Induction machine condition monitoring using neural network modeling

被引:203
作者
Su, Hua
Chong, Kil To
机构
[1] MIT, Dept Computat Design & Optimizat, Cambridge, MA 02139 USA
[2] Chonbuk Natl Univ, Dept Elect & Comp Engn, Jeonju 561756, South Korea
关键词
condition monitoring; induction motors; neural networks; vibration signal;
D O I
10.1109/TIE.2006.888786
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Condition monitoring is desirable for increasing machinery availability, reducing consequential damage, and improving operational efficiency. Model-based methods are efficient monitoring systems for providing warning and predicting certain faults at early stages. However, the conventional methods must work with explicit motor models, and cannot be applied effectively for vibration signal diagnosis due to their nonadaptation and the random nature of vibration signal. In this paper, an analytical redundancy method using neural network modeling of the induction motor in vibration spectra is proposed for machine fault detection and diagnosis. The short-time Fourier transform is used to process the quasi-steady vibration signals to continuous spectra for the neural network model training. The faults are detected from changes in the expectation of vibration spectra modeling error. The effectiveness of the proposed method is demonstrated through experimental results, and it is shown that a robust and automatic induction machine condition monitoring system has been produced.
引用
收藏
页码:241 / 249
页数:9
相关论文
共 13 条
[1]  
BETTA G, 2002, IEEE T INSTRUM MEAS, V51
[2]  
Gao XZ, 2000, IEEE SYS MAN CYBERN, P2386, DOI 10.1109/ICSMC.2000.884348
[3]  
*HEWL PACK, 1990, 2431 HEWL PACK
[4]   Reducing the impact of false alarms in induction motor fault diagnosis [J].
Kim, K ;
Parlos, AG .
JOURNAL OF DYNAMIC SYSTEMS MEASUREMENT AND CONTROL-TRANSACTIONS OF THE ASME, 2003, 125 (01) :80-95
[5]  
KIM K, 2003, MECH SYSTEM SIGNAL P, V16, P80
[6]  
KIM K, 2005, MECH SYST SIGNAL PR, V116, P223
[7]  
LAGAN PA, 1999, P IEE C UND YOUR CON, P1
[8]  
MOHANTI N, 1987, SIGNAL PROCESSING SI
[9]  
Norgaard M., 2000, ADV TK CONT SIGN PRO
[10]   Multi-step-ahead prediction using dynamic recurrent neural networks [J].
Parlos, AG ;
Rais, OT ;
Atiya, AF .
NEURAL NETWORKS, 2000, 13 (07) :765-786