Deep convolutional neural networks for automatic coil pitches detection systems in induction motors

Abstract

Abstract Stator winding structures are one of the most important parameters affecting motor performance in induction motor (IM). When deciding on the coil pitch, the winding structure and the power performance of the motor are also taken into consideration. The stator coil pitch of the IM is known at the design stage of the motor. The stator coil pitch of an IM manufactured and in use may be wanted to be changed with the desire to improve the performance of the motor and suppress some harmonics. In this case, it is necessary to determine the motor winding structure and coil pitch by opening the stator cover of the motor, removing the rotor, and manually examining the stator winding structure visually. However, this process prolongs this improvement process considerably. A system that can detect the stator coil pitch according to the stator current behavior while the motor is running can significantly shorten this improvement process. For this purpose, in this study, a deep convolutional neural network (DCNN) model that can automatically estimate IM stator coil pitch angle with an accuracy rate of 100% is designed and applied.