Estimation Of Battery State Of Health Based On Random Weight PSO-ELM

Abstract

The estimation of the battery's state of health is instructive for the use and maintenance of the battery. The more accurate the estimated health status is, the higher the reliability of the system. Because the battery is influenced by many elements such as internal resistance, temperature and voltage, it is difficult to directly calculate its health status. Aiming at problems such as difficulty in measuring internal parameters and difficulty in mathematical modeling when estimating battery health status under operating conditions, this paper first predicts the health status of the battery through an extreme learning machine (ELM), and then uses random weighted particle swarm algorithm to optimize the ELM, and finally through the comparison of the prediction results of the extreme learning machine and the random weighted particle swarm optimization extreme learning machine, the validity of the battery health prediction used in this paper is verified.