$!esc.html($userInfo.givenName) $!esc.html($userInfo.surname)
$!esc.html($userInfo.givenName) $!esc.html($userInfo.surname)


PhD Candidate

Short Bio.

I received my B.Sc & M.Sc in Electrical Engineering - Electrical Power & Machines from Mosul University, Iraq in 1998 & 2002 respectively. During (2002/2010) I Worked as a Lecturer in Department of Electrical Engineering, Mosul University, Iraq and lectured Different subjects Such as "Basic of electrical engineering", "Electrical circuit analysis", "Engineering Analysis", "Mathematics", ' Electrical machines ", and" Control Engineering ". From May 2011 I jointed Lulea University of Technology, Department of Computer Science & Electrical Engineering, Division of Control Engineering, as a PhD Candidate.

My current research focus on Fault Detection and Diagnosis in the field of electrical machines and Especially in three-phase induction motors.

The proposed fault detection method are based on:

1-the Set Membership Identification (SMI) technique and a novel proposed minimum boundary violation fault detection

2-The second method is an alternative broken bars fault classification method that classifies the operating condition of an induction motor as healthy or faulty. The faulty condition represents a  broken bar. This method has major advantages. It will be demonstrated here that this method will use the theoretically derived features to construct (SVMs)  that will therefore do not need training steps.

A lot of researchers focus on the results of using SVMs for broken bars detection by using training steps,
 here we focus more on what are the theoretical properties and fundamental limitations of using
SVMs  for broken bars detection based on a model based approach. More specific the model of SVM will be based on the model of induction motor (motor parameters) in case the motors for which there is no possibility of collecting training set.