Title :
The intelligent fault modeling of induction motor
Author :
Ling-yan, Lin ; Jian-cheng, Song ; Mu-qin, Tian
Author_Institution :
Coll. of Electr. & Power Eng., Taiyuan Univ. of Technol., Taiyuan, China
Abstract :
The study of early intelligent obstacle diagnosis for large-sized mechanical equipment is of momentous social significance and far-reaching economic importance. The equipment directly influences production safety for enterprises, and concern economic efficiencies. So it is very important for the induction motor to guarantee non-failure work time and the whole cutting process without fault. The early-term fault and in-time diagnosis, however, is the most basic prerequisite for the amount ahead of schedule of maintenance.
Keywords :
fault diagnosis; induction motors; maintenance engineering; fault diagnosis; induction motor; intelligent fault modeling; maintenance scheduling; nonfailure work time; Background noise; Fault diagnosis; Frequency; Hopfield neural networks; Induction motors; Neural networks; Power generation economics; Signal processing; Vibrations; Wavelet packets; fault modelling; inteligence; neuralnetwork;
Conference_Titel :
Probabilistic Methods Applied to Power Systems (PMAPS), 2010 IEEE 11th International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4244-5720-5
DOI :
10.1109/PMAPS.2010.5529002