APPLICATION OF NEURAL NETWORKS TO DETECT ECCENTRICITY OF INDUCTION MOTORS
Paweł Ewert 1  
 
 
More details
Hide details
1
Wroclaw University of Science and Technology
 
Power Electronics and Drives 2017;2 (37)(2)
Article (PDF)
 
KEYWORDS:
TOPICS:
ABSTRACT:
In the paper the possibility of using neural networks to detect eccentricity of induction motors is presented. A field-circuit model, which was used to generate a diagnostic pattern is discussed. The formulas on the characteristic fault frequencies for static, dynamic and mixed eccentricity, occurring in the stator current spectrum, are presented. Teaching and testing data for neural networks, based on a preliminary analysis of diagnostic signals (phase currents), were prepared. Two types of neural networks are discussed: general regression neural network (GRNN) and multilayer perceptron (MLP) neural network. This paper presents the results obtained for each type of the neural network. Developed neural detectors are characterized by high detection effectiveness of induction motor eccentricity.
CORRESPONDING AUTHOR:
Paweł Ewert   
Wroclaw University of Science and Technology, ul. Smoluchowskiego 19, 50-372 Wroclaw, Poland
eISSN:2543-4292
ISSN (print):2451-0262