A State-of-Health Estimation Method for Lithium Batteries Based on Fennec Fox Optimization Algorithm–Mixed Extreme Learning Machine

Abstract

A reliable and accurate estimation of the state-of-health (SOH) of lithium batteries is critical to safely operating electric vehicles and other equipment. This paper proposes a state-of-health estimation method based on fennec fox optimization algorithm–mixed extreme learning machine (FFA-MELM). Firstly, health indicators are extracted from lithium-battery-charging data, and grey relational analysis (GRA) is employed to identify highly correlated features with the state-of-health of the battery. Subsequently, a state-of-health estimation model based on mixed extreme learning machine is constructed, and the hyperparameters of the model are optimized using the fennec fox optimization algorithm to improve estimation accuracy and convergence speed. The experimental results demonstrate that the proposed method has significantly improved the accuracy of the state-of-health estimation for lithium batteries compared to the extreme learning machine. Furthermore, it can achieve precise state-of-health estimation results for multiple batteries, even under complex operating conditions and with limited charge/discharge cycle data.

A Method for Assessing the Technical Condition of Traction Batteries Using the Metalog Family of Probability Distributions

“…This, of course, reduces the aging process of the batteries and extends their proper operation time in the vehicle [46,47]. Scientists have developed, and engineers have already implemented, in industrial practice, a large number of algorithms and techniques that allow the health of individual cells or entire battery packs to be determined [48]. Very interesting and useful methods for assessing the technical condition of batteries from electric vehicles have been described by Hassini et al [49].…”