IC engine air/fuel ratio prediction and control using discrete-time nonlinear adaptive techniques

In this paper, simulation results are presented for internal combustion (IC) engine air/fuel ratio (AFR) prediction and control with discrete-time nonlinear adaptive techniques. A crank-angle domain nonlinear engine model is used for the simulations. A feedforward artificial neural network is used as a function approximator for both AFR prediction and control. Least squares and gradient methods are applied to update the parameters of the neural networks for prediction and control, respectively. The control results are compared with a competing nonlinear sliding mode controller. It is shown that the adaptive controller, without the use of the air mass flow rate signal, gives results comparable with the sliding mode controller which uses air mass flow rate measurement