Identification of leakages in the inlet system of an internal combustion engine with the use of Wigner-Ville transform and RBF neural networks

Abstract

In recent years the number of vehicles using the roads all over the world has been constantly increasing. A continuous progress in the field of new technologies causes that they become cheaper and cheaper to manufacture and at the same time more accessible. In order to balance the positive and negative effects of motorisation development, world organisations introduce stricter and stricter regulations concerning the safety and the natural environment protection. Each car produced now is equipped with an on-board diagnostic system OBD. Such systems serve to assess the efficiency of the basic elements in a vehicle. The article attempts to determine the lacks of tightness in the inlet system of the internal combustion engine on the basis of vibration effects emitted by the engine. On the basis of a model prepared with the use of Wigner-Ville transform a series of experiments has been conducted to achieve a design of a properly functioning neural classifier which may extend the operation of an OBD system. © 2012 Springer-Verlag.