机车底部故障图像识别技术研究
|
摘要
在机车故障诊断的各项检修中,主要的方式有：人工肉眼判别、基于机器视觉的图像自动识别。机车底部部件结构复杂度高,细小部件多,仅靠人工检查,很难准确记住所有部件的正常状态和形式,易由视觉疲劳造成漏检,尤其在高速运行状态下的列车任何一个细小、细微的故障,都可能引发重大事故。机器视觉图像技术作为智能自动识别已经广泛应用于各个行业,对提高铁路车辆安全检测技术水平,具有重要意义。本论文旨在应用图像分割、特征描绘等图像处理技术实现列车底部心盘故障图像的自动识别,减少人为影响误差,提高检测效率。
论文在研究目前铁路故障轨边图像检测系统和图像处理技术的基础上,分析了图像特征提取的各种方法和性质。然后结合机车底部心盘图像特有的结构特性,首先定义五个分割特征,利用线性加窗灰度投影进行粗分割,定位出待检测螺栓的目标区域,然后根据特征定义间关系分割得到各个螺栓图。对分割得到的螺栓图经过滤波、灰度直方均衡增强、面积阈值法二值图像、提取面积大小与故障特征疑似的区域判别、建立封闭矩形描绘子等图像处理技术,最终实现机车底部心盘螺栓丢失故障图像识别算法模型的设计。
最后,设计了机车底部图像采集的方案,实现方案搭建和图像采集实验,并用实际图像对建立的算法模型进行了验证。该算法能够准确自动识别螺栓丢失故障,满足代替人作业的要求,提高列车检修效率。本课题对类似故障识别的案例或者自动检测系统的研发也具指导作用。
In recent years, with the rapid development of world's high-speed railway, especially for the running of high-speed motor train units, rail safety inspection accept new challenge, more rigorous and sophisticated maintenance and monitoring of trains are put forward to implement. Because of complexity structures and so many small-parts, it is too hard and tired for works to accurately handle all problems. Any subtle fault could cause a serious accident in high speed. As intelligent automatic recognition technology, machine vision image processing technology which been widely used has great significance to realize railway vehicle safety inspection.
Aiming at designing locomotive-bottom-image acquisition system and realizing faults automatic recognition to reduce man-made influence and improve detection efficiency, it is guided for the research of similar cases or automatic detection system.
In the paper, on the premise of investigating and summarizing railway image detection technologies and devices and image processing technologies, locomotive-bottom image acquisition system is designed and set up. Combining with analysis of properties of image feature extraction methods and structure characteristics of train, five structure-segmentation rules are defined. Take the integration of rectangular function and gray projection to segment image, and then get the object-bolts image date based on the relationship between each structure-segmentation rule. A set of defects recognition algorithms are proposed based on filtering, histogram equalization, area thresh, connected region extraction, closed rectangular areas descriptors. Faults of bolts missing can be positioned accurately through using the proposed method in the testing image. Over all, it will give some guidelines for the work afterward.
论文在研究目前铁路故障轨边图像检测系统和图像处理技术的基础上,分析了图像特征提取的各种方法和性质。然后结合机车底部心盘图像特有的结构特性,首先定义五个分割特征,利用线性加窗灰度投影进行粗分割,定位出待检测螺栓的目标区域,然后根据特征定义间关系分割得到各个螺栓图。对分割得到的螺栓图经过滤波、灰度直方均衡增强、面积阈值法二值图像、提取面积大小与故障特征疑似的区域判别、建立封闭矩形描绘子等图像处理技术,最终实现机车底部心盘螺栓丢失故障图像识别算法模型的设计。
最后,设计了机车底部图像采集的方案,实现方案搭建和图像采集实验,并用实际图像对建立的算法模型进行了验证。该算法能够准确自动识别螺栓丢失故障,满足代替人作业的要求,提高列车检修效率。本课题对类似故障识别的案例或者自动检测系统的研发也具指导作用。
In recent years, with the rapid development of world's high-speed railway, especially for the running of high-speed motor train units, rail safety inspection accept new challenge, more rigorous and sophisticated maintenance and monitoring of trains are put forward to implement. Because of complexity structures and so many small-parts, it is too hard and tired for works to accurately handle all problems. Any subtle fault could cause a serious accident in high speed. As intelligent automatic recognition technology, machine vision image processing technology which been widely used has great significance to realize railway vehicle safety inspection.
Aiming at designing locomotive-bottom-image acquisition system and realizing faults automatic recognition to reduce man-made influence and improve detection efficiency, it is guided for the research of similar cases or automatic detection system.
