Estimation of Speed, Stator and Rotor Winding Temperature of an Induction Machine Using a CFNN

Because of the financial costs associated with delayed output, induction motor failures can be quite costly. According to studies conducted by the IEEE Industry Applications Society, the insulation of the stator winding is responsible for 30% of motor failures. Because of the financial costs associated with delayed output, induction motor failures can be quite costly. Based on a cascade-forward neural network (CFNN) with Bayesian Regulation Backpropagation (BRBP), a sensorless speed, stator and rotor resistance, and temperature estimator for induction motors is proposed in this research. Because we don't want to employ a thermal sensor, we'll use a thermal model to estimate the temperature of the BDC machine. Previous research has suggested either nonintelligent estimators that rely on the model, such as the extended Kalman filter and Luenberger's observer, or estimators that do not estimate the speed, temperature, and resistance all at the same time. Simulation and comparison with simulation findings from the literature have both been used to verify the suggested method.