摘要
铁路货车走行部弹簧作为转向架的关键部件,在使用过程中会因原材料缺陷及异常的冲击等因素而产生缺损,失去缓冲和减振的作用,进而影响到行车安全。
一直以来,弹簧缺损故障的检测主要是由人工完成,不仅效率低、可靠性差,而且工人劳动强度大,存在很大的安全隐患。国内的货车运行故障动态图像检测系统能通过人机结合的方式,检测出弹簧缺损,在一定程度上减小了工人的劳动强度,提高了故障发现率。但实质上,该系统本身仅是完成了图像的采集、传输及适当的预处理,弹簧故障的判断仍是通过人工肉眼浏览采集到的图片来完成的,依然存在很多问题,需要进一步改进和升级。基于此,本文研究了如何利用图像处理技术来实现弹簧缺损故障的自动识别,对于提高故障检出率,保障货车安全运行具有十分重要的意义。
本文首先在调研国内外走行部弹簧缺损图像检测技术的研究现状的前提下,研究了基于特征扫描的弹簧图像定位算法。思路是：先对采集到的走行部图像进行光照不均校正、二值化处理,然后扫描分析二值图像,根据图像特征找到弹簧区域边界位置,实现定位。通过对120幅图像进行实验及处理,结果表明：该算法能适用于不同车型不同光照环境下的弹簧图像定位,并且准确率达到95%以上
其次,本文根据弹簧本身的宽度特征,提出了弹簧丢失自动识别算法：在对定位后的弹簧组合进行单个弹簧的分割后,通过比较相邻弹簧的宽度,可判断是否存在弹簧丢失故障。
最后研究了基于模式识别理论的弹簧断裂自动识别算法：利用灰度共生矩阵提取图像纹理特征；基于Relief算法进行特征选择；利用最小距离分类器对未知样本进行分类判断。利用模拟的断裂弹簧图片进行样本训练和测试,结果表明：弹簧断裂识别率可达到90%以上。
本文的研究为实现弹簧缺损自动检测提供了算法依据,准确率高、通用性好,具有良好的应用前景。
As the key component of the freight car's bogie, running gear springs are easily fractured and lost because of the materials defects and abnormal impact, which will lose the role of buffering and damping vibration and threaten freight car's security.
Since always, detection of the springs defects was mainly accomplished by manual work. Not only the efficiency was low, the reliability was poor, but also the labor intensity was big, and there's a security risk. The trouble of moving freight car detection system could detect the springs defects by the way of man-machine integration, which, to some extent, reduced the labor intensity and improved the defects detection rate. But in fact, the system itself only finished image collection, transmission and some pretreatment, defects recognition was still completed by worker's naked eye. So there were still many problems and needed to be further improved and upgraded. Consequently, this thesis studied how to automatically identify the springs defects through using image processing techniques in order to improve the defects detection rate and guarantee the freight car's security.
Firstly, on the premise of investigating the research status of automatic recognition of springs defects based on image processing techniques at home and abroad, springs location algorithm was studied in this thesis. It was first to correct the uneven illumination and take binaryzation on image. Then the springs'boundary was found by binary image scanning and features analysis. Through experiment on120images, the results showed that the algorithm was appropriate for springs location of different models and different illumination environment, and the accuracy rate was above95%.
Secondly, according to the structure features of spring itself, a spring loss recognition algorithm was proposed. After springs location, division of single spring was operated, then one could judge whether there was spring loss by comparison of the adjacent spring width.
Finally, spring fracture recognition algorithm based on pattern recognition theory was studied in this thesis. Gray level co-occurrence matrix was used to extract the image texture feature; Relief algorithm was used to choose the optimal feature subset of image; minimum distance of template matching was used in image recognition. Through experiment on fracture springs images which were simulated, the judgment accuracy rate was above90%.
This study provides algorithm reference for the realization of springs defects automatic recognition with high accuracy and good commonality and has a good application prospect.
