A NEURAL NETWORK APPROACH TO REAL-TIME CONDITION MONITORING OF INDUCTION-MOTORS

Induction motors are subject to incipient faults which, if undetected, can lead to serious machine failures. Incipient fault detection methods applied in large induction motors of greater than 100 hp are often too costly or physically impractical for use on small- and medium-size induction motors. This paper develops a neural network-based incipient fault detector for small- and medium-size induction motors. The neural network-based incipient fault detector avoids the problems associated with traditional incipient fault detection schemes by employing more readily available information such as rotor speed and stator current. The neural network design is evaluated in real time in the laboratory on a 3/4-hp permanent magnet induction motor. The results of this evaluation indicate that the neural network-based incipient fault detector provides a satisfactory level of accuracy, greater than 95%, which is suitable for real-world applications.