International Journal of Scientific & Engineering Research, Volume 5, Issue 10, October-2014 946 ISSN 2229-5518 IJSER © 2014 http://www.ijser.org Artificial Intelligent Techniques In Real-Time Diagnosis Of Stator And Rotor Faults In Induction Machines Uhunmwangho Roland and Omorogiuwa Eseosa ABSTRACT: This work involves the development of an artificial intelligent (AI) scheme in the detection of rotor and stator faults in induction machines. Using discrete wavelet transform technique to process the stator current signals measured from faulty motors with isolated cases of rotor and stator faults, the signals are then matched against known fault signatures for the types of fault. The statistical features of fault signals such as mean, Skewness etc. were then extracted and fed to an Artificial Neural Network (ANN) for training. Different ANN architectures were then compared in terms of their accuracy in classification. The network with the lowest mean squared error was then tested with separate data set and the results found to be satisfactory ——————————  —————————— 1 INTRODUCTION/BACKGROUND OF STUDY Three-phase induction machines also known as asynchronous machines are the most popular type of rotating electrical machines (Okan Ozgonenel et al., 2011) and widely used in many industrial processes such as automotive, manufacturing, mining, construction etc. Example is the squirrel cage type and has the advantage of being extremely rugged, requiring very low maintenance due to its construction mode. These attributes combined with its relatively low cost makes it an integral component in industrial processes (Jawadekar et al., 2011). Regardless of these advantages, the work by Bellini et al., 2008, illustrates that induction machines are subject to unexpected machine failures especially due to high stresses, which results in reduced productivity, increased production downtime, and damage of related machinery. Thus regular maintenance of the machine is scheduled in order to detect faults early before they result in catastrophic failures. There arise the need for reduction in costs associated with frequent scheduled maintenance while preventing excessive downtime due to machine failure. Figure 1.0 Average downtime costs for different industries due to faults (Grubic et al, 2009) The major faults associated with three-phase induction machines are broadly classified into two (Pandey et al., 2012): Electrical and Mechanical faults. The electrical faults have two main divisions: Stator faults and Rotor faults The mechanical faults are damaged bearing, Eccentricity, Misalignment and Bent shaft IJSER