The battery state-of-charge (SOC) is a very important part of battery prognostics and health management (PHM). For the problem that the SOC of lithium-ion battery cannot be measured directly, a kind of battery SOC estimation method using random forest regression is proposed in this paper. Firstly, a training set was constructed which used the battery current, battery voltage, battery temperature and other correlation factors as the model's training input and the corresponding battery SOC as the model's training output. Then, the model was trained with random forest algorithm. Finally, the trained model was applied to the battery SOC estimation. In this paper, this method is applied separately to the battery steady discharge process and dynamic discharge process for the estimation of battery SOC. Experimental results show that, the proposed method can effectively estimate the battery SOC and has a higher estimation precision than BP neural network estimation method.
Keywords-lithium-ion battery; random forest regression; state-of-charge (SOC) estimationI.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.