引文
[1]王随.机车一系圆簧断裂原因分析[J].电力机车与城轨车辆,2009,32(5)：45
[2]陈士伟.影响货车圆柱螺旋压缩弹簧疲劳的主要因素[J].机车车辆工艺,2004(2)：33-35
[3]田中健.铁路货车转向架圆弹簧疲劳寿命影响因素的分析研究[D].重庆大学工程硕士学位论文,2005：14-16
[4]赵阳春,张黎俐.货车运用常见故障分析与处理[M].北京：中国铁道出版社,2000：161-163
[5]陈雷.TFDS检查货车故障案例汇编[M].北京：中国铁道出版社,2008
[6]刘宪.机车走行部弹簧超声波探伤研究[J].机车电传动,2006(5)：57-59
[7]刘瑞扬,王毓敏.铁路货车运行故障动态图像检测系统(TFDS)原理及应用[M].北京：中国铁道出版社,2005
[8]郑雄,许峰,黄志宏.浅谈TFDS系统运用中存在的问题和改进措施[J].海峡科学,2007(11)：56-58
[9]白建军,王玮.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
[10]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)：51-53
[11]安立愿,张瑞田,王剑飞.关于货车运行故障动态图像检测系统(TFDS)运用管理的思考[J].铁路机车车辆,2007(增)：152-153
[12]姜媛,周富强,张广军.货车枕簧丢失故障动态图像识别方法[J].光学技术,2007,33(5)：662-665
[13]戴鹏.基于计算机视觉的故障自动识别系统的设计和实现[D].哈尔滨工业大学硕士学位论文,2006：26-31
[14]曹份槟.基于PCA和SVM的货车故障检测[D].北京交通大学硕士学位论文,2011：26-44
[15]梁琳,何卫平,雷蕾等.光照不均图像增强方法综述[J].计算机应用研究,2010,27(5)：1625-1626
[16]黄华,蒋永馨,王孝通等.一种基于Ardely分割算法的夜间图像增强方法[C].第十四届全国图像图形学学术会议论文集.北京：中国图像图形学学会,2008：86-87
[17]张铮,王艳平,薛桂香.数字图像处理与机器视觉—Visual C++与Matlab实现[M].北京：人民邮电出版社,2010：90
[18]姚若河,黄继武,吴湘淇.改进的直方图均衡化图像增强算法[J].铁道学报,1997,19(6)：78-81
[19]Zeyun Yu, Chandrajit Bajaj. A fast and adaptive method for image contrast enhancement[C]. Proc. of International Conference on Image Processing, 2004. Institute of Electrical and Electronics Engineers Computer Society, 2004:1001~1004
[20]曹聚亮,吕宝海,李冠章.基于自适应局部灰度修正的直方图均衡算法[J].红外与激光工程,2004,33(5)：513-515
[21]Yinpeng Jin, Laura Fayad, Andrew Laine. Contrast enhancement by multiscale adaptive histogram equalization[C]. Proc. of International Conference on Wavelets,2001. Applications in Signal and Image Processing, 2001:206~213
[22]马天龙,张成义.基于Matlab的同态滤波器的优化设计[J].应用光学,2010,31(4)：584-588
[23]王冬梅,路敬祎,王秀芳.基于Matlab的同态滤波算法的研究[J].科学技术与工程,2010,10(26)：6562-6564
[24]张新明,沈兰荪.基于小波的同态滤波器用于图像对比度增强[J].电子学报,2001,29(4)：531-533
[25]Stephane G.Mallat. A theory for multiresolution signal decomposition:the wavelet representation[J]. IEEE Trans. PAMI, 1987,11(7):674~693
[26]孙忠贵.数字图像光照不均匀校正及Matlab实现[J].微计算机信息,2008,24(4)：313-314
[27]P.T.Jackway. Improved morphological top-hat[J]. IEEE Electronics Letters,2000, 36(14):1194~1195
[28]Hany Farid. Blind inverse Gamma correction[J]. IEEE Trans. on Image Processing, 2001,10(2):1428~1433
[29]杨金锋,杨国庆,吴仁彪.减少光照影响的自适应Gamma矫正方法[J].信号处理,2005,21(4)：261-264
[30]Nobuyuki Otsu. A Threshold Selection Method from Gray-Level Histograms[J]. IEEE Trans. SMC,1979,9(1):62~69
[31]Bernsen J. Dynamic thresholding of gray level images[C]. Proc.8th Int. Conf. on Pattern Recongnition, Paris, 1986. IEEE Computer Society Press,1986:1251~1255
