State of Health Diagnosis and Remaining Useful Life Prediction for Lithium-ion Battery Based on Data Model Fusion Method

Xiangbo Cui,Tete Hu

doi:10.1109/access.2020.3038182

Abstract

Accurate state-of-health (SOH) diagnosis and remaining useful life (RUL) prediction of lithium-ion batteries (LIBs) play an extremely important role in ensuring safe and reliable operation of electric and hybrid vehicles. However, due to the complex electrochemical properties, it is difficult to achieve the goal of accurate diagnosis and prediction. Here, we propose a novel data-model fusion method to perform accurate SOH estimation and RUL prediction for LIBs, which considers nonlinear dynamics of not only discharging process but also charging process. A long short-term memory (LSTM) network is first employed to model battery SOH dynamics. A neural network (NN) model is then developed to describe battery capacity degradation mechanism according to the prior knowledge extracted from the charging process. Finally, an unscented Kalman filter (UKF) algorithm is incorporated with the LSTM network and NN model to filter out the noises and further reduce the estimation errors. Different from the traditional model fusion approaches, this proposed method uses full information from all sensors, and with no need for any physical model. Experiments and verification demonstrate both the effectiveness of this proposed method and its superior modeling performance as compared with several commonly used methods.

Highlights

In recent years, with the rapid development of energy storage technology, lithium-ion batteries (LIBs) have been widely used in the field of engineering applications, e.g., electric vehicles (EVs), hybrid EVs and so forth, due to the advantages of high energy density, high power density, and long lifetime [1], [2]
One of the most important issues in the application of LIBs is to meet the safety-critical and energy-efficient requirements, in which effective SOH diagnosis and remaining useful life (RUL) prediction are considered as a key enabler, because the electrical properties, stability and safety alterations often change with battery SOH and RUL [3], [4]
The experimental data were collected from the battery prognostics test bed, including power supply, DC electronic load, electrochemical impedance spectroscopy (EIS), voltmeter, thermocouple sensor, thermal chamber, peripheral component interconnect (PCI) extensions for instrumentation chassis based on data acquisition, and experimental control conditions

Summary

Introduction

With the rapid development of energy storage technology, LIBs have been widely used in the field of engineering applications, e.g., electric vehicles (EVs), hybrid EVs and so forth, due to the advantages of high energy density, high power density, and long lifetime [1], [2]. One of the most important issues in the application of LIBs is to meet the safety-critical and energy-efficient requirements, in which effective SOH diagnosis and RUL prediction are considered as a key enabler, because the electrical properties, stability and safety alterations often change with battery SOH and RUL [3], [4]. SOH is defined as a percentage of internal resistance or capacity, which is utilized to describe the aging level of battery in each charge-discharge cycle. RUL is defined as the number of remaining useful charge-discharge cycles at a specific cycle, which is calculated by the k-step-ahead projection of SOH [5], [6].

Objectives

Methods

Findings

Conclusion