钢轨缺陷无损检测与评估技术综述
|
摘要
钢轨缺陷的检测对于保障铁路安全具有重要的意义。在研究钢轨无损检测与评估技术的背景下,对国内外采用的钢轨缺陷检测方法进行了全面的综述,包括物理检测方法和机器视觉检测方法。阐述并分析了钢轨缺陷评估方法在机器视觉方面的应用情况,同时对所采用的钢轨无损检测与评估技术进行对比,论述和总结了包括射线检测在内的物理检测及包括图像处理在内的机器视觉检测两类检测方法的差异性。分析和研讨了现代无损检测与评估技术及其在发展中涉及的相关技术问题,并对钢轨缺陷无损检测与评估技术的未来发展给出设想。
The detection of rail defect is of great significance for guaranteeing railway safety. In the background of studying the non-destructive testing and evaluation technology of rail, this paper comprehensively reviews the methods of rail defect detection adopted at home and abroad, including physical detection method and machine vision inspection method. The application of rail defect evaluation method by machine vision is presented and analyzed. Meanwhile, the non-destructive testing technology and evaluation technology for rail are compared. The differetiation of physical inspection by radiation inspection and the machine vision detection by image processing is discussed and summarized. The modern non-destructive testing, evaluation technology, and related technical problems involved in the development are analyzed and discussed. The future development of non-destructive testing and evaluation technology for rail defect is assumed.
The detection of rail defect is of great significance for guaranteeing railway safety. In the background of studying the non-destructive testing and evaluation technology of rail, this paper comprehensively reviews the methods of rail defect detection adopted at home and abroad, including physical detection method and machine vision inspection method. The application of rail defect evaluation method by machine vision is presented and analyzed. Meanwhile, the non-destructive testing technology and evaluation technology for rail are compared. The differetiation of physical inspection by radiation inspection and the machine vision detection by image processing is discussed and summarized. The modern non-destructive testing, evaluation technology, and related technical problems involved in the development are analyzed and discussed. The future development of non-destructive testing and evaluation technology for rail defect is assumed.
引文
[1] PAPAELIAS M P, ROBERTS C, DAVIS C L. A review on non-destructive evaluation of rails: State-of-the-art and future development [J]. Proceedings of the Institution of Mechanical Engineers Part F Journal of Rail & Rapid Transit, 2008, 222(4): 367-384.
[2] LIU Z, LI W, XUE F, et al. Electromagnetic tomography rail defect inspection [J]. IEEE Transactions on Magnetics, 2015, 51(10): 1-7.
[3] HESSE D. Surface wave modes in rails [J]. Journal of the Acoustical Society of America, 2006, 120(2): 733-740.
[4] HESSE D, CAWLEY P. Excitation of surface wave modes in rails and their application for defect detection [C]. American Institute of Physics, 2006, 820(1):1593-1600.
[5] SEO J, KWON S, JUN H, et al. Fatigue crack growth behavior of surface crack in rails [J]. Procedia Engineering, 2010, 2(1): 865- 872.
[6] ZUMPANO G, MEO M. A new damage detection technique based on wave propagation for rails [J]. International Journal of Solids & Structures, 2006, 43(5): 1023-1046.
[7] ROGER L. Introduction to the damage tolerance behaviour of railway rails - A review [J]. Engineering Fracture Mechanics, 2009, 76(17): 2563- 2601.
[8] SANTIAGO M J, JUAN F S, et al. Dry and lubricated wear of rail steel under rolling contact fatigue-wear mechanisms and crack growth [J]. Wear, 2017(380-381): 240- 250.
[9] SHEN Z Y. Research on the contact surface wavy wear and contact fatigue of high-speed and heavy-duty wheel-rail [J]. Academic development, 2004(2): 19- 23.
[10] HE C G, GUO J, LIU Q Y, et al. Experimental investigation on the effect of operating speeds on wear and rolling contact fatigue damage of wheel materials [J]. Wear, 2016(364-365): 257- 269.
[11] WILCOX P, PAVLAKOVIC B, EVANS M, et al. Long range inspection of rail using guided waves [C]. Review of Progress in Quantitative Non-destructive Evaluation. American Institute of Physics, 2003, 657(1): 236- 243.
[12] LOVEDAY P W. Guided wave inspection and monitoring of railway track [J]. Journal of Nondestructive Evaluation, 2012, 31(4): 303-309.
[13] 祝连庆,董明利,孙军华.钢轨高速探伤检测系统中的伤损分析[J].仪器仪表学报,2003,24(4):222- 224.ZHU L Q, DONG M L, SUN J H. Analysis of damage in rail high speed flaw detection system [J]. Journal of Scientific Instrument, 2003, 24(4): 222- 224.
[14] ZHAO X Q, WANG W J, ZHONG W, et al. Study on coupling relation between rolling fatigue crack and wear of rail [J]. Journal of the China Railway Society, 2009, 31(2): 84- 87.
[15] SANTUR Y, KARAKOSE M, AKIN E. A new rail inspection method based on deep learning using laser cameras [C]. IEEE International Artificial Intelligence and Data Processing Symposium, 2017: 1- 6.
[16] KARAHALIOU A. Evaluation of railway rails with non-destructive techniques [J]. Key Engineering Materials, 2014(605): 641- 644.
[17] 田贵云,高斌,高运来.铁路钢轨缺陷伤损巡检与监测技术综述[J].仪器仪表学报,2016,37(8):1763-1780.TIAN G Y, GAO B, GAO Y L. Summary of inspection and monitoring technology for railway rail defect damage [J]. Chinese Journal of Scientific Instrument, 2016, 37(8): 1763-1780.
