一种库坝系统水下成像探查有缆机器人系统设计模式
A Design Pattern for a Cabled Robot System for Underwater Imaging and Inspection in Reservoir Dam Systems
DOI: 10.12677/airr.2025.145112, PDF,    国家自然科学基金支持
作者: 樊棠怀:南昌理工学院电子与信息学院,江西 南昌;江西水利电力大学信息工程学院,江西 南昌;樊飞燕:江西水利电力大学信息工程学院,江西 南昌;程晓玲, 罗中华:南昌理工学院电子与信息学院,江西 南昌;沈克永:南昌理工学院计算机信息工程学院,江西 南昌
关键词: 库坝系统水下机器人水下探查可见光图像目标检测Reservoir Dam System Underwater Robot Underwater Inspection Visible Light Image Target Detection
摘要: 库坝系统是由水库与坝体构成的综合水利设施,是兼具水资源调控、防洪减灾与水电能源供应功能的核心枢纽工程,其涵盖坝体、防洪堤防、水电站厂房、闸门等关键水工结构。这些结构长期受水流冲击、水质侵蚀等影响,易出现结构损毁、漏水等问题。为解决传统人工探查效率低、风险高等问题,本文提出一种库坝系统水下成像探查有缆机器人系统(简称:CRS-UII)设计模式及实现方案。该模式以有缆机器人为载体,集成光学成像与环境感知设备,通过硬件架构与协同化软件算法,实现对水下结构多类型异常的有效探查,为库坝系统水下多场景探查机器人的研发提供通用性的参考设计框架。
Abstract: The reservoir dam system is a comprehensive water conservancy facility composed of reservoirs and dam bodies. It is a core hub project with functions of water resource regulation, flood control and disaster reduction, and hydropower energy supply, covering key hydraulic structures such as dam bodies, flood control dikes, hydropower station workshops, and sluices. These structures are prone to structural damage, water leakage and other problems due to long-term impact of water flow, water quality erosion and other factors. To solve the problems of low efficiency and high risk in traditional manual inspection, this paper proposes a design pattern and implementation scheme for a Cabled Robot System for Underwater Imaging and Inspection (CRS-UII) in reservoir dam systems. This pattern takes the cabled robot as the carrier, integrates optical imaging and environmental perception equipment, and realizes effective inspection of multiple types of abnormalities in underwater structures through hardware architecture and collaborative software algorithms, providing a universal reference design framework for the research and development of robots for multi-scene underwater inspection in reservoir dam systems.
文章引用:樊棠怀, 樊飞燕, 程晓玲, 沈克永, 罗中华. 一种库坝系统水下成像探查有缆机器人系统设计模式[J]. 人工智能与机器人研究, 2025, 14(5): 1186-1195. https://doi.org/10.12677/airr.2025.145112

参考文献

[1] 盛金保, 厉丹丹, 蔡荨, 等. 大坝风险评估与管理关键技术研究进展[J]. 中国科学, 2018, 48(10): 1057-1067.
[2] Varughese, A. (2016) Application of Remote Operated Vehicle as a Post Construction Instrumentation for an Existing Dam: A Case Study. International Journal of Latest Technology in Engineering, Management & Applied Science, 5, 8-13.
[3] Sugimoto, H., Moriya, Y. and Ogasawara, T. (2017) Underwater Survey System of Dam Embankment by Remotely Operated Vehicle. 2017 IEEE Underwater Technology (UT), Busan, 21-24 February 2017, 1-6. [Google Scholar] [CrossRef
[4] Liu, H., Yuan, J., Ren, Q., Li, M., Qi, Z. and Deng, X. (2025) Remotely Operated Vehicle (ROV) Underwater Vision-Based Micro-Crack Inspection for Concrete Dams Using a Customizable CNN Framework. Automation in Construction, 173, Article 106102. [Google Scholar] [CrossRef
[5] 陈永灿, 陈嘉杰, 王皓冉, 等. 大直径长引水隧洞水下检测机器人系统关键技术[J]. 清华大学学报: 自然科学版, 2023, 63(7): 1015-1031.
