基于稀疏编码空间金字塔匹配和GA-SVM的列车故障自动识别

孙国栋; 周振; 王俊豪; 张杨; 赵大兴

doi:doi:10.3788/ope.20182612.3087

光学精密工程, 2018, 26 (12): 3087, 网络出版: 2019-01-27

基于稀疏编码空间金字塔匹配和GA-SVM的列车故障自动识别

Automatic fault recognition algorithm for key parts of train based on sparse coding based spatial pyramid matching and GA-SVM

论文大纲

孙国栋 ^1,*周振 ¹王俊豪 ¹张杨 ^1,2赵大兴 ¹

作者单位

¹ 湖北工业大学机械工程学院, 湖北武汉 430068

² 南京大学计算机科学与技术系, 江苏南京 210023

摘要

针对货车运行故障动态图像中车辆挡键、集尘器和安全链锁紧螺栓的故障检测, 提出一种基于稀疏编码空间金字塔匹配和遗传算法优化的支持向量机相结合的通用故障自动识别算法。首先在不同尺度空间对样本图像进行划分, 对每个部分提取尺度不变特征变换特征, 利用随机抽取样本的SIFT特征通过迭代学习生成字典并进行稀疏编码; 其次利用主成分分析定义编码后的特征对故障识别准确率的贡献值, 并据此对编码特征进行降维; 然后利用编码降维后的特征结合遗传算法对线性SVM分类器进行训练; 最后用训练好的分类器模型对挡键、集尘器和安全链锁紧螺栓的故障进行识别。实验结果表明, 本文提出的算法能较好的应用于3种不同类型的故障识别, 识别率分别为97.25%、99.00%和97.50%, 同时对噪声和光照变化具有一定的鲁棒性, 能满足车辆故障的实际检测需求。

Abstract

A general automatic fault recognition algorithm based on sparse-coding-based spatial pyramid matching and Genetic Algorithm Optimized Support Vector Machine (GA-SVM) was proposed for fault detection of the bogie block key, dust collector, and fastening bolt in the Trouble of moving Freight car Detection System (TFDS). First, the image of a sample was divided into patch areas in different scale spaces, and the Scale-Invariant Feature Transforms (SIFT) of each patch area was extracted. Sparse coding was then performed by iteratively learning dictionaries using the SIFT features of randomly extracted samples. Second, principal component analysis was used to define the contribution of the encoded features towards fault recognition accuracy and reduce the dimensionality of the coding features. Then, the SVM classifier was trained using the reduced dimension features after coding and optimization with the genetic algorithm. Finally, the trained classifier was used to detect the bogie block key, dust collector, and fastening bolt faults from their images. The experimental results show that the algorithm can adaptively recognize the three different kinds of faults. The fault recognition rates were 97.25%, 99.00%, and 97.50% for bogie block key, dust collector, and fastening bolts, respectively. This technique is robust to noise and illumination changes and can meet the actual detection requirements of a vehicle's structural faults.

参考文献

[1] 刘瑞扬. 货车运行故障动态图像检测系统(TFDS)的原理与应用［J］. 中国铁路, 2005, (5): 26-37.

LIU R Y. Principle and application of trouble of moving freight car detection system (TFDS)［J］. Chinese Railways, 2005, (5): 26-37. (in Chinese)

[2] ZHENG C, WEI Z Z. Automatic online vision-based inspection system of coupler yoke for freight trains［J］. Journal of Electronic Imaging, 2016, 25(6): 061602.

[3] 赵大兴, 王博, 周唯倜, 等. 基于有向线段重构轮廓与成对几何直方图的缓解阀盖图像匹配算法［J］. 中国机械工程, 2017, 28(6): 721-727.

ZHAO D X, WANG B, ZHOU W T, et al.. Image matching algorithm of release valve bonnet based on contours reconstructed by oriented line segment and pairwise geometrical histogram［J］. China Mechanical Engineering, 2017, 28(6): 721-727. (in Chinese)

[4] 孙国栋, 汤汉兵, 林凯, 等. 基于多特征融合和BP-AdaBoost的列车关键零件故障自动识别算法［J］. 中国机械工程, 2017, 28(21): 1-6.

SUN G D, TANG H B, LIN K, et al.. Automatic fault recognition algorithm for key parts of train based on multi-feature fusion and BP-AdaBoost［J］. China Mechanical Engineering, 2017, 28(21): 2588-2594. (in Chinese)

[5] 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.

JIANG Y, ZHOU F Q, ZHANG G J. An automatic recognition method for trouble of sleeper springs of freight cars［J］. Optical Technique, 2007, 33(5): 662-665. (in Chinese)

[6] LIU L, ZHOU F, HE Y. Automated status inspection of fastening bolts on freight trains using a machine vision approach［J］. Proceedings of the Institution of Mechanical Engineers Part F: Journal of Rail & Rapid Transit, 2016, 230(7): 1159-66.

[7] LIU L, ZHOU F Q, HE Y Z. Automated visual inspection system for bogie block key under complex freight train environment［J］. IEEE Transactions on Instrumentation and Measurement, 2016, 65(1): 2-14.

[8] LI N, WEI Z, CAO Z. Automatic fault recognition for Brake-Shoe-Key losing of freight train［J］. Optik - International Journal for Light and Electron Optics, 2015, 126(23): 4735-4742.

