基于核主元约简与半监督核模糊聚类的车辆行驶工况判别
|
摘要
为有效利用汽车行驶工况中与类别属性间的统计特征,提高汽车行驶工况判别的准确性与快速性,首先选择车速和踏板信号的数据信息构建特征集,利用相关性分析和核主元分析对特征集中能敏感反映工况类别的特征数据信息进行二次特征提取,按累计贡献率大于90%的标准进行主要特征量的选择,实现输入变量的二次约简;利用小波核函数的非线性映射能力构建半监督核模糊C均值聚类方法进行车辆行驶工况的判别。通过长春某混合动力公交车试验结果表明,该方法更全面准确地反映了工况特性,有效降低了输入特征参数的维数,更加准确有效地提取了不同工况条件下汽车行驶状态的数据特征,通过半监督核模糊C均值聚类算法中加入少量的训练样本来引导聚类过程,聚类精度可达到98.75%。
In order to utilize the statistic characteristics among the information that associated with categories in vehicle driving cycle effectively, the speed and the pedal signal data information are selected to construct feature set to improve the accuracy and rapidity of distinguishing the vehicle driving cycle firstly. Then, to realize the second reduction of the input variables, second feature which sensitively reflects characteristic data information of driving cycle category is extracted through the correlation analysis and the kernel principal component analysis. According to the standard of accumulation contribution rate that greater than 90%, the main feature is chosen to achieve secondary reduction of input variables. The nonlinear mapping ability of the wavelet kernel function is adopted to establish semi-supervised kernel fuzzy C means clustering algorithm for the working condition judgments. The experimental results show that this algorithm can reflect the driving cycle characteristics more comprehensively and accurately. In addition, the dimension of the input characteristic parameters is reduced effectively. And the data characteristics of vehicle driving condition are extracted under different working conditions more accurately and availably. Simultaneously, the clustering accuracy can reach 98.75% by adding a small amount of training samples in semi-supervised kernel fuzzy C means clustering algorithm to guide the clustering process.
In order to utilize the statistic characteristics among the information that associated with categories in vehicle driving cycle effectively, the speed and the pedal signal data information are selected to construct feature set to improve the accuracy and rapidity of distinguishing the vehicle driving cycle firstly. Then, to realize the second reduction of the input variables, second feature which sensitively reflects characteristic data information of driving cycle category is extracted through the correlation analysis and the kernel principal component analysis. According to the standard of accumulation contribution rate that greater than 90%, the main feature is chosen to achieve secondary reduction of input variables. The nonlinear mapping ability of the wavelet kernel function is adopted to establish semi-supervised kernel fuzzy C means clustering algorithm for the working condition judgments. The experimental results show that this algorithm can reflect the driving cycle characteristics more comprehensively and accurately. In addition, the dimension of the input characteristic parameters is reduced effectively. And the data characteristics of vehicle driving condition are extracted under different working conditions more accurately and availably. Simultaneously, the clustering accuracy can reach 98.75% by adding a small amount of training samples in semi-supervised kernel fuzzy C means clustering algorithm to guide the clustering process.
引文
[1]姜平,石琴,陈无畏.基于马尔科夫的城市道路行驶工况构建方法[J].农业机械学报,2009,40(11):26-30.JIANG Ping,SHI Qin,CHEN Wuwei.Driving cycle construction methodology of city road based on Markov process[J].Transaction of the Chinese Society of Agricultural Machinery,2009,40(11):26-30.
[2]石琴,李友文,郑与波.随机数在汽车行驶工况构建中的应用[J].西南交通大学学报,2010,45(6):938-945.SHI Qin,LI Youwen,ZHENG Yubo.Application of random number in driving cycle model[J].Journal of Southwest Jiao Tong University,2010,45(6):938-945.
[3]田毅,张欣,张良,等.神经网络工况识别的混合动力电动汽车模糊控制策略[J].控制理论与应用,2011,28(3):363-369.TIAN Yi,ZHANG Xin,ZHANG Liang,et al.Fuzzy control strategy for hybrid electric vehicle based on neural network identification of driving conditions[J].Control Theory&Applications,2011,28(3):363-369.
[4]MAZUROWSKI M A,HABAS P A,ZURADA J M,et al.Training neural network classifiers for medical decision making:The effects of imbalanced datasets on classification performance[J].Neural Networks,2008,21(2-3):427-436.
[5]康家银,纪志成,龚成龙.一种核模糊C均值聚类算法及其应用[J].仪器仪表学报,2010,31(7):1657-1663.KANG Jiayin,JI Zhicheng,GONG Chenglong.Kernelized fuzzy C-menas clustering algorithm and its application[J].Chinese Journal of Scientific Instrument,2010,31(7):1657-1663.
[6]李丹,顾宏,张立勇.基于属性权重区间监督的模糊C均值聚类算法[J].控制与决策,2010,25(3):457-465.LI Dan,GU Hong,ZHANG Liyong.Fuzzy C-means algorithm with interval-supervised attribute weights[J].Control and Decision,2010,25(3):457-465.
[7]郭磊,陈进,朱义,等.基于小波函数的核主元特征约简方法研究[J].振动工程学报,2009,22(3):287-291.GUO Lei,CHEN Jin,ZHU Yi,et al.Feature reduction method based on wavelet kernel-PCA[J].Journal of Vibration Engineering,2009,22(3):287-291.
[8]徐超,张培林,任国全,等.基于改进半监督模糊C-均值聚类的发动机磨损故障诊断[J].机械工程学报,2011,47(17):55-60.XU Chao,ZHANG Peilin,REN Guoquan,et al.Engine wear fault diagnosis based on improved semi-supervised fuzzy C-means clustering[J].Journal of Mechanical Engineering,2011,47(17):55-60.
