Research on fault detection of belt conveyor roller based on thermal infrared image
-
摘要: 针对目前带式输送机巡检机器人搭载红外采集设备移动受限，存在不能实时进行数据采集、数据处理并上传至监控终端，无法完成远程故障检测，续航能力不足等问题，提出了一种基于热红外图像的带式输送机托辊故障检测方法。带式输送机巡检机器人搭载托辊故障检测器及红外热像仪，红外热像仪将采集的托辊热红外图像序列与温度数据传输给托辊故障检测器进行托辊故障检测，检测结果由托辊故障检测器内置的WH−L101无线传输模块发送给上位机。提出了一种带式输送机托辊故障检测算法：利用YOLOv5s目标检测算法提取托辊热红外图像的感兴趣区域（ROI），采用维纳滤波和自适应中值滤波算法对ROI图像进行滤波，利用自适应直方图均衡化和图像锐化算法对滤波后的ROI图像进行增强，采用基于形态学的Otsu图像分割算法对增强后的ROI图像进行图像分割，得到待检测的托辊图像，利用Harris角点检测算法提取托辊图像特征，获得托辊位置信息，提取相应位置的温度信息，并采用基于相对温差法的托辊故障检测算法判定托辊故障。实验结果表明：① YOLOv5s网络模型提取托辊ROI的目标检测结果平均准确率为99.12%。② 提出的托辊故障检测算法对托辊故障（无故障、轴承锈蚀、托辊卡转、筒体磨穿）检测的平均准确率为97.625%，帧率为16 帧/s。③ 将检测结果通过无线传输模块传送至上位机，可显示故障类型及关键区域温度，并进行报警。
-
关键词:
- 带式输送机 /
- 托辊故障检测 /
- 热红外图像 /
- YOLOv5s网络模型 /
- 带式输送机巡检机器人
Abstract: Currently, the inspection robot for belt conveyors equipped with infrared acquisition devices is limited in movement. There are problems such as inability to collect data, process data, upload data to monitoring terminals in real-time and complete remote fault detection, insufficient endurance and so on. A fault detection method of belt conveyor roller based on thermal infrared images has been proposed. The belt conveyor inspection robot is equipped with a roller fault detector and an infrared thermal imager. The infrared thermal imager transmits the collected roller thermal infrared image sequence and temperature data to the roller fault detector for roller fault detection. The WH-L101 wireless transmission module in the roller fault detector is used to send the detection results to the upper computer. A belt conveyor roller fault detection algorithm is proposed. The algorithm uses the YOLOv5s object detection algorithm to extract the region of interest (ROI) of the roller thermal infrared image. The image of the ROI is filtered using Wiener filtering and adaptive median filtering algorithms. The filtered ROI image is enhanced by using adaptive histogram equalization and image sharpening algorithms. The Otsu image segmentation algorithm based on morphology is used to segment the enhanced ROI image, obtaining the roller image to be detected. The Harris corner detection algorithm is used to extract the features of the roller image, and obtain the position information of the roller. The temperature information of the corresponding position is extracted, and a roller fault detection algorithm based on the relative temperature difference method is used to determine the idler fault. The experimental results show: ① The average accuracy of object detection in the roller ROI extracted by YOLOv5s network model is 99.12%. ② The proposed roller fault detection algorithm has an average accuracy of 97.625% and a frame rate of 16 frames per second for detecting roller faults (no faults, bearing rust, roller jamming, and cylinder wear). ③ The detection results are transmitted to the upper computer through a wireless transmission module, which can display the fault type and key area temperature, and provide an alarm. -
-
![]()
图 1 基于热红外图像带式输送机托辊故障检测系统
Figure 1. Fault detection system of belt conveyor roller based on thermal infrared image
![]()
图 7 基于形态学的Otsu图像分割算法处理结果
Figure 7. Image processing results by morphology-based Otsu image segmentation algorithm
![]()
图 8 基于Harris角点检测算法的特征提取结果
Figure 8. Feature extraction results by Harris corner point detection algorithm
![]()
图 9 带式输送机托辊故障检测器硬件组成
Figure 9. Hardware composition of fault detector for belt conveyor roller
![]()
图 11 带式输送机托辊故障检测实验平台
Figure 11. Experimental platform for belt conveyor idler fault detection
![]()
图 14 4种状态下TA区域最大温度及BA区域平均温度
Figure 14. The maximum temperature in TA region and average temperature in BA region under 4 states
表 1 网络训练和测试平台配置
Table 1 Network training and test platform configuration
设备 参数 CPU Intel（R） Xeon（R） CPU E5−2678 GPU Nvidia Geforce GTX1080Ti 内存 64 GiB DDR4 操作系统 64位Ubuntu 18.04LTS 深度学习框架 Pytorch 
下载: 导出CSV
表 2 托辊故障判定标准
Table 2 Roller fault judgment criteria
指标 轴承锈蚀故障（B1） 托辊卡转故障（C1） 筒体磨穿故障（D1） 相对温差/% 76.7≤$ \alpha $<82.2 82.2≤$ \alpha $<92.3 $ \alpha $≥92.3
下载: 导出CSV
表 3 托辊故障检测正确数量
Table 3 Correct number of roller fault detection
张 托辊 A0 B1 C1 D1 托辊1 99 96 98 98 托辊2 100 97 96 97 总正确量 199 193 194 195
下载: 导出CSV
-
[1] YAN Chen,HE Xue. Model and dynamic simulation of belt conveyor[C]. International Conference on Intelligent Systems Design and Engineering Applications,Changsha,2010:949-951.