[18] 柳杰.钢轨高速电磁巡检下的涡流效应及补偿研究[D].南京:南京航空航天大学,2012.LIU J. Study on eddy current effect and compensation under high-speed electromagnetic inspection of rail [D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2012.
[19] ZHANG C Y, SU Z W, QIAO L, et al. Inspection system for detection of defects on rail surface based on LED and linear laser [J]. Science Technology & Engineering, 2012, 12(36): 9877-9880,9884.
[20] XIONG Z M, L Q Q, M Q Z, et al. A 3D laser profiling system for rail surface defect detection [J]. Sensors, 2017, 17(8): 1791-1810.
[21] QIAO J H, LI L S, ZHANG J G. Design of rail surface crack-detecting system based on linear CCD sensor [C]. IEEE International Conference on Networking, Sensing and Control, 2008: 1626-1631.
[22] TANG Y F, ZHU T. Application of linear array CCD photography technology to railway detecting field [J]. Railway Computer Application, 2004,13(5): 23- 25.
[23] 马子骥,董艳茹,刘宏立,等.基于多线结构光视觉的钢轨波磨动态测量方法[J].仪器仪表学报,2018,39(6):189-197.MA Z W, DONG Y R, LIU H L, et al. Dynamic measurement method of rail wave grinding based on multi-line structured light vision [J]. Chinese Journal of Scientific Instrument, 2018, 39(6): 189-197.
[24] 占栋,景德炎,吴命利,等.钢轨轮廓测量基准对齐和重采样方法研究[J].仪器仪表学报, 2018,39(2):149-159.ZHAN D, JING D Y, WU M L, et al. Research on calibration and resampling method of rail profile measurement [J]. Chinese Journal of Scientific Instrument, 2018, 39(2): 149-159.
[25] PENG J P, LI W, GAO X R, et al. Dynamic detection technology for the irregularity state of railway track based on linear array CCD [C]. International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment. International Society for Optics and Photonics, 2009: 728313-728313- 5.
[26] XU K, ZHOU P, HU C. 3D detection technique of surface defects for heavy rail based on binocular stereo vision [C]. International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment. International Society for Optics and Photonics, 2012: 841707- 841707- 5.
[27] CLARK R. Rail flaw detection: Overview and needs for future developments [J]. Ndt & E International, 2004, 37(2): 111-118.
[28] CHEN L, GUO J Q, GAO X R, et al. Research on rail defect detection system based on FPGA [C]. IEEE Technology & Application Forum, 2017: 195- 200.
[29] SUN M J, LIN X W, WU Z H, et al. Non-destructive photoacoustic detecting method for high-speed rail surface defects [C]. IEEE Instrumentation and Measurement Technology Conference, 2014: 896-900.
[30] DI S F, BARTOLI I, RIZZO P, et al. High-speed defect detection in rails by noncontact guided ultrasonic testing [J]. Transportation Research Record: Journal of the Transportation Research Board, 2005, 1916(1): 66-77.
[31] RIZZO P, COCCIA S, SCALEA F L D, et al. Unsupervised learning algorithm for high-speed defect detection in rails by laser/air-coupled non-contact ultrasonic testing [C]. Smart Structures & Materials. International Society for Optics and Photonics, 2006(6174): 777-788.
[32] 李骏.基于时频空特征的钢轨探伤识别研究[D].广州:华南理工大学,2017.LI J. Research on rail flaw detection based on time-frequency and space features [D]. Guangzhou: South China University of Technology, 2017.
[33] 赵洁.基于多传感器信息融合的轨道缺陷在线检测方法的研究[D].成都:西南交通大学,2015.ZHAO J. Research on on-line detection method of track defects based on multi-sensor information fusion [D]. Chengdu: Southwest Jiaotong University, 2015.
[34] SUN M J, CHENG X Z, WANG Y, et al. Method for detecting high-speed rail surface defects by photoacoustic signal [J]. Acta Physica Sinica, 2016, 65(3),doi:10.7498/aps.65.038105.
[35] 王握.基于超声导波的钢轨缺陷检测研究[D].南京:东南大学,2017.WANG W. Research on rail defect detection based on ultrasonic guided wave [D]. Nanjing: Southeast University, 2017.
[36] ROSE J L, AVIOLI M J, MUDGE P, et al. Guided wave inspection potential of defects in rail [J]. Ndt & E International, 2004, 37(2): 153-161.
[37] 卢超,魏运飞,徐薇.钢轨踏面斜裂纹超声表面波B扫成像检测研究[J].仪器仪表学报,2010,31(10):2272- 2278.LU CH, WEI Y F, XU W. Ultrasonic surface wave B-scan imaging detection of rail tread oblique crack [J]. Chinese Journal of Scientific Instrument, 2010, 31(10): 2272- 2278.
[38] 门平,董世运,卢超,等.钢轨踏面低频超声表面波传播模式研究[J].仪器仪表学报,2018,39(3):13- 20.MEN P, DONG SH Y, LU CH, et al. Study on the propagation mode of low frequency ultrasonic surface wave on rail tread [J]. Chinese Journal of Scientific Instrument, 2018, 39(3): 13- 20.
[39] 朱力强,许西宁,余祖俊,等.基于超声导波的钢轨完整性检测方法研究[J].仪器仪表学报,2016,37(7):1603-1609.ZHU L Q, XU X N, YU Z J, et al. Research on inspection method of rail integrity based on ultrasonic guided wave [J]. Journal of Instrument and Measurement, 2016, 37(7): 1603-1609.
