The application of the equipment fault diagnosis based on modified Elman neural network

The aluminum electrolysis cell is the most important equipment in electrolytic process, which has many types of fault and high occurrence rate. So, it is a high energy consumption process and the process control is very difficult, which reduce the production and quality of the aluminum and waste a lot of electricity energy. Therefore, this paper proposes an equipment fault diagnosis method based on modified output feedback wavelet Elman neural network. This fault diagnosis model adopts wavelet function, with wavelet expansion coefficient and translation coefficient, which results in the guarantee of the speed and accuracy, avoiding falling into local optimal values, and improving the rate of fault diagnosis. Simulation results prove the effectiveness of this method.