Speed estimation for submersible motor based on elman neural network

In consideration of the difficulty to install speed sensor result form special high temperature working environment of submersible motor, in this paper, a method of Elman neural network is used to estimate the speed of sensorless submersible motor. In the experiment, the stator current measured by data collector was analyzed by wavelet, thus the influence of high frequency noisy caused by high temperature is filtered off, and the useful signal is extracted as sample input, the speed signal collected by speed sensor as sample output, a neural network is trained on the principle 'training off-line, estimating on-line', so that the network can estimate the speed only using stator current. It is proved to have very high precision and good dynamic quality. Furthermore, the estimation result can provide powerful security for closed-loop control and fault diagnosis.