Recent train accidents have reaffirmed the need for developing a rail defect detection system more effective than that currently used. One of the most promising techniques in rail inspection is the use of ultrasonic guided waves and noncontact probes. A rail inspection prototype based on these concepts and devoted to the automatic damage detection of defects in rail head is the focus of this paper. The prototype includes an algorithm based on wavelet transform and outlier analysis. The discrete wavelet transform is utilized to denoise ultrasonic signals and to generate a set of relevant damage sensitive data. These data are combined into a damage index vector fed to an unsupervised learning algorithm based on outlier analysis that determines the anomalous conditions of the rail. The first part of the paper shows the prototype in action on a railroad track mock-up built at the University of California, San Diego. The mock-up contained surface and internal defects. The results from three experiments are presented. The importance of feature selection to maximize the sensitivity of the inspection system is demonstrated here. The second part of the paper shows the results of field testing conducted in south east Pennsylvania under the auspices of the U.S. Federal Railroad Administration. 1. Introduction Safety statistics data from the US Federal Railroad Administration [1, 2] indicate that train accidents caused by track failures including rail, joint bars and anchoring resulted in 2700 derailments and 441？M in direct costs, during the 1992–2002 decade. The primary cause of these accidents is the ‘transverse defect’ type that was found responsible for 541 derailments and 91？M in cost during the same period. Transverse defects are cracks developing in a direction perpendicular to the rail running direction, and include transverse fissures, initiated inside the rail head, and detail fractures, initiated at the head surface as rolling contact fatigue defects. The most common methods of rail inspection are magnetic induction and contact ultrasonic testing [3–5]. The first method is affected by environmental magnetic noise and it requires a small lift-off distance for the sensors in order to produce adequate sensitivity [6, 7]. Ultrasonic testing is conventionally performed from the top of the rail head in a pulse-echo configuration. In this system, ultrasonic transducers are located inside a water-filled wheel and are oriented at 0° from the surface of the rail head to detect horizontal cracks and at 70° to detect transverse cracks. Such an approach suffers from
References
[1]
Federal Railroad Administration, “Safety statistics data: 1992–2002,” U.S. Department of Transportation, 2002.
[2]
http://safetydata.fra.dot.gov/OfficeofSafety/.
[3]
H. A. Toliyat, K. Abbaszadeh, M. M. Rahimian, and L. E. Olson, “Rail defect diagnosis using wavelet packet decomposition,” IEEE Transactions on Industry Applications, vol. 39, no. 5, pp. 1454–1461, 2003.
[4]
R. Clark, “Rail flaw detection: overview and needs for future developments,” NDT and E International, vol. 37, no. 2, pp. 111–118, 2004.
[5]
F. Lanza di Scalea, “Ultrasonic testing in the railroad industry,” in Non-Destructive Testing Handbook, pp. 9–16, American Society for Nondestructive Testing, Columbus, Ohio, USA, 3rd edition, 2007.
[6]
L. Oukhellou, P. Aknin, and J.-P. Perrin, “Dedicated sensor and classifier of rail head defects,” Control Engineering Practice, vol. 7, no. 1, pp. 57–61, 1999.
[7]
R. Pohl, A. Erhard, H.-J. Montag, H.-M. Thomas, and H. Wüstenberg, “NDT techniques for railroad wheel and gauge corner inspection,” NDT and E International, vol. 37, no. 2, pp. 89–94, 2004.
[8]
R. J. Greene, J. R. Yates, and E. A. Patterson, “Crack detection in rail using infrared methods,” Optical Engineering, vol. 46, no. 5, Article ID 051013, 2007.
[9]
P. Wilcox, M. Evans, B. Pavlakovic et al., “Guided wave testing of rail,” Insight, vol. 45, no. 6, pp. 413–420, 2003.
[10]
P. Cawley, M. J. S. Lowe, D. N. Alleyne, B. Pavlakovic, and P. Wilcox, “Practical long range guided wave testing: applications to pipes and rail,” Materials Evaluation, vol. 61, no. 1, pp. 66–74, 2003.
[11]
D. Hesse and P. Cawley, “Surface wave modes in rails,” Journal of the Acoustical Society of America, vol. 120, no. 2, pp. 733–740, 2006.
[12]
J. L. Rose, M. J. Avioli, P. Mudge, and R. Sanderson, “Guided wave inspection potential of defects in rail,” NDT and E International, vol. 37, no. 2, pp. 153–161, 2004.
[13]
J. L. Rose, M. J. Avioli, and W.-J. Song, “Application and potential of guided wave rail inspection,” Insight, vol. 44, no. 6, pp. 353–358, 2002.