[9] SUN G D, FENG W, ZHAO D X, et al.. An automatic fault recognition method for side frame key in TFDS［J］. The Open Mechanical Engineering Journal, 2015, 9(1): 22-27.

[10] LIU L, ZHOU F, HE Y. Vision-based fault inspection of small mechanical components for train safety［J］. Iet Intelligent Transport Systems, 2016, 10(2): 130-139.

[11] SUN J H, XIAO Z W, XIE Y X. Automatic multi-fault recognition in TFDS based on convolutional neural network［J］. Neurocomputing. 2017, 222: 127-136.

[12] LI C, WEI Z, XING J. Online inspection system for the automatic detection of bolt defects on a freight train［J］. Proceedings of the Institution of Mechanical Engineers Part F: Journal of Rail & Rapid Transit, 2016, 230(4): 271-288.

[13] 邹荣, 李健康, 徐家祥, 等. 复杂场景下铁路货车锁紧板偏转故障检测［J］. 铁道科学与工程学报, 2015, (4): 917-922.

ZOU R, LI J K, XU J X, et al.. Deflection fault detection for locking plate of freight trains under complex scene［J］. Journal of Railway Science and Engineering, 2015, (4): 917-922. (in Chinese)

[14] ZHOU F, ZOU R, QIU Y, et al.. Automated visual inspection of angle cocks during train operation［J］. Proceedings of the Institution of Mechanical Engineers Part F: Journal of Rail & Rapid Transit, 2013, 228(7): 794-806.

[15] LU S, NAN G, ZHANG G. Automated visual inspection of brake shoe wear［C］. Applied Optics and Photonics China, 2015: 96752F.

[16] DAVID G. Distinctive image features from scale-invariant keypoints［J］. International Journal of Computer Vision. 2004, 60(2): 91-110.

[17] 屈玉福, 刘子悦, 江云秋, 等. 自适应变尺度特征点提取方法［J］. 光学精密工程, 2017, 25(1): 188-197.

QU Y F, LIU Z Y, JIANG Y Q, et al.. Self-adaptative variable-metric feature point extraction method［J］. Opt. Precision Eng., 2017, 25(1): 188-197. (in Chinese)

[18] LAZEBNIK S, SCHMID C, PONCE J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories［J］. IEEE Conference Society Conference on Computer Vision & Pattern Recognition, 2006, 2(1/2): 2169-2178.

[19] DONG B. A new scene classification method based on spatial pyramid matching model［J］. Journal of Information & Computational Science. 2015, 12(3): 1073-1080.

[20] 韩玉兰, 赵永平, 王启松, 等. 稀疏表示下的噪声图像超分辨率重构［J］. 光学精密工程, 2017, 25(6): 1619-1626.

HAN Y L, ZHAO Y P, WANG Q S, et al.. Reconstruction of super resolution for noise image under the sparse representation［J］.Opt. Precision Eng., 2017, 25(6) : 1619-1626. (in Chinese)

[21] 王雪虎, 杨健, 艾丹妮, 等. 结合先验稀疏字典和空洞填充的CT图像肝脏分割［J］.光学精密工程, 2015, 23(9): 2687-2697.

WANG X H, YANG J, AI D N, et al.. Liver segmentation in CT image based on priori sparse dictionary and hole filling［J］. Opt. Precision Eng., 2015, 23(9): 2687-2697. (in Chinese)

[22] ZHANG K, ZHANG L, YANG M H. Fast compressive tracking［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 36(10): 2002-2015.

[23] 杨洁, 郑宁, 刘董, 等. 基于遗传算法的SVM带权特征和模型参数优化［J］. 计算机仿真, 2008, 25(9): 115-117.

YANG J, ZHENG N, LIU D, et al.. Optimization of features with weight and model parameters of SVM based on genetic algorithm［J］. Computer Simulation. 2008, 25(9): 115-117. (in Chinese)

[24] 张杨. 基于改进马尔科夫随机场与精确高度函数的列车故障图像层次特征匹配［D］. 武汉: 湖北工业大学, 2017.

ZHANG Y. Hierarchical feature matching of the fault image based improved Markov random field and exact height function in TFDS［D］. Wuhan: Hubei University of Technology, 2017. (in Chinese)

[25] ZHAO Z, FENG G C. Efficient algorithm for sparse coding and dictionary learning with applications to face recognition［J］. Journal of Electronic Imaging, 2015, 24(2): 023009.

[26] SUN G D, ZHANG Y, TANG H B, et al.. Railway equipment detection using exact height function shape descriptor based on fast adaptive Markov random field［J］. Optical Engineering, 2018, 57(5): 1.

孙国栋, 周振, 王俊豪, 张杨, 赵大兴. 基于稀疏编码空间金字塔匹配和GA-SVM的列车故障自动识别[J]. 光学精密工程, 2018, 26(12): 3087. SUN Guo-dong, ZHOU Zhen, WANG Jun-hao, ZHANG Yang, ZHAO Da-xing. Automatic fault recognition algorithm for key parts of train based on sparse coding based spatial pyramid matching and GA-SVM[J]. Optics and Precision Engineering, 2018, 26(12): 3087.

基于稀疏编码空间金字塔匹配和GA-SVM的列车故障自动识别

关于本站 Cookie 的使用提示

全站搜索

基于稀疏编码空间金字塔匹配和GA-SVM的列车故障自动识别

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索