CN-121978538-A - Battery state evaluation method, system and storage medium

CN121978538ACN 121978538 ACN121978538 ACN 121978538ACN-121978538-A

Abstract

The invention relates to the technical field of batteries and discloses a battery state evaluation method, a system and a storage medium, wherein the method comprises the steps of obtaining a manufacturing parameter set and an operation parameter set associated with a target battery; and performing feature fusion on the manufacturing parameter set and the operation parameter set to obtain cross fusion features, wherein the cross fusion features are used for representing the interactive influence relationship between the manufacturing parameter set and the operation parameter set, and performing state evaluation on the target battery based on the cross fusion features to obtain an evaluation result. The invention solves the problems of inaccurate evaluation and large prediction deviation caused by the fact that the traditional battery health evaluation method fails to model the coupling effect of manufacturing and use.

Inventors

KANG YIFEI
SHANG BIN

Assignees

北京理未科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260309

Claims (10)

1. A battery state evaluation method, characterized in that the method comprises: acquiring a manufacturing parameter set and an operation parameter set associated with a target battery; Performing feature fusion on the manufacturing parameter set and the operation parameter set to obtain cross fusion features, wherein the cross fusion features are used for representing interaction influence relations between the manufacturing parameter set and the operation parameter set; And carrying out state evaluation on the target battery based on the cross fusion characteristics to obtain an evaluation result.
2. The method of claim 1, wherein the obtaining the set of manufacturing parameters and the set of operating parameters associated with the target battery comprises: Obtaining a pre-constructed battery basic library, wherein the battery basic library stores a plurality of preset manufacturing parameters of preset batteries, and the preset manufacturing parameters at least comprise thickness of a pole piece, compaction density, formation efficiency, moisture content and material formula batch; Acquiring a pre-constructed battery operation library, wherein the battery operation library stores historical operation parameters of a plurality of preset batteries, and the historical operation parameters at least comprise the number of times of quick charge, the frequency of deep discharge, the voltage difference of single batteries, the temperature difference of the batteries, the accumulated charge-discharge cycle number and the environmental temperature range; And acquiring a manufacturing parameter set of the target battery from the battery basic library, and acquiring an operation parameter set of the target battery from the battery operation library.
3. The method of claim 1, wherein feature fusing the set of manufacturing parameters and the set of operating parameters to obtain cross-fused features comprises: extracting static manufacturing characteristics from the manufacturing parameter set, wherein the static manufacturing characteristics comprise at least one of initial capacity, initial internal resistance, pole piece thickness and deviation, compaction density, material residual water content, anode prelithiation rate, formation test first-week efficiency and pole piece defect mark; Extracting dynamic operation characteristics from the operation parameter set, wherein the dynamic operation characteristics comprise instant state characteristics and historical statistical characteristics, the instant state characteristics comprise at least one of a real-time state-of-charge value, a real-time temperature value and a real-time monomer pressure difference, and the historical statistical characteristics comprise at least one of accumulated cycle times, equivalent full charge cycle times, historical average discharge depth, preset state-of-charge residence time ratio, maximum temperature pressure difference in a historical time period and capacity reduction percentage in the historical time period; And combining and calculating the static manufacturing feature and the dynamic operation feature to generate the cross fusion feature.
4. The method of claim 3, wherein said combining the static manufacturing feature with the dynamic operating feature to generate the cross-fusion feature comprises: Obtaining a pre-constructed battery fault mode library, wherein the battery fault mode library stores a mapping relation between a preset fault mode and a preset feature combination; Determining at least one set of target static manufacturing features and target dynamic operating features associated with a target failure mode from the static manufacturing features and the dynamic operating features based on the mapping relationship; And carrying out logic combination operation on the target static manufacturing characteristics and the target dynamic operation characteristics associated with the target fault mode to generate the cross fusion characteristics.
5. The method according to claim 1, wherein the performing the state evaluation on the target battery based on the cross fusion feature to obtain an evaluation result includes: Constructing at least one layered state index of the target battery according to the cross fusion characteristics; weighting and fusing the layering state indexes to obtain a target state value; Predicting the future state of the target battery based on the layered state index to obtain a state prediction result; and taking the layered state index, the target state value and the state prediction result as the evaluation result of the target battery.
6. The method of claim 5, wherein said constructing at least one hierarchical state index of the target battery from the cross-fusion feature comprises: Calculating a capacity index of the target battery based on the cross-fusion feature, wherein the capacity index is used for representing a capacity fading state of the target battery; calculating a consistency index of the target battery based on the cross fusion feature, wherein the consistency index is used for representing the performance difference between the single units of the target battery; and calculating a risk index of the target battery based on the cross fusion characteristics, wherein the risk index is used for representing the potential fault risk degree of the target battery.
7. The method of claim 5, wherein predicting the future state of the target battery based on the layered state index to obtain a state prediction result comprises: acquiring historical sequence data of each layering state index; calculating a predicted state index of each layered state index in a future time period according to the historical sequence data; And calculating the residual effective duration and the replacement prompting time of the target battery based on the predicted state indexes, and taking the residual effective duration and the replacement prompting time as the state prediction results.
8. The method according to claim 1, wherein after performing a state evaluation on the target battery based on the cross-fusion feature, the method further comprises: Acquiring a business object label associated with the target battery; generating early warning information corresponding to the evaluation result aiming at each business object label; And outputting the evaluation result and the early warning information to the business object corresponding to the business object label.
9. The battery state evaluation system is characterized by comprising a data acquisition module, a feature fusion module and a state evaluation module, wherein the data acquisition module is connected with the feature fusion module, and the feature fusion module is connected with the state evaluation module; the data acquisition module is used for acquiring a manufacturing parameter set and an operation parameter set associated with the target battery; The feature fusion module is used for carrying out feature fusion on the manufacturing parameter set and the operation parameter set to obtain cross fusion features, wherein the cross fusion features are used for representing interaction influence relations between the manufacturing parameter set and the operation parameter set; And the state evaluation module is used for performing state evaluation on the target battery based on the cross fusion characteristic to obtain an evaluation result.
10. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 8.

