A lithium battery remaining life prediction method for an electric fork truck

By combining empirical mode decomposition and long short-term memory neural networks with Gaussian process regression and stable distribution, the health status of lithium batteries is decomposed into multiple parts, solving the accuracy problem of predicting the remaining service life of lithium batteries, achieving more accurate prediction and fault warning, and improving the reliability of lithium battery systems.

CN117110923BActive Publication Date: 2026-07-17ZHEJIANG SCI-TECH UNIV
View PDF 4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG SCI-TECH UNIV
Filing Date
2022-02-14
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing methods for predicting the remaining lifespan of lithium batteries need improvement in terms of accuracy, especially since they fail to effectively consider the internal working mechanism and capacity regeneration phenomenon of lithium batteries, leading to inaccurate predictions.

Method used

By combining empirical mode decomposition and long short-term memory neural network with Gaussian process regression and stable distribution, the health status of lithium battery is decomposed into normal degradation trend, capacity regeneration and random fluctuation. Prediction is then made using the health status of lithium battery, initial charge status and rest time.

Benefits of technology

It improves the accuracy and reliability of lithium battery remaining life prediction, enables effective early warning of lithium battery failures, and enhances the reliability of energy storage systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117110923B_ABST
    Figure CN117110923B_ABST
Patent Text Reader

Abstract

The application discloses a lithium battery remaining life prediction method for an electric fork truck, and divides a lithium battery health state degradation curve into a normal degradation trend part, a capacity regeneration part and a random fluctuation part. The lithium battery capacity degradation curve is subjected to empirical mode decomposition to obtain a known long-term degradation trend part of the lithium battery. A long short-term memory neural network is used to predict future normal degradation trend on the basis of the known long-term degradation trend data of the lithium battery. The lithium battery health state, an initial capacity state and a rest time are taken as input quantities of Gaussian process regression, the capacity regeneration part of the lithium battery is predicted, the lithium battery capacity degradation rate failure threshold is set, the random fluctuation part is obtained by adopting a Stable distribution, the influence of the regenerated capacity and the random fluctuation on the lithium battery degradation process is accurately considered, and the accuracy of the lithium battery remaining life prediction is improved.
Need to check novelty before this filing date? Find Prior Art