Lithium battery SOH estimation method based on multi-source degradation characterization diagram and dynamic feature fusion

By generating multi-source degradation characterization maps and constructing a dynamic feature fusion network model, the problem of incomplete quantification of aging state in lithium battery SOH estimation in existing technologies is solved, and higher accuracy lithium battery health state estimation is achieved.

CN120928203AActive Publication Date: 2025-11-11GUANGDONG UNIV OF TECH
5 Cites 0 Cited by

Patent Information

Application Number
CN202511189139.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-25
Publication Date
2025-11-11
Estimated Expiration
2045-08-25

AI Technical Summary

Technical Problem

Existing lithium battery SOH estimation methods rely on single data source conversion and simple feature fusion to capture the coupling effect of multiple physical variables in the aging process, and ignore the coordinated change trends of temperature, voltage, and current, resulting in incomplete quantification of battery aging status.

Method used

By generating gray trajectory maps, temperature heatmaps, degradation state maps, and multi-source fusion maps, a dynamic feature fusion network model and a multi-source feature constraint loss function are constructed to adaptively fuse complementary information from different graphs, thereby improving the comprehensiveness of aging characterization.

Benefits of technology

It improves the accuracy of SOH estimation for lithium batteries, comprehensively quantifies the battery aging state, and overcomes the problems of one-sided characterization, inefficient fusion, and high redundancy in existing technologies.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a lithium battery SOH (state of health) estimation method based on multi-source degradation characterization diagram and dynamic feature fusion. The method comprises the following steps: synchronously acquiring voltage, current and temperature data in a specific state of charge interval in a lithium battery discharge cycle; generating a gray trajectory diagram based on the voltage and current data, generating a temperature thermodynamic diagram in combination with the temperature data, generating a degradation state diagram based on the number of cycles and aging characteristics, and forming a multi-source fusion diagram through weighted fusion; constructing a dynamic feature fusion network model and a multi-source feature constraint loss function; the dynamic feature fusion network model is trained and then deployed to a battery management system, and the SOH of the battery is estimated online. According to the method, the multi-source degradation representation graph is constructed, the aging state of the battery is comprehensively quantified, heterogeneous feature information is effectively fused through the dynamic feature fusion network model and the multi-source feature constraint loss function, and the SOH estimation precision of the lithium battery is improved.
Need to check novelty before this filing date? Find Prior Art