Description

Battery state evaluation method, system and storage medium Technical Field The invention relates to the technical field of batteries, in particular to a battery state evaluation method, a battery state evaluation system and a storage medium. Background Along with the rapid development of new energy automobiles and energy storage industry, the accurate assessment of the health state and the management and control of fault risks of power batteries become vital. Accurate determination of State of Health (SOH) is directly related to system operational safety and asset value management. Currently, conventional battery health management methods rely mainly on data during use, such as based on capacity fade statistics or optimized charging strategies, which reflect partial aging phenomena, but are difficult to comprehensively and deeply evaluate complex performance degradation and potential failure risks caused by the combination of the congenital manufacturing differences and the acquired use stresses of the battery. Some prior art solutions have attempted to introduce multidimensional data for a more comprehensive battery health assessment. For example, the health report is generated by integrating multi-source information such as user behaviors, environmental conditions and the like through a cloud-based collaborative architecture, or the health index is formed by combining multiple indexes such as voltage, internal resistance and the like. However, such schemes have significant limitations at the data fusion level, in that they typically integrate manufacturing process parameters (e.g., pole piece characteristics, moisture content) with usage process data (e.g., fast charge frequency, temperature profile) as parallel input features, and lack feature engineering means that model specifically for the interaction impact relationship between manufacturing parameters and operating parameters. Due to the failure to effectively extract and utilize the cross fusion characteristics between the two types of parameters, the existing method has difficulty in accurately quantifying the accelerated aging or failure mode triggered by specific manufacturing defects under specific use conditions (for example, the gas production risk of a high-moisture battery at high temperature), so that the evaluation of the full life cycle health state of the battery is not accurate enough, the residual life prediction has deviation, and the failure caused by the coupling effect of manufacturing and use cannot be early warned. Disclosure of Invention In view of the above, the embodiments of the present invention provide a battery state evaluation method, system and storage medium, so as to solve the problems of inaccurate evaluation and large prediction deviation caused by failure in modeling the coupling effect of manufacturing and use in the existing battery health evaluation method. In a first aspect, an embodiment of the present invention provides a battery state evaluation method, including: acquiring a manufacturing parameter set and an operation parameter set associated with a target battery; Performing feature fusion on the manufacturing parameter set and the operation parameter set to obtain cross fusion features, wherein the cross fusion features are used for representing interaction influence relations between the manufacturing parameter set and the operation parameter set; And carrying out state evaluation on the target battery based on the cross fusion characteristics to obtain an evaluation result. Further, the obtaining the manufacturing parameter set and the operation parameter set associated with the target battery includes: Obtaining a pre-constructed battery basic library, wherein the battery basic library stores a plurality of preset manufacturing parameters of preset batteries, and the preset manufacturing parameters at least comprise thickness of a pole piece, compaction density, formation efficiency, moisture content and material formula batch; Acquiring a pre-constructed battery operation library, wherein the battery operation library stores historical operation parameters of a plurality of preset batteries, and the historical operation parameters at least comprise the number of times of quick charge, the frequency of deep discharge, the voltage difference of single batteries, the temperature difference of the batteries, the accumulated charge-discharge cycle number and the environmental temperature range; And acquiring a manufacturing parameter set of the target battery from the battery basic library, and acquiring an operation parameter set of the target battery from the battery operation library. Further, the feature fusion of the manufacturing parameter set and the operation parameter set to obtain a cross fusion feature includes: extracting static manufacturing characteristics from the manufacturing parameter set, wherein the static manufacturing characteristics comprise at least one of initial capacity, initial