No abstract

The necessity to insure a continuous and safety operation for induction motors, involves preventive maintenance program with fault detection techniques. This paper presents the application of a pattern recognition approach in order to detect hmken bars in an induction motor. The aim is to identify the operating conditions according to the level of load. For this purpose, only electrical measurements are used. Some time or freqnency-dependent parameters, which are relevant for fault detection, are described. They are used to build up a pattern vector. This vector is represented by a point and the operating condition of the induction motor are represented by classes in the space. As the dimension of the space is greater than three, the classes and their evolutions can be visualized after a principal component analysis. Then a decision system, based on this signature and the k-nearest neighbors d e , is proposed.

No abstract

No abstract

Absfract-Intensive research efforts have been focused on the Signature Analysis (SA) to detect electrical and mechanical fault condition of induction machines. Different signals can be used: voltage, current, flux and power, This paper is a comparative analysis of two different diagnosis methods that are used to detect and localize failures in induction motors. Thc first one is based on leakage flux measurement and the econd one is a diagnosis method based on.current, electrical bower measurement and pattern recognition. A synthesis. of two methods will be developed. It mainly concerns rotor faults.