Research of Fault Diagnosis Method Based on Immune Neural Network

A fault diagnosis method based on immune neural network is proposed in this paper. In this method the weights of neural network is encoded as the antibody, and the network error is considered as the antigen. Firstly the weights of the network are searched globally using immune algorithm, then searched locally using BP algorithm. The simulation is done through the experiment of the pump-jack, and the diagnosis method proposed in this paper is compared with the fault diagnosis method based on BP neural network. The result shows that the fault diagnosis method based on immune neural network has the capability in escaping local minimum and improving the algorithm speed.