Adaptive control of gasoline engine air-fuel ratio using artificial neural networks

Adaptive control is seen as playing an important role in meeting the ever tightening legislation on vehicle emissions and the requirement to maintain these low emission levels throughout the lifetime of the vehicle. Due to the highly non-linear air and fuel flow processes involved, adaptive control based on linear techniques is ineffectual. However, artificial neural networks (ANNs) offer the capability to model the process non-linearities, clearing the way for non-linear ANN model based predictive engine control. This paper presents work undertaken by EDS, Ricardo Consulting Engineers Ltd. and the University of Newcastle, under the auspices of the Neuro Control Club, to investigate the application of ANNs for adaptive Air Fuel Ratio (AFR) control in gasoline engines. A multiple ANN architecture has been designed and implemented to accommodate the variable time constant, gain and time delay aspects of the engine process. The paper discusses the rationale behind the multiple network design, the problems encountered in developing an ANN model of a process already under control, and a possible technique for online adaption of that model.