Abstract
The development of automatic and reliable monitoring systems is an open issue in continuous industrial chemical processes. The challenges lay on simultaneously managing multiple normal modes of operation as well as the transitions among them with reasonable false alarm rates, and in reaching early fault detection. This work explores and attests the capacity of the signal processing method called hidden Markov model (HMM) in contributing to overcome these issues. After presenting the motivation for its use in this engineering field, the methodology is introduced and an application is illustrated. Here, the HMM ability of directly learning from process historical data both desired features system dynamics and structure of correlations is shown. Aiming to reach practical insights a real case study based on operations of an industrial boiler is used. A comparison with Principal Components Analysis (PCA) and Self-Organizing Maps (SOM) shows the effectiveness of the proposed HMM-based fault detection system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Rabiner, L.: A tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proc. IEEE 77(2), 257–286 (1989)
Rabiner, L., Juang, B.: An Introduction to Hidden Markov Models. IEEE ASSP Mag. 3(1), 4–16 (1986)
Kosky, T.: Hidden Markov Models of Bioinformatics. Springer, New York (2002)
Cappe, O., Moulines, E.: Inference in Hidden Markov Models. Springer, New York (2010)
Mamom, R.S., Elliott, R.J.: Hidden Markov Models in Finance. Springer, New York (2007)
Chiang, L.H., Russell, E.L., Braatz, R.D.: Fault Detection and Diagnosis in Industrial Systems. Springer, London (2001)
Wang, X.Z.: Data Mining and Knowledge Discovery for Process Monitoring and Control. Springer, London (1999)
Almeida, G.M., Reis, M.P.S., Park, S.W.: A Signal Processing Approach for Fault Detection Problem: Application to the DAMADICS Actuator Benchmark Problem. To appear in: 22nd European Symposium on Computer Aided Process Engineering (ESCAPE), IChemE Press, London (2012)
Chen, J., Chang, W.: Applying Wavelet-Based Hidden Markov Tree to Enhancing Performance of Process Monitoring. Chem. Eng. Sc. 60(18), 5129–5143 (2005)
Sun, W., Palazoglu, A., Romagnoli, J.A.: Detecting Abnormal Process Trends by Wavelet-Domain Hidden Markov Models. AIChE Journal 49(1), 140–150 (2003)
Wong, J.C., McDonald, K.A., Palazoglu, A.: Classification of Abnormal Plant Operation Using Multiple Process Variable Trends. J. Proc. Control 11(4), 409–418 (2001)
Bakhtazad, A., Palazoglu, A., Romagnoli, J.A.: Detection and Classification of Abnormal Process Situations Using Multidimensional Wavelet Domain Hidden Markov Trees. Comp. and Chem. Eng. 24(2-7), 769–775 (2000)
Wong, J.C., McDonald, K.A., Palazoglu, A.: Classification of Process Trends Based on Fuzzified Symbolic Representation and Hidden Markov Models. J. Proc. Control 8(5-6), 395–408 (1998)
Venkatasubramanian, V., Rengaswamy, R., Kavuri, S.N., Yin, K.: A Review of Process Fault Detection and Diagnosis - Part III: Process History Based Methods. Comp. Chem. Eng. 27(3), 327–346 (2003)
Vakkilainen, E.K.: Kraft Recovery Boilers - Principles and Practice. Valopaino Oy., Helsink (2005)
Adams, T.N., Frederick, W.J., Grace, T.M., Hupa, M., Iisa, K., Jones, A.K., Tran, H.: Kraft Recovery Boilers. Tappi Press, Atlanta (1997)
Viterbi, A.J.: Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm. IEEE Trans. Inform. Theory IT-13, 260–269 (1967)
Baum, L.E., Petrie, T., Soules, G., Weiss, N.: A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains. Ann. Math. Stat. 41(1), 164–171 (1970)
Montgomery, D.C.: Introduction to Statistical Quality Control, 6th edn. Wiley, New York (2008)
Aguirre, L.A.: Introducao a Identificacao de Sistemas, 3a edn. UFMG, Belo Horizonte (2007)
Kresta, J.V., Macgregor, J.F., Marlin, T.E.: Multivariate Statistical Monitoring of Process Operating Performance. Can. J. Chem. Eng. 69(1), 35–47 (1991)
Kohonen, T.: Self-Organizing Maps. Springer, Helsink (1995)
Russel, E.L., Chiang, L.H., Braatz, R.D.: Fault Detection in Industrial Processes using Canonical Variate Analysis and Dynamic Principal Component Analysis. Chemometr. Intell. Lab. Syst. 51, 81–93 (2000)
Ku, W., Storer, R.H., Georgakis, C.: Disturbance Detection and Isolation by Dynamic Principal Component Analysis. Chemometr. Intell. Lab. Syst. 30(1), 179–196 (1995)
Barreto, G.A., Mota, J.C.M., Souza, L.G.M., Frota, R.A., Aguayo, L.: Condition Monitoring of 3G Cellular Networks Through Competitive Neural Models. IEEE Trans. Neural Netw. 16(5), 1064–1075 (2005)
Patton, R.J.: Preface. Control Eng. Prac. 14(6), 575–576 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
de Almeida, G.M., Park, S.W. (2012). Fault Detection in Continuous Industrial Chemical Processes: A New Approach Using the Hidden Markov Modeling. Case Study: A Boiler from a Brazilian Cellulose Pulp Mill. In: Yin, H., Costa, J.A.F., Barreto, G. (eds) Intelligent Data Engineering and Automated Learning - IDEAL 2012. IDEAL 2012. Lecture Notes in Computer Science, vol 7435. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32639-4_88
Download citation
DOI: https://doi.org/10.1007/978-3-642-32639-4_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32638-7
Online ISBN: 978-3-642-32639-4
eBook Packages: Computer ScienceComputer Science (R0)