基于参数优化的最小二乘支持向量机HEV阀控铅酸蓄电池SOC预测王琪.pdfVIP

46 1 () Vol.46 No.1 2015 1 Journal of Central South University (Science and Technology) Jan. 2015 DOI: 10.11817/j.issn.1672−7207.2015.01.016 HEV SOC 1, 2 2, 3 1, 2 (1. 212013 2. 212013 3. 211167) (LS-SVM)(HEV) (VRLA)(SOC) LS-SVM (BEF) (LOOCV) TP912 A 1672−7207(2015)01−0113−07 SOC prediction of VRLA battery for HEV based on parameter-optimized least square support vector machines WANG Qi1, 2, SUN Yukun2, 3, HUANG Yonghong1, 2 (1. School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China; 2. Key Laboratory of Facility Agriculture Measurement and Control Technology and Equipment of Machinery Industry, Jiangsu University, Zhenjiang 212013, China; 3. School of Electrical Power Engineering, Nanjing Institute of Technology, Nanjing 211167, China) Abstract: Least square support vector machines (LS-SVM) method was used to predict valve regulated lead acid (VRLA) battery’s state of charge (SOC) for hybrid electric vehicles (HEV). Considering that parameter selection of support vector machines exerted a major influence on SOC predict, a SOC prediction algorithm was presented on the basis of parameter-optimized least square support vector machines. Firstly, in the training process of nonlinear regression predicted model, simulate anneal arithmetic was adopted to determine starting values of the LS-SVM algorithm for better