An Evaluation of Wavelet Network-Based Stator Estimation for Induction Motor Temperature Monitoring

A novel motor stator estimation scheme for the purpose of monitoring the temperature in steady state is proposed and the feasibility of wavelet network-based estimation of the stator resistance as an indicator of stator winding temperature is evaluated. By the use of wavelet network that accurately localizes the characteristics of a signal both in the time and frequency domains, the occurring instants of the signal change can be identified by the multi-scale representation of the signal. The improved least squares algorithm transform is used to fulfill the network structure initialization and parameter identification, and then the mapping relationship between the stator voltage, stator current, power factor angle and the rotor speed is obtained. The stator resistance and rotor resistance are identified with motor mathematical model, and then the corresponding temperature is calculated according to the principle that the metal resistance depends on its temperature. The simulated results verify the validity of the proposed method and the analysis for asynchronous motor temperature monitoring.