Neural networks as controllers
Control of automobile engine operating under idle conditions, must operate far away from its optimal region of operation. The idling is highly nonlinear time-varying process influenced by electric loads, shifting from neutral to drive in automatic transmissions, and other periodic or random disturbances. Regulating the engine control by using physical modeling and traditional adaptive control is a difficult problem, because there are a number of unknown variables in the physical model, and because of random disturbances. This is precisely a situation where neural network control might offer an alternate and more effective approach.
KeywordsCombustion Manifold Torque Propa Cuted
Unable to display preview. Download preview PDF.
- G.V. Puskorius and L.A. Feldkamp, Neurocontrol on nonlinear dynamical systems with Kalman filter-trained recurrent networks, IEEE Trans. on Neural Networks, to appear.Google Scholar
- Handbook of Intelligent Control. Neural, Fuzzy and Adaptive Approaches. Edited by D.A. White and D.A. Sofge, Van Nostrand, New York (1992).Google Scholar
- B.K. Powell and J.A. Cook, Nonlinear low frequency phenomenological engine modeling and analysis, in “Proceedings of the 1987 American Control Conference,” vol 1 (1987), 336–340.Google Scholar