[6] 唐湘茜, 卢建华, 高大水, 等. 视声一体化深水渗漏探测技术[J]. 水利水电快报, 2019, 40(4): 6-7.
[7] 马建业, 郑东健, 孙建伟. 基于生物启发神经网络的水下坝面表观裂缝检测路径规划算法[J]. 水利水电科技进展, 2022, 42(6): 60-65.
[8] 罗中华, 李柯, 李连国, 苑鸿骥, 沈克永, 杨扬. 一种基于AUV的大水域水质三维空间分层检测系统设计模式[J]. 软件工程与应用, 2022, 11(3): 582-589.
[9] Li, Y., Bao, T., Huang, X., Wang, R., Shu, X., Xu, B., et al. (2023) An Integrated Underwater Structural Multi-Defects Automatic Identification and Quantification Framework for Hydraulic Tunnel via Machine Vision and Deep Learning. Structural Health Monitoring, 22, 2360-2383. [Google Scholar] [CrossRef
[10] 智研咨询. 2025-2031年中国水下机器人行业市场深度分析及投资决策建议报告[R]. 北京: 智研咨询, 2025.
https://caifuhao.eastmoney.com/news/20250122145626735323690, 2025-08-13.
[11] 严浙平, 曲思瑜, 邢文. 水下图像增强方法研究综述[J]. 智能系统学报, 2022, 17(5): 860-873.
[12] 陈燕, 肖澳, 李云, 胡小春, 井佩光. 多路融合深度聚合学习的水下图像增强[J]. 激光与光电子学进展, 2025, 62(2): 1-9.
[13] Xu, M., Wu, X., Zhang, Z. and Lu, Y. (2021) Compound-Eye Imaging Imitation-Based Whole-Field Flow Measurement. Computers & Electrical Engineering, 92, Article 107141. [Google Scholar] [CrossRef
[14] Li, B., Chen, Z., Lu, L., Qi, P., Zhang, L., Ma, Q., et al. (2025) Cascaded Frameworks in Underwater Optical Image Restoration. Information Fusion, 117, Article 102809. [Google Scholar] [CrossRef
[15] 李扬涛, 赵海涛, 魏洋, 等. 视觉驱动的涉水混凝土结构水下多类别缺陷辨识和区域弱监督定位方法[J]. 应用基础与工程科学学报, 2025, 33(1): 60-75.
[16] 陶显, 侯伟, 徐德. 基于深度学习的表面缺陷检测方法综述[J]. 自动化学报, 2021, 47(5): 1017-1034.
[17] Zou, Z., Chen, K., Shi, Z., Guo, Y. and Ye, J. (2023) Object Detection in 20 Years: A Survey. Proceedings of the IEEE, 111, 257-276. [Google Scholar] [CrossRef
[18] Ciaparrone, G., Luque Sánchez, F., Tabik, S., Troiano, L., Tagliaferri, R. and Herrera, F. (2020) Deep Learning in Video Multi-Object Tracking: A Survey. Neurocomputing, 381, 61-88. [Google Scholar] [CrossRef
[19] Li, Y., Bao, T., Huang, X., Chen, H., Xu, B., Shu, X., et al. (2022) Underwater Crack Pixel-Wise Identification and Quantification for Dams via Lightweight Semantic Segmentation and Transfer Learning. Automation in Construction, 144, Article 104600. [Google Scholar] [CrossRef
[20] 李永龙, 王皓冉, 张华. 水下机器人在水利水电工程检测中的应用现状及发展趋势[J]. 中国水利水电科学研究院学报, 2018, 6(6): 586-590.
[21] 杨承霖, 赵千慧, 邵宏权. 有缆遥控水下机器人的设计与应用[J]. 电子元器件与信息技术, 2024, 8(10): 99-101.
[22] 徐鹏飞, 陈梅雅, 开艳, 王子鹏, 李新宇, 万刚, 王延杰. 大型水电站坝体检测水下机器人研究进展[J]. 清华大学学报(自然科学版), 2023, 63(7): 1032-1040.