[1]白健鹏,王巍,陈雨溪,等.基于轻量型YOLOv5的风机桨叶检测与空间定位[J].智能系统学报,2022,17(6):1173-1181.[doi:10.11992/tis.202204016]
BAI Jianpeng,WANG Wei,CHEN Yuxi,et al.Detection and spatial location of wind turbine blades based on lightweight YOLOv5[J].CAAI Transactions on Intelligent Systems,2022,17(6):1173-1181.[doi:10.11992/tis.202204016]
点击复制
BAI Jianpeng,WANG Wei,CHEN Yuxi,et al.Detection and spatial location of wind turbine blades based on lightweight YOLOv5[J].CAAI Transactions on Intelligent Systems,2022,17(6):1173-1181.[doi:10.11992/tis.202204016]
基于轻量型YOLOv5的风机桨叶检测与空间定位
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
17
期数:
2022年第6期
页码:
1173-1181
栏目:
学术论文—智能系统
出版日期:
2022-11-05
- Title:
- Detection and spatial location of wind turbine blades based on lightweight YOLOv5
- Keywords:
- wind turbine; unmanned aerial vehicle; object detection; YOLOv5; lightweight; deep learning; blade tip; accurate positioning
- 分类号:
- TP138;TP242
- 文献标志码:
- 2022-08-24
- 摘要:
- 应用无人机对风力发电机进行自主巡检时，需对其桨叶叶尖进行精准定位，同时因机载计算板的计算能力有限，常规目标检测算法检测效率低下。为此提出了一种基于轻量型YOLOv5的风机桨叶检测与空间定位方法，首先对YOLOv5目标检测算法进行轻量化改进，将ShuffleNetv2作为特征提取主干网络；然后利用该算法对风机全景图像中的风机轮毂和桨叶进行检测，以得到轮毂和桨叶叶尖的像素坐标；最后利用无人机位姿信息和空间平面的几何关系，对风机桨叶进行精准定位。实验表明，所改进的目标检测算法以1.536×106的参数量在大疆MANIFOLD2-C上的检测速度提升47%，可达29.4 f/s，所设计的定位方法可对风机桨叶叶尖进行精准定位，水平和高度定位误差均为±5 cm，三维整体定位误差为±10 cm。
- Abstract:
- The application of unmanned aerial vehicles (UAVs) for autonomous inspection of wind turbines requires precise positioning of the paddle blade tips, but the detection efficiency of conventional target detection algorithms is low due to the limited computing power of the onboard computer. Therefore, a method of the blade and spatial location detection of wind turbines based on lightweight YOLOv5 is proposed. Initially, the YOLOv5 target detection algorithm is lightly improved using ShuffleNetv2 as the feature extraction backbone network. The algorithm is then used to detect the hub and blades of the turbine in the panoramic image to obtain the pixel coordinates of the hub and blade tips. Finally, the UAV positional information and geometric relationship between the spatial planes are used to accurately locate the wind turbine blades. The tests show that the improved target detection algorithm with 1.536 × 106 parameters on the DJI MANIFOLD2-C improves detection speed by 47%, up to 29.4 f/s. The designed positioning method can accurately locate the tips of wind turbine blades with both horizontal and height positioning errors of ±5 cm and a three-dimensional overall positioning error of ±10 cm.
- 参考文献/References:
-
[1] 陈诗一, 许璐. “双碳”目标下全球绿色价值链发展的路径研究[J]. 北京大学学报(哲学社会科学版), 2022, 59(2): 5–12
CHEN Shiyi, XU Lu. A study on the development path of global green value chain to achieve the targets of carbon peaking and carbon neutrality[J]. Journal of Peking University (philosophy and social sciences edition), 2022, 59(2): 5–12
[2] 蒋元锐. 武钢委员: “双碳”目标呼唤风电赋能[N]. 中华工商时报, 2022-03-11(2).
JIANG Yuanrui. Member WU Gang: The targets of carbon peaking and carbon neutrality call for wind power energization[N]. China bussiness times, 2022-03-11(2).
[3] CHATTERJEE J, DETHLEFS N. Scientometric review of artificial intelligence for operations & maintenance of wind turbines: the past, present and future[J]. Renewable and sustainable energy reviews, 2021, 144: 111051.
[4] 田枫, 白欣宇, 刘芳, 等. 一种轻量化油田危险区域入侵检测算法[J]. 智能系统学报, 2022, 17(3): 634–642
TIAN Feng, BAI Xinyu, LIU Fang, et al. A lightweight intrusion detection algorithm for hazardous areas in oilfields[J]. CAAI transactions on intelligent systems, 2022, 17(3): 634–642
[5] ZHOU Yan, CHEN Shaochang, WANG Yiming, et al. Review of research on lightweight convolutional neural networks[C]//2020 IEEE 5th Information Technology and Mechatronics Engineering Conference. Chongqing: IEEE, 2020: 1713-1720.
