Quantification of Signal Reconstruction Uncertainty in Fault Detection Systems



Sameer Al-Dahidi Piero Baraldi Francesco Di Maio Enrico Zio


In Condition-Based Maintenance (CBM), Fault Detection (FD) systems monitor the health state of the components and aid the operator to decide whether a maintenance intervention is necessary. A FD system is a decision-aid tool typically based on i) a reconstruction model that estimates (reconstructs) the values of measurable signals in normal conditions, and ii) an analyzer of the differences (residuals) between the measured and reconstructed values: abnormal conditions are detected when residuals are statistically significant. The performance of the reconstruction model is influenced by several sources of uncertainty which can influence the operator decision: 1) measurement errors, 2) intrinsic stochasticity of the physical process, 3) uncertainty on the settings of the model parameters, and 4) uncertainty on the model output due to incompleteness of the training data. The objective of the present work is the quantification of the overall uncertainty affecting the model reconstructions. The proposed novel approach for uncertainty quantification relies on the estimation of Prediction Intervals (PIs) by using Order Statistics (OS) for
a pre-defined confidence level. The proposed approach is verified with respect to an artificial case study; the obtained results show that the approach is able to guarantee the desired level of confidence on the correctness of the detection and provide the decision maker with the required information for establishing whether a maintenance intervention is necessary.

How to Cite

Al-Dahidi, S., Baraldi, P., Maio, F. D., & Zio, E. (2014). Quantification of Signal Reconstruction Uncertainty in Fault Detection Systems. PHM Society European Conference, 2(1). https://doi.org/10.36001/phme.2014.v2i1.1473
Abstract 41 | PDF Downloads 43



fault detection, uncertainty, Signal Reconstruction, Order Statistics, Scale Factor, Prediction Intervals, Auto-Associative Kernel Regression