[40] HAYASHI T, SONG W J, ROSE J L. Guided wave dispersion curves for a bar with an arbitrary cross-section, a rod and rail example [J]. Ultrasonics, 2004, 41(3): 175-183.
[41] CHONG M L, ROSE J L, CHO Y. A guided wave approach to defect detection under shelling in rail [J]. Ndt & E International, 2009, 42(3): 174-1802.
[42] SEBKO V P, SUCHKOV G M, KAMARDIN V M. Sensitivity of the electromagnetic acoustical technique for testing railway rails by the mirror-shadow method [J]. Russian Journal of Nondestructive Testing, 2004, 40(3): 170-177.
[43] DIXON S, EDWARDS R S, JIAN X. Inspection of rail track head surfaces using electromagnetic acoustic transducers [J]. Or Insight, 2004, 46(6): 326-330.
[44] ZHANG X, WHANG K, WANG Y, et al. An improved method of rail health monitoring based on CNN and multiple acoustic emission events [C]. IEEE Instrumentation and Measurement Technology Conference, 2017: 1- 6.
[45] JIAN X, DIXON S, GUO N, et al. Pulsed rayleigh wave scattered at a surface crack [J]. Ultrasonics, 2006, 44(4): e1131-e1134.
[46] 陈晓阳.用于钢轨轨底缺陷检测的电磁超声换能器设计[D].哈尔滨:哈尔滨工业大学,2014.CHEN X Y. Design of electromagnetic ultrasonic transducer for rail bottom defect detection [D]. Harbin: Harbin Institute of Technology, 2014.
[47] 苏日亮.基于电磁超声斜入射SV波的钢轨缺陷检测方法研究[D].哈尔滨:哈尔滨工业大学,2011.SU R L. Research on rail defect detection method based on electromagnetic ultrasonic oblique incidence SV wave [D]. Harbin: Harbin Institute of Technology, 2011.
[48] 汪开灿.基于电磁超声的钢轨缺陷检测系统的研究[D].哈尔滨:哈尔滨工业大学,2010.WANG K C. Research on rail defect detection system based on electromagnetic ultrasonic [D]. Harbin: Harbin Institute of Technology, 2010.
[49] 时亚,石文泽.钢轨踏面检测电磁超声表面波换能器优化设计[J].仪器仪表学报,2018,39(8):239- 249.SHI Y, SHI W Z. Optimization design of electromagnetic ultrasonic surface wave transducer for rail tread detection [J]. Chinese Journal of Scientific Instrument, 2018, 39(8): 239- 249.
[50] YANG J, UME I C. Laser ultrasonic technique for evaluating solder bump defects in flip chip packages using modal and signal analysis methods [J]. IEEE Transactions on Ultrason Ferroelectr Freq Control, 2010, 57(4): 920-932.
[51] ZHAO Y, SUN J H, MA J, et al. Application of the hybrid laser ultrasonic method in rail inspection[J]. Insight-Non-Destructive Testing and Condition Monitoring, 2014, 56(7): 360-366.
[52] GARCIA G, KALAY S. Laser-based ultrasonic rail inspection system [J]. Railway Track & Structures, 2007, 103(10): 21- 23.
[53] KENDERIAN S, DJORDJEVIC B B, CERNIGLIA D, et al. Dynamic railroad inspection using the laser-air hybrid ultrasonic technique [J]. Insight-Non-Destructive Testing and Condition Monitoring, 2006, 48(6): 336-341.
[54] NIELASEN S, BARDENSHTEIN A, THOMMESEN A, et al. Automatic laser ultrasonics for rail inspection[C].16th World Conference on NDT, 2004:1- 8.
[55] LIU Z, LI W, XUE F, et al. Electromagnetic tomography rail defect inspection [J]. IEEE Transactions on Magnetics, 2015, 51(10): 1-7.
[56] LIU Z, ZHOU F, HE Y. Automated visual inspection system for bogie block key under complex freight train environment [J]. IEEE Transactions on Instrumentation & Measurement, 2015, 65(1): 2-14.
[57] LIU Z, JIA W, ZHU L X, et al. Rail defect inspection using alternating current excitation coils with digital demodulation algorithm [C]. IEEE Instrumentation and Measurement Technology Conference, 2011: 1- 4.
[58] WEI Q, ZHANG X, WANG Y, et al. Rail defect detection based on vibration acceleration signals [C]. IEEE International Instrumentation and Measurement Technology Conference, 2013: 1194-1199.
[59] FAGHIH R S, HAJIZADEH S. Deep convolutional neural networks for detection of rail surface defects [C]. IEEE International Joint Conference on Neural Networks, 2016,doi:10.1109/IJCNN.2016.7727522.
[60] EDWARDS R S, SOPHIAN A, DIXON S, et al. Dual EMAT and PEC non-contact probe: Applications to defect testing [J]. Ndt & E International, 2006, 39(1): 45- 52.
[61] 彭谢丹.面向钢轨踏面斜裂纹伤损的脉冲涡流检测方法研究[D].杭州:浙江大学,2018.PENG X D. Research on pulse eddy current detection method for oblique crack of rail tread [D]. Hangzhou: Zhejiang University, 2018.
[62] 汪路明,金合丽,周煊勇.基于机器视觉和脉冲涡流复合的在线钢轨表面缺陷检测系统设计[J].浙江树人大学学报(自然科学版),2018,18(1):7-11.WANG L M, JIN H L, ZHOU Y Y. Design of on-line rail surface defect detection system based on machine vision and pulsed eddy current composite [J]. Journal of Zhejiang Shuren University (Natural Science), 2018, 18(1): 7-11.
