A neural-network-based adaptive variable structure control methodology isproposed for the tracking problem of nonlinear discrete-time input-output systems. The unknowndynamics of the system are approximated via radial...A neural-network-based adaptive variable structure control methodology isproposed for the tracking problem of nonlinear discrete-time input-output systems. The unknowndynamics of the system are approximated via radial basis function neural networks. The control lawis based on sliding modes and simple to implement. The discrete-time adaptive law for tuning theweight of neural networks is presented using the adaptive filtering algorithm with residueupper-bound compensation. The application of the proposed controller to engine idle speed controldesign is discussed. The results indicate the validation and effectiveness of this approach.展开更多
The intake air control system of a gasoline engine is a typical nonlinear system, and included among the adverse fac-tors that always induce poor idle-speed control stability are dead time and disturbances in the inta...The intake air control system of a gasoline engine is a typical nonlinear system, and included among the adverse fac-tors that always induce poor idle-speed control stability are dead time and disturbances in the intake air control process. In this paper, to improve the responsiveness when idling with regard to disturbances, a mean-value engine model (MVEM) with dead time was constructed as the control object, and the two servo structures of sliding mode control (SMC) were studied for better idle control performance, especially in transient process of speed change. The simulation results confirmed that under the constraint condition of control input, the robustness of idle speed control that is being subjected to torque disturbances and noise disturbances can be greatly improved by use of the servo structure II.展开更多
基金This project is supported by National Natural Science Foundation of China (No.59806007)
文摘A neural-network-based adaptive variable structure control methodology isproposed for the tracking problem of nonlinear discrete-time input-output systems. The unknowndynamics of the system are approximated via radial basis function neural networks. The control lawis based on sliding modes and simple to implement. The discrete-time adaptive law for tuning theweight of neural networks is presented using the adaptive filtering algorithm with residueupper-bound compensation. The application of the proposed controller to engine idle speed controldesign is discussed. The results indicate the validation and effectiveness of this approach.
文摘The intake air control system of a gasoline engine is a typical nonlinear system, and included among the adverse fac-tors that always induce poor idle-speed control stability are dead time and disturbances in the intake air control process. In this paper, to improve the responsiveness when idling with regard to disturbances, a mean-value engine model (MVEM) with dead time was constructed as the control object, and the two servo structures of sliding mode control (SMC) were studied for better idle control performance, especially in transient process of speed change. The simulation results confirmed that under the constraint condition of control input, the robustness of idle speed control that is being subjected to torque disturbances and noise disturbances can be greatly improved by use of the servo structure II.
