Neural Network Control of Air-to-Fuel Ratio in a Bi-Fuel Engine

In this paper, a neural network-based control system is proposed for fine control of the intake air/fuel ratio in a bi-fuel engine. This control system is an add-on module for an existing vehicle manufacturer's electronic control units (ECUs). Typically the ECU is calibrated for gasoline and provides a good control of the intake air/fuel ratio with gasoline. The neural network-based control system is developed to allow the conversion of a gasoline ECU to a bi-fuel form with compressed natural gas at minimal cost. The effectiveness of the neural control system is demonstrated by using a simulation of a Dodge four-stroke bi-fuel engine.