A SOH online estimation method and device, electronic equipment and storage medium

By combining real-time data acquisition and preprocessing with multi-mode stationary point identification and OCV-SOC relationship calibration, and by combining cross-day state continuation and physical rule calculation of capacity attenuation, the SOH value is predicted using a random forest model. This solves the problems of low data utilization and poor reliability of traditional methods under frequency modulation conditions, and achieves high-precision SOH estimation.

CN121978573BActive Publication Date: 2026-07-21深圳织算科技有限公司
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
深圳织算科技有限公司
Filing Date
2026-04-07
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Traditional SOH estimation methods suffer from low data utilization and high estimation failure rate under complex frequency modulation conditions, making them unsuitable for high-frequency dynamic conditions. Furthermore, data-driven methods lacking physical constraints have poor interpretability.

Method used

By preprocessing real-time battery data, using a multi-mode resting point identification mechanism and dynamic calibration of the OCV-SOC relationship curve, and combining a cross-day state continuation mechanism to match and screen resting point combinations, capacity decay is calculated based on physical rules, and SOH values ​​are predicted by training a random forest model. Finally, SOH values ​​are obtained through adaptive weighted fusion or decay weight filtering.

Benefits of technology

It significantly improves the accuracy and reliability of SOH estimation, adapts to complex working conditions, and enhances data utilization and engineering applicability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121978573B_ABST
    Figure CN121978573B_ABST
Patent Text Reader

Abstract

Embodiments of the present application disclose a SOH online estimation method and device, electronic equipment and storage medium, relating to the technical field of battery state of health (SOH) online estimation, wherein the method comprises: collecting battery operation data in real time, intelligently detecting high / low SOC static points after preprocessing by using a multi-mode static point identification mechanism, and dynamically calibrating SOC values in combination with an OCV-SOC relationship curve. The SOC change amount is calculated by matching and screening static point combinations through a cross-day state continuation mechanism, and the SOH estimation value and confidence evaluation are derived based on physical rules (such as ampere-hour integration). The random forest model is trained by extracting statistical features from historical data to predict the SOH value, and the uncertainty is quantified by out-of-bag estimation. According to the confidence and uncertainty output by the physical rules and machine learning, the adaptive weighted fusion or decay weight filtering is used to process the historical data by sliding average to obtain the SOH value. The present application effectively solves the problems of low data utilization and poor reliability in the prior art.
Need to check novelty before this filing date? Find Prior Art