A Composite State of Charge Estimation for Electric Vehicle Lithium-Ion Batteries Using Back-Propagation Neural Network and Extended Kalman Particle Filter

Abstract

Accurate estimation of battery state of charge (SOC) plays a crucial role for facilitating intelligent battery management system development. Due to the high nonlinear relationship between the battery open-circuit voltage (OCV) and SOC, and the shortcomings of traditional polynomial fitting approach, it is an even more challenging task for predicting battery SOC. To address these challenges, we present a composite SOC estimation approach for lithium-ion batteries using back-propagation neural network (BPNN) and extended Kalman particle filter (EKPF). First, a second-order resistance capacitance model is established to make parameters identification of a lithium-ion battery cell using recursive least squares algorithm with forgetting factors (FFRLS) approach. Then, BPNN is used to fit the desired OCV-SOC relationship with relatively high precision. Next, by incorporating the extended Kalman filter (EKF) into the particle filter (PF), an expected EKPF approach is presented to realize the SOC estimation. Finally, the performances of SOC estimation using different methods, namely the PF, EKF and the EKPF are compared and analyzed under constant current discharge and urban dynamometer driving schedule working conditions. The experimental results show that the proposed method has higher accuracy and robustness compared to the other two SOC estimation methods.

Review—Optimized Particle Filtering Strategies for High-Accuracy State of Charge Estimation of LIBs

“…Hui Pang et al 140 proposed a composite SOC estimation approach for LIBs using a back-propagation neural network (BPNN) and extended Kalman particle filter (EKPF). The experimental results show that the proposed method has higher accuracy and robustness compared to the other two SOC estimation methods.…”

State of Charge Estimation of Supercapacitor Under Different Temperatures Using Particle Filter Algorithm Based on Fractional-Order Model

“…This method can improve the accuracy of SOC at low temperatures, in an environment of 0 °C, The mean error of the estimated SOC is 0.60% in FUDS cycle and 0.68% in US06 cycle. Pang et al 34 2022 This paper established a second-order RC model and estimated battery SOC using a combination of EKF and PF methods.…”

“…33 Pang et al proposed a combination of extended Kalman filter and particle filter to estimate battery SOC, the experimental results show that the proposed method has higher accuracy and robustness. 34 Hao et al proposed a combination of unscented Kalman algorithm and particle filter algorithm to form the unscented particle filter (UPF) algorithm, Results show that the proposed algorithm estimates the SOC with good convergence and high system robustness. 35 To sum up, fractional-order models have higher accuracy compared to integer order models, and particle filtering has higher accuracy and robustness in estimating SOC.…”

Data-Driven State of Health Estimation for Lithium-Ion Batteries Based on Universal Feature Selection

“…13,14 Model-based methods require physical (e.g., equivalent circuit 15,16 or electrochemical 17,18 ) models of degradation behavior and have estimation accuracies that depend on model complexity and the precision of internal battery parameter identification. [19][20][21] Moreover, these methods cannot simulate all external environment factors such as ambient temperature changes and certain reactions such as the growth of solid-electrolyte interphases inside the battery, which leads to unsatisfactory accuracy. 9 In contrast, the simpler data-driven methods ignore the complex electrochemical reactions and degradation mechanism inside the battery and extract health indicators (HIs) from previously acquired experimental data to establish a mapping between HIs and the SOH and thus estimate the latter.…”