基于级联卷积网络的紧固件异常检测
|
摘要
紧固件广泛应用于日常生活和工业生产制造中,其异常状态在许多场景中会导致严重的安全隐患。目前紧固件异常检测仍依赖人工排查,很难通过常规无损检测技术自动识别。针对该问题,提出了一种基于级联卷积网络的自动检测方案,能够快速的检测固定场景下的紧固件异常情况。首先采集紧固件图像,使用目标检测网络确定所有紧固件区域;接着使用所提出的紧固件关键点回归网络预测关键点特征信息;最后通过对比同一紧固件不同时刻的关键点特征信息实现紧固件异常检测。在自制的重庆市轻轨轨道梁指型板紧固件数据集进行了测试,实验结果显示该方法在准确率达到96. 5%时,对于异常紧固件的召回率高达99%,结果表明该方法具有可行性,在类似场景中具有实际应用价值。
Fasteners are widely used in daily life and industrial manufacturing. In many scenarios,the its abnormal state could cause security risks. For now,it's hard to automatically detect the abnormal state of fastener by non-destructive testing,and still relies on manual checking. In this paper,a solution based on cascade convolutional neural network is presented to quickly detect abnormal state of fasteners in fixed scenes. The workflow is first to collect images and use objective-detection network to detect the fastener regions. Then,the proposed key-point regression network is used in prediction of key points on fasteners and getting the feature of key point. Finally,the abnormal detection of fasteners is conducted by comparing the key point feature information of the same fastener through two measurements at different times. The proposed approachisevaluated on dataset of fasteners on finger plate in Chongqing railway transportation,experimental results reach performance with accuracy of 96. 5% and recall of 99% which shows the great value of practical application of the proposed approach.
Fasteners are widely used in daily life and industrial manufacturing. In many scenarios,the its abnormal state could cause security risks. For now,it's hard to automatically detect the abnormal state of fastener by non-destructive testing,and still relies on manual checking. In this paper,a solution based on cascade convolutional neural network is presented to quickly detect abnormal state of fasteners in fixed scenes. The workflow is first to collect images and use objective-detection network to detect the fastener regions. Then,the proposed key-point regression network is used in prediction of key points on fasteners and getting the feature of key point. Finally,the abnormal detection of fasteners is conducted by comparing the key point feature information of the same fastener through two measurements at different times. The proposed approachisevaluated on dataset of fasteners on finger plate in Chongqing railway transportation,experimental results reach performance with accuracy of 96. 5% and recall of 99% which shows the great value of practical application of the proposed approach.
引文
[1]屈文忠,张梦阳,周俊宇,等.螺栓松动损伤的亚谐波共振识别方法[J].振动.测试与诊断,2017,37(02):279-283,403.QU W Z,ZHANG M Y,ZHU J Y,et al.Subharmonic resonance identification method for bolt loosening damage[J].Vibration,Testing and Diagnosis,2017,37(2):279-283,403.
[2]郭世旭,刘胜,陈秀丽,等.管道微小泄漏内检测近场声信号特性研究[J].电子测量与仪器学报,2016,30(6):834-844.GUO S X,LIU S,CHEN X L,et al.Study on the characteristics of near-field acoustic signals for pipeline micro-leakage detection[J].Journal of Electronic Measurement and Instruments,2016,30(6):834-844.
[3]缑百勇,陆秋海,王波,等.利用固有频率异常值分析法检测螺栓拧紧力[J].振动与冲击,2015,34(23):77-82.HOU B Y,LU Q H,WANG B,et al.Detection of bolt tightening force by natural frequency abnormal value analysis method[J].Vibration and Impact,2015,34(23):77-82.
[4]陈卓,郝永刚,易水洪,等.塔机螺栓松动检测新方法研究[J].中国特种设备安全,2015,31(9):50-53.CHEN ZH,HE Y G,YI SH H,et al.Research on new testing method for bolt looseness of tower crane[J].Safety of Special Equipment in China,2015,31(9):50-53.
[5]修成竹,任亮,李宏男.自感式拉力传感器理论模型与实验研究[J].仪器仪表学报,2016,37(12):2797-2804.XIU CH Z,REN L,LI H N.Theoretical model and experimental study of self-inductance tension sensor[J].Journal of Instruments and Instruments,2016,37(12):2797-2804.
[6]赵志永,王闳毅,朱礼尧,等.基于Zig Bee的地磁车辆检测系统设计[J].电子测量技术,2016,39(7):110-115.ZHAO ZH G,WANG H Y,ZHU L Y,et al.Design of geomagnetic vehicle detection system based on Zig Bee[J].Electronic Measurement Technology,2016,39(7):110-115.
[7]吴键,傅少武,金伟.低功耗多点螺栓松动监测系统研究[J].电子设计工程,2015,23(9):77-80.WU J,FU SH W,JIN W.Research on low power multipoint bolt loosening monitoring system[J].Electronic Design Engineering,2015,23(9):77-80.
[8]向志海,黄俊涛.螺栓松紧程度的受控敲击检测方法[J].实验力学,2012,27(5):545-551.XIANG ZH H,HUANG J T.Controlled tapping test method for bolt tightness[J].Experimental Mechanics,2012,27(5):545-551.
[9]龙林,王宁,陶俊林,等.振动环境中螺栓连接结构状态声发射试验研究[J].噪声与振动控制,2010,30(4):166-170.LONG L,WANG N,TAO J L,et al.Acoustic emission test of bolted connection structure in vibration environment[J].Noise and Vibration Control,2010,30(4):166-170.
[10]CHA Y J,YOU K,CHOI W.Vision-based detection of loosened bolts using the Hough transform and support vector machines[J].Automation in Construction,2016(71):181-188.
