Please wait a minute...
工程设计学报  2019, Vol. 26 Issue (5): 527-533    DOI: 10.3785/j.issn.1006-754X.2019.05.005
智能设计     
基于深度学习算法的矿用巡检机器人设备识别
卢万杰1, 付华2, 赵洪瑞3
1.辽宁工程技术大学 机械工程学院, 辽宁 阜新 123000
2.辽宁工程技术大学 电气工程学院, 辽宁 葫芦岛 125000
3.煤科集团沈阳研究院有限公司, 辽宁 沈阳 110000
Equipment recognition of mining patrol robot based on deep learning algorithm
LU Wan-jie1, FU Hua2, ZHAO Hong-rui3
1.College of Mechanical Engineering, Liaoning University of Engineering and Technology, Fuxin 123000, China
2.College of Electrical Engineering, Liaoning University of Engineering and Technology, Huludao 125000, China
3.CCTEG (China Coal Technology & Engineering Group) Shenyang Research Institute Co., Ltd., Shenyang 110000, China
 全文: PDF(2549 KB)   HTML
摘要: 为了实现矿用巡检机器人对煤矿井下设备的识别与匹配,通过基于卷积神经网络的深度学习算法建立了煤矿设备类型识别模型,分别在明亮环境下、昏暗环境下以及设备重叠情况下采集大量待识别设备图像样本,再对识别模型进行训练,实现巡检机器人对煤矿设备的精确识别与分类。使用基于粒子群优化的SVM(support vector machine,支持向量机)建立了煤矿设备匹配模型,将巡检机器人相对于煤矿坐标系的三轴位置信息、三自由度角度和视觉相机转角作为匹配模型的输入量,将相机视野中设备序号作为输出量,实现煤矿设备类型识别模型识别出的设备与已知设备序号一一对应。实验结果表明基于深度学习算法的煤矿设备类型识别模型对外界的干扰不敏感,识别准确率高;基于SVM的煤矿设备匹配模型的匹配准确率达到了93.2%,在匹配准确率的训练和测试效率上均优于基于BP(back propagation,反向传播)神经网络的匹配模型。研究结果可为煤矿井下巡检机器人的研制提供参考。
关键词: 巡检机器人深度学习算法支持向量机目标识别设备匹配    
Abstract: In order to realize the recognition and matching of underground equipment by mining patrol robots, a coal mine equipment type of recognition model was established by deep learning algorithm based on convolution neural network. A large number of image samples of equipment to be identified were collected under the bright, dark and equipment overlapping conditions, and the recognition model was trained to realize the accurate recognition and classification of coal mine equipment by patrol robot. A coal mine equipment of matching model was established by using the SVM(support vector machine) based on particle swarm optimization. The three-axis position information, three-degree-of-freedom angle and the rotation angle of visual camera of the patrol robot relative to the coal mine coordinate system were taken as the input of the matching model, and the serial number of equipment in the camera field of vision was taken as the output to realize the correspondence between the equipment identified by the coal mine equipment type identification model and the known equipment serial number. The experimental results showed that the coal mine equipment type of recognition model based on deep learning algorithm was insensitive to external interference and had high recognition accuracy. The coal mine equipment of matching model based on support vector machine achieved 93.2% accuracy of equipment matching, and it was superior to the matching model based on the BP (back propagation) neural network in training and testing efficiency of equipment matching accuracy. The research results provide a reference for the development of patrol robot in coal mine.
Key words: patrol robot    deep learning algorithm    support vector machine    target recognition    equipment matching
收稿日期: 2019-05-20 出版日期: 2019-10-28
CLC:  TP 242  
基金资助: 辽宁省自然科学基金指导计划项目(20180550438)
作者简介: 卢万杰(1979—),女,辽宁阜新人,讲师,博士,从事机器人智能控制研究,E-mail:2144778378@qq.com,https://orcid.org/0000-0002-8371-5567
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  
卢万杰
付华
赵洪瑞

引用本文:

卢万杰, 付华, 赵洪瑞. 基于深度学习算法的矿用巡检机器人设备识别[J]. 工程设计学报, 2019, 26(5): 527-533.

LU Wan-jie, FU Hua, ZHAO Hong-rui. Equipment recognition of mining patrol robot based on deep learning algorithm. Chinese Journal of Engineering Design, 2019, 26(5): 527-533.

链接本文:

https://www.zjujournals.com/gcsjxb/CN/10.3785/j.issn.1006-754X.2019.05.005        https://www.zjujournals.com/gcsjxb/CN/Y2019/V26/I5/527

1 ZHENGXing, ZHANGGao-feng, WANGHong-qi. Development of two-stage information detection robot system for coal mine disaster rescue [J]. Coal Science and Technology, 2017, 45 (5): 58-64.
2 CAILi-hua, FANGHai-feng, GAOJin-ke, et al. Design of walking mechanism and gait analysis of coal mine exploration robot[J]. Industrial and Mining Automation, 2017, 43 (6): 47-51.
[1] 肖圳, 何彦, 李育锋, 吴鹏程, 刘德高, 杜江. 改进MDSMOTEPSO-SVM在汽车组合仪表分类预测中的应用[J]. 工程设计学报, 2022, 29(1): 20-27.
[2] 刘羽嘉, 潘滨, 李东泽, 李凤迪, 张迁, 孙丰刚, 兰鹏. 民宿无人值守智能管理系统设计与实现[J]. 工程设计学报, 2020, 27(3): 389-397.
[3] 李成兵, 叶超, 毛熙皓. 改进人工蜂群算法优化的LSSVM在混合气体定量分析中的应用[J]. 工程设计学报, 2020, 27(1): 94-102.
[4] 江岳春, 杨旭琼, 陈礼锋, 贺飞. 基于EMD-SC和AGSA优化支持向量机的超短期风电功率组合预测[J]. 工程设计学报, 2017, 24(2): 187-195.
[5] 李占福, 童昕. 基于AFSA-SimpleMKL对振动筛建模及筛机优化[J]. 工程设计学报, 2016, 23(2): 181-187.
[6] 郑严, 程文明, 程跃, 吴晓. 基于支持向量机的非概率可靠性分析[J]. 工程设计学报, 2011, 18(5): 327-331.
[7] 陈笑然, 章林柯, 阎兆立, 陈 杰, 程晓斌. 基于主动超声的轴流水泵空化监测方法研究[J]. 工程设计学报, 2011, 18(3): 214-217.
[8] 杨克己, 方文平, 乔华伟, 黄一春. 基于复小波变换和支持向量机的缺陷类型识别[J]. 工程设计学报, 2008, 15(3): 182-186.
[9] 许葆华, 李洪儒. 某型导弹发射装置液压元件故障的预测[J]. 工程设计学报, 2007, 14(6): 449-452.