Idle Speed Stabilization by Neural Network Model-Based Control of Ignition in SI Engine

The paper presents an algorithm of idle speed control of the spark ignition automotive engine by means of spark advance control.

The control algorithm is based on a neural network model of the effective torque. The additional load is estimated as effective torque less brake torque on the basis of a linear quadratic model. The additional load is understood as the sum of the alternator brake torque and the momentary and/or permanent changes of the engine's characteristics.

The additional load value estimated, the required value of angular acceleration can be determined to make the engine return to the specified speed. This acceleration is achieved by adjusting spark advance. The required value of spark advance is estimated on the basis of the neural network model converse to that of the effective torque.

The algorithm was experimentally compared with PID and adaptive algorithms in the same test bed. The tests were conducted under sudden change of external load. The proposed algorithm proved to be more effective in terms of control error.