[6] 何锐波, 狄岚, 梁久祯. 一种改进的深度学习的道路交通标识识别算法[J]. 智能系统学报, 2020, 15(6): 1121–1130
HE Ruibo, DI Lan, LIANG Jiuzhen. An improved deep learning algorithm for road traffic identification[J]. CAAI transactions on intelligent systems, 2020, 15(6): 1121–1130
[7] JACOB B, KLIGYS S, CHEN Bo, et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 2704-2713.
[8] KRISHNAMOORTHI R. Quantizing deep convolutional networks for efficient inference: a whitepaper[EB/OL]. (2018-06-21)[2022-04-11].https://arxiv.org/abs/1806.08342.
[9] LUO JIAN-HAO, WU JIANXIN. An entropy-based pruning method for CNN compression[EB/OL]. (2017-06-19)[2022-04-11].https://arxiv.org/abs/1706.05791.
[10] HINTON G, VINYALS O, DEAN J. Distilling the knowledge in a neural network[EB/OL]. (2015-03-09)[2022-04-11].https://arxiv.org/abs/1503.02531.
[11] LI Yahui, LIU Jun, WANG Lilin. Lightweight network research based on deep learning: a review[C]//2018 37th Chinese Control Conference (CCC). Wuhan: IEEE, 2018: 9021-9026.
[12] SANDLER M, HOWARD A, ZHU Menglong, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510-4520.
[13] MA Ningning, ZHANG Xiangyu, ZHENG Haitao, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[C]//European Conference on Computer Vision. Cham: Springer, 2018: 122-138.
[14] WU Bichen, WAN A, YUE Xiangyu, et al. Shift: a zero FLOP, zero parameter alternative to spatial convolutions[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 9127-9135.
[15] HAN Kai, WANG Yunhe, TIAN Qi, et al. GhostNet: more features from cheap operations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle: IEEE, 2020: 1577-1586.
[16] 潘佳捷. 风机叶片的无人机自主巡检系统[D]. 成都: 电子科技大学, 2020.
PAN Jiajie. An autonomous inspection system for wind turbine blade based on unmanned aerial vehicle[D]. Chengdu: University of Electronic Science and Technology of China, 2020.
[17] 朱凯华. 面向风机叶片巡检的无人机自动航迹线规划研究[D]. 北京: 北京交通大学, 2021.
ZHU Kaihua. Research on automatic path planning of UAV for wind turbine blade inspection[D]. Beijing: Beijing Jiaotong University, 2021.
[18] 勾月凯, 代海涛, 董健, 等. 风力发电机组叶片智能巡检系统研究[C]//第五届中国风电后市场专题研讨会. 上海: [出版者不详], 2018: 203-208.
GOU Yuekai, DAI Haitao, DONG Jian, et al. Research on intelligent inspection system of wind turbine blades[C]//Proceedings of the 5th China Wind Power Post Market Symposium. Shanghai: [s,n.], 2018: 203-208.
[19] KANELLAKIS C, FRESK E, MANSOURI S S, et al. Towards visual inspection of wind turbines: a case of visual data acquisition using autonomous aerial robots[J]. IEEE access, 2020, 8: 181650–181661.
[20] GUO Haowen, CUI Qiangqiang, WANG Jinwang, et al. Detecting and positioning of wind turbine blade tips for UAV-based automatic inspection[C]//IGARSS 2019—2019 IEEE International Geoscience and Remote Sensing Symposium. Yokohama: IEEE, 2019: 1374-1377.
[21] MOOLAN-FEROZE O, KARACHALIOS K, NIKOLAIDIS D N, et al. Simultaneous drone localisation and wind turbine model fitting during autonomous surface inspection[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Macao: IEEE, 2019: 2014-2021.
[22] REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. (2018-04-08)[2022-04-11].https://arxiv.org/abs/1804.02767.
[23] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//European Conference on Computer Vision. Cham: Springer, 2014: 346-361.
[24] LIU Shu, QI Lu, QIN Haifang, et al. Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8759-8768.
[25] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. Scaled-YOLOv4: scaling cross stage partial network[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville: IEEE, 2021: 13024-13033.
- 相似文献/References:
-
[1]秦世引,潘宇雄,苏善伟.小型无人机编队飞行的控制律设计与仿真[J].智能系统学报,2009,4(3):218.