[2] QURESHI M,HUSSAIN S. A reusable software component-base development process model[J]. Advances in Engineering Software,2008,39(2):88-94. DOI: 10.1016/j.advengsoft.2007.01.021
[3] 刘莉莉. 基于机器视觉的带式输送机带速检测的研究[D]. 天津:天津工业大学,2019. LIU Lili. Research on belt speed detection of belt conveyor based on machine vision[D]. Tianjin:Tiangong University,2019.
[4] ANDREJIOVA M,GRINCOVA A,MARASOVA D. Measurement and simulation of impact wear damage to industrial conveyor belts[J]. Wear,2016,368/369:400-407. DOI: 10.1016/j.wear.2016.10.010
[5] 贾原生. 智能带式输送机巡检机器人在煤矿的应用[J]. 矿业装备,2022(4):238-239. JIA Yuansheng. Application of intelligent belt conveyor inspection robot in coal mine[J]. Mining Equipment,2022(4):238-239.
[6] 吕茁. 火电厂输煤系统设备运行故障分析[J]. 中国设备工程,2021(12):68-69. LYU Zhuo. Fault analysis of equipment operation of coal handling system in thermal power plant[J]. China Plant Engineering,2021(12):68-69.
[7] 韩建斌. 煤矿带式输送机常见故障与改善方法[J]. 机械管理开发,2020,35(8):289-291. HAN Jianbin. Common fault and improvement method of coal mine belt conveyor[J]. Mechanical Management and Development,2020,35(8):289-291.
[8] 张高祥. 基于声音信号的带式输送机托辊故障检测系统设计与研究[D]. 徐州:中国矿业大学,2022. ZHANG Gaoxiang. Design and research of belt conveyor idler fault detection system based on acoustic signal[D]. Xuzhou:China University of Mining and Technology,2022.
[9] 吴文臻,程继明,李标. 矿用带式输送机托辊音频故障诊断方法[J]. 工矿自动化,2022,48(9):25-32. WU Wenzhen,CHENG Jiming,LI Biao. Audio fault diagnosis method of mine belt conveyor roller[J]. Journal of Mine Automation,2022,48(9):25-32.
[10] RAVIKUMAR S,KANAGASABAPATHY H,MURALIDHARAN V. Fault diagnosis of self-aligning troughing rollers in belt conveyor system using k-star algorithm[J]. Measurement,2019,133:341-349. DOI: 10.1016/j.measurement.2018.10.001
[11] 朱振. 带式输送机托辊运行状态在线巡检机器人关键技术研究[D]. 阜新:辽宁工程技术大学,2020. ZHU Zhen. Research on the key technology of on-line inspection robot for the running state of belt conveyor roller[D]. Fuxin:Liaoning Technical University,2021.
[12] 苏耀瑞. 远程带式输送机托辊非接触式故障识别方法研究[D]. 银川:宁夏大学,2021. SU Yaorui. Research on non-contact fault iIdentification method of remote belt conveyor roller[D]. Yinchuan:Ningxia University,2021.
[13] 马宏伟,杨文娟,张旭辉. 带式输送机托辊红外图像分割与定位算法[J]. 西安科技大学学报,2017,37(6):892-898. MA Hongwei,YANG Wenjuan,ZHANG Xuhui. Segmentation and location algorithm for infrared image of roller on conveyor belt[J]. Journal of Xi'an University of Science and Technology,2017,37(6):892-898.
[14] 金学智. 基于红外图像的带式输送机故障预警方法研究[D]. 银川:宁夏大学,2021. JIN Xuezhi. Research on failure prognostic method of belt conveyor based on infrared image[D]. Yinchuan:Ningxia University,2021.
