CMAC Neural Network Application on Fault Diagnosis of Water Circulation System

In this paper, a CMAC (cerebellar model articulation controller) neural network application on fault diagnosis for water circulation system is proposed. Firstly, we build a CMAC neural network based diagnosis system depending on the fault types. Secondly, the fault patterns, obtained from the China scholar’s technical data, would be employed to train the CMAC neural network off-line. Thirdly, the learning algorithm was developed to guarantee the learning convergence. Finally, combining the MATLAB program the trained neural network can be used to diagnose the possible fault types of water circulation system. Comparing with the traditional schemes, following advantages are obtained at least:(1)Eliminate the weights interference between different fault type patterns.(2) Improve the noise rejection ability.(3) Alleviate the dependency to expert’s expertise.(4) Memory size can be reduced by new excited addresses coding technique . (5) High learning and diagnosis speed.