Surge is a phenomenon of large oscillations of pressure and flow that occurs in dynamic compressors when the compressor is operated at too low a flow rate for a given discharge pressure. In order to prevent damage to the compressor, surge must be avoided. A typical surge prevention measure for compressor operation is so-called surge avoidance control, which normally relies on a map of the operating conditions for surge occurrence, i.e. surge map or surge line. The surge map currently used in industry practice is insufficient since surge occurrence is affected by many more process variables, especially ambient air conditions. If large uncertainty exists in surge conditions, the compressor has to be operated conservatively far away from the surge line, which limits the dynamic range and usually sacrifices the efficiency. In order to obtain more accurate surge map adaptively, a data-driven surge map modeling approach has been developed using support vector machine (SVM) approach based on surge test data. Surge map is obtained as the classification surface between surge and not-surge data. Principal components analysis (PCA) is used to identify the variables that contribute most to surge. The method of asymmetric support vector machines (ASVM) is developed to reduce the possibilities of missed surge prediction. The developed methodology was verified with the actual testing data on the centrifugal air compressor in Toyota Motors.

1.
N. P. Cheremisinoff and P. N. Cheremisinoff, Compressors and Fans, Prentice Hall, Englewood Cliffs, New Jersey, 1992.
2.
B. de Jager, “Rotating Stall and Surge Control: A Survey,” Proceedings of the 34th Conference on Decision & Control, pp. 1857–1862, 1995
3.
Wernet
M. P.
,
Bright
M. M.
, and
Skoch
G. J.
, “
An Investigation of Surge in a High-Speed Centrifugal Compressor Using Digital PIV
,”
ASME Journal of Turbomachinery
, Vol.
123
,
2001
, pp.
418
428
4.
Fink
D. A.
,
Cumpsty
N. A.
, and
Greitzer
E. M.
, “
Surge Dynamics in a Free-Spool Centrifugal Compressor System
,”
ASME Journal of Turbomachinery
, Vol.
114
, pp.
321
332
,
1992
5.
Botros
K. K.
, “
Transient Phenomena in Compressor Stations During Surge
,”
Journal of Engineering for Gas Turbines and Power
, Vol.
116
,
1994
, pp.
133
142
6.
Elder
R. L.
, and
Gill
M. E.
, “
Discussion of the Factors Affecting Surge in Centrifugal Compressors
,”
Journal of Engineering for Gas Turbines and Power
, Vol.
107
,
1985
, pp.
499
506
7.
Elzahby
A.
,
Ghenaiet
A.
, and
Elfeki
S.
, “
Theoretical Prediction of Radial Flow Compressor Surge Line
,”
Modelling, Measurement, and Control
, Vol.
41
,
1994
, pp.
53
63
8.
Gravdahl
J. T.
and
Egeland
O.
, “
Speed and Surge Control for a Low Order Centrifugal Compressor Model
,”
Modeling, Identification and Control
, Vol.
19
,
1998
, pp.
13
29
9.
E. Logan Jr., Turbomachinery, Basic Theory and Applications, Marcel Dekker, Inc., New York, 1981, pp.45–53
10.
P. C. Hanlon, Compressor Handbook. New York: McGraw-Hill, 2001, pp. 4.16–4.45
11.
R. N. Brown, Compressors Selection and Sizing, Houston, TX: Gulf Publishing Company, 1986, pp. 183–184.
12.
J. T. Gravdahl, and O. Egeland, Compressor Surge and Rotating Stall, Springer-Verlag London Limited, 1999.
13.
Peck
J. P.
and
Burrows
J.
. “
On-line condition monitoring of rotating equipment using neural networks
”,
ISA Transactions
, v
33
, n
2
, July,
1994
, p
159
164
.
14.
Li
C. J.
and
Yu
X.
. “
High pressure air compressor valve fault diagnosis using feedforward neural networks
”,
Mechanical Systems & Signal Processing
, Vol.
9
, No.
5
, pp.
527
536
, September
1995
.
15.
Aretakis
N.
and
Mathioudakis
K.
, “
Classification of radial compressor faults using pattern-recognition techniques
”,
Control Engineering Practice
, Vol.
6
, No.
10
, October,
1998
, pp.
1217
1223
.
16.
Wang
K.
and
Lei
B.
, “
Using B-spline neural network to extract fuzzy rules for a centrifugal pump monitoring
”,
Journal of Intelligent Manufacturing
, Vol.
12
, No.
1
, March,
2001
, pp.
5
11
.
17.
Bevilacqua
M.
,
Braglia
M.
,
Frosolini
M.
and
Montanari
R.
. “
Failure rate prediction with artificial neural networks
”,
Journal of Quality in Maintenance Engineering
, Vol.
11
, No.
3
, pp.
279
294
,
2005
.
18.
Yang
B.-S.
,
Hwang
W.-W.
,
Kim
D.-J.
and
Tan
A. C.
, “
Condition classification of small reciprocating compressor for refrigerators using artificial neural networks and support vector machines
.
Mechanical Systems and Signal Processing
, Vol.
19
, No.
2
, March
2005
, pp.
371
390
.
19.
Bechtler
H.
,
Browne
M. W.
,
Bansal
P. K.
and
Kecman
V.
, “
New approach to dynamic modeling of vapour-compression liquid chillers: artificial neural networks
”,
Applied Thermal Engineering
, v
21
, n
9
, June,
2001
, p
941
953
20.
Nelson
S. A.
,
Filipi
Z. S.
, and
Assanis
D. N.
, “
The use of neural nets for matching fixed or variable geometry compressors with diesel engines
.
Journal of Engineering for Gas Turbines and Power
, Vol.
125
, No.
2
, April,
2003
, pp.
572
579
.
21.
Han
I.-S.
and
Han
C.
, “
Modeling of multistage aircompression systems in chemical processes
”,
Industrial and Engineering Chemistry Research
, Vol.
42
, No.
10
, May
2003
, pp.
2209
2218
.
22.
Lo
C. F.
and
Shi
G. Z.
, “
Wind-Tunnel Compressor Stall Monitoring Using Neural Networks
,”
Journal of Aircraft
, Vol.
29
,
1992
, pp.
736
738
.
23.
S. Haykin, Neural Networks; A Comprehensive Foundation, ed. 2, New Jersey: Prentice Hall, 1999.
24.
L. I. Smith, A Tutorial on Principal Components Analysis, 2002. Available on-line at www.csnet.otago.ac.nz/cosc453/student_tutorials/principal_components.pdf.
25.
Vapnik
V. N.
, “
Overview of statistical learning theory
”,
IEEE Transactions on Neural Networks
, Vol.
10
, No.
5
,
1999
, pp.
988
999
.
26.
Byun
H.
and
Lee
S.
, “
A Survey on Pattern Recognition Applications of Support Vector Machines
,”
International Journal of Pattern Recognition and Artificial Intelligence
, Vol.
17
,
2003
, pp.
459
486
.
This content is only available via PDF.
You do not currently have access to this content.