Dynamic Process Identification for Steam Generator Based on Wavelet Neural Network

In the operation of nuclear steam generator(SG), the reverse thermal-dynamic effects make its dynamics characteristic difficult to identify. In order to improve the effect of identification, a new method based on wavelet neural network(WNN) was proposed in this paper. The identification model employs series parallel model and the train algorithm for the WNN adopts the back propagation algorithm of Levenberg Marququar dt type (LMBP). The identification on steam generator typical operation modes was implemented. The results show that employing WNN can identify steam generator dynamic process correctly and has adequate precision.