View in EDS

UAV inspection path optimization in offshore wind farms using the OPTION-A*-DQN algorithm.

Saved in:
Bibliographic Details
Title: UAV inspection path optimization in offshore wind farms using the OPTION-A*-DQN algorithm.
Authors: Xu M; School of Computer Science and Engineering, Guangdong Ocean University, Guangdong, China., Deng C; School of Computer Science and Engineering, Guangdong Ocean University, Guangdong, China., Hu X; School of Computer Science and Engineering, Guangdong Ocean University, Guangdong, China., Lu Y; School of Computer Science and Engineering, Guangdong Ocean University, Guangdong, China., Xue W; School of Mechanical and Energy Engineering, Guangdong Ocean University, Guangdong, China., Zhu B; Three Gorges New Energy Yangjiang Power Generation Co., Ltd., Yangjiang, Guangdong, China.
Source: PloS one [PLoS One] 2025 Nov 24; Vol. 20 (11), pp. e0336935. Date of Electronic Publication: 2025 Nov 24 (Print Publication: 2025).
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
Imprint Name(s): Original Publication: San Francisco, CA : Public Library of Science
MeSH Terms: Wind* , Algorithms* , Unmanned Aerial Devices*, Models, Theoretical
Abstract: Competing Interests: The authors have declared that no competing interests exist.
In response to the inefficiencies in offshore wind farm inspections caused by path redundancy and mission omissions, this study proposes a novel path planning method for Unmanned Aerial Vehicle (UAV) inspections, integrating multi-constraint optimization and intelligent scheduling. First, a four-dimensional constraint model is established, encompassing wind speed, charging, minimum UAV fleet size, and dynamic obstacle avoidance. Second, the OPTION-A*-DQN hybrid algorithm is developed by synergizing A* heuristic search with deep reinforcement learning (DRL) to balance global navigation and local optimization. An improved K-Means algorithm further enables efficient topological partitioning for multi-UAV collaboration. Comparative evaluations against original OPTION-DQN and conventional heuristic methods (Dijkstra and Simulated Annealing) demonstrate that the proposed method achieves three key improvements: (1) a 10% higher task completion rate, (2) a 14.9% reduction in path distance, and (3) a 20% faster simulation time. This work significantly advances intelligent path planning for offshore wind farm inspections.
(Copyright: © 2025 Xu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
References: PLoS One. 2022 Dec 27;17(12):e0279438. (PMID: 36574399)
PLoS One. 2025 Jan 16;20(1):e0312559. (PMID: 39821118)
Entry Date(s): Date Created: 20251124 Date Completed: 20251124 Latest Revision: 20251127
Update Code: 20251127
PubMed Central ID: PMC12643302
DOI: 10.1371/journal.pone.0336935
PMID: 41284680
Database: MEDLINE
Description
Abstract:Competing Interests: The authors have declared that no competing interests exist.<br />In response to the inefficiencies in offshore wind farm inspections caused by path redundancy and mission omissions, this study proposes a novel path planning method for Unmanned Aerial Vehicle (UAV) inspections, integrating multi-constraint optimization and intelligent scheduling. First, a four-dimensional constraint model is established, encompassing wind speed, charging, minimum UAV fleet size, and dynamic obstacle avoidance. Second, the OPTION-A*-DQN hybrid algorithm is developed by synergizing A* heuristic search with deep reinforcement learning (DRL) to balance global navigation and local optimization. An improved K-Means algorithm further enables efficient topological partitioning for multi-UAV collaboration. Comparative evaluations against original OPTION-DQN and conventional heuristic methods (Dijkstra and Simulated Annealing) demonstrate that the proposed method achieves three key improvements: (1) a 10% higher task completion rate, (2) a 14.9% reduction in path distance, and (3) a 20% faster simulation time. This work significantly advances intelligent path planning for offshore wind farm inspections.<br /> (Copyright: © 2025 Xu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
ISSN:1932-6203
DOI:10.1371/journal.pone.0336935