Fault diagnosis competitive neural network with prioritized modification rule of connection weights

Abstract

In this paper, a competitive neural network architecture is used as an intelligent fault diagnosis system to detect the fault sources in different subsystems or elements of a plant or any other device. The prioritized modification rule for connection weights is introduced and four different procedures are studied and compared from the viewpoint of their efficiency. It is shown that the fourth procedure is more convenient for human type decision-making. The output functions of different neurons are considered as the possibility of being fault sources for different units. The system starts from a vague initial state and the connection weights are modified during the learning procedures. The simulation results of different strategies are analyzed and compared. A typical CNC machine is considered as a case study.