In the paper, on the premise of investigating and summarizing railway image detection technologies and devices and image processing technologies, locomotive-bottom image acquisition system is designed and set up. Combining with analysis of properties of image feature extraction methods and structure characteristics of train, five structure-segmentation rules are defined. Take the integration of rectangular function and gray projection to segment image, and then get the object-bolts image date based on the relationship between each structure-segmentation rule. A set of defects recognition algorithms are proposed based on filtering, histogram equalization, area thresh, connected region extraction, closed rectangular areas descriptors. Faults of bolts missing can be positioned accurately through using the proposed method in the testing image. Over all, it will give some guidelines for the work afterward.
引文
[1].齐辉.对TFDS货车运行故障动态图像检测系统运用情况的初步探索[J].铁道机车车辆.2007,27(4)：51-54.
[2].周云燕.基于图像分析理论的机械故障诊断研究[D].华中科技大学.2007年10月.
[3]. 戴鹏.火车典型故障图像识别算法算法研究[D].哈尔滨工业大学.2010年5月.
[4]. Li Zhinong, He Yongyong, Chu Fulei. Application of the blind source separation in machine fault diagnosis:A review and prospect.Mechanical Systems and Signal Processing,2005,1(1):1-24.
[5]. 徐敏等.设备故障诊断手册——机械设备状态监测和故障诊断[M].西安：交通大学出版社,1998：3-19.
[6]. 刘瑞杨,王毓民.铁路货车滚动轴承早期故障轨边声学诊断系统(TADS)原理及应用[M].北京：中国铁道出版社,2005：70-157.
[7]. 王柯童.基于图像处理的列车故障自动检测系统设计[D].哈尔滨工业大学.2008年6月.
[8]. Liu Zhigang,He Zhengyou,Zhang Dabo,et al.The study of Maglev train diagnosis system based on ADS'ideas.Autonomous Decentralized Systems,ISADS,2005:224-229.
[9]. Francescomaria Marino,Arcangelo Distante,Pier Luigi Mazzeo,et al.A Real-Time Visual Inspection System for Railway Maintenance:Automatic Hexagonal-Headed Bolts Detection. IEEE Transactions on Systems, Man, and Cybernetics—Part C:Applications and Reviews,2007,37(3):418-428.
[10]. P.L. Mazzeo, M. Nitti, E. Stella, et al. Visual recongnition of fastening bolts for railroad maintenance. Pattern Recongnition Letters,2004,25 (6):669-676.
[11]. 周卫国.基于图像分析的炉体喷涂缺陷自动检测方法[D].天津大学.2007.
[12]. Yang Xue Zhi. Pnag GK.H. Yung N.H.C. Fbaric defect detection using adaptive wavelet[C]. IEEE Intenrational Conefrence on Aeousties, SPeech, and Signal Processing,2001, Vol.6:3697-3700.
[13].万海涛.基于图像的螺纹表面缺陷检测[D].青岛大学.2005：1-25.
[14]. Richard Szeliski. Computer Vision:Algorithms and Applications[M].2010.
[15].白建军,王伟.货车故障轨边图像检测系统(TFDS)运用现状及问题分析[J].太原铁道科技.2010(1)：16-19.
[16].陈燕,郭峰.TFDS系统心盘螺栓丢失故障的自动识别检测技术[J].郑州轻工业学院学报.2010,25(3)：90-94.
[17].王新宇.TFDS抗阳光干扰系统的研究与应用[J].哈尔滨铁道科技.2009：5-8.
[18].张晓波.基于图像处理技术的表面缺陷自动检测系统的研究[D].天津大学精密仪器与光电子工程.2004：16-17.
[19].谈新权.CCD高分辨率成像技术(二)[J],电子自动化,1999,(3)：53-55.
[20].王庆有,孙学珠.CCD应用技术[M].天津：天津大学出版社.1993：14-16.
[21].黄艳红.受电弓滑板磨耗图像检测算研究[D].西南交通大学.2008,12：18-25.
[22].张铮,王艳平.数字图像处理与机器视觉[M].人民邮电出版社.2010.
[23].迟军,周晓军,宋立军,数字图像处理技术在锻件缺陷检测中的应用[J],机床与液压,2005(11)：139-140.
[24]. Fabrizio Russo. A Method Based on Piecewise Linear Models for Accurate Restoration of Images Corrupted by Gaussian Noise[J]. IEEE Transactions on Instrumentation and Measurement,2006,55(6):1935-1943.
[25].孙莹涛,李玉山.多运动目标跟踪及连通域标记方法[J].电子元器件应用.2007,9(57)：44-45.
[26].高红波,王卫星.一种二值图像连通区域标记的新算法[J].计算机应用,2007,27(11)：2776-2777.
[27].孙辉.快速灰度投影算法及其在电子稳像中的应用[J].光学精密工程.2007,15(3)：412-416.
