EFFICIENCY ESTIMATION OF INDUCTION MOTORS AT DIFFERENT SIZES WITH ARTIFICIAL NEURAL NETWORKS AND LINEAR ESTIMATION USING CATALOG VALUES

Induction motors are the most preferable motors for the locomotives because of their simple but robust structure. The efficiency of the preferred motor is crucial for the limitation of the load pulled by the locomotive and suitability for the geographic conditions. For this reason, determining energy efficiency and operating conditions in induction motors is a very important issue. It is often not possible to experimentally realize the efficiency of induction motors, because this means that the motor is stopped during that time. This is an obstacle to the efficiency of the operator while trying to contribute to energy efficiency in the enterprise.   Therefore, estimation the efficiency of the motor provides a significant contribution to the operation and energy efficiency. Many studies have been made in the literature, which related to this issue. The difference of this study is that efficency estimations of induction motors at 17 different power are realized with artificial neural networks and linear prediction by looking at the values of speed, current and moment in the catalog. And also before the estimation is applied, the statistical relations between efficiency and moment, efficiency and speed, efficiency and current of the motor are also analyzed and presented.