[63] CHEN ZH J, XUAN J Q, WANG P, et al. Simulation on high speed rail magnetic flux leakage inspection [C]. IEEE Instrumentation & Measurement Technology Conference, 2011,doi:10.1109/IMTC.2011.5944294.
[64] WILSON J, TIAN G Y. 3D magnetic field sensing for magnetic flux leakage defect characterisation [J]. Insight-Non-Destructive Testing and Condition Monitoring, 2006, 48(6): 357-359.
[65] OLIVERIA H, CORREIA P L. Automatic road crack detection and characterization [J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(1): 155-168.
[66] GAO J S, YU W, HE C. The research on defect recognition method for rail magnetic flux leakage detecting [C]. IEEE International Conference on Measurement, 2012: 745-750.
[67] GAO J S, DU G H, WEI H L. The research of defect detection test system based on magnetic flux leakage [C]. IEEE International Forum on Strategic Technology, 2011: 1225-1229.
[68] ANTIPOV A G, MARKOV A A. Evaluation of transverse cracks detection depth in MFL rail NDT [J]. Russian Journal of Nondestructive Testing, 2014, 50(8): 481- 490.
[69] 高运来,王平,田贵云,等.钢轨裂纹高速漏磁巡检中的动态磁化及速度效应分析[J].无损检测,2013,35(10):53- 58.GAO Y L, WANG P, TIAN G Y, et al. Dynamic magnetization and velocity effect analysis of rail crack high-speed magnetic leakage inspection [J]. Non-destructive Testing, 2013, 35(10): 53- 58.
[70] 白坚,王平,邹朋朋.基于轨面适应承载机构的钢轨表面缺陷的漏磁检测[J].无损检测,2017,39(11):16-19.BAI J, WANG P, ZOU P P. Magnetic flux leakage detection of rail surface defects based on rail surface adaptation bearing mechanism [J]. Non-destructive Testing, 2017, 39(11): 16-19.
[71] 郝思思.阵列式漏磁巡检设备的开发及钢轨裂纹定量分析[D].南京:南京航空航天大学,2014.HAO S S. Development of array magnetic flux leakage inspection equipment and quantitative analysis of rail cracks [D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2014.
[72] DEUTSCHL E, GASSER C, NIEL A, et al. Defect detection on rail surfaces by a vision based system [C]. IEEE Intelligent Vehicles Symposium, 2004: 507- 511.
[73] NITTI M, MANDRIOTA C, STELLA E, et al. Real time classification of rail defects [J]. Publication of WIT Press, 2002(61): 335-344.
[74] MANDRIOTA C, NITTI M, ANCONA N, et al. Filter-based feature selection for rail defect detection [J]. Machine Vision & Applications, 2004, 15(4): 179-185.
[75] 贺振东,王耀南,毛建旭,等.基于反向P-M扩散的钢轨表面缺陷视觉检测[J].自动化学报,2014,40(8):1667-1679.HE ZH D, WANG Y N, MAO J X, et al. Vision detection of rail surface defects based on reverse P-M diffusion [J]. Acta Automatica Sinica, 2014, 40(8): 1667-1679.
[76] 贺振东,王耀南,刘洁,等.基于背景差分的高铁钢轨表面缺陷图像分割[J].仪器仪表学报,2016,37(3):640- 649.HE ZH D, WANG Y N, LIU J, et al. Image segmentation of high-iron rail surface defects based on background difference [J]. Chinese Journal of Scientific Instrument, 2016, 37(3): 640- 649.
[77] 闵永智,岳彪,马宏锋,等.基于图像灰度梯度特征的钢轨表面缺陷检测[J].仪器仪表学报,2018,39(4):220- 229.MIN Y ZH, YUE B, MA H F, et al. Detection of rail surface defects based on image gray gradient features [J]. Chinese Journal of Scientific Instrument, 2018, 39(4): 220- 229.
[78] 张辉,金侠挺,JONATHAN W Q M,等.基于曲率滤波和改进GMM的钢轨缺陷自动视觉检测方法[J].仪器仪表学报,2018,39(4):181-194.ZHANG H, JIN X T, JONATHAN W Q M, et al. Automatic vision detection method for rail defects based on curvature filtering and improved GMM [J]. Chinese Journal of Scientific Instrument, 2018, 39(4): 181-194.
[79] LI Q Y, REN S W. A real-time visual inspection system for discrete surface defects of rail heads [J]. IEEE Transactions on Instrumentation and Measurement, 2012, 61(8): 2189- 2199.
[80] MIN Y, XIAO B, DANG J, et al. Real time detection system for rail surface defects based on machine vision [J]. EURASIP Journal on Image and Video Processing, 2018(1): 3.
[81] TASTIMUR C, KARAKOS M, AKIN E, et al. Rail defect detection with real time image processing technique [C]. IEEE International Conference on Industrial Informatics, 2017: 411- 415.
[82] TASTIMUR C, YAMAN O, KARAKOSE M, et al. A real time interface for vision inspection of rail components and surface in railways [C]. International Artificial Intelligence and Data Processing Symposium, 2017: 1- 6.
[83] ABBAS M A. Improving deep learning performance using random forest HTM cortical learning algorithm [C]. First International Workshop on Deep and Representation Learning, 2018: 13-18.
[84] DE-BRUIN T, VERBERT K, BABUSKA R. Railway Track circuit fault diagnosis using recurrent neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 28(3): 523- 533.
[85] TRINH H, HAAS N, LI Y, et al. Enhanced rail component detection and consolidation for rail track inspection [C]. IEEE Workshop on the Applications of Computer Vision, 2012: 289- 295.
[86] GIBERT X, PATEL V M, CHELLAPPA R. Robust fastener detection for autonomous visual railway track inspection [C]. IEEE Applications of Computer Vision, 2015: 694-701.
