基于ANFIS和减法聚类的动力电池放电峰值功率预测

摘要
图/表
参考文献
相关文章 (11)

全文: PDF (990 KB)
输出: BibTeX | EndNote (RIS)

摘要动力电池的短时峰值功率预测对于实际使用来说至关重要。本文采用基于一阶Sugeno模糊推理系统的自适应神经模糊推理系统（ANFIS）模型估计放电峰值功率。选取温度、SOC和欧姆内阻为模型输入量,10s脉冲放电峰值功率为输出变量。基于实测和曲线拟合相结合的方法得到训练数据组,采用305组数据组模型进行训练,采用网格生成法和减法聚类法分别生成模糊集合,并采用单一BP神经网络方法和混合训练方法分别进行模型训练。发现采用减法聚类法生成模糊结构,能大幅减少模糊规则的数目,并提高收敛速度,在满足预测准确度的前提下降低了模型的复杂程度;采用混合训练方法进行网络学习能够加强模型的收敛能力并克服单一BP算法的局部最优问题,准确度更高。最后,采用125组数据组模型进行验证,预测误差在10%以内,基于ANFIS的模型能够很好地估计电池的脉冲峰值功率。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	孙丙香
	高科
	姜久春
	罗敏
	何婷婷
	郑方丹
	郭宏榆

关键词 ：动力电池, 峰值功率, ANFIS, 减法聚类, 混合训练

Abstract：Short-term peak power prediction of power battery is essential for practical use. In this paper, the adaptive neuro-fuzzy inference system(ANFIS) model is used to estimate the discharge peak power based on first order Sugeno fuzzy inference system. Temperature, SOC and ohmic resistance are selected as the inputs and 10-seconds pulse discharge peak power as the output. The training data pairs are obtained by the combination of measurements and curve fitting. Mesh generation and subtraction clustering methods are used to generate fuzzy sets. BP neural network and hybrid training methods are used to train the model based on 305 pairs of data. It found that the number of fuzzy rules is significantly reduced by using fuzzy clustering method to generate subtraction structure, the convergence rate is improved and the complexity of the model is reduced on the premise of meet the precision. Network learning by hybrid training method can strengthen the convergence ability and overcome the problem of local optimum by BP algorithm. Finally, 305 pairs of data is used to validate the model, the prediction is within 10%, ANFIS model can be well estimated the pulse peak power of the battery.

Key words： Power battery peak power adaptive neuro-fuzzy inference system subtraction clustering hybrid training

收稿日期: 2014-07-24 出版日期: 2015-04-13

PACS:

TM911

基金资助:国家高技术研究发展计划（863计划）（2012AA050211）资助项目

作者简介: 孙丙香女,1979年生,博士,讲师,研究方向为动力电池成组应用技术。高科男,1988年生,硕士研究生,研究方向为动力电池成组应用技术。

引用本文:

孙丙香,高科,姜久春,罗敏,何婷婷,郑方丹,郭宏榆. 基于ANFIS和减法聚类的动力电池放电峰值功率预测[J]. 电工技术学报, 2015, 30(4): 272-280. Sun Bingxiang,Gao Ke,Jiang Jiuchun,Luo Min,He Tingting,Zheng Fangdan,Guo Hongyu. Research on Discharge Peak Power Prediction of Battery Based on ANFIS and Subtraction Clustering. Transactions of China Electrotechnical Society, 2015, 30(4): 272-280.

链接本文:

http://dgjsxb.ces-transaction.com/CN/Y2015/V30/I4/272

[1] Idaho National Engineering & Environmental Labora- tory. Freedom car battery test manual for power-assist hybrid electric vehicles[S]. 2003.
[2] PNGV Battery Test Manual. 2001.
[3] Japan electric vehicle society. Test method of input and output power density of nickel-hydride battery for hybrid electric vehicles[S]. Japan, 2003.
[4] Sun Bingxiang, Wang Lifang, Liao Chenglin. SOC estimation of NiMH battery for HEV based on adaptive neuro-fuzzy inference system[C]. IEEE Vehicle Power and Propulsion Conference, 2008.
[5] 周湶, 孙威, 张昀. 基于改进型ANFIS的负荷密度指标求取新方法[J]. 电力系统保护与控制, 2011, 39(1): 29-34. Zhou Quan, Sun Wei, Zhang Yun. A new method to obtain load density based on improved ANFIS[J]. Power System Protection and Control, 2011, 39(1): 29-34.
[6] 张钧, 何正友, 谭熙静. 一种基于ANFIS的配电网故障分类方法及其适应性分析[J]. 电力系统保护与控制, 2011, 39(4): 23-29. Zhang Jun, He Zhengyou, Tan Xijing. An ANFIS based fault classification in distribution network and its adaptability analysis[J]. Power System Protection and Control, 2011, 39(4): 23-29.
[7] Zhang Tiejun, Chen Duo, Sun Jie. Research on neural network model based on subtraction clustering and its applications[J]. Physics Procedia, 2012, 25: 1642- 1647.
[8] 李培强, 李欣然, 陈辉华, 等. 基于减法聚类的模糊神经网络负荷建模[J]. 电工技术学报, 2006, 21(9): 1-6, 12. Li Peiqiang, Li Xinran, Chen Huihua, et al. Fuzzy neural network load modeling based on subtractive clustering[J]. Transactions of China Electrotechnical Society, 2006, 21(9): 1-6, 12.
[9] 杨茂, 熊昊, 严干贵, 等. 基于数据挖掘和模糊聚类的风电功率实时预测研究[J]. 电力系统保护与控制, 2013, 41(1): 1-6. Yang Mao, Xiong Hao, Yan Gangui, et al. Real-time prediction of wind power based on data mining and fuzzy clustering[J]. Power System Protection and Control, 2013, 41(1): 1-6.
[10] 白俊良, 梅华威. 改进相似度的模糊聚类算法在光伏阵列短期功率预测中的应用[J]. 电力系统保护与控制, 2014, 42(6): 84-90. Bai Junliang, Mei Huawei. Improved similarity based fuzzy clustering algorithm and its application in the PV array power short-term forecasting[J]. Power System Protection and Control, 2014, 42(6): 84-90.
[11] 郭宏榆, 姜久春, 王吉松, 等. 功率型锂离子动力电池的内阻特性[J]. 北京交通大学学报, 2011, 35(5): 119-123. Guo Hongyu, Jiang Jiuchun, Wang Jisong, et al. Characteristic on internal resistance of lithiumion power battery[J]. Journal of Beijing Jiaotong University, 2011, 35(5): 119-123.
[12] 文锋. 纯电动汽车用锂离子电池组管理技术基础问题研究[D]. 北京: 北京交通大学, 2010.
[13] 杨晟院, 舒适. 一种基于特征线的曲面网格分割方法[J]. 计算机工程与应用, 2008, 44(26): 166-167, 182. Yang Shengyuan, Shu Shi. Method of mesh segmenta- tion based on feature lines[J]. Computer Engineering and Applications, 2008, 44(26): 166-167, 182.
[14] Sun Bingxiang, Wang Lifang. The SOC estimation of NIMH battery pack for HEV based on BP neural network[C]. International Workshop on Intelligent Systems and Applications, 2009.
[15] 范成洲, 曹钧, 王发林, 等. 竖井钻速ANFIS预测模型训练参数正交试验优化[J]. 矿山机械, 2013(10): 108-112. Fan Chengzhou, Cao Jun, Wang Falin, et al. Optimiza- tion on training parameters of shaft-drilled speed prediction model based on ANFIS by orthogonal test[J]. Mining & Processing Equipment, 2013(10): 108-112.