[32]李久芳.基于二值化的边缘图像滤波方法[J].电子工业专用设备,2010,39(2)：26
[33]王爱玲,叶明生,邓秋香.Matlab R2007图像处理技术与应用[M].北京：电子工业出版社,2008：165
[34]杨淑莹.模式识别与智能计算—Matlab技术实现[M].北京：电子工业出版社,2008
[35]Yu Zhong, Anil K Jain. Object localization using color, texture and shape[J]. Pattern Recognition, 2000,33(4):671-684
[36]翟俊海,赵文秀,王熙照.图像特征提取研究[J].河北大学学报(自然科学版),2009,29(1)：106-110
[37]Hong Ziquan, Yang Jingyu. Algebraic feature extraction of image for recognition[J]. Pattern Recognition, 1991,24(3):211-219
[38]Andrew Laine, Jian Fan. Texture classification by wavelet packet signatures[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1993,15(11): 1186-1191
[39]Clausi D.A, Jernigan M.E. A fast method to determine co-occurrence texture features[J]. IEEE Trans. on Geoscience and Remote Sensing, 1988, 36(1):298-300
[40]Abdulrahman, Al-Janobi. Performance evaluation of cross-diagonal texture matrix method of texture analysis[J]. Pattern Recognition, 2001, 34(1): 171-180
[41]Robert M.Haralick, K.Shanmugan. Textural features for image classification[J]. IEEE Trans. on System, Man and Cybernetics, 1973, SMC-3(6):610-621
[42]H Tamura, S Mori, T Yamawaki. Textural features corresponding to visual perception[J]. IEEE Trans. on System, Man and Cybernetics, 1978, 8(6): 460-473
[43]高程程,惠晓威.基于灰度共生矩阵的纹理特征提取[J].计算机系统应用,2010,19(6)：195-197
[44]苏映雪.特征选择算法研究[D].国防科学技术大学硕士学位论文,2006：1-3
[45]Kenji Kira, Larry A.Rendell. The feature selection problem:Traditional methods and a new algorithm[C]. Proceedings of National Conference on Artificial Intelligence. New Orleans:AAAIPress,1992:129-134
[46]Koby Crammer, Ran Gilad-Bachrach, Amir Navot. Margin analysis of the LVQ algorithm[A]. Proc. 17th Conference on Neural Information Proeessing Systems[C].2002
[47]Igor Kononenko. Estimating attributes:analysis and extensions of Relief[C]. Proceedings of the 1994 European Conference on Machine Learning, 1994: 171-182
[48]Marko Robnik-Sikonja, Igor Kononenko. Theoretical and Empirical Analysis of ReliefF and RReliefF[J]. Machine Learning, 2003,53(1):23~69
[49]Anil K.Jain, Robert P.W.Duin, Jianchang Mao. Statistical Pattern Recognition:A Review[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000,22(1):4~37
[50]Leen-Kiat Soh, Costas Tsatsoulis. Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices[J]. IEEE Trans. on Geoscience and Remote Sensing, 1999, 37(2):780~795
[51]刘伟.图像型垃圾邮件的特征选择算法研究及实现[D].电子科技大学硕士学位论文,2010：25
