Please wait a minute...
工程设计学报  2026, Vol. 33 Issue (3): 398-407    DOI: 10.3785/j.issn.1006-754X.2026.06.126
可靠性与保质设计     
基于锚索状态图像识别的退锚机器人作业可行性判别
刘治翔1,2,庄源2(),谢春雪3
1.辽宁工程技术大学 矿产资源开发利用技术及装备研究院,辽宁 阜新 123000
2.辽宁工程技术大学 机械工程学院,辽宁 阜新 123000
3.辽宁工程技术大学 力学与工程学院,辽宁 阜新 123000
Operation feasibility discrimination of anchor withdrawing robot based on anchor cable state image recognition
Zhixiang LIU1,2,Yuan ZHUANG2(),Chunxue XIE3
1.Research Institute of Mineral Resources Development and Utilization Technology and Equipment, Liaoning University of Engineering and Technology, Fuxin 123000, China
2.School of Mechanical Engineering, Liaoning University of Engineering and Technology, Fuxin 123000, China
3.School of Mechanics and Engineering, Liaoning University of Engineering and Technology, Fuxin 123000, China
 全文: PDF(5893 KB)   HTML
摘要:

考虑到锚索散开状态和弯曲状态会影响退锚器具对锚索的破切作业,提出了基于图像识别的锚索状态识别方法。首先使用YOLOv8目标检测算法对锚索散开状态进行识别,然后使用PSPnet语义分割和图像处理方法对锚索弯曲状态进行识别。基于YOLOv8算法的锚索散开状态识别方法对完好锚索、轻微散开锚索和完全散开锚索的检测精度均达到了0.900以上,说明检测模型具有较好的锚索散开状态识别能力。基于PSPnet语义分割和图像处理的锚索弯曲状态识别方法可实现对完好锚索、整体弯曲锚索和部分弯曲锚索弯曲角度的识别,为退锚设备的选择提供了依据。通过对锚索散开状态与弯曲状态的识别,可实现退锚机器人作业可行性判别,从而为退锚机器人的研制提供理论支撑。

关键词: 退锚作业图像识别锚索角度识别    
Abstract:

Considering that the scattered and bending states of anchor cables will affect the cutting operation of anchor withdrawing equipment on anchor cables, an anchor cable state recognition method based on image recognition was proposed. First, the YOLOv8 object detection algorithm was used to recognize the scattered states of the anchor cables. Then, the PSPnet semantic segmentation and image processing methods were employed to recognize the bending states of the anchor cables. The anchor cable scattered state recognition method based on YOLOv8 algorithm achieved a detection accuracy of over 0.900 for normal anchor cable, slightly scattered anchor cable and completely scattered anchor cable, indicating that the detection model had a good ability to recognize the scattered states of anchor cables. The anchor cable bending state recognition method based on PSPnet semantic segmentation and image processing could recognize the bending angles of normal anchor cable, overall bending anchor cable and partially bending anchor cable, providing a basis for the selection of anchor withdrawing equipment. By recognizing the scattered and bending states of anchor cables, the operation feasibility discrimination can be achieved, thereby providing theoretical support for the development of the anchor withdrawing robot.

Key words: anchor withdrawing operation    image recognition    anchor cable    angle recognition
收稿日期: 2026-01-20 出版日期: 2026-06-27
CLC:  TP 028.8  
基金资助: 国家自然科学基金资助项目(51904142)
通讯作者: 庄源     E-mail: 1653510342@qq.com
作者简介: 刘治翔(1988—),男,副教授,博士,从事机器人系统设计、矿山智能装备研发等研究,E-mail: lzxcndl @yeah.net, https://orcid.org/0000-0001-6785-3110
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
刘治翔
庄源
谢春雪

引用本文:

刘治翔,庄源,谢春雪. 基于锚索状态图像识别的退锚机器人作业可行性判别[J]. 工程设计学报, 2026, 33(3): 398-407.

Zhixiang LIU,Yuan ZHUANG,Chunxue XIE. Operation feasibility discrimination of anchor withdrawing robot based on anchor cable state image recognition[J]. Chinese Journal of Engineering Design, 2026, 33(3): 398-407.