Ahmad, R., & Kamaruddin, S. (2012). An overview of timebased and condition-based maintenance in industrial application. Computers & Industrial Engineering, 63(1), 135–149. doi: 10.1016/j.cie.2012.02.002
Ak, R., Li, Y. F., Vitelli, V., & Zio, E. (2013). A Genetic Algorithm and Neural Network Technique for Predicting Wind Power under Uncertainty. Prognostics and System Health Management Conference PHM-2013 (1-6), September 9-11, Milan, Italy. doi: 10.3303/CET1333155
Aven, T., & Zio, E. (2012). Foundational issues in risk assessment and risk management. Risk Analysis, 32(10), 1647-1656. doi: 10.1111/j.1539-6924.2012.01798.x
Baraldi, P., Canesi, R., Zio, E., Seraoui, R., & Chevalier, R. (2010). Signal Grouping for Condition Monitoring of Nuclear Power Plants Components. Control and Human-Machine Interface Technologies.
Baraldi, P., Zio, E., Gola, G., Roverso, D., & Hoffmann, M. (2011). Signal reconstruction by a GA-optimized ensemble of PCA models, Nuclear Engineering and Design, 241, 301-309. doi: 10.1016/j.nucengdes.2010.10.012
Baraldi, P., Canesi, R., Zio, E., Seraoui, R., & Chevalier, R. (2011). Genetic Algorithm-based Wrapper Approach for Grouping Condition Monitoring Signal of Nuclear Power Plant Components. Integrated Computer-Aided Engineering, 18(3), 221-234. doi: 10.3233/ICA-2011-0375
Baraldi, P., Di Maio, F., Pappaglione, L., Zio, E., & Seraoui, R. (2012). Condition monitoring of electrical power plant components during operational transients. Proceedings of the Institution of Mechanical Engineers, Part O, Journal of Risk and Reliability, 226(6), 568–583. doi: 10.1177/1748006X12463502
Baraldi, P., Di Maio, F., Genini, D., & Zio, E. (2013). A Fuzzy Similarity Based Method for Signal Reconstruction during Plant Transients. Prognostics and System Health Management Conference PHM-
2013 (889-894), September 9-11, Milan, Italy. doi: 10.3303/CET1333149
Baraldi, P., Di Maio, F., & Zio, E. (2013). Unsupervised Clustering for Fault Diagnosis in Nuclear Power Plants Components. International Journal of Computational Intelligence Systems, 6(4), 764-777. doi: 10.1080/18756891.2013.804145
Batur, C., Zhou, L., & Chan, C. C. (2002). Support vector machines for fault detection. In Decision and Control, Proceedings of the 41st IEEE Conference on (1355-1356), December 10-13, Las Vega, Nevada USA. doi: 10.1109/CDC.2002.1184704
Bouckaert, R. R., Frank, E., Holmes, G., & Fletcher, D. (2011). A Comparison of Methods for Estimating Prediction Intervals in NIR Spectroscopy: Size Matters. Chemometrics and Intelligent Laboratory
Systems, 109(2), 139-145. doi: 10.1016/j.chemolab.2011.08.008
Campos, J. (2009). Development in the application of ICT in condition monitoring and maintenance. Computers in Industry, 60(1), 1-20. doi: 10.1016/j.compind.2008.09.007
Chevalier, R., Provost, D., & Seraoui, R. (2009). Assessment of statistical and Classification model for monitoring EDF’s assets. Control and Human-Machine Interface Technologies.
Denning, R. S., Aldemir, T., & Nakayama, M. (2012). The use of latin hypercube sampling for the efficient estimation of confidence intervals, in Proceedings of the International Congress on Advances in Nuclear Power Plants ( ICAPP '12), Chicago, Ill, USA.
Di Maio, F., Baraldi, P., Zio, E., & Seraoui, R. (2013). Fault Detection in Nuclear Power Plants Components by a Combination of Statistical Methods, IEEE Transaction on Reliability, Vol. 62(4), 833 - 845. doi: 10.1109/TR.2013.2285033
Ding, J., Hines, J.W., & Rasmussen, R. (2003). Independent component analysis for redundant sensor validation. Proceedings of the 2003 Maintenance and Reliability Conference (MARCON 2003), Knoxville, TN.
Garcıa-Alvarez, D. (2009). Fault detection using principal component analysis (PCA) in a wastewater treatment plant (WWTP). In Proceedings of the International Student’s Scientific Conference.
Helton, J. C. (1994). Treatment of uncertainty in performance assessments for complex systems, Risk analysis, 14(4), 483-511.
Hines, J.W., Wrest, D.J., & Uhrig, R.E. (1997). Signal validation using an adaptive neural fuzzy inference system, Nuclear Technology, 119, 181–193.
Laouti, N., Sheibat-Othman, N., & Othman, S. (2011). Support vector machines for fault detection in wind turbines. In Proceedings of IFAC World Congress (7067-7072), August 28th – September 2nd, Milan, Italy.
Lin, Y., & Stadtherr, M. A. (2008). Fault detection in nonlinear continuous-time systems with uncertain parameters. AIChE journal, 54(9), 2335-2345.
Montes de Oca, S., Puig, V., & Blesa, J., (2012). Robust fault detection based on adaptive threshold generation using interval LPV observers, International Journal of Adaptive Control and Signal Processing, Vol. 26(3), 258-283. doi: 10.1002/acs.1263
Office of Nuclear Regulatory Research. (2007). Technical Review of On-Line Monitoring Techniques for Performance Assessment, 2 Theoretical Issues, ORNL/TM-2007/188, NUREG/CR-6895.
Rahman, S. A. S. A. (2010). Application of Artificial Neural Network in Fault Detection Study of Batch Esterification Process. International Journal of Engineering and Technology IJET-IJENS, 10(3).
Ramuhalli, P., Lin, G., Crawford, SL., Konomi, A., Braatz, BG., Coble, JB., Shumaker, BD., Hashemian, HM., (2013). Uncertainty Quantification Techniques for Sensor Calibration Monitoring in Nuclear Power Plants, Pacific Northwest National Laboratory.
Rasmussen, B., Wesley Hines, J., & Gribok, A. V. (2003). An Applied Comparison of the Prediction Intervals of Common Empirical Modeling Strategies. Proceedings of the 2003 Annual Maintenance and Reliability Conference, Knoxville, TN.
Safty, S. M. E., Ashour, H. A., Dessouki, H. E., & Sawaf, M. E. (2004). Online fault detection of transmission line using artificial neural network. IEEE International Conference on Power System Technology (1629-1632), November 21-24, Singapore. doi: 10.1109/ICPST.2004.1460264
Secchi, P., Zio, E., & Di Maio, F. (2008). Quantifying uncertainties in the estimation of safety parameters by using bootstrapped artificial neural networks. Annals of Nuclear Energy, 35(12), 2338-2350. doi: 10.1016/j.anucene.2008.07.010
Thurston, M., & Lebold, M. (2001). Standards Developments for Condition-Based Maintenance Systems. Ft. Belvoir Defense Technical Information Center, Applied Research Laboratory, Penn State
Wald, A. (1947). Sequential Analysis. John Wiley & Sons, New York, NY.
Zavaljevski, N., & Gross, K.C. (2000). Support vector machines for nuclear reactor state estimation. Proceedings of the ANS Topical Meeting on Advances in Reactor Physics and Mathematics and Computation into the Next Millennium, Pittsburgh, Pennsylvania, USA.
Zhao, W., Baraldi, P., & Zio, E. (2011). Confidence in Signal Reconstruction by the Evolving Clustering Method. IEEE Prognostics and System Health Management Conference (1-7), May 24-25, Shenzhen, China. doi: 10.1109/PHM.2011.5939535
Zhao, W., Tao, T., Ding, Z. S., & Zio, E. (2013). A dynamic particle filter-support vector regression method for reliability prediction. Reliability Engineering and System Safety, 119, 109–116.
Zheng, J., & Frey, H. C. (2005). Quantitative analysis of variability and uncertainty with known measurement error: methodology and case study. Risk Analysis, 25(3), 663-675. doi: 10.1111/j.1539-
Technical Papers