Fast classification for rail defect depths using a hybrid intelligent method

Abstract In view of the fact that the traditional laser ultrasonic imaging test takes a long time and cannot achieve large area scanning of rail. This paper explores the possibility of combing the laser-ultrasonic technology and a hybrid intelligent method to fast achieve classification and evaluation of artificial rolling contact fatigue (RCF) defect in different depths. The laser ultrasonic scanning detection system is used to collect data samples from different locations of the defects quickly, and the signals are detected by an interferometer. Once the characteristic information of different rail defects is acquired and trained by Support Vector Machine (SVM), the high efficient and high-precision rail detection can be realized through the input of the feature in the detection process. The hybrid method is composed by Wavelet Packet Transform (WPT), Kernel Principal Component Analysis (KPCA) and SVM. The WPT is used to decompose the signal of surface defect in different frequency bands. The KPCA is used to eliminate the redundancy of the original feature set, thereby reducing the correlation among all the defect features. Wavelet packet time-frequency coefficient (X), energy (E) and local entropy (F) are generated and a new feature (Ynew) is created by fusing X, E and F, as a result of WPT and KPCA. Finally, a support vector machine (SVM) method is used to classify RCF defect in different depths. It implements a fast classification of small data. Compared with single features, fusion feature has the highest accuracy rate up to 98.73%.

[1]  Tang Zhifeng.  Application of laser-induced ultrasound on rail flaw inspection , 2009 .

[2]  Luo Lin,et al.  Simulation of Laser Ultrasonics for Detection of Surface-Connected Rail Defects , 2017 .

[3]  Yitao Liang,et al.  A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM , 2015 .

[4]  P. S. Heyns,et al.  WEAR MONITORING IN TURNING OPERATIONS USING VIBRATION AND STRAIN MEASUREMENTS , 2001 .

[5]  Ruxu Du,et al.  FEATURE EXTRACTION AND ASSESSMENT USING WAVELET PACKETS FOR MONITORING OF MACHINING PROCESSES , 1996 .

[6]  Yanxi Zhang,et al.  Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding , 2014 .

[7]  Philip W. Loveday,et al.  Guided Wave Inspection and Monitoring of Railway Track , 2012 .

[8]  Radovan Kovacevic,et al.  A Laser-Based Vision System for Weld Quality Inspection , 2011, Sensors.

[9]  Ryutaro Tanaka,et al.  Effect of different features to drill-wear prediction with back propagation neural network , 2014 .

[10]  Maksym Spiryagin,et al.  Rail Flaw Detection Technologies for Safer, Reliable Transportation: A Review , 2018 .

[11]  Tao Liu,et al.  Fault diagnosis of a mine hoist using PCA and SVM techniques , 2008 .

[12]  E. G. Bazulin.  Comparison of systems for ultrasonic nondestructive testing using antenna arrays or phased antenna arrays , 2013, Russian Journal of Nondestructive Testing.

[13]  Gui Yun Tian,et al.  Investigation into eddy current pulsed thermography for rolling contact fatigue detection and characterization , 2015 .

[14]  Joachim M. Buhmann,et al.  Wheel Defect Detection With Machine Learning , 2018, IEEE Transactions on Intelligent Transportation Systems.

[15]  Gui Yun Tian,et al.  Review of railway rail defect non-destructive testing and monitoring , 2016 .

[16]  Kyungmi Lee,et al.  Feature extraction and gating techniques for ultrasonic shaft signal classification , 2007, Appl. Soft Comput..

[17]  Rajiv Tiwari,et al.  Optimum multi-fault classification of gears with integration of evolutionary and SVM algorithms , 2014 .

[18]  Yi Jiang,et al.  Laser ultrasonic quantitative recognition based on wavelet packet fusion algorithm and SVM , 2017 .

[19]  Cem Selcuk,et al.  An automated long range ultrasonic rail flaw detection system based on the support vector machine algorithm , 2012 .

[20]  Cheng Zu-hai.  Laser Ultrasonic Technology and its Applications , 2005 .

[21]  Bingang Xu.  Intelligent fault inference for rotating flexible rotors using Bayesian belief network , 2012, Expert Syst. Appl..

[22]  Uwe Zerbst,et al.  Failure and damage tolerance aspects of railway components , 2011 .

[23]  Sung-Jin Song,et al.  A new technique for the identification of ultrasonic flaw signals using deconvolution. , 2004, Ultrasonics.

[24]  Wang Xue.  Overview and Future Development of Rails Nondestructive Inspection , 2013 .

[25]  E. García Plaza,et al.  Application of the wavelet packet transform to vibration signals for surface roughness monitoring in CNC turning operations , 2018 .

[26]  Mahmood Fateh,et al.  Automatic defect classification in long-range ultrasonic rail inspection using a support vector machine-based ?smart system? , 2004 .

[27]  Wei Guo,et al.  A hybrid intelligent multi-fault detection method for rotating machinery based on RSGWPT, KPCA and Twin SVM. , 2017, ISA transactions.

[28]  Zhonghua Shen,et al.  Numerical simulation of laser-generated ultrasound in non-metallic material by the finite element method , 2007 .

[29]  Gui Yun Tian,et al.  A FEATURE EXTRACTION TECHNIQUE BASED ON PRINCIPAL COMPONENT ANALYSIS FOR PULSED EDDY CURRENT NDT , 2003 .

[30]  M. H. Rosli,et al.  Enhancement of ultrasonic surface waves at wedge tips and angled defects , 2011 .

[31]  Geok Soon Hong,et al.  Multi-category micro-milling tool wear monitoring with continuous hidden Markov models , 2009 .

[32]  Soundarr T. Kumara,et al.  Flank Wear Estimation in Turning Through Wavelet Representation of Acoustic Emission Signals , 2000 .

[33]  M Ph Papaelias,et al.  A review on non-destructive evaluation of rails: State-of-the-art and future development , 2008 .

[34]  Thomas W. Krause,et al.  Real Time Pulsed Eddy Current Detection of Cracks in F/A-18 Inner Wing Spar Using Discriminant Separation of Modified Principal Components Analysis Scores , 2014, IEEE Sensors Journal.

[35]  Johan A. K. Suykens,et al.  Automated structural health monitoring based on adaptive kernel spectral clustering , 2017 .