[14]
J. D. McNamara, F. Lanza di Scalea, and M. Fateh, “Automatic defect classification in long-range ultrasonic rail inspection using a support vector machine-based 'smart system',” Insight, vol. 46, no. 6, pp. 331–337, 2004.
[15]
I. Bartoli, F. Lanza di Scalea, M. Fateh, and E. Viola, “Modeling guided wave propagation with application to the long-range defect detection in railroad tracks,” NDT and E International, vol. 38, no. 5, pp. 325–334, 2005.
[16]
F. Lanza di Scalea, I. Bartoli, P. Rizzo, and M. Fateh, “High-speed defect detection in rails by non-contact guided ultrasonic testing,” Journal of the Transportation Research Board, vol. 1961, pp. 66–77, 2006.
[17]
G. Alers, “Railroad rail flaw detection system based on electromagnetic acoustic transducers,” Tech. Rep. DOT/FRA/ORD-88/09, U.S. Department of Transportation, 1988.
[18]
R. S. Edwards, S. Dixon, and X. Jian, “Characterisation of defects in the railhead using ultrasonic surface waves,” NDT and E International, vol. 39, no. 6, pp. 468–475, 2006.
[19]
S. Kenderian, D. Cerniglia, B. B. Djordjevic, G. Garcia, J. Sun, and M. Snell, “Rail track field testing using laser/air hybrid ultrasonic technique,” Materials Evaluation, vol. 61, no. 10, pp. 1129–1133, 2003.
[20]
T. Hayashi, W.-J. Song, and J. L. Rose, “Guided wave dispersion curves for a bar with an arbitrary cross-section, a rod and rail example,” Ultrasonics, vol. 41, no. 3, pp. 175–183, 2003.
[21]
J. McNamara and F. L. di Scalea, “Improvements in noncontact ultrasonic testing of rails by the discrete wavelet transform,” Materials Evaluation, vol. 62, no. 3, pp. 365–372, 2004.
[22]
F. L. di Scalea, P. Rizzo, S. Coccia et al., “Non-contact ultrasonic inspection of rails and signal processing for automatic defect detection and classification,” Insight, vol. 47, no. 6, pp. 346–353, 2005.
[23]
W. Staszewski, C. Boller, and G. Tomlinson, Health Monitoring of Aerospace Structures, John Wiley & Sons, Munich, Germany, 2006.
[24]
P. Rizzo and F. Lanza di Scalea, “Wavelet-based unsupervised and supervised learning algorithms for ultrasonic structural monitoring of waveguides,” in Progress in Smart Materials and Structures Research, chapter 8, pp. 227–290, Nova Science, Hauppauge, NY, USA, 2007.
[25]
P. Rizzo and F. L. di Scalea, “Wavelet-based feature extraction for automatic defect classification in strands by ultrasonic structural monitoring,” Smart Structures and Systems, vol. 2, no. 3, pp. 253–274, 2007.
[26]
P. Rizzo and F. L. di Scalea, “Ultrasonic inspection of multi-wire steel strands with the aid of the wavelet transform,” Smart Materials and Structures, vol. 14, no. 4, pp. 685–695, 2005.
[27]
P. Rizzo, I. Bartoli, M. Cammarata, and S. Coccia, “Digital signal processing for rail monitoring by means of ultrasonic guided waves,” Insight, vol. 49, no. 6, pp. 327–332, 2007.
[28]
P. Rizzo, M. Cammarata, D. Dutta, H. Sohn, and K. A. Harries, “Unsupervised learning algorithm for fatigue crack detection in waveguides,” Smart Materials and Structures, vol. 18, Article ID 025016, 11 pages, 2009.
[29]
P. Rizzo, S. Coccia, I. Bartoli, and F. Lanza di Scalea, “On line high-speed rail defect detection–prototype assembling and field testing,” Tech. Rep. SSRP-06/17, University of California, San Diego, Calif, USA, 2006.
[30]
S. Coccia, I. Bartoli, F. Lanza di Scalea, and P. Rizzo, “Non-contact rail defect detection: first and second field tests,” Tech. Rep. SSRP-07/15, University of California, San Diego, Calif, USA, 2007.
[31]
S. Coccia, R. Phillips, I. Bartoli, S. Salamone, and F. Lanza di Scalea, “Non-contact rail defect detection,” Tech. Rep. SSRP-08/02, Federal Railroad Administration, University of California, San Diego, Calif, USA, 2008.
[32]
S. Coccia, I. Bartoli, R. Phillips, S. Salamone, and F. Lanza di Scalea, “Non-contact rail defect detection: fourth field test,” Tech. Rep. SSRP-09/04, Federal Railroad Administration, University of California, San Diego, Calif, USA, 2009.
