Shaft alignment prediction is essential for the development of effective coupling and rotating equipment maintenance systems. In this paper, we present a modified support vector regression (SVR) approach for shaft alignment predictions based on fast Fourier transform generated spectra data. The modified SVR approach uses data-dependent parameters in order to reduce computation time and achieve better predictions. The spectra data used is characterized by a large number of descriptors and very few data points. The strengths of SVR for shaft misalignment prediction include its ability to represent data in high-dimensional space through kernel functions. We reduce the dimension of the data using a multivariate AIC criterion in order to guarantee that the selected spectra are response dependent. We compare the performance of SVR with two of the most popular techniques used in condition monitoring, partial least squares, and principal components regression. Our results show that we can improve the performance of shaft misalignment prediction using SVR and the approach compares very favorably with partial least squares and principal components regression approaches. Also, we present a quantitative measure, shaft misalignment monitoring index, which can be used to facilitate easy identification of the alignment condition and as input to maintenance systems design.

1.
Wowk
,
V.
, 2000,
Machine Vibration: Alignment
,
McGraw-Hill
, New York.
2.
Kuropatwinski
,
J. J.
,
Jesse
,
S.
,
Hines
,
J. W.
,
Edmondson
,
A.
, and
Carley
,
J.
, 1997, “
Prediction of Motor Misalignment Using Neural Networks
,”
Proceedings of Maintenance and Reliability Conference (MARCON 97)
,
Knoxville, TN
.
3.
Hines
,
J. W.
,
Jesse
,
S.
,
Edmondson
,
A.
, and
Nower
,
D.
, 1999, “
Motor Shaft Misalignment Versus Bearing Load Analysis: Study Shows Shaft Misalignment Reduces Bearing Life
,” Maintenance Technology, April, pp.
11
17
.
4.
Casada
,
D. A.
, 1996, “
Using Motor Data as a Diagnostic Tool: A Collection of Scattered Thoughts
,” Presentation at the University of Tennessee, Knoxville, TN.
5.
Nower
,
D.
, 1996, “
Alignment Tolerances-Why Use Them?
,”
Vibration Institution Meeting Proceedings
.
6.
Hines
,
J. W.
,
Jesse
,
S.
,
Kuropatwinski
,
J.
,
Carley
,
T.
,
Kueck
,
J.
, and
Nower
,
D.
, 1997, “
Motor Shaft Alignment Versus Efficiency Analysis
,”
P/PM Technology
, October, pp.
10
13
.
7.
Hines
,
J. W.
,
Jesse
,
S.
,
Edmondson
,
A.
, and
Nower
,
D.
, 1998, “
Effects of Motor Misalignment on Rotating Machinery
,”
Proceedings of the Maintenance and Reliability Conference (MARCON 98)
.
8.
Haykin
,
S.
, 1999,
Neural Networks: A Comprehensive Foundation
,
Prentice-Hall
, Englewood Cliffs, NJ.
9.
Venkatasubramanian
,
V.
,
Rengaswamy
,
R.
,
Kavuri
,
S. N.
, and
Yin
,
K.
, 2003, “
A Review of Process Fault Detection and Diagnosis, Part III: Process History Based Methods
,”
Comput. Chem. Eng.
0098-1354
27
, pp.
327
346
.
10.
Piotrowski
,
J.
, 1995,
Shaft Alignment Handbook
,
Marcel Dekker
, New York.
11.
Eisenmann
,
R. C.
, Sr.
, and
Eisenmann
,
R. C.
, Jr.
, 1998,
Machinery Malfunction Diagnosis and Correction
,
Prentice-Hall
, Englewood Cliffs, NJ.
12.
Miller Brewing Company
, 2005, “
Miller Study
,” http://www.infraspection.com/products/pdresearch.htmlhttp://www.infraspection.com/products/pdresearch.html (downloaded June 14, 2005).
13.
Wold
,
H.
, 1966, “
Estimation of Principal Components and Related Models by Iterative Least Squares
,”
Multivariate Analysis
,
P. R.
Krishnaiah
,
ed.
,
Academic
, New York, pp.
391
420
.
14.
Massy
,
W. F.
, 1965, “
Principal Components Regression in Exploratory Statistical Research
,”
J. Am. Stat. Assoc.
0003-1291,
60
, pp.
234
246
.
15.
Eastment
,
H. T.
, and
Krzanowski
,
W. J.
, 1982, “
Cross-Validatory Choice of the Number of Components From a Principal Component Analysis
,”
Technometrics
0040-1706,
24
(
1
), pp.
73
77
.
16.
Vapnik
,
V.
, 1995,
The Nature of Statistical Learning Theory
,
Springer-Verlag
, New York.
17.
Vapnik
,
V.
, 1998,
Statistical Learning Theory
,
Wiley
, New York.
18.
Bishop
,
C. M.
, 1995,
Neural Networks for Pattern Recognition
,
Clarendon
, Oxford.
19.
Cherkassky
,
V.
, and
Ma
,
Y.
, 2004, “
Practical Selection of SVM Parameters and Noise Estimation for SVM Regression
,”
Neural Networks
0893-6080,
17
(
1
), pp.
113
126
.
20.
Kwon
,
Y.
,
Jeong
,
M. K.
, and
Omitaomu
,
O. A.
, 2005, “
Adaptive Support Vector Regression Analysis of Closed-Loop Inspection Accuracy
,”
Int. J. Mach. Tools Manuf.
0890-6955,
45
(
12
), pp.
1
8
.
21.
Webb
,
A.
, 1999,
Statistical Pattern Recognition
,
Arnold
, New York.
22.
Jeong
,
M. K.
,
Lu
,
J. C.
,
Huo
,
X.
,
Vidakovic
,
B.
, and
Chen
,
D.
, 2006, “
Wavelet-Based Data Reduction Techniques for Process Fault Detection
,”
Technometrics
0040-1706,
48
(
1
), pp.
26
40
.
23.
Guyon
,
I.
, and
Elisseeff
,
A.
, 2003, “
An Introduction to Variable and Feature Selection
,”
J. Mach. Learn. Res.
1532-4435,
3
, pp.
1157
1182
.
24.
Bedrick
,
E. J.
, and
Tsai
,
C.-L.
, 1994, “
Model Selection for Multivariate Regression in Small Samples
,”
Biometrics
0006-341X
50
, pp.
226
231
.
25.
Gunn
,
S. R.
, 1998, “
Support Vector Machines for Classification and Regression
,”
Technical Report, Image Speech and Intelligent Systems Research Group
,
University of Southampton
, UK, http://www.isis.ecs.soton.ac.uk/isystems/kernel/http://www.isis.ecs.soton.ac.uk/isystems/kernel/
You do not currently have access to this content.