车用汽油机瞬态空燃比的混沌时序非线性组合辨识模型  

Chaotic Sequence Nonlinear Combination Identification Model of Transient Air-fuel Ratio of Gasoline Engine

作　　者：李岳林[1] 解福泉[1,2] 徐东辉[3] 吴钢[1] 胡忠录[1] 

机构地区：[1]长沙理工大学汽车与机械工程学院,湖南长沙410076 [2]河南交通职业技术学院,河南郑州450005 [3]宜春学院物理科学与工程技术学院,江西宜春336000

出　　处：《中国公路学报》2015年第4期109-115,共7页China Journal of Highway and Transport

基　　金：教育部高等学校博士学科点专项科研基金项目(20104316110002);国家自然科学基金项目(51176014;51406017);河南省交通运输厅科研项目(2012PII10);工程车辆轻量化与可靠性技术湖南省重点实验室开放基金项目(2013kfjj02);江西省科技计划项目(20151BBE50108)

摘　　要：为提高汽油机瞬态空燃比的辨识精度,提出了混沌时序非线性组合辨识模型。采用2种单项辨识方法,包括最小二乘支持向量机(LS-SVM)及径向基函数(RBF)前向型神经网络,分别对瞬态空燃比时间序列进行建模与辨识。采用非线性组合方法利用BP神经网络对2种单项辨识方法的结果进行组合辨识,并与Elman神经网络模型及最小二乘辨识模型进行比较。结果表明:混沌时序非线性组合辨识模型的辨识精度优于Elman神经网络模型及最小二乘辨识模型,具有更强的非线性辨识能力,能提高瞬态空燃比的辨识精度,为空燃比反馈控制的成功实行提供了有力依据。In order to improve the identification accuracy of transient air-fuel ratio of gasoline engine, a chaotic sequence nonlinear combination identification model was proposed. With two kinds of individual identification methods, including the least squares support vector machine （LS-SVM） and the radial basis function （RBF） forward neural network, the sequence of transient air-fuel ratio was modeled and identified respectively. With the nonlinear combination method and the BP neural network, the results of the two individual identification methods were combined and identified, which were compared with the identification methods of Elman neural network model and the recursion algorithm of the least-square. The results show that the identification accuracy of the chaotic sequence nonlinear combination identification model is superior to the Elman neural network model and the recursion algorithm of the least-square, with stronger nonlinear recognition ability, which can improve the identification accuracy of the transient air-fuel ratio and provide a strong basis for successful feedback control of air-fuel ratio.

关 键 词：汽车工程 混沌时序 非线性组合 辨识 支持向量机 RBF神经网络 

分 类 号：U464.171[机械工程—车辆工程]