Signature Analysis as a Medium for Faults Detection in Induction Motors

An induction motor (IM) is an essential component in process industries and power plants. Therefore, for most applications requiring IMs, the reliability, efficiency and performance are the key factors. Since the costs of break down and unforeseen shut downs in these industries are extremely high, the need for high reliability is always demanded. Most of the failures in IMs are caused by incipient faults progressed over a certain period. If such faults are detected in a reasonable time, it will save progression towards catastrophic damage. Therefore, condition monitoring of IM became increasingly significant. This paper proposes electrical method for online monitoring of IM such as Motor Current Signature Analysis (MCSA) and it proposes elimination of any other sensors. The MCSA technique makes use of the stator current signature for detecting fault frequencies and spectrum. When there is a fault in a motor, the harmonic frequency contents of the line current differ than that of a healthy motor. So, in this work, unbalance and misalignment faults detection methods are implemented using MCSA in LabVIEW with the help of fast fourier transform (FFT) and artificial neural network (ANN).