State of Health Diagnosis and Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Multi-Feature Data and Mechanism Fusion

Jingyun Xu,Zhiduan Cai,Dongming Jiang,Peiliang Wang,Aigang Zhen,Kaidi Gao

doi:10.1109/access.2021.3083395

Abstract

State of Health (SOH) Diagnosis and Remaining Useful Life (RUL) Prediction of lithium-ion batteries (LIBs) are subject to low accuracy due to the complicated aging mechanism of LIBs. This paper investigates a SOH diagnosis and RUL prediction method to improve prediction accuracy by combining multi-feature data with mechanism fusion. With the approach of the normal particle swarm optimization, a support vector regression (SVR)-based SOH diagnosis model is developed. Compared with existing works, more comprehensive features are utilized as the feature variables, including three aspects: the representative feature during a constant-voltage protocol; the capacity; internal resistance. Further, the optimized regularized particle filter (ORPF) model with uncertainty expression is integrated to obtain more accurate RUL prediction and SOH diagnosis. Experiments validate the effectiveness of the proposed method. Results show that the proposed SOH diagnosis and RUL prediction method has higher accuracy and better stability compared with the traditional methods, which help to realize the decision of the maintenance process.

Highlights

Lithium-ion batteries (LIBs) are the main power sources of electric vehicles owing to high energy density, long service life, and low self-discharge rate [1]
In order to verify the effectiveness of Remaining Useful Life (RUL) prediction based on the optimized regularized particle filter (ORPF) method, four battery data sets are tested in this paper, and the experiment results are compared with the NSVRm-PF and NSVRm-ORPF method
regularized particle filter (RPF) is used to replace PF, which solves the problem of particle diversity loss and improves the accuracy of uncertainty expression of prediction results

Summary

INTRODUCTION

Lithium-ion batteries (LIBs) are the main power sources of electric vehicles owing to high energy density, long service life, and low self-discharge rate [1]. J. Xu et al.: SOH Diagnosis and RUL Prediction of LIBs Based on Multi-Feature Data and Mechanism Fusion gauss-hermite PF model. The PSO algorithm does not take full advantage of the information obtained in the calculation process, and the parameters obtained by PSO get stuck in the local optimal solution and cannot accurately predict RUL and diagnose SOH of LIBs. The SVR methods do not make full use of the existing representative feature, which hinders the improvement of RUL and SOH estimation accuracy. This study proposes a novel RUL prediction and SOH diagnosis method by combining multi-feature data with mechanism fusion.

EXPERIMENTAL DATA ANALYSIS

SVR METHOD

NPSO ALGORITHM

ORPF ALGORITHM

CONCLUSION