Leak detection in compressed air systems using unsupervised anomaly detection techniques

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Oct 2, 2017
Antoine Desmet Matthew Delore

Abstract

Critical components of mobile mining machinery, such as brake and lubrication, are typically powered by compressed air. The compressed air system is subject to leaks in either pipelines or the air-actuated components; and these leaks can cause accelerated wear or unexpected machine shutdowns. Given the size of these machines, fault-finding can be timeconsuming. Remote diagnostics is possible by analysing the machine’s air accumulator pressure with respect to component activation times. However, since every component draws air directly from the accumulator, the resulting drops in pressure all superimpose over the accumulator’s charge and discharge cycles. The result is a highly dynamic trend, making visual diagnostic difficult for anything but major leaks. In this paper, we apply unsupervised anomaly detection techniques to detect developing air leaks. Our method uses machine learning to associate patterns in pressure drop from the accumulator with the activation of each air-powered component. We first apply a wavelet transform to the accumulator pressure trend to make patterns apparent in the time-frequency domain. We then use the Random Forest algorithm’s feature importance to select the most informative wavelet scales. Finally, we trial two anomaly detection methods over the selected inputs: the first uses a clustering approach (LOF), while the second uses a neural-network approach (autoencoder).
Once the learning phase (using historical data) is complete, we test the system on an intermittent leak which occurs only when a particular component is activated. We find that both systems perform well, and the LOF trades accuracy for speed with respect to the autoencoder.

How to Cite

Desmet, A., & Delore, M. (2017). Leak detection in compressed air systems using unsupervised anomaly detection techniques. Annual Conference of the PHM Society, 9(1). https://doi.org/10.36001/phmconf.2017.v9i1.2401
Abstract 882 | PDF Downloads 939