[87] GAN J R, LI Q Y, WANG J Z, et al. A Hierarchical extractor-based visual rail surface inspection system [J]. IEEE Sensors Journal, 2017, 17(23): 7935-7944.
[88] ZHANG X, WANG K W, WANG Y, et al. An improved method of rail health monitoring based on CNN and multiple acoustic emission events [C]. IEEE Instrumentation and Measurement Technology Conference, 2017: 1- 6.
[89] SHANG L D, YANG, Q S, WANG J N, et al. Detection of rail surface defects based on CNN image recognition and classification [C]. International Conference on Advanced Communications Technology, 2018(2): 45- 51.
[90] YI Z, WANG K, KANG L, et al. Rail flaw detection system based on electromagnetic acoustic technique [C]. IEEE Industrial Electronics and Applications, 2010: 211- 215.
[91] CHEN F C, JAHANSHAHI M R. NB-CNN: Deep learning-based crack detection using convolutional neural network and na?ve Bayes data fusion [J]. IEEE Transactions on Industrial Electronics, 2018, 65(5): 4392- 4400.
[2] LIU Z, LI W, XUE F, et al. Electromagnetic tomography rail defect inspection [J]. IEEE Transactions on Magnetics, 2015, 51(10): 1-7.
[3] HESSE D. Surface wave modes in rails [J]. Journal of the Acoustical Society of America, 2006, 120(2): 733-740.
[4] HESSE D, CAWLEY P. Excitation of surface wave modes in rails and their application for defect detection [C]. American Institute of Physics, 2006, 820(1):1593-1600.
[5] SEO J, KWON S, JUN H, et al. Fatigue crack growth behavior of surface crack in rails [J]. Procedia Engineering, 2010, 2(1): 865- 872.
[6] ZUMPANO G, MEO M. A new damage detection technique based on wave propagation for rails [J]. International Journal of Solids & Structures, 2006, 43(5): 1023-1046.
[7] ROGER L. Introduction to the damage tolerance behaviour of railway rails - A review [J]. Engineering Fracture Mechanics, 2009, 76(17): 2563- 2601.
[8] SANTIAGO M J, JUAN F S, et al. Dry and lubricated wear of rail steel under rolling contact fatigue-wear mechanisms and crack growth [J]. Wear, 2017(380-381): 240- 250.
[9] SHEN Z Y. Research on the contact surface wavy wear and contact fatigue of high-speed and heavy-duty wheel-rail [J]. Academic development, 2004(2): 19- 23.
[10] HE C G, GUO J, LIU Q Y, et al. Experimental investigation on the effect of operating speeds on wear and rolling contact fatigue damage of wheel materials [J]. Wear, 2016(364-365): 257- 269.
[11] WILCOX P, PAVLAKOVIC B, EVANS M, et al. Long range inspection of rail using guided waves [C]. Review of Progress in Quantitative Non-destructive Evaluation. American Institute of Physics, 2003, 657(1): 236- 243.
[12] LOVEDAY P W. Guided wave inspection and monitoring of railway track [J]. Journal of Nondestructive Evaluation, 2012, 31(4): 303-309.
[13] 祝连庆,董明利,孙军华.钢轨高速探伤检测系统中的伤损分析[J].仪器仪表学报,2003,24(4):222- 224.ZHU L Q, DONG M L, SUN J H. Analysis of damage in rail high speed flaw detection system [J]. Journal of Scientific Instrument, 2003, 24(4): 222- 224.
[14] ZHAO X Q, WANG W J, ZHONG W, et al. Study on coupling relation between rolling fatigue crack and wear of rail [J]. Journal of the China Railway Society, 2009, 31(2): 84- 87.
[15] SANTUR Y, KARAKOSE M, AKIN E. A new rail inspection method based on deep learning using laser cameras [C]. IEEE International Artificial Intelligence and Data Processing Symposium, 2017: 1- 6.
[16] KARAHALIOU A. Evaluation of railway rails with non-destructive techniques [J]. Key Engineering Materials, 2014(605): 641- 644.
[17] 田贵云,高斌,高运来.铁路钢轨缺陷伤损巡检与监测技术综述[J].仪器仪表学报,2016,37(8):1763-1780.TIAN G Y, GAO B, GAO Y L. Summary of inspection and monitoring technology for railway rail defect damage [J]. Chinese Journal of Scientific Instrument, 2016, 37(8): 1763-1780.
[18] 柳杰.钢轨高速电磁巡检下的涡流效应及补偿研究[D].南京:南京航空航天大学,2012.LIU J. Study on eddy current effect and compensation under high-speed electromagnetic inspection of rail [D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2012.
[19] ZHANG C Y, SU Z W, QIAO L, et al. Inspection system for detection of defects on rail surface based on LED and linear laser [J]. Science Technology & Engineering, 2012, 12(36): 9877-9880,9884.
[20] XIONG Z M, L Q Q, M Q Z, et al. A 3D laser profiling system for rail surface defect detection [J]. Sensors, 2017, 17(8): 1791-1810.
[21] QIAO J H, LI L S, ZHANG J G. Design of rail surface crack-detecting system based on linear CCD sensor [C]. IEEE International Conference on Networking, Sensing and Control, 2008: 1626-1631.
[22] TANG Y F, ZHU T. Application of linear array CCD photography technology to railway detecting field [J]. Railway Computer Application, 2004,13(5): 23- 25.
