Remaining Useful Life Prediction and State of Health Diagnosis for Lithium-Ion Batteries Using Particle Filter and Support Vector Regression

TLDR

Accurate RUL prediction and SOH diagnosis are crucial for safety, durability, and cost of lithium‑ion battery energy storage systems, yet the complex aging mechanisms make this challenging. This paper proposes a novel method for battery RUL prediction and SOH estimation. The approach builds a support vector regression–based SOH state‑space model using capacity as the state and constant‑current/constant‑voltage protocol features as inputs, outputs impedance variables linked to capacity, and employs a particle filter to mitigate current/voltage noise and estimate impedance degradation parameters, with experiments validating the framework. Experiments demonstrate that the SOH estimation achieves accurate and robust results, and the RUL prediction framework delivers precise predictions.

Abstract

Accurate remaining useful life (RUL) prediction and state-of-health (SOH) diagnosis are of extreme importance for safety, durability, and cost of energy storage systems based on lithium-ion batteries. It is also a crucial challenge for energy storage systems to predict RUL and diagnose SOH of batteries due to the complicated aging mechanism. In this paper, a novel method for battery RUL prediction and SOH estimation is proposed. First, a novel support vector regression-based battery SOH state-space model is established to simulate the battery aging mechanism, which takes the capacity as the state variable and takes the representative features during a constant-current and constant-voltage protocol as the input variables. The estimated impedance variables are taken as the output due to the correlation between battery capacity and the sum of charge transfer resistance and electrolyte resistance. Second, in order to suppress the measurement noises of current and voltage, a particle filter is employed to estimate the impedance degradation parameters. Furthermore, experiments are conducted to validate the proposed method. The results show that the proposed SOH estimation method can provide an accurate and robustness result. The proposed RUL prediction framework can also ensure an accurate RUL prediction result.