Active Current Sensor Fault-Tolerant Control of Induction Motor Drive with Online Neural Network-Based Rotor and Stator Resistance Estimation

Abstract This article presents an active current sensor (CS) fault-tolerant control (FTC) strategy for induction motor (IM) drive with adaptation of rotor and stator resistances. The estimator online resistance parameters was applied the reconstruction missing signals. A model reference adaptive system (MRAS), based on a neural network (NN), used to estimate resistance. Additionally, estimation ratio index. use such solution allowed significant increase in quality reconstruction, which is particularly important design CS fault detection (FD) compensation algorithms. wide range simulation studies have been carried out different operating conditions IM drive. results showed that applying can improve by up approximately 95% under rated point. study nominal low speeds, two, one, without healthy CS.