[23] 马子骥,董艳茹,刘宏立,等.基于多线结构光视觉的钢轨波磨动态测量方法[J].仪器仪表学报,2018,39(6):189-197.MA Z W, DONG Y R, LIU H L, et al. Dynamic measurement method of rail wave grinding based on multi-line structured light vision [J]. Chinese Journal of Scientific Instrument, 2018, 39(6): 189-197.
[24] 占栋,景德炎,吴命利,等.钢轨轮廓测量基准对齐和重采样方法研究[J].仪器仪表学报, 2018,39(2):149-159.ZHAN D, JING D Y, WU M L, et al. Research on calibration and resampling method of rail profile measurement [J]. Chinese Journal of Scientific Instrument, 2018, 39(2): 149-159.
[25] PENG J P, LI W, GAO X R, et al. Dynamic detection technology for the irregularity state of railway track based on linear array CCD [C]. International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment. International Society for Optics and Photonics, 2009: 728313-728313- 5.
[26] XU K, ZHOU P, HU C. 3D detection technique of surface defects for heavy rail based on binocular stereo vision [C]. International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment. International Society for Optics and Photonics, 2012: 841707- 841707- 5.
[27] CLARK R. Rail flaw detection: Overview and needs for future developments [J]. Ndt & E International, 2004, 37(2): 111-118.
[28] CHEN L, GUO J Q, GAO X R, et al. Research on rail defect detection system based on FPGA [C]. IEEE Technology & Application Forum, 2017: 195- 200.
[29] SUN M J, LIN X W, WU Z H, et al. Non-destructive photoacoustic detecting method for high-speed rail surface defects [C]. IEEE Instrumentation and Measurement Technology Conference, 2014: 896-900.
[30] DI S F, BARTOLI I, RIZZO P, et al. High-speed defect detection in rails by noncontact guided ultrasonic testing [J]. Transportation Research Record: Journal of the Transportation Research Board, 2005, 1916(1): 66-77.
[31] RIZZO P, COCCIA S, SCALEA F L D, et al. Unsupervised learning algorithm for high-speed defect detection in rails by laser/air-coupled non-contact ultrasonic testing [C]. Smart Structures & Materials. International Society for Optics and Photonics, 2006(6174): 777-788.
[32] 李骏.基于时频空特征的钢轨探伤识别研究[D].广州:华南理工大学,2017.LI J. Research on rail flaw detection based on time-frequency and space features [D]. Guangzhou: South China University of Technology, 2017.
[33] 赵洁.基于多传感器信息融合的轨道缺陷在线检测方法的研究[D].成都:西南交通大学,2015.ZHAO J. Research on on-line detection method of track defects based on multi-sensor information fusion [D]. Chengdu: Southwest Jiaotong University, 2015.
[34] SUN M J, CHENG X Z, WANG Y, et al. Method for detecting high-speed rail surface defects by photoacoustic signal [J]. Acta Physica Sinica, 2016, 65(3),doi:10.7498/aps.65.038105.
[35] 王握.基于超声导波的钢轨缺陷检测研究[D].南京:东南大学,2017.WANG W. Research on rail defect detection based on ultrasonic guided wave [D]. Nanjing: Southeast University, 2017.
[36] ROSE J L, AVIOLI M J, MUDGE P, et al. Guided wave inspection potential of defects in rail [J]. Ndt & E International, 2004, 37(2): 153-161.
[37] 卢超,魏运飞,徐薇.钢轨踏面斜裂纹超声表面波B扫成像检测研究[J].仪器仪表学报,2010,31(10):2272- 2278.LU CH, WEI Y F, XU W. Ultrasonic surface wave B-scan imaging detection of rail tread oblique crack [J]. Chinese Journal of Scientific Instrument, 2010, 31(10): 2272- 2278.
[38] 门平,董世运,卢超,等.钢轨踏面低频超声表面波传播模式研究[J].仪器仪表学报,2018,39(3):13- 20.MEN P, DONG SH Y, LU CH, et al. Study on the propagation mode of low frequency ultrasonic surface wave on rail tread [J]. Chinese Journal of Scientific Instrument, 2018, 39(3): 13- 20.
[39] 朱力强,许西宁,余祖俊,等.基于超声导波的钢轨完整性检测方法研究[J].仪器仪表学报,2016,37(7):1603-1609.ZHU L Q, XU X N, YU Z J, et al. Research on inspection method of rail integrity based on ultrasonic guided wave [J]. Journal of Instrument and Measurement, 2016, 37(7): 1603-1609.
[40] HAYASHI T, SONG W J, ROSE J L. Guided wave dispersion curves for a bar with an arbitrary cross-section, a rod and rail example [J]. Ultrasonics, 2004, 41(3): 175-183.
[41] CHONG M L, ROSE J L, CHO Y. A guided wave approach to defect detection under shelling in rail [J]. Ndt & E International, 2009, 42(3): 174-1802.
[42] SEBKO V P, SUCHKOV G M, KAMARDIN V M. Sensitivity of the electromagnetic acoustical technique for testing railway rails by the mirror-shadow method [J]. Russian Journal of Nondestructive Testing, 2004, 40(3): 170-177.
[43] DIXON S, EDWARDS R S, JIAN X. Inspection of rail track head surfaces using electromagnetic acoustic transducers [J]. Or Insight, 2004, 46(6): 326-330.
[44] ZHANG X, WHANG K, WANG Y, et al. An improved method of rail health monitoring based on CNN and multiple acoustic emission events [C]. IEEE Instrumentation and Measurement Technology Conference, 2017: 1- 6.
[45] JIAN X, DIXON S, GUO N, et al. Pulsed rayleigh wave scattered at a surface crack [J]. Ultrasonics, 2006, 44(4): e1131-e1134.
