Estimação de Parâmetros Elétricos do Motor de Indução Trifásico Utilizando Redes Neurais Artificiais

Abstract

The three-phase induction motor is the most widely used machine in industry for drive systems due to its robustness and simple maintenance. Understanding the parameters of the motor’s equivalent circuit is essential for sizing and designing the control system, enhancing the system’s efficiency and reliability. With the advancement of intelligent systems, computational techniques are increasingly applied to this task, emerging as an alternative to conventional methods. In this context, this work proposes a reliable and generalist method based on artificial neural networks to estimate the parameters of the equivalent electrical circuit of three-phase induction motors based on data provided by the manufacturer. A total of 542 different motors was considered, with power ranging from 0.75 kW to 55 kW. Two approaches were compared: the first uses a single neural network to estimate all parameters of the machine, while the second employs a specialist network to estimate each parameter individually. The proposed methodology presented results consistent with the literature.