【作者】 陈渝光； 钱微； 廖仕利；

【Author】 Yuguang Chen~(1,2) Wei Qian~1 Shili Liao~1 (1)Chongqing Institute of Technology,Chongqing 400050(E-mail:cyg6610@cqit.edu.cn) (2)The Key Lab of Automobile Parts& Test Technique in Chongqing,Chongqing 400050

【机构】 重庆工学院； 重庆市汽车零部件及其检测技术重点实验室；

【摘要】 针对汽车发动机参数具有离散性、非线性和不确定性,难以精确控制瞬态过程的过量空气系数和点火时刻的问题,提出了一种基于免疫神经网络的发动机自适应控制。该方法很好地融合了基于遗传算法的模糊控制参数离线寻优和基于BP神经网络的免疫在线调节优势。在模糊控制参数离线优化的基础上,探讨了基于BP神经网络的免疫在线自适应调节。实验表明,发动机的动力性、经济性指标和自适应能力取得到了明显提高。更多还原

【Abstract】 Because the parameters of a car-engine are of the discreteness,nonlinear and uncertain characteristics,it is hard to control accurately the excess air coefficient and the spark advance angle in dynamic procedure.A self-adapting control based on immune neural network was proposed.It absorbs well the advantages both off-line optimization of the fuzzy control parameters on genetic arithmetic and on-line regulation on an immune neural network.Self-adaptive immune regulation based on BP neural network was probed on the basis of the fuzzy control parameters’ optimization.The experiment results demonstrate that the dynamic performances,economic performances and self-adaptation are all improved obviously.更多还原