[28].杨晓敏,吴炜等.图像特征点提取及匹配技术[J].光学精密工程.2009.17(9)：2276-2281.
[29].田娟,郑郁正.模板匹配技术在图像识别中的应用[J].传感器与微系统.2008.27(1)：112-117.
[301.张瑞娟,蒲宝明,潘世铭.模板匹配算法在动车零部件故障检测系统中的应用[J].计算机系统应用.2011.20(8)：134-17.
[31]. M. Brown, D. Lowe, Invariant features from interest point groups, in:BMVC, 2002.
[32]. Yan Ke, Rahul Sukthankar. PCA-SIFT:A More Distictive Representation for Local Image Descriptors. In:CVPR (2). (2004):506-513.
[33]. LINDEBERG T. Feature detection with automatic scale selection[J]. International Joural of Computer Vision,1998,30(2):79-116.
[34].阎若梅.基于区域的要干立体像对压缩算法研究[D].西安电子科技大学.2010.
[35]. BAY H, TUVTELLARS T, GOOL L Van. SURF:speeded up robust features [C]. Proceedings of the European Conference on Computer Vision,2006:404-417.
[36]. Herbert Bay, Andreas Ess. Speeded-Up Robust Features (SURF) [J].Computer Vision and Image Understanding.2008.110:346-359.
[37]. VIOLA P,JONES M J. Rapid object detection using a boosted cascade of simple features[C]. Conference on Computer Vision and Pattern Recognition, 2001:511-518.
[38J.张锐娟,张建奇,杨翠.基于SURF的图像配准方法研究[J].红外与激光工程[J].2009,38(1)：160-165.
[39]. Luo Juan. Oubong Gwun. A Comparison of SIFT, PCA-SIFT and SURF[J]. International Journal of Image Processing (IJIP) Volume(3), Issue(4).143-152.
[40].孙兆林.MATLAB6. x[M].清华大学出版社.
[41].刘直芳,游志胜,王运琼.基于PCA和ICA的人脸识别.激光技术[J].2004.28(1)：78-81.
[42]. Karhunen J. Paiunen, Oja E. Nonlinear PCA type approaches for source separation and independent component analysis[C]. Proceedings of the 1995 IEEE International Conference on Neural Networds(ICNN'95),1995:995-1000.
[43].逯鹏,李永强等.基于视觉感知的故障图像检测算法[J].仪器仪表学报.2010.31(9)：1997-2002.
[44].王明祥.独立分量分析方法及在图像处理中的应用研究[M].上海：上海大学出版社.2005.
[45].杨福生,洪波.独立分量分析的原理与应用[M].北京：清华大学出版社.2006.
[46].杨行峻,郑君里.人工神经网络与盲信号处理[M].北京：北京大学出版社,2003.
[2].周云燕.基于图像分析理论的机械故障诊断研究[D].华中科技大学.2007年10月.
[3]. 戴鹏.火车典型故障图像识别算法算法研究[D].哈尔滨工业大学.2010年5月.
[4]. Li Zhinong, He Yongyong, Chu Fulei. Application of the blind source separation in machine fault diagnosis:A review and prospect.Mechanical Systems and Signal Processing,2005,1(1):1-24.
[5]. 徐敏等.设备故障诊断手册——机械设备状态监测和故障诊断[M].西安：交通大学出版社,1998：3-19.
[6]. 刘瑞杨,王毓民.铁路货车滚动轴承早期故障轨边声学诊断系统(TADS)原理及应用[M].北京：中国铁道出版社,2005：70-157.
[7]. 王柯童.基于图像处理的列车故障自动检测系统设计[D].哈尔滨工业大学.2008年6月.
[8]. Liu Zhigang,He Zhengyou,Zhang Dabo,et al.The study of Maglev train diagnosis system based on ADS'ideas.Autonomous Decentralized Systems,ISADS,2005:224-229.
[9]. Francescomaria Marino,Arcangelo Distante,Pier Luigi Mazzeo,et al.A Real-Time Visual Inspection System for Railway Maintenance:Automatic Hexagonal-Headed Bolts Detection. IEEE Transactions on Systems, Man, and Cybernetics—Part C:Applications and Reviews,2007,37(3):418-428.
[10]. P.L. Mazzeo, M. Nitti, E. Stella, et al. Visual recongnition of fastening bolts for railroad maintenance. Pattern Recongnition Letters,2004,25 (6):669-676.
[11]. 周卫国.基于图像分析的炉体喷涂缺陷自动检测方法[D].天津大学.2007.
[12]. Yang Xue Zhi. Pnag GK.H. Yung N.H.C. Fbaric defect detection using adaptive wavelet[C]. IEEE Intenrational Conefrence on Aeousties, SPeech, and Signal Processing,2001, Vol.6:3697-3700.