链接本文:

https://www.zjujournals.com/gcsjxb/CN/10.3785/j.issn.1006-754X.2026.06.126        https://www.zjujournals.com/gcsjxb/CN/Y2026/V33/I3/398

图1  千斤顶式退锚器
图2  水力切割式退锚器
图3  破切式退锚器
图4  液压退锚车
图5  锚索状态
图6  退锚机器人设计方案
图7  锚索状态识别方案
图8  YOLOv8 网络框架
参数数值参数数值
lr00.01hsv_h0.015
lrf0.01hsv_s0.7
最终学习率0.000 1hsv_v0.4
余弦学习率FalsedeterministicTrue
优化器ADAMtranslate0.1
标签平滑参数0scale0.5
正则化0epochs300
Weight_decay5×10-4imgsz640
warmup_epochs3flipud0
warmup_momentum0.8fliplr0.5
warmup_bias_lr0.1halfTrue
box0.05conf0.5
cls0.5line_thickness8
cls_pw1iou0.7
obj1max_det300
obj_pw1anchor_t4
iou_t0.2splitval
表1  YOLOv8目标检测模型参数设置
图9  YOLOv8目标检测模型训练过程
图10  锚索散开状态识别效果
类别精度召回率mAP50 (B)mAP50-95 (B)
完好锚索0.9190.9230.9460.829
轻微散开锚索0.9911.0000.9950.924
完全散开锚索0.9880.9700.9760.971
锁具0.8580.9260.7750.724
托盘0.9100.6900.7780.692
整体0.8330.9020.8940.828
表2  YOLOv8目标检测指标值
图11  锚索弯曲状态识别技术路线
图12  PSPNet模型结构
图13  锁具和锚索分割结果
图14  锁具和锚索轮廓及相对角度识别结果
  
