Keywords
Digital twin
YOLO v10
Water plant
Submitted : 2025-05-07
Accepted : 2025-05-22
Published : 2025-06-06
Abstract
Inspection is a fundamental task for water plants, yet traditional methods are often labor-intensive, time-consuming, and costly. The rapid advancement of drone technology has significantly transformed environmental inspections, particularly in water plant assessments. Digital twins enhance modeling and simulation capabilities by integrating real-time data and feedback. This paper presents an intelligent water plant detection system based on YOLOv10 and drone technology. The system aims to monitor environmental conditions around water facilities and automatically identify anomalies in real time. The design utilizes dataset images of construction vehicles, maintenance hole covers, and pipe leaks collected from publicly accessible websites. The system integrates real-time drone inspection data into a digital twin platform for dynamic monitoring.
References
International Water Association (IWA), 2023, Global Trends in Digital Water Adoption. IWA Publishing.
California Department of Water Resources, 2023, Case Study: AI-Powered Drone Inspections in Los Angeles Water Plants. Technical Report.
Zheng Y, 2022, Construction of Smart Water Plants based on Digital twin. Intelligent Building Electrical Technology, 16(3): 7.
IBM Corporation, 2024, Smart Water Management: IoT and AI Solutions for Sustainable Cities. IBM White Paper.
Li X, Zhang Y, Liu H, 2023, Digital Twin-Driven Predictive Maintenance for Urban Water Supply Networks. Water Resources Management, 37(5): 1897–1916.
Wang S, 2025, Application and Prospect of Digital Technology in Water Conservancy Project Construction Management. Heilongjiang Province Water Conservancy Science and Technology, (02): 131–134 + 139.
Grieves M, Vickers J, 2017, Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems, Transdisciplinary Perspectives on Complex Systems, Springer, 85–113.
Tao F, Liu W, Zhang M, et al., 2019, Digital Twin Five-dimensional Model and Ten Applications. Journal of Computer Integrated Manufacturing System, 25(01): 1–18. https://doi.org/10.13196/j.cims.2019.01.001
Tao F, Liu W, Liu J, et al., 2018, Twin and Application of Digital Exploration. Journal of Computer Integrated Manufacturing System, 24(01): 1–18. https://doi.org/10.13196/j.cims.2018.01.001
Xie J, Zhang Y, Jiang H, 2021, Research and Construction of Intelligent Water Supply Management System based on Digital Twin. Urban Water Supply, (1): 4.
Chen J, 2022, Research on Ways to Realize Smart Water Supply by Using Digital Twin in the Water Industry. Knowledge Economy, 595(002): 17–18.
PUB, Singapore’s National Water Agency, 2024, Digital Water: Singapore’s Experience, viewed April 5, 2025, https://doi.org/10.2166/9781789064957.
Tencent News, 2025, The Dali UAV’s Intelligent Inspection Efficiency 16 Years, viewed April 5, 2025. https://news.qq.com/rain/a/20250120A09PBU00.
Redmon J, Divvala S, Girshick R, et al., 2016, You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779–788.
Wang CY, Bochkovskiy A, Liao HYM, 2023, YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 7464–7475. https://doi.org/10.1109/CVPR52729.2023.00721