[13].万海涛.基于图像的螺纹表面缺陷检测[D].青岛大学.2005：1-25.
[14]. Richard Szeliski. Computer Vision:Algorithms and Applications[M].2010.
[15].白建军,王伟.货车故障轨边图像检测系统(TFDS)运用现状及问题分析[J].太原铁道科技.2010(1)：16-19.
[16].陈燕,郭峰.TFDS系统心盘螺栓丢失故障的自动识别检测技术[J].郑州轻工业学院学报.2010,25(3)：90-94.
[17].王新宇.TFDS抗阳光干扰系统的研究与应用[J].哈尔滨铁道科技.2009：5-8.
[18].张晓波.基于图像处理技术的表面缺陷自动检测系统的研究[D].天津大学精密仪器与光电子工程.2004：16-17.
[19].谈新权.CCD高分辨率成像技术(二)[J],电子自动化,1999,(3)：53-55.
[20].王庆有,孙学珠.CCD应用技术[M].天津：天津大学出版社.1993：14-16.
[21].黄艳红.受电弓滑板磨耗图像检测算研究[D].西南交通大学.2008,12：18-25.
[22].张铮,王艳平.数字图像处理与机器视觉[M].人民邮电出版社.2010.
[23].迟军,周晓军,宋立军,数字图像处理技术在锻件缺陷检测中的应用[J],机床与液压,2005(11)：139-140.
[24]. Fabrizio Russo. A Method Based on Piecewise Linear Models for Accurate Restoration of Images Corrupted by Gaussian Noise[J]. IEEE Transactions on Instrumentation and Measurement,2006,55(6):1935-1943.
[25].孙莹涛,李玉山.多运动目标跟踪及连通域标记方法[J].电子元器件应用.2007,9(57)：44-45.
[26].高红波,王卫星.一种二值图像连通区域标记的新算法[J].计算机应用,2007,27(11)：2776-2777.
[27].孙辉.快速灰度投影算法及其在电子稳像中的应用[J].光学精密工程.2007,15(3)：412-416.
[28].杨晓敏,吴炜等.图像特征点提取及匹配技术[J].光学精密工程.2009.17(9)：2276-2281.
[29].田娟,郑郁正.模板匹配技术在图像识别中的应用[J].传感器与微系统.2008.27(1)：112-117.
[301.张瑞娟,蒲宝明,潘世铭.模板匹配算法在动车零部件故障检测系统中的应用[J].计算机系统应用.2011.20(8)：134-17.
[31]. M. Brown, D. Lowe, Invariant features from interest point groups, in:BMVC, 2002.
[32]. Yan Ke, Rahul Sukthankar. PCA-SIFT:A More Distictive Representation for Local Image Descriptors. In:CVPR (2). (2004):506-513.
[33]. LINDEBERG T. Feature detection with automatic scale selection[J]. International Joural of Computer Vision,1998,30(2):79-116.
[34].阎若梅.基于区域的要干立体像对压缩算法研究[D].西安电子科技大学.2010.
[35]. BAY H, TUVTELLARS T, GOOL L Van. SURF:speeded up robust features [C]. Proceedings of the European Conference on Computer Vision,2006:404-417.
[36]. Herbert Bay, Andreas Ess. Speeded-Up Robust Features (SURF) [J].Computer Vision and Image Understanding.2008.110:346-359.
[37]. VIOLA P,JONES M J. Rapid object detection using a boosted cascade of simple features[C]. Conference on Computer Vision and Pattern Recognition, 2001:511-518.
[38J.张锐娟,张建奇,杨翠.基于SURF的图像配准方法研究[J].红外与激光工程[J].2009,38(1)：160-165.
[39]. Luo Juan. Oubong Gwun. A Comparison of SIFT, PCA-SIFT and SURF[J]. International Journal of Image Processing (IJIP) Volume(3), Issue(4).143-152.
[40].孙兆林.MATLAB6. x[M].清华大学出版社.
[41].刘直芳,游志胜,王运琼.基于PCA和ICA的人脸识别.激光技术[J].2004.28(1)：78-81.
[42]. Karhunen J. Paiunen, Oja E. Nonlinear PCA type approaches for source separation and independent component analysis[C]. Proceedings of the 1995 IEEE International Conference on Neural Networds(ICNN'95),1995:995-1000.
[43].逯鹏,李永强等.基于视觉感知的故障图像检测算法[J].仪器仪表学报.2010.31(9)：1997-2002.
[44].王明祥.独立分量分析方法及在图像处理中的应用研究[M].上海：上海大学出版社.2005.
[45].杨福生,洪波.独立分量分析的原理与应用[M].北京：清华大学出版社.2006.
[46].杨行峻,郑君里.人工神经网络与盲信号处理[M].北京：北京大学出版社,2003.