No abstract

This paper presents an neural network based approach to identify in real time faulty components found on industrial brushless exciters. A brushless exciter or "rotating rectifier" is a key component of a synchronous motor. Improper operation of this component can prove costly for the motor's owner. A method is based on Fourier analysis combined with the use of neural networks is presented to detect some common failures involving a three phase rotating rectifier. A laboratory setup was constructed to create fault condition data sets. These data sets were used to determine a preprocessing technique in conjunction with an appropriate neural net structure and training algorithm. Robustness of the system was tested using various levels of measurement noise to good result.

The power electronic converters, electric machines, and mechanical loads are key parts of the electric drives systems, and these components are usually modeled and analyzed using specific simulation tools. The overall performances of the electric drives are influenced by system's interconnected components. One solution, to investigate the interaction between different parts of these multi-domain systems, is to integrate them into only one simulation environment. This paper presents the development of two integrated models of a three-phase induction motor (IM) drive: one, based on d-q machine model using MATLAB/SimulinkSimscape, the second being based on finite element analysis (FEA) motor model using ANSYS Simplorer/Maxwell software. The goal is to analyze the system models capabilities to simulate the faults detection caused by failures of different drive's components. The motor current signature analysis is used, in this paper, for monitoring the operation of the IM fed through a pulse-width-modulated (PWM) power inverter. Finally, two case studies are presented, one illustrating the effects of a faulty device of the PWM inverter, and the second case demonstrating the influence of the IM's stator fault. Another objective of this study is to provide users a convenient way of instruction in the area of faults detection and power quality of alternating current (ac) machines and drives.

No abstract

No abstract