Performance Improvement of DTC for Induction Motor-Fed by Three-Level Inverter With an Uncertainty Observer Using RBFN

A stable sensorless controller for DTC of induction motor fed by three-level inverter using the Radial Basis Function Network (RBFN) is presented in this paper. The torque ripple can be drastically reduced and low speed performance can be obtained in the DTC system for high performance induction motor drives. However, speed control performance is still influenced by the lumped uncertainties of the system such as parameter variations, external load disturbances, and unmodeled dynamics which make it difficult to obtain an exact mathematical model. In this paper, the lumped uncertainties are estimated on-line by the RBFN. Simulations as well as experimental results are shown to illustrate the performance of the proposed system.