##plugins.themes.bootstrap3.article.details##

Keywords

wavelet transform, clustering, anomalies detection, Air Leakage, autoencoder

References
Arora, A., Candel, A., Lanford, J., LeDell, E., , & Parmar, V. (2015, August). Deep learning with h2o [Computer software manual]. Retrieved from
http://h2o.ai/resources
Bevenot, X., Trouillet, A., Veillas, C., Gagnaire, H., & Clement, M. (2000). Hydrogen leak detection using an optical fibre sensor for aerospace applications. Sensors and Actuators B: Chemical, 67(1), 57 - 67. doi: http://dx.doi.org/10.1016/S0925-4005(00)00407-X
Boecking, B., Chalup, S. K., Seese, D., & Wong, A. S. (2014). Support vector clustering of time series data with alignment kernels. Pattern Recognition Letters, 45, 129–135.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. doi: 10.1023/A:1010933404324
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000). Lof: Identifying density-based local outliers. In Proceedings of the 2000 acm sigmod international conference on management of data (pp. 93–104). New York, NY, USA: ACM. doi: 10.1145/342009.335388
Callegari, C., Gazzarrini, L., Giordano, S., Pagano, M., & Pepe, T. (2014). Improving pca-based anomaly detection by using multiple time scale analysis and kullbackleibler divergence. International Journal of Communication Systems, 27(10), 1731–1751. doi: 10.1002/dac.2432
Colombo, A. F., Lee, P., & Karney, B. W. (2009). A selective literature review of transient-based leak detection methods. Journal of Hydroenvironment
Research, 2(4), 212 - 227. doi: http://dx.doi.org/10.1016/j.jher.2009.02.003
Cooper, P. S., Wong, A. S., Fulham, W. R., Thienel, R., Mansfield, E., Michie, P. T., & Karayanidis, F. (2015). Theta frontoparietal connectivity associated
with proactive and reactive cognitive control processes. Neuroimage, 108, 354–363.
Datta, S., & Sarkar, S. (2016). A review on different pipeline fault detection methods. Journal of Loss Prevention in the Process Industries, 41, 97 - 106. doi: http://dx.doi.org/10.1016/j.jlp.2016.03.010
Ester, M., Kriegel, H.-P., Sander, J., & Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. In (pp. 226–231). AAAI Press.
Fuchs, H., & Riehle, R. (1991). Ten years of experience with leak detection by acoustic signal analysis. Applied acoustics, 33(1), 1–19.
Gelman, L., Patel, T. H., Persin, G., Murray, B., & Thomson, A. (2013). Novel technology based on the spectral kurtosis and wavelet transform for rolling bearing diagnosis. International Journal of Prognostics and Health Management, ISSN, 2153–2648.
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: data mining, inference and prediction (2nd ed.). Springer.
Hodge, V., & Austin, J. (2004). A survey of outlier detection methodologies. Artificial intelligence review, 22(2), 85–126.
Huang, C. T., Thareja, S.,&Shin, Y. J. (2006, Aug).Waveletbased real time detection of network traffic anomalies. In 2006 securecomm and workshops (p. 1-7). doi: 10.1109/SECCOMW.2006.359584
Khan, M. M., Chalup, S. K., & Mendes, A. (2016). Parkinsons disease data classification using evolvable wavelet neural networks. In Australasian conference on artificial life and computational intelligence (pp. 113–124).
Kriegel, H.-P., Krger, P., Sander, J., & Zimek, A. (2011). Density-based clustering. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1(3), 231–240. doi: 10.1002/widm.30
Liaw, A., &Wiener, M. (2002). Classification and regression by randomforest. R News, 2(3), 18-22. Retrieved from http://CRAN.R-project.org/doc/Rnews/
Martinelli, M., Tronci, E., Dipoppa, G., & Balducelli, C. (2004). Electric power system anomaly detection using neural networks. In M. G. Negoita, R. J. Howlett, & L. C. Jain (Eds.), Knowledge-based intelligent information and engineering systems: 8th international conference, kes 2004, wellington, new zealand, september 20-25, 2004, proceedings, part i (pp. 1242–1248). Berlin, Heidelberg: Springer Berlin Heidelberg.
Montgomery, D. (2005). Introduction to statistical quality control. Hoboken, N.J: John Wiley.
Murvay, P.-S., & Silea, I. (2012). A survey on gas leak detection and localization techniques. Journal of Loss Prevention in the Process Industries, 25(6), 966 - 973. doi: http://dx.doi.org/10.1016/j.jlp.2012.05.010
Paula, E. L., Ladeira, M., Carvalho, R. N., & Marzago, T. (2016, Dec). Deep learning anomaly detection as support fraud investigation in brazilian exports and antimoney laundering. In 2016 15th ieee international conference on machine learning and applications (icmla) (p. 954-960). doi: 10.1109/ICMLA.2016.0172
Perzyk, M., Kochanski, A., Kozlowski, J., Soroczynski, A., & Biernacki, R. (2014). Comparison of data mining tools for significance analysis of process
parameters in applications to process fault diagnosis. Information Sciences, 259, 380 - 392. doi: https://doi.org/10.1016/j.ins.2013.10.019
Qin, S. J. (2012). Survey on data-driven industrial process monitoring and diagnosis. Annual Reviews in Control, 36(2), 220–234.
Ramirez, A., Daily, W., Binley, A., LaBrecque, D., & Roelant, D. (1996). Detection of leaks in underground storage tanks using electrical resistance methods. Journal of Environmental and Engineering Geophysics, 1(3), 189-203. doi: 10.4133/JEEG1.3.189
Sakurada, M., & Yairi, T. (2014). Anomaly detection using autoencoders with nonlinear dimensionality reduction. In Proceedings of the mlsda 2014 2nd workshop on machine learning for sensory data analysis (pp. 4:4–4:11). New York, NY, USA: ACM. doi: 10.1145/2689746.2689747
Sandberg, C., Holmes, J., McCoy, K., & Koppitsch, H. (1989, Sep). The application of a continuous leak detection system to pipelines and associated equipment. IEEE Transactions on Industry Applications, 25(5), 906-909. doi: 10.1109/28.41257
Sarkar, S., Reddy, K. K., Giering, M., & Gurvich, M. R. (2016). Deep learning for structural health monitoring: A damage characterization application. In (Vol. 7). Prognostics and Health Management Society.
Seungmin, L., Gisung, K., & Sehun, K. (2011). Selfadaptive and dynamic clustering for online anomaly detection. Expert Systems with Applications, 38(12), 14891 - 14898.
Song, J., Takakura, H., Okabe, Y., & Nakao, K. (2013). Toward a more practical unsupervised anomaly detection system. Information Sciences, 231, 4 - 14. (Data Mining for Information Security)
Wong, A. S., Chalup, S. K., Bhatia, S., Jalalian, A., Kulk, J., Nicklin, S., & Ostwald, M. J. (2012). Visual gaze analysis of robotic pedestrians moving in urban space. Architectural Science Review, 55(3), 213–223.
Yan, W., & Yu, L. (2015). On accurate and reliable anomaly detection for gas turbine combustors: A deep learning approach. In Proceedings of the annual conference of the prognostics and health management society.
Zhang, G., Kinsner, W., & Huang, B. (2009). Electrocardiogram data mining based on frame classification by dynamic time warping matching. Computer methods in biomechanics and biomedical engineering, 12(6), 701–707.
Zhao, J., Liu, K.,Wang,W., & Liu, Y. (2014). Adaptive fuzzy clustering based anomaly data detection in energy system of steel industry. Information Sciences, 259, 335 - 345.
Section
Technical Research Papers