基于Faster R-CNN的设备故障检测与识别
|
摘要
现阶段环境检测设备故障频发,需要自动判断该设备是否发生故障,虽然在设备机房中该设备没有触发设备报警装备,但是监测数据仍然超出了正常工作范围,导致检测数据出错.为了解决这一类设备故障问题,提出了基于Faster R-CNN的故障检测与识别的方法,通过对人工标注的图片数据进行卷积特征训练,得到了用于该场景下开关、指示灯、数字仪器三种设备的检测识别模型.实验表明, Faster R-CNN算法对不同拍摄角度、有遮挡物、不同光照条件下的这三种设备的故障检测都能得到理想的效果,也能基本达到实时监测的速率.
At the present stage, the environmental testing equipment failures occur frequently and it is necessary to automatically judge whether the equipment fails. Although the equipment does not trigger alarm equipment in the equipment room, the monitoring data is beyond the normal working range. In order to solve this kind of equipment fault problem, a method of target detection and recognition based on Faster R-CNN is proposed. By training the convolutional feature map for the manually marked image data, the detection and recognition model of switch, indicator and digital instrument in this scenario is obtained. Experiments show that the Faster R-CNN algorithm can detect the faults of the three kinds of equipment with different shooting angles, occlusion, and different illumination conditions, and can achieve ideal results and basically achieve the efficiency of real-time monitoring.
At the present stage, the environmental testing equipment failures occur frequently and it is necessary to automatically judge whether the equipment fails. Although the equipment does not trigger alarm equipment in the equipment room, the monitoring data is beyond the normal working range. In order to solve this kind of equipment fault problem, a method of target detection and recognition based on Faster R-CNN is proposed. By training the convolutional feature map for the manually marked image data, the detection and recognition model of switch, indicator and digital instrument in this scenario is obtained. Experiments show that the Faster R-CNN algorithm can detect the faults of the three kinds of equipment with different shooting angles, occlusion, and different illumination conditions, and can achieve ideal results and basically achieve the efficiency of real-time monitoring.
引文
1康晓风,于勇,张迪,等.新形势下环境监测科技发展现状与展望.中国环境监测,2015,31(6):5-8.[doi:10.3969/j.issn.1002-6002.2015.06.002]
2卢竹茂,王天正,俞华,等.基于红外图像分析的电力设备热故障检测技术研究.现代电子技术,2017,40(11):123-126.
3冯俊.基于图像分析的电力设备故障检测技术研究.现代电子技术,2015,38(24):7-11.
4 Ren SQ,He KM,Girshick R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks.Proceedings of the 28th International Conference on NeuralInformation Processing Systems.Montreal,Canada.2015.91-99.
5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.计算机工程,2018,44(7):36-41.
6戴陈卡,李毅.基于Faster RCNN以及多部件结合的机场场面静态飞机检测.计算机应用,2017,37(S2):85-88.
7胡正委,朱明.基于改进Faster RCNN与Grabcut的商品图像检测.计算机系统应用,2018,27(11):128-135.[doi:10.15888/j.cnki.csa.006631]
8 Girshick R.Fast R-CNN.Proceedings of 2015 IEEEInternational Conference on Computer Vision.Santiago,Chile.2015.1440-1448.
2卢竹茂,王天正,俞华,等.基于红外图像分析的电力设备热故障检测技术研究.现代电子技术,2017,40(11):123-126.
3冯俊.基于图像分析的电力设备故障检测技术研究.现代电子技术,2015,38(24):7-11.
4 Ren SQ,He KM,Girshick R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks.Proceedings of the 28th International Conference on NeuralInformation Processing Systems.Montreal,Canada.2015.91-99.
5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.计算机工程,2018,44(7):36-41.
6戴陈卡,李毅.基于Faster RCNN以及多部件结合的机场场面静态飞机检测.计算机应用,2017,37(S2):85-88.
7胡正委,朱明.基于改进Faster RCNN与Grabcut的商品图像检测.计算机系统应用,2018,27(11):128-135.[doi:10.15888/j.cnki.csa.006631]
8 Girshick R.Fast R-CNN.Proceedings of 2015 IEEEInternational Conference on Computer Vision.Santiago,Chile.2015.1440-1448.