Gear Noise Diagnosis System For Automobile Transmission Using Artificial Intelligence (Convergence of Training Process)

The present study deals with a new gear noise diagnosis system for automobile transmission units with an artificial intelligence; i.e., the neural net. In order to use this system, first of all, the system must be trained with teacher signals. This training process includes iterative calculations, so that the convergence in the training process is a very important issue. In the present paper, conditions were determined for the convergence. Then, the judgement performance of the developed system was discussed. As a result, the system can realize over 70% performance of noise evaluation experts.