Peng Yao

To address the challenges of Unmanned Aerial Vehicles (UAVs) performing missions such as detection, reconnaissance, and combat in environments characterized by complex mountainous terrain and dense threats, this paper establishes a multi-objective path planning model integrating threat zones. The model incorporates radar detection zones and no-fly zones as distinct threat constraints, aiming to optimize three objective functions: path length, detection threat, and path smoothness. On the algorithmic front, an Improved Multi-Objective Artificial Bee Colony (IMOABC) algorithm is proposed. Several strategic enhancements are introduced, including a global optimization update mechanism, a weak elite greedy selection operator, an archive-based intelligent scout bee strategy, and a robustness-driven path repair mechanism. These enhancements effectively tackle the low search efficiency typically encountered in high-dimensional non-convex terrains and strike a superior balance between global exploration and local exploitation, thereby preventing the algorithm from converging prematurely to local optima. To validate the proposed method, extensive experiments were conducted across nine challenging scenarios characterized by urban structures, karst caves, and mountainous terrains. Comprehensive comparisons with three state-of-the-art multi-objective optimization algorithms reveal that the IMOABC achieves superior performance regarding Hypervolume (HV), Friedman Average Rank (FAR), and computational time. The empirical results demonstrate that the proposed algorithm can robustly generate Pareto-optimal solution sets, providing highly safe and feasible flight paths for UAVs in complex environments. The study exhibits exceptional robustness and significant potential for engineering applications, offering a novel methodology for three-dimensional UAV path planning in intricate environments.

The scheduling of harbor tugboats is a crucial task in port operations, aiming to optimize resource allocation and reduce operational costs, including fuel consumption of tugboats and the time cost of vessels waiting for operations. Due to the complexity of the port environment, traditional scheduling methods, often based on experience and practice, lack scientific and systematic decision support, making it difficult to cope with real-time changes in vessel dynamics and environmental factors. This often leads to scheduling delays and resource waste. To address this issue, this study proposes a mathematical model based on fuzzy programming, accounting for the uncertainty of the arrival time of target vessels. Additionally, we introduce the NRPER-DDPG algorithm (DDPG Algorithm with Prioritized Experience Replay and Noise Reduction), which combines a prioritized replay mechanism with a decaying noise strategy based on the DDPG algorithm. This approach optimizes the time for tugboats to reach the task location as a continuous action space, aiming to minimize the total system cost and improve scheduling efficiency. To verify the effectiveness of the mathematical model and algorithm, this study conducted experimental validation. Firstly, the optimal algorithm hyperparameter combinations were adjusted through random examples to ensure the stability and reliability of the algorithm. Subsequently, large-scale examples and actual port cases were used to further verify the performance advantages of the algorithm in practical applications. Experimental results demonstrate that the proposed mathematical model and algorithm significantly reduce system costs and improve scheduling efficiency, providing new insights and methods for the sustainable development of port operations.

With the continuous prosperity of maritime transportation on a global scale and the resulting escalation in port trade volume, tugboats assume a pivotal role as essential auxiliary tools influencing the ingress and egress of vessels into and out of ports. As a result, the optimization of port tug scheduling becomes of paramount importance, as it contributes to the heightened efficiency of ship movements, cost savings in port operations, and the promotion of sustainable development within the realm of maritime transportation. However, a majority of current tugboat scheduling models tend to focus solely on the maximum operational time. Alternatively, the formulated objective functions often deviate from real-world scenarios. Furthermore, prevailing scheduling methods exhibit shortcomings, including inadequate solution accuracy and incompatibility with integer programming. Consequently, this paper introduces a novel multi-objective tugboat scheduling model to align more effectively with practical considerations. We propose a novel optimization algorithm, the Improved Grey Wolf Optimization (IGWO), for solving the tugboat scheduling model. The algorithm enhances convergence performance by optimizing convergence parameters and individual updates, making it particularly suited for solving integer programming problems. The experimental session designs several scale instances according to the reality of the port, carries out simulation experiments comparing several groups of intelligent algorithms, verifies the effectiveness of IGWO, and verifies it in the comprehensive port area of Huanghua Port to get the optimal scheduling scheme of this port area, and finally gives management suggestions to reduce the cost of tugboat operation through sensitivity analysis.