Infrared Detection and Identification of Rotating Machinery Based on Faster R-CNN
-
摘要: 旋转机械是机械设备的核心部件，一旦发生故障会造成不可估量的损失，因此旋转机械的实时监测诊断显得尤为必要。无人值守的红外智能监测诊断将是故障诊断新的发展方向，要实现红外智能监测诊断首先要准确识别旋转机械部件。本文利用红外热像仪监测旋转机械的运行状态，获得了电动机、联轴器、轴承座、齿轮箱等设备的红外热图；采用Faster R-CNN算法对测量得到的旋转机械红外图像进行了学习训练和目标识别，结果表明该算法能够准确识别旋转机械部件；研究了单角度和旋转角度红外监测的识别效果，发现在相同角度下使用红外灰度图像进行训练的检测效果比使用红外伪彩色图像训练的检测效果更佳；对比了4种预训练网络对于红外目标识别的影响，采用Resnet50预训练网络的平均检测精度为0.9345，识别精度更高。
-
关键词:
- 旋转机械 /
- 红外检测 /
- 目标识别 /
- Faster R-CNN
Abstract: Rotating machinery is the core component of mechanical equipment and can thus cause a significant loss if it breaks down. Therefore, real-time monitoring and diagnosis of the rotating machinery is critical. Automated infrared intelligent monitoring and diagnosis is a recent development in fault diagnosis. To realize infrared intelligent monitoring and diagnosis, it is necessary to accurately identify rotating machinery components. In this study, an infrared thermal camera was used to monitor the running state of the rotating machinery and infrared images of the motor, coupling, bearing seat, gearbox, and other equipment. The Faster R-CNN algorithm was used to train the rotating-machinery infrared images and to identify the targets. The results showed that the algorithm can accurately identify rotating machinery components. The recognition effect of single-angle and rotating-angle infrared monitoring was studied. It was found that the detection effect of infrared gray images fortraining at the same angle is better than that of infrared pseudo-color images. The influence of four types of pre-training networks on infrared target recognition was compared. The average detection accuracy of the resnet50 pre-training network was 0.9345, and the recognition accuracy was higher.-
Key words:
- rotating machinery /
- infrared detection /
- object identification /
- Faster R-CNN
-
图 4 四种不同数量数据集训练的探测器对单张图片检测效果
Figure 4. Detection effect of detectors trained by four different datasets on one image
图 5 不同图像类型下训练的探测器对单张图片检测效果
Figure 5. Detection effect of detector trained under different image types on single image
图 6 不同预训练网络下的单张图片检测效果
Figure 6. Effect of single image detection in different pre-training networks
图 7 Alexnet预训练网络下6个目标的PR曲线
Figure 7. PR curves of six targets under alexnet pre-training network
图 8 VGG19预训练网络下6个目标的PR曲线
Figure 8. PR curves of six targets under VGG19 pre-training network
图 9 Googlenet预训练网络下6个目标的PR曲线
Figure 9. PR curves of six targets under Googlenet pre-training network
图 10 Resnet50预训练网络下6个目标的PR曲线
Figure 10. PR curves of six targets under Resnet50 pre-training network
表 1 四种不同数量数据集下网络训练检测情况
Table 1. Network training and detection situation under fourdifferent datasets
Number of datasets Training time /s mAP IoU 75 303 1 0.8969 150 514 1 0.8836 300 990 1 0.9108 600 1846 1 0.8487 
下载: 导出CSV
表 2 不同图像类型下网络训练检测情况
Table 2. Network training and detection situation under differentimage types
Image types Training time /s mAP IoU Gray image 990 1 0.9108 Pseudo color image 1067 1 0.8932
下载: 导出CSV
-
[1] 孙颖.旋转机械故障的研究及常见故障[J].知识经济, 2010(16): 117. http://www.cnki.com.cn/Article/CJFDTotal-ZZJJ201016099.htmSUN Ying. Research on common faults and faults of rotating machinery[J]. Knowledge Economy, 2010(16): 117. http://www.cnki.com.cn/Article/CJFDTotal-ZZJJ201016099.htm [2] 沈庆根, 郑水英.设备故障诊断[M].北京:化学工业出版社, 2005.SHEN Qinggen, ZHENG Yongying. Equipment fault diagnosis[M]. Beijing: Chemical Industry Press, 2005. [3] 程玉兰.红外诊断技术与应用(一)[J].设备管理与维修, 2003(9): 41-43. http://qikan.cqvip.com/Qikan/Article/Detail?id=8292337CHENG Yulan. Infrared diagnosis technology and Application(1)[J]. Plant Maintenance Engineering, 2003(9): 41-43. http://qikan.cqvip.com/Qikan/Article/Detail?id=8292337 [4] Bagavathiappan S, Lahiri B B, Saravanan T, et al. Infrared thermography for condition monitoring – A review[J]. Infrared Physics & Technology, 2013, 60(5): 35-55. [5] Tran Van Tung, YANG Bo-Suk, GU Fengshou, et al. Thermal image enhancement using bi-dimensional empirical mode decomposition in combination with relevance vector machine for rotating machinery fault diagnosis[C]//Mechanical Systems & Signal Processing, 2013, 38(2): 601-614. [6] 孙富成, 宋文渊, 滕红智, 等.