Parameters identification of induction motor dynamic model for offshore applications

The paper presents a technique to identify parameters of the LuGre dynamic friction model applied to represent mechanical losses of an induction motor. This method is based on Artificial Neural Networks (ANNs) system identification which is able to estimate parameters of nonlinear mathematical models. Within the presented approach, the network is first trained to associate model parameters with predicted friction torque, being given the reference motor speed. When this process completes, the inverse operation is performed and the network delivers estimated parameters of the model based on the reference friction torque. These parameters are then integrated with the dynamic model of the induction motor to form a complete virtual simulator of an electrical actuation system. The advantages and practical significance of the proposed technique are illustrated by an example of a scaled version of an induction motor used in an offshore pipe handling machine. It is demonstrated that the model of this system accurately simulates behavior of the experimental motor in the presence of speed and current reference profiles which resemble the ones characterized by offshore conditions. Hence, the model could be successfully applied in simulation based control system design.