Fault diagnosis expert system of artillery radar based on neural network

Abstract

The fault of new type artillery radar is highly complex and correlative. The neural network technology was incorporated into the radar fault diagnosis after the fault features of new type artillery radar and the shortage of the expert diagnosis system were analyzed. There are many difficulties in the process of the servicing for the artillery radar, such as technology level is low, fault diagnosis is difficult. To resolve the problem, a fault diagnosis expert system was realized based on RBF(Radial Basis Function) neural network. The collectivity structure of expert system, structure and function of software were discussed. Accordingly, several key techniques such as the fault diagnosis principle of RBF neural network, knowledge database, reasoning engine were also given in detail. The application results showed that the expert system proved its feasibility and practical, the servicing efficiency and fault diagnosis ability are improved.