[46] 陈晓阳.用于钢轨轨底缺陷检测的电磁超声换能器设计[D].哈尔滨:哈尔滨工业大学,2014.CHEN X Y. Design of electromagnetic ultrasonic transducer for rail bottom defect detection [D]. Harbin: Harbin Institute of Technology, 2014.
[47] 苏日亮.基于电磁超声斜入射SV波的钢轨缺陷检测方法研究[D].哈尔滨:哈尔滨工业大学,2011.SU R L. Research on rail defect detection method based on electromagnetic ultrasonic oblique incidence SV wave [D]. Harbin: Harbin Institute of Technology, 2011.
[48] 汪开灿.基于电磁超声的钢轨缺陷检测系统的研究[D].哈尔滨:哈尔滨工业大学,2010.WANG K C. Research on rail defect detection system based on electromagnetic ultrasonic [D]. Harbin: Harbin Institute of Technology, 2010.
[49] 时亚,石文泽.钢轨踏面检测电磁超声表面波换能器优化设计[J].仪器仪表学报,2018,39(8):239- 249.SHI Y, SHI W Z. Optimization design of electromagnetic ultrasonic surface wave transducer for rail tread detection [J]. Chinese Journal of Scientific Instrument, 2018, 39(8): 239- 249.
[50] YANG J, UME I C. Laser ultrasonic technique for evaluating solder bump defects in flip chip packages using modal and signal analysis methods [J]. IEEE Transactions on Ultrason Ferroelectr Freq Control, 2010, 57(4): 920-932.
[51] ZHAO Y, SUN J H, MA J, et al. Application of the hybrid laser ultrasonic method in rail inspection[J]. Insight-Non-Destructive Testing and Condition Monitoring, 2014, 56(7): 360-366.
[52] GARCIA G, KALAY S. Laser-based ultrasonic rail inspection system [J]. Railway Track & Structures, 2007, 103(10): 21- 23.
[53] KENDERIAN S, DJORDJEVIC B B, CERNIGLIA D, et al. Dynamic railroad inspection using the laser-air hybrid ultrasonic technique [J]. Insight-Non-Destructive Testing and Condition Monitoring, 2006, 48(6): 336-341.
[54] NIELASEN S, BARDENSHTEIN A, THOMMESEN A, et al. Automatic laser ultrasonics for rail inspection[C].16th World Conference on NDT, 2004:1- 8.
[55] LIU Z, LI W, XUE F, et al. Electromagnetic tomography rail defect inspection [J]. IEEE Transactions on Magnetics, 2015, 51(10): 1-7.
[56] LIU Z, ZHOU F, HE Y. Automated visual inspection system for bogie block key under complex freight train environment [J]. IEEE Transactions on Instrumentation & Measurement, 2015, 65(1): 2-14.
[57] LIU Z, JIA W, ZHU L X, et al. Rail defect inspection using alternating current excitation coils with digital demodulation algorithm [C]. IEEE Instrumentation and Measurement Technology Conference, 2011: 1- 4.
[58] WEI Q, ZHANG X, WANG Y, et al. Rail defect detection based on vibration acceleration signals [C]. IEEE International Instrumentation and Measurement Technology Conference, 2013: 1194-1199.
[59] FAGHIH R S, HAJIZADEH S. Deep convolutional neural networks for detection of rail surface defects [C]. IEEE International Joint Conference on Neural Networks, 2016,doi:10.1109/IJCNN.2016.7727522.
[60] EDWARDS R S, SOPHIAN A, DIXON S, et al. Dual EMAT and PEC non-contact probe: Applications to defect testing [J]. Ndt & E International, 2006, 39(1): 45- 52.
[61] 彭谢丹.面向钢轨踏面斜裂纹伤损的脉冲涡流检测方法研究[D].杭州:浙江大学,2018.PENG X D. Research on pulse eddy current detection method for oblique crack of rail tread [D]. Hangzhou: Zhejiang University, 2018.
[62] 汪路明,金合丽,周煊勇.基于机器视觉和脉冲涡流复合的在线钢轨表面缺陷检测系统设计[J].浙江树人大学学报(自然科学版),2018,18(1):7-11.WANG L M, JIN H L, ZHOU Y Y. Design of on-line rail surface defect detection system based on machine vision and pulsed eddy current composite [J]. Journal of Zhejiang Shuren University (Natural Science), 2018, 18(1): 7-11.
[63] CHEN ZH J, XUAN J Q, WANG P, et al. Simulation on high speed rail magnetic flux leakage inspection [C]. IEEE Instrumentation & Measurement Technology Conference, 2011,doi:10.1109/IMTC.2011.5944294.
[64] WILSON J, TIAN G Y. 3D magnetic field sensing for magnetic flux leakage defect characterisation [J]. Insight-Non-Destructive Testing and Condition Monitoring, 2006, 48(6): 357-359.
[65] OLIVERIA H, CORREIA P L. Automatic road crack detection and characterization [J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(1): 155-168.
[66] GAO J S, YU W, HE C. The research on defect recognition method for rail magnetic flux leakage detecting [C]. IEEE International Conference on Measurement, 2012: 745-750.
[67] GAO J S, DU G H, WEI H L. The research of defect detection test system based on magnetic flux leakage [C]. IEEE International Forum on Strategic Technology, 2011: 1225-1229.
[68] ANTIPOV A G, MARKOV A A. Evaluation of transverse cracks detection depth in MFL rail NDT [J]. Russian Journal of Nondestructive Testing, 2014, 50(8): 481- 490.
