Condition Monitoring of a Reciprocating Compressor Using Wavelet Transformation and Support Vector Machines



Published Oct 2, 2017
Shawn Falzone Jason R. Kolodziej


Condition monitoring techniques were applied to a reciprocating compressor in order to determine if faults were present in a system. Through the use of vibration based sensors, fault monitoring of the crank-side discharge valve springs was accomplished. Data was collected through a range of injected fault conditions and analyzed through the use of discrete wavelet transformations. The wavelet coefficients produced were transformed into a six-dimensional feature space though the use of first and second order statistics. By using a support vector machine classifier, the nominal and faulted condition data was used to train a fault monitoring classifier. This classifier was verified through the use of additional test data, and resulted in classification rates of 90% and above. This result is based on the trial of a multitude of different wavelets and support vector kernels in order to achieve the optimal performance for the dataset.

How to Cite

Falzone, S., & Kolodziej, J. R. (2017). Condition Monitoring of a Reciprocating Compressor Using Wavelet Transformation and Support Vector Machines. Annual Conference of the PHM Society, 9(1).
Abstract 246 | PDF Downloads 728



condition based maintenance (CBM), applications: industrial, data driven methods

Bloch, H. P., & Hoefner, J. J. (1996). Reciprocating Compressors - Operations and Maintinence. Elsevier Inc. doi:
Campbell, C., & Ying, Y. (2011). Learning with Support Vector Machines. Synthesis Lectures on Artificial Intelligence and Machine Learning, 1-95.
Feng, K., Jiang, Z., He, W., & Ma, B. (2011). A Recognition and Novelty Detection Approach Based on Curvelet Transform, Nonlinear PCA and SVM with Application to Indicator Diagram Diagnosis. Expert Syst. Appl., 38(10), 12721-12729. doi:10.1016/j.eswa.2011.04.060
Fletcher, T. (2008). Support Vector Machines Explained. Izenman, A. J. (2008). Modern Multivariate Statistical Techniques - Regression, Classification, and Manifold Learning. New York: Springer.
Jawahar, M., Babu, N. K., & Vani, K. (2014). Leather texture classification using wavelet feature extraction technique. IEEE International Conference on
Computational Intelligence and Computing Research (pp. 1-4). Coimbatore: IEEE.
Kecman, V. (2005). Support Vector Machines - An Introduction. Berlin Heidelberg: Springer. doi:
Lin, Y.-H., Wu, H.-C., & Wu, C.-Y. (2006). Automated condition classification of a reciprocating compressor using time–frequency analysis and an
artificial neural network. Smart Materials and Structures,, 15(6), 1576-1584.
Love, B. C. (2002). Comparing supervised and unsupervised category learning. Psychonomic Bulletin & Review, 829-835.
Mallat, S. (1999). A wavelet tour of signal processing, 2nd Edition, . Academic Press.
Pan, G. (2009). Intuitive Introduction to Wavelets. In G. Pan, Wavelets in Electromagnetics and Device Modeling, (pp. 15–29). Hoboken, N.J.: John Wiley & Sons, Inc.
Prajapati, A., Bechtel, J., & Ganesan, S. (2012). Condition based maintenance: a survey. Journal of Quality in Maintenance Engineering, 18(4), 384–400.
Randall, R. B. (2010). Vibration-based Condition Monitoring: Industrial, Aerospace and Automotive Applications. Hoboken, N.J.: John Wiley & Sons,
Inc. doi:
Trout, J. N., & Kolodziej, J. R. (2016). Condition monitoring and classification of reciprocating compressor valve faults using time-frequency analysis and imagebased pattern recognition. PHM Society, (pp. 1-10). Denver, CO.
Technical Research Papers