High pressure air compressors (HPAC) are a high maintenance machine for they break down more often than expected and they serve critical roles. This study established the utility of an unsupervised pattern classifier system integrating a clustering algorithm based on DBSCAN and a dynamic classifier based on projection network to classify the condition of a 4-stage high pressure air compressor. The clustering algorithm is used to form clusters from un-labeled data and eliminate outliers. Subsequently, a system of projection networks is established to recognize all the significant clusters. The compressor data is consisted of pressures and temperatures at all four stages taken under various conditions including different baseline conditions, 3rd stage suction valve fault, 3rd stage discharge valve fault, and cylinder pitting and corrosion. The clustering algorithm was able to form clusters that each individually contains data mostly from a single class, and the projection network was able to differentiate these clusters and therefore classify the condition of the compressor correctly about 94% of the time. The ability of unsupervised classification does come with a price of lower classification accuracy. It was about 5% lower than what was accomplished by supervised classification.

1.
Li
C. J.
and
Yu
X.
,
1995
, “
High Pressure Air Compressor Valve Fault Diagnosis Using Feed-forward Neural Networks
,”
Mechanical Systems and Signal Processing
, Vol.
9
, no.
5
, pp.
527
536
.
2.
Jansuwan, C. and Li, C. James, 2003, “Utility of Projection Network for Diagnosis of High Pressure Air Compressor Faults,” Symposium on Advanced Condition Monitoring and Maintenance Technologies, International Mechanical Engineering Congress & Exposition, November 16–21, 2003, Washington, D.C. Proceedings of 2003 ASME International Mechanical Engineering Congress, Vol. 3, paper IMECE 43505.
3.
Baird, B. and Eeckman, F., 1993, “A Normal Form Projection Algorithm for Associative Memory,” Associative Neural Memories, M. H. Hassoun, Editor, Oxford University Press, New York, pp. 135–166.
4.
Dietterich
T. G.
&
Bakiri
G.
,
1995
, “
Solving multiclass learning problems via error-correcting output codes
,”
Journal of Artificial Intelligence Research
, Vol.
2
, pp.
263
286
.
5.
McKee, K., 2000, “Multivariate Outlier Detection in Mechanical Engineering,” Master Thesis, Rensselaer Polytechnic Institute, Troy, New York.
6.
1986, “Systems and Equipment Maintenance Monitoring for Surface Ships (SEMMSS) FF1052 High-Pressure Compressed Air System Study,” Final Report, NAVSEA N00024-84-D-4312, Technical Instruction 050-501, June 30, 1986.
7.
Jansuwan, C., 2003, “Dynamic Projection Network for Associative Memory and Pattern Classification and its Utility for Mechanical Diagnosis,” Rensselaer Polytechnic Institute, Troy, New York.
This content is only available via PDF.
You do not currently have access to this content.