摘要
现有电池荷电状态(SOC)估计方法所需训练和学习时间较长,很难满足动力电池的实时性要求。为解决该问题,利用小脑模型关节控制器(CMAC)神经网络对电池SOC进行评估,CMAC神经网络具有学习算法简单和逼近任意非线性函数的能力。对镍氢电池的模拟测试结果表明,与反向传播神经网络相比,CMAC神经网络的学习和收敛速度较快,能实时估计出电池SOC,并使估计误差在可接受范围内。
Existing battery State of Charge(SOC) estimation methods are time consuming for the training and learning process, and it restricts the application in electrical vehicles. In order to resolve the problem, this paper uses Cerebellar Model Articulation Controller(CMAC) neural network to estimate SOC. The CMAC neural network has simpler learning algorithms and it has the ability of approximating arbitrary nonlinear functions. Experiment using the data of nickel hydride batteries demonstrate the better learning speed and convergence of CMAC method compared with Back Prooagation(BP) neural network, it can meet the real time requirement in SOC, and the estimation error of the CMAC is acceptable.
出处
《计算机工程》
CAS
CSCD
北大核心
2011年第14期200-201,204,共3页
Computer Engineering
基金
湖南省自然科学基金资助项目(09JJ5039)
关键词
小脑模型关节控制器
神经网络
电池荷电状态
嵌入式系统
Cerebellar Model Articulation Controller(CMAC)
neural network
battery State of Charge(SOC)
embedded system
作者简介
汤哲(1977-),男,副教授,主研方向:智能控制,自动化控制;E-mail:tz@csu.edu.cn
刘万臣,硕士研究生;
郑果,工程师