  
[1] 杨晓明. 采煤工作面端头三角区岩层弱化技术研究[J]. 矿业装备, 2024(2): 41-43.
YANG X M. Study on strata weakening technology in triangle area at the end of coal mining face[J]. Mining Equipment, 2024(2): 41-43.
[2] 郭海军, 冯志忠, 徐朝, 等. 大采高三角区坚硬顶板治理技术研究[J]. 中国煤炭, 2023, 49(S2): 272-276.
GUO H J, FENG Z Z, XU C, et al. Study on treatment technology of hard roof in triangle area with large mining height[J]. China Coal, 2023, 49(S2): 272-276.
[3] 崔计平. 矿用水切割机在煤矿退锚中的应用[J]. 机械管理开发, 2021, 36(7): 139-140.
CUI J P. Application of mine water cutting machine in coal mine anchoring[J]. Mechanical Management and Development, 2021, 36(7): 139-140.
[4] 伊永杰. 退锚装置在保德煤矿的应用[J]. 中国高新技术企业, 2016(26): 144-145.
YI Y J. Application of anchor withdrawing device in Baode coal mine[J]. China High-Tech Enterprises, 2016(26): 144-145.
[5] 赵垚庭, 张博, 李晋. 水力切割技术在退锚工序中的应用[J]. 山东煤炭科技, 2022, 40(7): 92-93, 99.
ZHAO Y T, ZHANG B, LI J. Application of hydraulic cutting technology in anchor withdrawal process[J]. Shandong Coal Science and Technology, 2022, 40(7): 92-93, 99.
[6] 管守军, 刘晟, 张凯辉. 麻家梁矿锚索破断机理研究及退锚创新应用[J]. 同煤科技, 2019(2): 37-40.
GUAN S J, LIU S, ZHANG K H. Study on breaking mechanism of anchor cable and innovative application of anchor removal in Majialiang Mine[J]. Science and Technology of Datong Coal Mining Administration, 2019(2): 37-40.
[7] 张德生, 任怀伟, 卞冀, 等. 综采工作面超前巷道自动化辅助作业技术现状与展望[J]. 矿山机械, 2020, 48(5): 1-6.
ZHANG D S, REN H W, BIAN J, et al. Present situation and prospect of automatic auxiliary operation technology used in advanced roadway of fully-mechanized mining face[J]. Mining & Processing Equipment, 2020, 48(5): 1-6.
[8] 张安宁, 叶国徽, 刘凯, 等. 锚杆退锚机锈死螺母破切器破切力分析[J]. 煤矿机械, 2012, 33(1): 101-102.
ZHANG A N, YE G H, LIU K, et al. Mechanical analysis for nut-breaking cutter of bolt unloader[J]. Coal Mine Machinery, 2012, 33(1): 101-102.
[9] 于进, 张东海. 矿用液压退锚车剖切机构优化设计[J]. 科技资讯, 2023, 21(24): 112-115.
YU J, ZHANG D H. Optimization design of the cutting mechanism of hydraulic anchor-unloading cars for mines[J]. Science & Technology Information, 2023, 21(24): 112-115.
[10] 刘建月, 崔小朝, 刘伟婧. Al2O3陶瓷环在锚具退锚中的应用研究[J]. 太原科技大学学报, 2015, 36(1): 68-71.
LIU J Y, CUI X C, LIU W J. Research on application of Al2O3 ceramic ring in anchorage system unload[J]. Journal of Taiyuan University of Science and Technology, 2015, 36(1): 68-71.
[11] 王晨灿, 李明. 基于YOLOv8的火灾烟雾检测算法研究[J]. 北京联合大学学报, 2023, 37(5): 69-77.
WANG C C, LI M. Research on fire smoke detection algorithms based on YOLOv8[J]. Journal of Beijing Union University, 2023, 37(5): 69-77.
[12] WANG H Q, WANG B N, GE C. Reparameterized YOLOv8 pavement disease detection algorithm [J]. Computer Engineering and Applications, 2024, 60(5): 191-199.
[13] 王安静, 袁巨龙, 朱勇建, 等. 基于改进YOLOv8s的鼓形滚子表面缺陷检测算法[J]. 浙江大学学报(工学版), 2024, 58(2): 370-380, 387.
WANG A J, YUAN J L, ZHU Y J, et al. Drum roller surface defect detection algorithm based on improved YOLOv8s[J]. Journal of Zhejiang University (Engineering Science), 2024, 58(2): 370-380, 387.
[14] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE Computer Society, 2016: 779-788.
[15] ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE Computer Society, 2017: 2881-2890.
[16] FENG X M, WANG T P, YANG X H, et al. ConvWin-UNet: UNet-like hierarchical vision Transformer combined with convolution for medical image segmentation[J]. Mathematical Biosciences and Engineering, 2022, 20(1): 128-144.
[17] 董钊辰, 李涛, 刘忻. 大语言模型在低对比度图像识别中的应用与探索[J]. 软件, 2025, 46(9): 23-28, 36.
DONG Z C, LI T, LIU X. Application and exploration of large language model in low contrast image recognition[J]. Computer Engineering & Software, 2025, 46(9): 23-28, 36.
[18] 熊彬, 张双德. 基于改进PSPNet的卫星遥感图像建筑物语义分割算法[J]. 遥感信息, 2023, 38(4): 73-79.
XIONG B, ZHANG S D. Semantic segmentation algorithm for buildings in satellite remote sensing images based on improved PSPNet[J]. Remote Sensing Information, 2023, 38(4): 73-79.
[19] 郭浩然, 郭继昌, 汪昱东. 面向水下场景的轻量级图像语义分割网络[J]. 浙江大学学报(工学版), 2023, 57(7): 1278-1286, 1296.
GUO H R, GUO J C, WANG Y D. Lightweight semantic segmentation network for underwater image[J]. Journal of Zhejiang University (Engineering Science), 2023, 57(7): 1278-1286, 1296.
[20] 周中, 张俊杰, 龚琛杰, 等. 基于深度语义分割的隧道渗漏水智能识别[J]. 岩石力学与工程学报, 2022, 41(10): 2082-2093.
ZHOU Z, ZHANG J J, GONG C J, et al. Automatic identification of tunnel leakage based on deep semantic segmentation[J]. Chinese Journal of Rock Mechanics and Engineering, 2022, 41(10): 2082-2093.
[1] 侯勇俊,贾文俊,刘博文,吴先进. 基于树莓派和视觉图像的钻井振动筛倾角调节系统[J]. 工程设计学报, 2024, 31(2): 254-262.
[2] 李宝志, 倪洪启, 林思雨, 孟宪春. 基于图像识别的波纹补偿器轴向尺寸检测方法[J]. 工程设计学报, 2022, 29(1): 10-19.