Wenyan Xue

Wenyan Xue

Auto-generated profile, based on publicly available information

Wenyan Xue

College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, P. R. China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2023 in Unmanned Systems
Verified
Journal Article
Closed access
WXWenyan Xue
Wenyan Xue
JHJie Huang
Jie Huang
NCNan Chen
Nan Chen
YCYutao Chen
Yutao Chen
DLDingci Lin
Dingci Lin

18 September 2024 in Unmanned Systems
Verified
Journal Article
Closed access
WXWenyan Xue
Wenyan Xue
JHJie Huang
Jie Huang
ZLZeyi Li
Zeyi Li
BXBin Xin
Bin Xin

2 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
WXWenyan Xue
Wenyan Xue
HWHoumin Wang
Houmin Wang
YLYue Lin
Yue Lin
SZSiyuan Zhan
Siyuan Zhan
Inspection of large offshore wind farms (OWFs) requires efficient coverage of spatially distributed turbines within limited operational windows. Cooperative deployment of multiple unmanned aerial vehicles (UAVs) enables parallel inspection and provides operational redundancy; however, changing wind conditions, limited battery endurance, flight-safety constraints, and unexpected changes in vehicle availability and inspection demand can alter flight feasibility and mission costs during operation, requiring task assignments and flight routes to be adapted accordingly. This study therefore develops a wind-aware dynamic mission planning framework that incorporates wind-dependent flight performance, energy consumption, safe-return requirements, and dynamic mission events. A hierarchical strategy separates task reassignment from route recovery: a constraint-aware deep Q-network (CADQN) assigns released or newly generated tasks only to feasible UAVs, while a memory-guided protective genetic algorithm (MGPGA) reconstructs affected route segments while preserving unaffected feasible portions. A site-informed OWF scenario is used for evaluation. Results show that offshore wind conditions alter the battery-constrained reachable region and affect mission-level energy consumption and completion time. Compared with a coupled DQN strategy, the proposed framework reduces total flight distance, energy consumption, and mission completion time by 10.7%, 13.1%, and 12.6%, respectively, demonstrating effective adaptive mission recovery under dynamic offshore operating conditions.

26 March 2026 in PLOS ONE
Verified
Journal Article
Open access
YLYunqi Liao
Yunqi Liao
SYShuyuan You
Shuyuan You
HWHoumin Wang
Houmin Wang
SYSiming Yu
Siming Yu
WXWenyan Xue
Wenyan Xue
To address the complex challenges associated with multiple unmanned aerial vehicles (multi-UAVs) cooperative inspection in offshore wind farms, including limited sensing and communication ranges, constrained battery capacity, and round-trip mission requirements, this paper introduces an optimal coordinated trajectory method for multi-UAV based on a distributed differential game (DDG) framework. The approach explicitly accounts for energy consumption, incorporating round-trip requirements into a game-theoretic objective function to facilitate energy-aware trajectory planning. Each UAV operates based solely on local information from neighboring UAVs, enabling distributed decision-making that ensures collision-free coordination while optimizing global inspection time and overall energy efficiency. The convergence of the proposed strategy to a global Nash equilibrium (G-NE), as confirmed by theoretical analysis, ensures system-level coordination optimality subject to round-trip and energy constraints. Simulation results demonstrate that the method significantly enhances inspection efficiency and reduces task completion time by up to 18.7 % compared to conventional approaches, while guaranteeing the safe return of all UAVs.