Monitoring of induction machines load torque disturbances: an alternative NN-based method

This paper addresses the problem of the real time rebuilding of the load torque disturbances in asynchronous machines. Since the load pattern modifies the motor´s supply current, it should be possible to use the current pattern to rebuild torque pattern, utilizing the machine itself as a torque sensor. In the paper the problem is studied utilizing both relationships developed under simplifying assumptions and a more complex model of the machine. The results obtained are compared with the experimental ones. Reference is made to low frequency torque disturbances, that cause a quasistationary machine behavior. It is shown that a neural network approach can be an alternative and efficient method for the torque pattern recognition.