response curve with a theoretical curve of the reference impedance evolution model in a corresponding aging stage; and calculating the characteristic difference degree representing the current cell aging state according to the comparison result, and taking the characteristic difference degree of the current cell aging state as the comprehensive evaluation result of the health state of the cell to be identified.
4. A method according to claim 3, wherein said comparing the impedance response curve with a theoretical curve of the reference impedance evolution model at a corresponding aging stage comprises: extracting factory calibration parameters of the battery cell from the first type of state information; Based on the factory calibration parameters, carrying out normalization pretreatment on the impedance response curve; And comparing the normalized impedance response curve with the theoretical curve.
5. The method of claim 2, wherein inputting the first type of state information and the impedance response curve into a joint analysis model generates a comprehensive evaluation result of the health state of the cell to be identified, further comprising: analyzing the precoded service environment data from the first type of state information; Inputting the service environment data into a preset multi-stress aging evaluation model to obtain a first aging evaluation result; Inputting the impedance response curve into an aging analysis model based on impedance to obtain a second aging evaluation result; and carrying out consistency check on the first aging evaluation result and the second aging evaluation result, and correcting or confirming the comprehensive evaluation result of the health state of the battery cell to be identified according to the check result.
6. The method of claim 5, wherein the modifying or confirming the comprehensive evaluation result of the health status of the cell to be identified according to the verification result comprises: If the deviation between the first aging evaluation result and the second aging evaluation result exceeds a preset tolerance, marking the evaluation result as abnormal; responding to the abnormality of the mark, and triggering the associated state review flow of other cells in the same batch according to the production batch information; and based on the statistical result of the association state review flow, carrying out feedback optimization on the parameters of the multi-stress aging evaluation model, and re-evaluating the current cell state by using the optimized model.
7. The method of claim 2, wherein outputting a conclusion of the state of the cell comprises: generating a dynamic maintenance two-dimensional code containing the comprehensive health state evaluation result; Writing or associating the dynamic maintenance two-dimensional code to the battery cell body to serve as a visual state conclusion to be output.
8. The utility model provides a battery core state recognition device based on sensing data which characterized in that includes: The acquisition module is used for acquiring the identity information of the battery cell to be identified, and the identity information is encoded through the two-dimensional code attached to the battery cell body; the extraction module is used for decoding the two-dimensional code and extracting first-class state information; The acquisition module is used for synchronously acquiring impedance response curves of the to-be-identified battery cells under the current working condition; The generation module is used for inputting the first type of state information and the impedance response curve into a joint analysis model to generate a comprehensive evaluation result of the health state of the battery cell to be identified; and the output module is used for outputting the state conclusion of the battery cell based on the comprehensive health state evaluation result.
9. A cell state identification device based on sensor data, comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any one of claims 1 to 7 when the computer program is executed by the processor.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.

Description

Cell state identification method, device and storage medium based on sensing data Technical Field The application belongs to the technical field of battery management, and particularly relates to a battery cell state identification method, device and storage medium based on sensing data. Background In the scenes of Battery Management System (BMS), echelon utilization detection, recovery sorting and the like, the quick and accurate identification of the health state of the battery cell is a core for guaranteeing the safety of the system, evaluating the residual value and realizing the fine management. The prior art mainly relies on two types of methods, direct analysis based on sensor data or static management based on identification information. Based on the direct analysis of the sensor data, for example, the physical signals such as the voltage, the current, the temperature and the electrochemical impedance spectrum of the current core are acquired, and the health state of the current core is deduced through a preset algorithm or model. Such methods, while straightforward, lack knowledge of the individual identity history of the cells. The aging paths and the characterization of the battery cells of the same model have obvious differences due to different production batches, initial performances and historical use environments (such as long-term high-temperature or high-rate charge and discharge), so that the evaluation accuracy is insufficient and the reliability is low. Based on static management of the identification information, for example, the basic information such as the model number, the production date and the like of the battery cell is recorded through a two-dimensional code or an RFID tag. Therefore, how to overcome the two defects of high misjudgment rate caused by lack of individual history information and weak evaluation capability caused by separation from real-time physical state of the identification information management method is a technical problem to be solved. Disclosure of Invention In view of the above, the embodiment of the application provides a method, a device and a storage medium for identifying a battery core state based on sensing data, which organically cooperate with three core technologies of two-dimensional code extraction of identity information, real-time impedance curve acquisition and multi-source information joint analysis, and realize deep fusion of individual historical information and real-time sensing data in the battery core state identification, thereby obtaining accuracy, reliability and practical value higher than those of a single data source evaluation method and providing reliable technical support for each link of battery full life cycle management. The embodiment of the application provides a battery cell state identification method based on sensing data, which comprises the following steps of: acquiring identity information of a battery cell to be identified, wherein the identity information is encoded through a two-dimensional code attached to a battery cell body; Decoding the two-dimensional code to extract first-class state information; synchronously collecting impedance response curves of the battery cells to be identified under the current working condition; inputting the first type of state information and the impedance response curve into a joint analysis model to generate a comprehensive evaluation result of the health state of the battery cell to be identified; And outputting a state conclusion of the battery cell based on the comprehensive health state evaluation result. In one embodiment, the first type of status information includes at least nominal specifications of the cells, production lot information, and historical service records. In an embodiment, the inputting the first type of state information and the impedance response curve into a joint analysis model, to generate a comprehensive evaluation result of the health state of the to-be-identified battery cell includes: Calling a corresponding reference impedance evolution model according to the life model identifier analyzed from the first type of state information; Comparing the impedance response curve with a theoretical curve of the reference impedance evolution model in a corresponding aging stage; and calculating the characteristic difference degree representing the current cell aging state according to the comparison result, and taking the characteristic difference degree of the current cell aging state as the comprehensive evaluation result of the health state of the cell to be identified. In an embodiment, the comparing the impedance response curve with the theoretical curve of the reference impedance evolution model in the corresponding aging stage includes: extracting factory calibration parameters of the battery cell from the first type of state information; Based on the factory calibration parameters, carrying out normalization pretreatment on the impedance response cur