基于预测的EFI发动机自适应混合控制  

Prediction Based Adaptive-hybrid Control of EFI Engine

作　　者：严寒冰[1] 秦东兴[1] 巨辉[1] 

机构地区：[1]成都信息工程学院控制工程系,四川成都610225

出　　处：《车用发动机》2014年第5期8-11,共4页Vehicle Engine

基　　金：四川省教育厅重点项目(11ZA266)

摘　　要：针对发动机非线性、时滞、时变对象在线控制问题,利用高斯函数作为CMAC神经网络的基函数降低网络计算量,结合自适应算法构建发动机空燃比控制方法。在此基础上,为获取精确控制效果,提出采用灰色马尔科夫模型预测下一时刻氧传感器的状况,从而对喷油量进行补偿,以消除由于传感器信号时间滞后对喷油补偿量的影响。在采用台架试验数据确定控制策略模型的结构参数的基础上,对提出的自适应混合控制方法进行了测试。测试结果说明,提出的控制方法不仅保证了稳态空燃比控制的准确性,同时提高了暂态工况下空燃比控制的有效性。For the online control problems of nonlinear, time-delaying and time-variant parameter, the engine air-fuel ratio control method was established based on the adaptive algorithm and the network calculation cutback caused by using the Gaussian function as the basis function of GMAC network. Then it was put forward that the following status of oxygen sensor was predicted with Gray-Markov model to decrease the sensor time-delaying influence on fuel compensation. The structural parame- ters of control model were determined with the bench test data and the proposed adaptive-hybrid control algorithm was further tested. The results show that the control method can ensure the control accuracy of air-fuel ratio under steady state and improve its control validity under transient state.

关 键 词：灰色马尔科夫预测 混合控制 自适应控制 空燃比 

分 类 号：TK411.2[动力工程及工程热物理—动力机械及工程] TP273.2[自动化与计算机技术—检测技术与自动化装置]