[15] DABEK P,SZREK J,ZIMROZ R,et al. An automatic procedure for overheated idler detection in belt conveyors using fusion of infrared and RGB images acquired during UGV robot inspection[J]. Energies,2022,15(2):601. DOI: 10.3390/en15020601
[16] 陈志琳. 基于面部特征的疲劳驾驶检测系统设计与实现[D]. 西安:西安工业大学,2022. CHEN Zhilin. Design and implementation of fatigue driving detection system based on facial features[D]. Xi'an:Xi'an Technological University,2022.
[17] 薛利敏. 基于粗糙集的声呐图像分割[D]. 呼和浩特:内蒙古大学,2019. XUE Limin. Sonar image segmentation based on rough set[D]. Hohhot:Inner Mongolia University,2019.
[18] 金飞,张彬,司璇,等. 基于维纳滤波的图像复原[J]. 中国传媒大学学报(自然科学版),2011,18(4):19-23. JIN Fei,ZHANG Bin,SI Xuan,et al. Image restoration based on Wiener Filtering[J]. Journal of Communication University of China(Science and Technology),2011,18(4):19-23.
[19] 张秉京. 基于机器视觉的铝丝楔焊机定位方法研究[D]. 长春:吉林大学,2018. ZHANG Bingjing. Research on positioning method of aluminum wire wedge bonder based on machine vision[D]. Changchun:Jilin University,2018.
[20] SABRINE C,ABIR S. Median filter for denoising MRI[J]. Revue d'Intelligence Artificielle,2022,36(3):483-488. DOI: 10.18280/ria.360317
[21] 张梦翔. 基于云服务的嵌入式人脸识别系统设计与实现[D]. 苏州:苏州大学,2017. ZHANG Mengxiang. Design and implementation of embedded face recognition system based on cloud service[D]. Suzhou:Soochow University,2017.
[22] 赵妍双,戴振东,王浩. 二维Otsu算法在壁虎脑切片图像处理中的应用[J]. 科技通报,2011,27(5):703-706. ZHAO Yanshuang,DAI Zhendong,WANG Hao. The application of 2D Otsu algorithm in the image processing of gecko's brain slices[J]. Bulletin of Science and Technology,2011,27(5):703-706.
[23] 姚依妮,王玮. Harris角点检测算法的应用研究[J]. 智能计算机与应用,2022,12(8):148-151. YAO Yini,WANG Wei. Application research on Harris corner detection algorithms[J]. Intelligent Computer and Applications,2022,12(8):148-151.
[24] 何铮. 基于边缘计算的企业物联网网关[J]. 电脑编程技巧与维护,2019(9):149-151,159. DOI: 10.3969/j.issn.1006-4052.2019.09.053 HE Zheng. Enterprise IoT gateway based on edge computing[J]. Computer Programming Skills & Maintenance,2019(9):149-151,159. DOI: 10.3969/j.issn.1006-4052.2019.09.053
[25] LIU Yi,MIAO Changyun,LI Xianguo,et al. Research on the fault analysis method of belt conveyor idlers based on sound and thermal infrared image features[J]. Measurement,2021,186. DOI: 10.1016/j.measurement.2021.110177.
-
期刊类型引用(9)
1. LI Jiamin，HAN Bo，JIANG Mingshun. Anomaly monitoring and early warning of electric moped charging device with infrared image. Optoelectronics Letters. 2025(03): 136-141 . 
必应学术
2. 陈辛镔，钟庆杨，廖辉，苏金辉. 管状带式输送机巡检机器人故障检测技术. 起重运输机械. 2025(01): 85-90 . 百度学术
3. 吴力兵. 煤矿井下带式输送机巡检系统研究. 能源与节能. 2025(03): 157-159 . 百度学术
4. 游卿华，伍鹏，马波. 带式输送机托辊轴承声信号增强方法. 工矿自动化. 2025(03): 70-77 . 本站查看
5. 孟铁柱. 基于物联网的矿用带式输送机托辊状态在线监测方法. 中国机械. 2024(06): 98-101 . 百度学术
6. 闫培培. 矿用皮带输送机智能巡检机器人系统设计. 自动化应用. 2024(09): 131-133+137 . 百度学术
7. 孙树根，王鹏. 矿用带式输送机托辊轴承故障诊断与监测技术分析. 能源与节能. 2024(06): 178-180+184 . 百度学术
8. 韩继玲，刘伟，奚辰，肖雨芯，朱仁杰，杨龙兴，张陈. 基于机器视觉的方形电池缺陷检测系统设计. 物联网技术. 2024(11): 9-11 . 百度学术
9. 周坪，马国庆，周公博，马天兵，李远博. 智能化带式输送机健康监测技术研究综述. 仪器仪表学报. 2023(12): 1-21 . 百度学术
其他类型引用(4)
计量
- 文章访问数: 1072
- HTML全文浏览量: 77
- PDF下载量: 89
- 被引次数: 13
