Monitoring and Control of an Internal Combustion Engine

This paper describes work in progress involving the development of techniques for use in enhanced internalcombustion engine-management systems for application in motor vehicles. The aim is to improve the control of the engine by the application of intelligent-systems techniques, thus leading to reduced exhaust emissions and improved fuel economy. A neural-network technique is described for the determination of the airfuel ratio in the engine. This is based on the neural interpretation of the signature which is formed from the voltage waveform at the spark plug. The neuralnetwork learning process requires that the air-fuel ratio is maintained accurately at a constant value during training; in order to facilitate this, a control system executing a fuzzy-logic paradigm was devised and this is also described.