NTLBO算法优化ELM的SOC预测方法

为提高锂电池荷电状态(SOC)预测的精度,提出了新型教与学优化(NTLBO)算法优化极限学习机的SOC预测方法.首先,采用Logistics混沌对种群中精英个体进行优化以改善算法的全局优化性能;其次,采用改进的TLBO算法优化调整ELM模型的输入权值和隐含层阈值,构建NTLBO-ELM预测模型以提升模型的泛化能力.以某...

The SOC Prediction Method of ELM Optimized by NTLBO Algorithm

In order to improve the prediction accuracy of state of charge(SOC),a prediction method of SOC based on optimized extreme learning machine(ELM)by the new teaching-learning-based optimization(NTLBO)algorithm was proposed.Firstly,Logistics chaos was employed to optimize the elite individuals in the population to improve the global optimization performance of the algorithm.Secondly,the input weights and hidden layer thresholds of the ELM model were optimized and adjusted by the improved TLBO algorithm,and the NTLBO-ELM prediction model was constructed to improve the generalization ability of the model.The NTLBO-ELM model was tested and verified on a lithium battery and compared with the other three models.The simulation results show that the proposed method has a small prediction error and good generalization ability,which verifies the validity of the model.