A Neural Network Based Overvoltage Prediction System for Long Cable Issue

Abstract

In most electrical applications, the motor is fed by Pulse Width Modulated(PWM) inverters and by design they are usually in separate locations, requiring long motor leads or cables. Overvoltage is a common phenomenon in AC motor drives that are fed by long cables from PWM inverters, as they use Insulated Gate Bipolar Transistors (IGBT) with small rise time and fall time. This paper proposes an Artificial Neural Network based system to predict overvoltage at the motor terminal with long cable using the parameters cable length and motor capacity.