Inverter Switching Vectors Data of An FCS-MPC Driven Induction Machine for Healthy and Faulty Conditions

Switching vectors of an inverter with model predictive control were collected for different conditions of an induction machine. The induction machine had a rated speed of w=3000 rpm and a rated torque of T=1.20 N·m. The switching vectors were recorded as data series for the induction machine operating at different combinations of speed and torque at healthy and faulty states. Each data series consisted of 22000 switching vectors. Inter-turn short circuit fault was introduced over 2 turns (out of 104 turns) in one phase of the machine. Collected data series were segregated into two sets such that the first set was for training and validation, and the second set was for the test. Each data series in the first set was further split into two data series. The first 70% of data points constituted a data series for training, and the remaining 30% constituted a data series for validation.