The damage caused by corrosion in chemical process installations can lead to unexpected plant shutdowns and the leakage of potentially toxic chemicals into the environment. When subjected to corrosion, structural changes in the material occur, leading to energy releases as acoustic waves. This acoustic activity can in turn be used for corrosion monitoring, and even for predicting the type of corrosion. Here we apply wavelet packet decomposition to extract features from acoustic emission signals. We then use the extracted wavelet packet coefficients for distinguishing between the most important types of corrosion processes in the chemical process industry: uniform corrosion, pitting and stress corrosion cracking. The local discriminant basis selection algorithm can be considered as a standard for the selection of the most discriminative wavelet coefficients. However, it does not take the statistical dependencies between wavelet coefficients into account. We show that, when these dependencies are ignored, a lower accuracy is obtained in predicting the corrosion type. We compare several mutual information filters to take these dependencies into account in order to arrive at a more accurate prediction.
References
[1]
Kane, RD. A new approach to corrosion monitoring. Chem. Eng 2007, 114, 34–41.
[2]
Winkelmans, M. Fusion of Non-Destructive Testing Techniques for Corrosion Monitoring in Chemical Process PlantsPh.D. Thesis, Katholieke Universiteit Leuven, Leuven, Belgium. 2004.
[3]
Brongers, MPH; Tubens, I. Corrosion Cost and Preventive Strategies in the United States, Appendix V, Chemical, Petrochemical and Pharmaceutical; U.S. Department of Transportation, Federal Highway Administration: Washington, DC, USA, 2001. Available online: http://www.corrosioncost.com/pdf/chem.pdf (accessed on 6 April 2011).
[4]
Wade, AP. Acoustic emission: Is industry listening? Chemometr. Intell. Lab. Syst 1990, 8, 305–310.
[5]
Soulsbury, KA; Wade, AP; Sibbald, DB. A rules-based approach to classification of chemical acoustic emission signals. Chemometr. Intell. Lab. Syst 1992, 15, 87–105.
[6]
Yuyama, S. Fundamental aspects of acoustic emission applications to the problems caused by corrosion. In Corrosion Monitoring in Industrial Plants Using Non-Destructive Testing and Electrochemical Methods; Moran, GC, Labine, P, Eds.; American Society for Testing and Materials: Philadelphia, PA, USA, 1986; pp. 43–74.
[7]
Seah, KHW; Lim, KB; Chew, CH; Teoh, SH. The correlation of acoustic emission with the rate of corrosion. Corros. Sci 1993, 34, 1707–1713.
[8]
Mazille, H; Rothéa, R; Tronel, C. An acoustic emission technique for monitoring pitting corrosion of austenitic stainless steels. Corros. Sci 1995, 37, 1365–1375.
[9]
Shaikh, H; Amirthalingam, R; Anita, T; Sivaibharasai, N; Jaykumar, T; Manohar, P; Khatak, HS. Evaluation of stress corrosion cracking phenomenon in an AISI type 316LN stainless steel using acoustic emission technique. Corros. Sci 2007, 49, 740–765.
[10]
Roberge, PR. Handbook of Corrosion Engineering; McGraw-Hill: New York, NY, USA, 2000; p. 11.
[11]
Huang, M; Jiang, L; Liaw, PK; Brooks, CR; Seeley, R; Klarstorm, DL. Using acoustic emission in fatigue and fracture materials research. JOM 1998, 50, 1–14.
[12]
Surgeon, M; Wevers, M. Modal analysis of acoustic emission signals from CFRP laminates. NDT E Int 1999, 32, 311–322.
[13]
Suzuki, H; Kinjo, T; Hayashi, Y; Takemoto, M; Ono, K. Wavelet transform of acoustic emission signals. JAE 1996, 14, 69–84.
[14]
Marec, A; Thomas, J-H; El Guerjouma, R. Damage characterization of polymer-based composite materials: Multivariable analysis and wavelet transform for clustering acoustic emission data. Mech. Syst. Signal Process 2008, 22, 1441–1464.
[15]
Van Dijck, G; Wevers, M; Van Hulle, MM. Wavelet packet decomposition for the identification of corrosion type from acoustic emission signals. Int. J. Wavelets Multiresolut. Inf. Process 2009, 7, 513–534.
[16]
Guyon, I; Elisseeff, A. An introduction to variable and feature selection. J. Mach. Learn. Res 2003, 3, 1157–1182.
[17]
Wickerhauser, MV. INRIA lectures on wavelet packet algorithms. Proceedings of Ondelettes et Paquets d’Ondes, Roquencourt, France, 17–21 June 1991; pp. 31–99.
[18]
Coifman, RR; Wickerhauser, MV. Entropy-based algorithms for best basis selection. IEEE Trans. Inform. Theory 1992, 38, 713–718.
[19]
Mallat, S. A Wavelet Tour of Signal Processing; Academic Press: New York, NY, USA, 1998.
[20]
Saito, N; Coifman, RR. Local discriminant bases and their applications. J. Math. Imaging Vis 1995, 5, 337–358.
[21]
Saito, N; Coifman, RR. Geological information extraction from acoustic well-logging waveforms using time-frequency wavelets. Geophysics 1997, 62, 1921–1930.
[22]
Saito, N; Coifman, RR; Geshwind, FB; Warner, F. Discriminant feature extraction using empirical probability density estimation and a local bases library. Pattern Recogn 2002, 35, 2841–2852.
[23]
Cover, TM; Thomas, JA. Elements of Information Theory, 2nd ed ed.; John Wiley & Sons: New York, NY, USA, 2006.
[24]
Van Dijck, G; Van Hulle, MM. Increasing and decreasing returns and losses in mutual information feature subset selection. Entropy 2010, 12, 2144–2170.
Kwak, N; Choi, C-H. Input feature selection by mutual information based on Parzen window. IEEE Trans. Pattern Anal. Mach. Intell 2002, 24, 1667–1671.
[30]
Van Dijck, G; Van Hulle, MM. Speeding up feature subset selection through mutual information relevance filtering. Proceedings of ECML/PKDD 2007, Warsaw, Poland, 17–21 September 2007; pp. 277–287.
[31]
Kozachenko, LF; Leonenko, NN. On statistical estimation of entropy of random vector. Probl. Inform. Transm 1987, 23, 95–101.
[32]
Estévez, PA; Tesmer, M; Perez, CA; Zurada, JM. Normalized mutual information feature selection. IEEE Trans. Neural Netw 2009, 20, 189–201.
[33]
Ding, C; Peng, H. Minimum redundancy feature selection from microarray gene expression data. Int. J. Data Min. Bioinform 2005, 3, 185–205.
[34]
Duda, RO; Hart, PE; Stork, DG. Pattern Classification, 2nd ed ed.; John Wiley & Sons: New York, NY, USA, 2001.
[35]
Hall, M; Frank, E; Holmes, G; Pfahringer, B; Reutemann, P; Witten, IH. The WEKA data mining software: An update. SIGKDD Explorations 2009, 11, 10–18.
[36]
McLachlan, G; Peel, D. Finite Mixture Models; John Wiley & Sons: New York, NY, USA, 2000.
[37]
Mitchell, T. Machine Learning; McGraw Hill: New York, NY, USA, 1997; p. 112.
