An adaptive neural network control method for automotive fuel-injection systems

An adaptive neural network methodology is developed for air-to-fuel (A/F) ratio control of automotive fuel-injection systems. The dynamics of internal combustion engines and fuel-injection systems are extremely nonlinear, impeding methodical application of control theories. Thus, the design of standard production controllers relies heavily upon calibration and look-up tables. A neural network-type controller is developed for its function approximation abilities and its learning and adaptive capabilities. A cerebellar model articulation controller (CMAC) neural network is implemented in a research automobile to demonstrate the feasibility of this control architecture