An investigation on acoustic emission detection of rail crack in actual application by chaos theory with improved feature detection method

Abstract In order to detect rail cracks by Acoustic Emission (AE) technology, many researches are carried out based on the theoretical and experimental conditions. However, how to detect the crack signals in real noise environment of railway is a key problem for actual application, which has few researches. In this paper, AE detection of rail cracks in real noise environment is investigated and an improved method is proposed to increase the accuracy of crack detection. The AE noise signals are acquired from real operation conditions. They are analyzed and reconstructed by chaos theory. Based on the reconstructed vectors, a reasonable Nonlinear AutoRegressive with eXogenous input (NARX) model of AE noises is built to eliminate noises. For suppressing the abnormal noise interference, a feature detection method is proposed to improve the detection accuracy based on the fused features. Meanwhile, the detection ability of the proposed method is further verified by a longer signal. The results illustrate that the proposed method is effective to detect crack signals in real noise environment. Moreover, the actual application of the proposed method is also discussed and it can provide a useful guidance for AE detection of rail cracks.

[1]  Alan Hase,et al.  Correlation between features of acoustic emission signals and mechanical wear mechanisms , 2012 .

[2]  Yi Shen,et al.  Detection method based on Kalman filter for high speed rail defect AE signal on wheel-rail rolling rig , 2018 .

[3]  Saeed Zolfaghari,et al.  Chaotic time series prediction with residual analysis method using hybrid Elman-NARX neural networks , 2010, Neurocomputing.

[4]  Marjan Kuchaki Rafsanjani,et al.  Chaotic time series prediction by artificial neural networks , 2016, J. Comput. Methods Sci. Eng..

[5]  Robert Lewis Reuben,et al.  Rail–wheel interaction monitoring using Acoustic Emission: A laboratory study of normal rolling signals with natural rail defects , 2010 .

[6]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[7]  Guilherme De A. Barreto,et al.  Long-term time series prediction with the NARX network: An empirical evaluation , 2008, Neurocomputing.

[8]  D. Bianchi,et al.  Wavelet packet transform for detection of single events in acoustic emission signals , 2015 .

[9]  Kristoffer Bruzelius,et al.  An initial investigation on the potential applicability of Acoustic Emission to rail track fault detection , 2004 .

[10]  K. Ono.  Application of acoustic emission for structure diagnosis , 2011 .

[11]  Yi Shen,et al.  Acoustic emission detection of rail defect based on wavelet transform and Shannon entropy , 2015 .

[12]  Mengjie Zhang,et al.  Cooperative coevolution of Elman recurrent neural networks for chaotic time series prediction , 2012, Neurocomputing.

[13]  Kara M. Kockelman,et al.  Chaos Theory and Transportation Systems: Instructive Example , 2004 .

[14]  Hengshan Hu,et al.  An improved AE detection method of rail defect based on multi-level ANC with VSS-LMS , 2018 .

[15]  Yi Shen,et al.  An analysis of the simulated acoustic emission sources with different propagation distances, types and depths for rail defect detection , 2014 .

[16]  Eugen Diaconescu,et al.  The use of NARX neural networks to predict chaotic time series , 2008 .

[17]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[18]  M. Rosenstein,et al.  A practical method for calculating largest Lyapunov exponents from small data sets , 1993 .

[19]  L. Cao.  Practical method for determining the minimum embedding dimension of a scalar time series , 1997 .

[20]  J. Salas,et al.  Nonlinear dynamics, delay times, and embedding windows , 1999 .

[21]  Zhaosheng Yang,et al.  Short-term traffic flow prediction model using particle swarm optimization–based combined kernel function-least squares support vector machine combined with chaos theory , 2016 .

[22]  Hongyan Ma,et al.  Defect detection and location in switch rails by acoustic emission and Lamb wave analysis: A feasibility study , 2016 .

[23]  A. Vannucci,et al.  Using artificial neural networks to forecast chaotic time series , 2000 .

[24]  Yi Shen,et al.  An investigation on rail health monitoring using acoustic emission technique by tensile test , 2015, 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[25]  Robin Clark,et al.  Rail flaw detection: overview and needs for future developments , 2004 .

[26]  Kanji Ono,et al.  STRUCTURAL INTEGRITY EVALUATION BY MEANS OF ACOUSTIC EMISSION , 2008 .

[27]  H. Abarbanel,et al.  Determining embedding dimension for phase-space reconstruction using a geometrical construction. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[28]  Yan Wang,et al.  Rail health monitoring using acoustic emission technique based on NMF and RVM , 2015, 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[29]  Kennel,et al.  Method to distinguish possible chaos from colored noise and to determine embedding parameters. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[30]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.