文献类型：期刊文献

英文题名：Research on activated carbon supercapacitors electrochemical properties based on improved PSO-BP neural network

作者：Liang, Xiaoyi[1]; Yang, Zhen[1]; Gu, Xingsheng[2]; Ling, Licheng[1]

机构：[1] State Key Laboratory of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China; [2] Information Science Institute, East China University of Science and Technology, Shanghai 200237, China

年份：2010

卷号：13

期号：2

起止页码：135

外文期刊名：Computers, Materials and Continua

收录：EI(收录号：20101712882690)

语种：英文

外文关键词：Capacitance - Supercapacitor - Neural networks - Electrochemical properties - Particle swarm optimization (PSO) - Specific surface area

摘要：Supercapacitors, also called electrical double-layer capacitors (EDLCs), occupy a region between batteries and dielectric capacitors on the Ragone plot describing the relation between energy and power. BET specific surface area and specific capacitance are two important electrochemical property parameters for activated carbon EDLCs, which are usually tested by experimental method. However, it is misspent time to repeat lots of experiments for EDLCs' studies. In this investigation, we developed one theoretical model based on improved particle swarm optimization algorithm back propagation (PSO-BP) neural network (NN) to simulate and optimize BET specific surface area and specific capacitance. Comparative studies between the predicted data and experimental data-earlier deduced by Liu et al, have revealed that improved PSO-BPNN model bears higher prediction accuracy, faster computation speed and better generalization performance.It is concluded that the improved PSO-BP NN is one simple and effective method to find optimal conditions of BET specific surface area and specific capacitance for activated carbon EDLCs.. Copyright ? 2010 Tech Science Press.