[11]蔡娟,李东新.基于优化k均值建模的运动目标检测算法[J].国外电子测量技术,2016,35(12):20-23.CAI J,LI D X.Moving target detection algorithm based on optimized K-means modeling[J].Foreign Electronic Measurement Technology,2016,35(12):20-23.
[12]KRIZHEVSKY A,SUTSKEVER I,HINTON G.Imagenet classification with deep convolutional neural networks[C].NIPS,Curran Associates Inc,2012.
[13]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C].2014 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE Computer Society,2014.
[14]GIRSHICK R.Fast R-CNN[C].IEEE International Conference on Computer Vision,2015.
[15]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[C].International Conference on Neural Information Processing Systems,2015.
[16]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal Loss for dense object detection[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2017(99):2999-3007.
[17]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C].Computer Vision and Pattern Recognition,IEEE,2016:779-788.
[18]REDMON J,FARHADI A.YOLO9000:Better,faster,stronger[C].IEEE Conference on Computer Vision and Pattern Recognition,IEEE,2017:6517-6525.
[19]REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[R].2018.
[20]IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shif[C].International Conference on International Conference on Machine Learning,JMLR.org,2015.
[21]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[J].2015.
[22]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[J].Computer Science,2016,DOI:10.1007/978-3-319-46448-0_2.
[23]LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:Common Objects in Context[J].Computer Science,2014,DOI:10.1007/978-3-319-10602-1_48.
[2]郭世旭,刘胜,陈秀丽,等.管道微小泄漏内检测近场声信号特性研究[J].电子测量与仪器学报,2016,30(6):834-844.GUO S X,LIU S,CHEN X L,et al.Study on the characteristics of near-field acoustic signals for pipeline micro-leakage detection[J].Journal of Electronic Measurement and Instruments,2016,30(6):834-844.
[3]缑百勇,陆秋海,王波,等.利用固有频率异常值分析法检测螺栓拧紧力[J].振动与冲击,2015,34(23):77-82.HOU B Y,LU Q H,WANG B,et al.Detection of bolt tightening force by natural frequency abnormal value analysis method[J].Vibration and Impact,2015,34(23):77-82.
[4]陈卓,郝永刚,易水洪,等.塔机螺栓松动检测新方法研究[J].中国特种设备安全,2015,31(9):50-53.CHEN ZH,HE Y G,YI SH H,et al.Research on new testing method for bolt looseness of tower crane[J].Safety of Special Equipment in China,2015,31(9):50-53.
[5]修成竹,任亮,李宏男.自感式拉力传感器理论模型与实验研究[J].仪器仪表学报,2016,37(12):2797-2804.XIU CH Z,REN L,LI H N.Theoretical model and experimental study of self-inductance tension sensor[J].Journal of Instruments and Instruments,2016,37(12):2797-2804.
[6]赵志永,王闳毅,朱礼尧,等.基于Zig Bee的地磁车辆检测系统设计[J].电子测量技术,2016,39(7):110-115.ZHAO ZH G,WANG H Y,ZHU L Y,et al.Design of geomagnetic vehicle detection system based on Zig Bee[J].Electronic Measurement Technology,2016,39(7):110-115.
[7]吴键,傅少武,金伟.低功耗多点螺栓松动监测系统研究[J].电子设计工程,2015,23(9):77-80.WU J,FU SH W,JIN W.Research on low power multipoint bolt loosening monitoring system[J].Electronic Design Engineering,2015,23(9):77-80.
[8]向志海,黄俊涛.螺栓松紧程度的受控敲击检测方法[J].实验力学,2012,27(5):545-551.XIANG ZH H,HUANG J T.Controlled tapping test method for bolt tightness[J].Experimental Mechanics,2012,27(5):545-551.
[9]龙林,王宁,陶俊林,等.振动环境中螺栓连接结构状态声发射试验研究[J].噪声与振动控制,2010,30(4):166-170.LONG L,WANG N,TAO J L,et al.Acoustic emission test of bolted connection structure in vibration environment[J].Noise and Vibration Control,2010,30(4):166-170.
[10]CHA Y J,YOU K,CHOI W.Vision-based detection of loosened bolts using the Hough transform and support vector machines[J].Automation in Construction,2016(71):181-188.
[11]蔡娟,李东新.基于优化k均值建模的运动目标检测算法[J].国外电子测量技术,2016,35(12):20-23.CAI J,LI D X.Moving target detection algorithm based on optimized K-means modeling[J].Foreign Electronic Measurement Technology,2016,35(12):20-23.
[12]KRIZHEVSKY A,SUTSKEVER I,HINTON G.Imagenet classification with deep convolutional neural networks[C].NIPS,Curran Associates Inc,2012.
[13]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C].2014 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE Computer Society,2014.
[14]GIRSHICK R.Fast R-CNN[C].IEEE International Conference on Computer Vision,2015.
[15]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[C].International Conference on Neural Information Processing Systems,2015.
[16]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal Loss for dense object detection[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2017(99):2999-3007.
[17]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection[C].Computer Vision and Pattern Recognition,IEEE,2016:779-788.
[18]REDMON J,FARHADI A.YOLO9000:Better,faster,stronger[C].IEEE Conference on Computer Vision and Pattern Recognition,IEEE,2017:6517-6525.
[19]REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[R].2018.
[20]IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shif[C].International Conference on International Conference on Machine Learning,JMLR.org,2015.
[21]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[J].2015.
[22]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot multibox detector[J].Computer Science,2016,DOI:10.1007/978-3-319-46448-0_2.
[23]LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:Common Objects in Context[J].Computer Science,2014,DOI:10.1007/978-3-319-10602-1_48.