QIN Shi-yin,PAN Yu-xiong,SU Shan-wei.Design and simulation of formation flight control laws for small unmanned aerial vehicles[J].CAAI Transactions on Intelligent Systems,2009,4():218.
[2]朱杰斌,秦世引.无人机编队飞行的分布式控制策略与控制器设计[J].智能系统学报,2010,5(5):392.[doi:10.3969/j.issn.1673-4785.2010.05.003]
ZHU Jie-bin,QIN Shi-yin.Distributed control strategy and controller design for UAV formation flight[J].CAAI Transactions on Intelligent Systems,2010,5():392.[doi:10.3969/j.issn.1673-4785.2010.05.003]
[3]刘敏,邹杰,冯星,等.人工蜂群算法的无人机航路规划与平滑[J].智能系统学报,2011,6(4):344.
LIU Min,ZOU Jie,FENG Xing,et al.Smooth trajectory planning of an unmanned aerial vehicleusing an artificial bee colony algorithm[J].CAAI Transactions on Intelligent Systems,2011,6():344.
[4]胡文超,孙新柱,陈孟元.音频感知哈希闭环检测的无人机仿生声呐SLAM算法研究[J].智能系统学报,2019,14(2):338.[doi:10.11992/tis.201708018]
HU Wenchao,SUN Xinzhu,CHEN Mengyuan.Research on BATSLAM algorithm for UAV based on audio perceptual hash closed-loop detection[J].CAAI Transactions on Intelligent Systems,2019,14():338.[doi:10.11992/tis.201708018]
[5]徐魏超,王冠凌,陈孟元.无人机协助下基于SR-CKF的无线传感器网络节点定位研究[J].智能系统学报,2019,14(3):575.[doi:10.11992/tis.201709019]
XU Weichao,WANG Guanling,CHEN Mengyuan.Node localization of wireless sensor networks based on SR-CKF assisted by unmanned aerial vehicles[J].CAAI Transactions on Intelligent Systems,2019,14():575.[doi:10.11992/tis.201709019]
[6]张飞,白伟,乔耀华,等.基于改进D*算法的无人机室内路径规划[J].智能系统学报,2019,14(4):662.[doi:10.11992/tis.201803031]
ZHANG Fei,BAI Wei,QIAO Yaohua,et al.UAV indoor path planning based on improved D* algorithm[J].CAAI Transactions on Intelligent Systems,2019,14():662.[doi:10.11992/tis.201803031]
[7]齐小刚,李博,范英盛,等.多约束下多无人机的任务规划研究综述[J].智能系统学报,2020,15(2):204.[doi:10.11992/tis.201811018]
QI Xiaogang,LI Bo,FAN Yingsheng,et al.A survey of mission planning on UAVs systems based on multiple constraints[J].CAAI Transactions on Intelligent Systems,2020,15():204.[doi:10.11992/tis.201811018]
[8]吴莹莹,丁肇红,刘华平,等.面向环境探测的多智能体自组织目标搜索算法[J].智能系统学报,2020,15(2):289.[doi:10.11992/tis.201908023]
WU Yingying,DING Zhaohong,LIU Huaping,et al.Self-organizing target search algorithm of multi-agent system for envi-ronment detection[J].CAAI Transactions on Intelligent Systems,2020,15():289.[doi:10.11992/tis.201908023]
[9]付昆,田金文,马懿超.多特征融合的异视角目标关联算法[J].智能系统学报,2020,15(5):847.[doi:10.11992/tis.202006037]
FU Kun,TIAN Jinwen,MA Yichao.Target association from different perspectives based on multi-feature fusion[J].CAAI Transactions on Intelligent Systems,2020,15():847.[doi:10.11992/tis.202006037]
[10]段海滨,辛龙,邓亦敏.仿信鸽归巢行为的导航技术研究进展[J].智能系统学报,2021,16(1):1.[doi:10.11992/tis.202009049]
DUAN Haibin,XIN Long,DENG Yimin.Technology research review on homing pigeon-inspired navigation[J].CAAI Transactions on Intelligent Systems,2021,16():1.[doi:10.11992/tis.202009049]
备注/Memo
收稿日期:2022-04-11。
作者简介:白健鹏，硕士研究生，主要研究方向为电力设备自主巡检;王巍，硕士研究生，主要研究方向为图像处理和电力视觉;焦嵩鸣，副教授，主要研究方向为机器人感知与控制、电力设备自主巡检
通讯作者:焦嵩鸣.E-mail:jiaosongming@ncepu.edu.cn
更新日期/Last Update:
1900-01-01