[69] 高运来,王平,田贵云,等.钢轨裂纹高速漏磁巡检中的动态磁化及速度效应分析[J].无损检测,2013,35(10):53- 58.GAO Y L, WANG P, TIAN G Y, et al. Dynamic magnetization and velocity effect analysis of rail crack high-speed magnetic leakage inspection [J]. Non-destructive Testing, 2013, 35(10): 53- 58.
[70] 白坚,王平,邹朋朋.基于轨面适应承载机构的钢轨表面缺陷的漏磁检测[J].无损检测,2017,39(11):16-19.BAI J, WANG P, ZOU P P. Magnetic flux leakage detection of rail surface defects based on rail surface adaptation bearing mechanism [J]. Non-destructive Testing, 2017, 39(11): 16-19.
[71] 郝思思.阵列式漏磁巡检设备的开发及钢轨裂纹定量分析[D].南京:南京航空航天大学,2014.HAO S S. Development of array magnetic flux leakage inspection equipment and quantitative analysis of rail cracks [D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2014.
[72] DEUTSCHL E, GASSER C, NIEL A, et al. Defect detection on rail surfaces by a vision based system [C]. IEEE Intelligent Vehicles Symposium, 2004: 507- 511.
[73] NITTI M, MANDRIOTA C, STELLA E, et al. Real time classification of rail defects [J]. Publication of WIT Press, 2002(61): 335-344.
[74] MANDRIOTA C, NITTI M, ANCONA N, et al. Filter-based feature selection for rail defect detection [J]. Machine Vision & Applications, 2004, 15(4): 179-185.
[75] 贺振东,王耀南,毛建旭,等.基于反向P-M扩散的钢轨表面缺陷视觉检测[J].自动化学报,2014,40(8):1667-1679.HE ZH D, WANG Y N, MAO J X, et al. Vision detection of rail surface defects based on reverse P-M diffusion [J]. Acta Automatica Sinica, 2014, 40(8): 1667-1679.
[76] 贺振东,王耀南,刘洁,等.基于背景差分的高铁钢轨表面缺陷图像分割[J].仪器仪表学报,2016,37(3):640- 649.HE ZH D, WANG Y N, LIU J, et al. Image segmentation of high-iron rail surface defects based on background difference [J]. Chinese Journal of Scientific Instrument, 2016, 37(3): 640- 649.
[77] 闵永智,岳彪,马宏锋,等.基于图像灰度梯度特征的钢轨表面缺陷检测[J].仪器仪表学报,2018,39(4):220- 229.MIN Y ZH, YUE B, MA H F, et al. Detection of rail surface defects based on image gray gradient features [J]. Chinese Journal of Scientific Instrument, 2018, 39(4): 220- 229.
[78] 张辉,金侠挺,JONATHAN W Q M,等.基于曲率滤波和改进GMM的钢轨缺陷自动视觉检测方法[J].仪器仪表学报,2018,39(4):181-194.ZHANG H, JIN X T, JONATHAN W Q M, et al. Automatic vision detection method for rail defects based on curvature filtering and improved GMM [J]. Chinese Journal of Scientific Instrument, 2018, 39(4): 181-194.
[79] LI Q Y, REN S W. A real-time visual inspection system for discrete surface defects of rail heads [J]. IEEE Transactions on Instrumentation and Measurement, 2012, 61(8): 2189- 2199.
[80] MIN Y, XIAO B, DANG J, et al. Real time detection system for rail surface defects based on machine vision [J]. EURASIP Journal on Image and Video Processing, 2018(1): 3.
[81] TASTIMUR C, KARAKOS M, AKIN E, et al. Rail defect detection with real time image processing technique [C]. IEEE International Conference on Industrial Informatics, 2017: 411- 415.
[82] TASTIMUR C, YAMAN O, KARAKOSE M, et al. A real time interface for vision inspection of rail components and surface in railways [C]. International Artificial Intelligence and Data Processing Symposium, 2017: 1- 6.
[83] ABBAS M A. Improving deep learning performance using random forest HTM cortical learning algorithm [C]. First International Workshop on Deep and Representation Learning, 2018: 13-18.
[84] DE-BRUIN T, VERBERT K, BABUSKA R. Railway Track circuit fault diagnosis using recurrent neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 28(3): 523- 533.
[85] TRINH H, HAAS N, LI Y, et al. Enhanced rail component detection and consolidation for rail track inspection [C]. IEEE Workshop on the Applications of Computer Vision, 2012: 289- 295.
[86] GIBERT X, PATEL V M, CHELLAPPA R. Robust fastener detection for autonomous visual railway track inspection [C]. IEEE Applications of Computer Vision, 2015: 694-701.
[87] GAN J R, LI Q Y, WANG J Z, et al. A Hierarchical extractor-based visual rail surface inspection system [J]. IEEE Sensors Journal, 2017, 17(23): 7935-7944.
[88] ZHANG X, WANG K W, WANG Y, et al. An improved method of rail health monitoring based on CNN and multiple acoustic emission events [C]. IEEE Instrumentation and Measurement Technology Conference, 2017: 1- 6.
[89] SHANG L D, YANG, Q S, WANG J N, et al. Detection of rail surface defects based on CNN image recognition and classification [C]. International Conference on Advanced Communications Technology, 2018(2): 45- 51.
[90] YI Z, WANG K, KANG L, et al. Rail flaw detection system based on electromagnetic acoustic technique [C]. IEEE Industrial Electronics and Applications, 2010: 211- 215.
[91] CHEN F C, JAHANSHAHI M R. NB-CNN: Deep learning-based crack detection using convolutional neural network and na?ve Bayes data fusion [J]. IEEE Transactions on Industrial Electronics, 2018, 65(5): 4392- 4400.