[9]张永志,董俊慧.基于模糊C均值聚类的模糊RBF神经网络预测焊接接头力学性能建模[J].机械工程学报,2014,50(12):58-64.ZHANG Yongzhi,DONG Junhui.Modeling fuzzy RBF neural network to predict of mechanical properties[J].Journal of Mechanical Engineering,2014,50(12):58-64.
[10]呼文亮,王惠文.基于贝叶斯准则的支持向量机预测模型[J].北京航空航天大学学报,2010,36(4):486-489.HU Wenliang,WANG Huiwen.Prediction modeling based on Bayes support vectormachine[J].Journal of Beijing University of Aeronautics and Astronautics,2010,36(4):486-489.
[11]ZHANG C,VAHIDI A.Role of terrain preview in energy management of hybrid electric vehicles[J].Transactions on Vehicular Technology.IEEE,2010,59(3):1139-1147.
[12]SAMARAS C,MEISTERLING K.Life cycle assessment of greenhouse gas emissions from plug-in hybrid vehicles:Implications for policy[J].Environmental Science&Technology,2008,42(9):3170-3176.
[13]张津涛.电动汽车城市道路行驶工况自学习方法的研究[D].天津:天津大学,2008.ZHANG Jintao.Self-learning algorithm of city driving cycles for electrical buses[D].Tianjin:Tianjin University,2008.
[14]田毅,张欣,张昕,等.计及行驶工况影响的混合动力汽车控制策略[J].汽车工程,2010,32(8):659-663.TIAN Yi,ZHANG Xin,ZHANG Xin,et al.Hybrid electric vehicle control strategy with consideration of theeffects of driving cycle[J].Automotive Engineering,2010,32(8):659-663.
[2]石琴,李友文,郑与波.随机数在汽车行驶工况构建中的应用[J].西南交通大学学报,2010,45(6):938-945.SHI Qin,LI Youwen,ZHENG Yubo.Application of random number in driving cycle model[J].Journal of Southwest Jiao Tong University,2010,45(6):938-945.
[3]田毅,张欣,张良,等.神经网络工况识别的混合动力电动汽车模糊控制策略[J].控制理论与应用,2011,28(3):363-369.TIAN Yi,ZHANG Xin,ZHANG Liang,et al.Fuzzy control strategy for hybrid electric vehicle based on neural network identification of driving conditions[J].Control Theory&Applications,2011,28(3):363-369.
[4]MAZUROWSKI M A,HABAS P A,ZURADA J M,et al.Training neural network classifiers for medical decision making:The effects of imbalanced datasets on classification performance[J].Neural Networks,2008,21(2-3):427-436.
[5]康家银,纪志成,龚成龙.一种核模糊C均值聚类算法及其应用[J].仪器仪表学报,2010,31(7):1657-1663.KANG Jiayin,JI Zhicheng,GONG Chenglong.Kernelized fuzzy C-menas clustering algorithm and its application[J].Chinese Journal of Scientific Instrument,2010,31(7):1657-1663.
[6]李丹,顾宏,张立勇.基于属性权重区间监督的模糊C均值聚类算法[J].控制与决策,2010,25(3):457-465.LI Dan,GU Hong,ZHANG Liyong.Fuzzy C-means algorithm with interval-supervised attribute weights[J].Control and Decision,2010,25(3):457-465.
[7]郭磊,陈进,朱义,等.基于小波函数的核主元特征约简方法研究[J].振动工程学报,2009,22(3):287-291.GUO Lei,CHEN Jin,ZHU Yi,et al.Feature reduction method based on wavelet kernel-PCA[J].Journal of Vibration Engineering,2009,22(3):287-291.
[8]徐超,张培林,任国全,等.基于改进半监督模糊C-均值聚类的发动机磨损故障诊断[J].机械工程学报,2011,47(17):55-60.XU Chao,ZHANG Peilin,REN Guoquan,et al.Engine wear fault diagnosis based on improved semi-supervised fuzzy C-means clustering[J].Journal of Mechanical Engineering,2011,47(17):55-60.
[9]张永志,董俊慧.基于模糊C均值聚类的模糊RBF神经网络预测焊接接头力学性能建模[J].机械工程学报,2014,50(12):58-64.ZHANG Yongzhi,DONG Junhui.Modeling fuzzy RBF neural network to predict of mechanical properties[J].Journal of Mechanical Engineering,2014,50(12):58-64.
[10]呼文亮,王惠文.基于贝叶斯准则的支持向量机预测模型[J].北京航空航天大学学报,2010,36(4):486-489.HU Wenliang,WANG Huiwen.Prediction modeling based on Bayes support vectormachine[J].Journal of Beijing University of Aeronautics and Astronautics,2010,36(4):486-489.
[11]ZHANG C,VAHIDI A.Role of terrain preview in energy management of hybrid electric vehicles[J].Transactions on Vehicular Technology.IEEE,2010,59(3):1139-1147.
[12]SAMARAS C,MEISTERLING K.Life cycle assessment of greenhouse gas emissions from plug-in hybrid vehicles:Implications for policy[J].Environmental Science&Technology,2008,42(9):3170-3176.
[13]张津涛.电动汽车城市道路行驶工况自学习方法的研究[D].天津:天津大学,2008.ZHANG Jintao.Self-learning algorithm of city driving cycles for electrical buses[D].Tianjin:Tianjin University,2008.
[14]田毅,张欣,张昕,等.计及行驶工况影响的混合动力汽车控制策略[J].汽车工程,2010,32(8):659-663.TIAN Yi,ZHANG Xin,ZHANG Xin,et al.Hybrid electric vehicle control strategy with consideration of theeffects of driving cycle[J].Automotive Engineering,2010,32(8):659-663.