Lithium ion battery health state estimation method based on fragmented charging data

By standardizing the processing of fragmented charging data and using a hybrid deep learning model, the accuracy and adaptability issues of existing lithium-ion battery SOH estimation methods under fragmented data are solved, achieving high-precision SOH estimation applicable to electric vehicles and energy storage systems.

CN121522490APending Publication Date: 2026-02-13HANGZHOU DIANZI UNIV
2 Cites 3 Cited by

Patent Information

Application Number
CN202610062456.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-18
Publication Date
2026-02-13

AI Technical Summary

Technical Problem

Existing lithium-ion battery SOH estimation methods rely on complete charge-discharge cycle data, which cannot adapt to fragmented charging scenarios. The models have insufficient generalization ability and low estimation accuracy, making it difficult to meet the needs of practical applications.

Method used

We employ a method based on fragmented charging data. Through standardized data preprocessing and a hybrid deep learning model, we use fragmented charging segments from the CC stage (100-600 seconds) for SOH estimation. We combine a hybrid model of parallel temporal convolutional network (PTCN) and Transformer attention encoder (PTCA-Net) to achieve multi-scale feature extraction and global temporal dependency.

Benefits of technology

It achieves high-precision SOH estimation under fragmented charging data, with strong cross-scenario adaptability, small error, and is applicable to fields such as electric vehicles and energy storage systems. It is adapted to different temperatures and charging and discharging protocols, improving practicality and estimation accuracy.

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

Abstract

The invention relates to a fragmented charging data-based lithium ion battery health state estimation method, which comprises the following steps of: acquiring voltage, current and timestamp original data of a constant current charging stage of a lithium ion battery, and intercepting a 100-600-second standardized fragmented charging fragment based on a window parameter consisting of an initial voltage threshold Vstart, a sampling interval delta t and a sampling point number n; the method comprises the following steps: calculating an accumulated charging capacity through a coulomb counting method, generating a voltage-capacity curve, deducing a capacity increment-voltage curve and a voltage increment-capacity curve, and carrying out smooth filtering, multi-modal data splicing and normalization processing to obtain a 3 * n multi-channel characteristic tensor; according to the method, complete charging and discharging data are not needed, different battery types and complex working conditions are adapted, the lowest SOH estimation root-mean-square error can reach 0.00355, the highest determination coefficient (R) can reach 0.99485, and the practicability and estimation efficiency in practical application are greatly improved.
Need to check novelty before this filing date? Find Prior Art