基于红外热图像的变速箱轴承状态监测与故障诊断[J].电光与控制, 2017, 24(7): 113-117. http://d.wanfangdata.com.cn/periodical/dgykz201707025SUN Fucheng, SONG Wenyuan, TENG Hongzhi, et al. Infrared Thermal Image Based Condition Monitoring and Fault Diagnosis of Gearbox Bearings[J]. Electronics Optics & Control, 2017, 24(7): 113-117. http://d.wanfangdata.com.cn/periodical/dgykz201707025 [7] Krizhevsky A, Sutskever I, Hinton G. ImageNet Classification with Deep Convolutional Neural Networks[J]. Communications of the ACM, 2017, 60(6): 84-90. doi: 10.1145/3065386 [8] Russakovsky O, Deng J, Su H, et al. Image Net Large Scale Visual Recognition Challenge[J]. International Journal of Computer Vision, 2015, 115(3): 211-252. http://dl.acm.org/citation.cfm?id=2846559 [9] Girshick R, Donahue J, Darrell T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587. [10] Girshick R. Fast R-CNN[C]//IEEE International Conference on Computer Vision, 2015: 1440-1448. [11] REN S, HE K, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 39(6): 1137-1149. [12] Redmon J, Divvala S, Girshick R, et al. You Only Look Once: Unified, Real-Time Object Detection[C]//IEEE Conference on Computer Vision & Pattern Recognition, 2016: 779-788. [13] LIU W, Anguelov D, Erhan D, et al. SSD: Single Shot MultiBox Detector[C]// European Conference on Computer Vision, 2016: 21-37. [14] Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger[C]//IEEE Conference on Computer Vision & Pattern Recognition, 2017: 6517-6525. [15] HE K, Gkioxari G, Dollar P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017(99): 1. doi: 10.1109/TPAMI.2018.2844175 [16] Redmon J, Farhadi A. YOLOv3: An Incremental Improvement[J/OL]. 2018, https: //arxiv.org/abs/1804.02767. [17] LIU L, OUYANG W, WANG X, et al. Deep Learning for Generic Object Detection: A Survey[J]. International Journal of Computer Vision, 2020, 128(2): 261-318. [18] 王林, 张鹤鹤. Faster R-CNN模型在车辆检测中的应用[J].计算机应用, 2018, 38(3): 666-670. http://www.cnki.com.cn/Article/CJFDTotal-JSJY201803012.htmWANG Lin, ZHANG Hehe. Application of Faster R-CNN model in vehicle detection[J]. Journal of Computer Applications, 2018, 38(3): 666-670. http://www.cnki.com.cn/Article/CJFDTotal-JSJY201803012.htm [19] 桑军, 郭沛, 项志立, 等. Faster-RCNN的车型识别分析[J].重庆大学学报, 2017, 40(7): 32-36. http://www.cnki.com.cn/Article/CJFDTotal-FIVE201707005.htmSANG Jun, GUO Pei, XIANG Zhili, et al. Vehicle detection based on faster-RCNN[J]. Journal of Chongqing University, 2017, 40(7): 32-36. http://www.cnki.com.cn/Article/CJFDTotal-FIVE201707005.htm [20] 张汇, 杜煜, 宁淑荣, 等.基于Faster RCNN的行人检测方法[J].传感器与微系统, 2019, 38(2): 147-149, 153. http://www.cnki.com.cn/Article/CJFDTotal-CGQJ201902042.htmZHANG Hui, DU Yu, NING Shurong, et al. Pedestrian detection method based on Faster RCNN[J]. Transducer and Microsystem Technologies, 2019, 38(2): 147-149, 153. http://www.cnki.com.cn/Article/CJFDTotal-CGQJ201902042.htm [21] 史凯静, 鲍泓, 徐冰心, 等.基于Faster RCNN的智能车道路前方车辆检测方法[J].计算机工程, 2018, 44(7): 36-41. http://d.wanfangdata.com.cn/periodical/jsjgc201807007SHI Kaijing, BAO Hong, XU Bingxin, et al. Forward Vehicle Detection Method of Intelligent Vehicle in Road Based on Faster RCNN[J]. Computer Engineering, 2018, 44(7): 36-41. http://d.wanfangdata.com.cn/periodical/jsjgc201807007 [22] 朱虹, 翟超, 吕志, 等.基于Faster-RCNN的智能家居行人检测系统设计与实现[J].工业控制计算机, 2018, 31(4): 68-70. http://www.cnki.com.cn/Article/CJFDTotal-GYKJ201804029.htmZHU Hong, ZHAI Chao, LU Zhi, et al. Smart Home Pedestrian Detection System Based on Faster-RCNN[J]. Industrial Control Computer, 2018, 31(4): 68-70. http://www.cnki.com.cn/Article/CJFDTotal-GYKJ201804029.htm [23] Szegedy C, Liu W, Jia Y, et al. Going Deeper with Convolutions[C]// IEEE Computer Vision and Pattern Recognition, 2015: 1-9. [24] Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition[J/OL]. 2014, https://arxiv.org/abs/1409. 1556. [25] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]// IEEE Computer Vision and Pattern Recognition, 2016: 770-778. -
点击查看大图
计量
- 文章访问数: 238
- HTML全文浏览量: 100
- PDF下载量: 32
- 被引次数: 0
