Gu Yanzhao, Wei Junhao, Li Zikun, Lu Baili, Pan Shirou, Cheong Ngai
Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China.
School of Economics and Management, South China Normal University, Guangzhou 510006, China.
PLoS One. 2025 Sep 3;20(9):e0322494. doi: 10.1371/journal.pone.0322494. eCollection 2025.
This paper analyzes the shortcomings of the traditional Whale Optimization Algorithm (WOA), mainly including the tendency to fall into local optima, slow convergence speed, and insufficient global search ability for high-dimensional and complex optimization problems. An improved Whale Optimization Algorithm (GWOA) is proposed to overcome these issues. By integrating several improvement strategies, such as adaptive parameter adjustment, enhanced prey encircling, and sine-cosine search strategies, GWOA significantly enhances global search ability and convergence efficiency. However, GWOA increases computational complexity, which may lead to longer computation times when handling large-scale problems. It may also fall into local optima in high-dimensional cases. Several experiments were conducted to verify the effectiveness of GWOA. First, 23 classic benchmark functions were tested, covering unimodal, multimodal, and compositional optimization problems. GWOA was compared with other basic metaheuristic algorithms, excellent WOA variants, and the latest algorithms. Then, a comparative scalability experiment is performed on GWOA. The experimental results showed that GWOA achieved better convergence speed and solution accuracy than other algorithms in most test functions, especially in multimodal and compositional optimization problems, with an Overall Efficiency (OE) value of 74.46%. In engineering optimization problems, such as pressure vessel design and spring design, GWOA effectively reduced costs and met constraints, demonstrating stronger stability and optimization ability. In conclusion, GWOA significantly improves the global search ability, convergence speed, and solution stability through multi-strategy integration. It shows great potential in solving complex optimization problems and provides an efficient tool for engineering optimization applications.
本文分析了传统鲸鱼优化算法（WOA）的缺点，主要包括容易陷入局部最优、收敛速度慢以及对高维复杂优化问题的全局搜索能力不足。为克服这些问题，提出了一种改进的鲸鱼优化算法（GWOA）。通过集成自适应参数调整、增强猎物包围和正弦余弦搜索策略等多种改进策略，GWOA显著提高了全局搜索能力和收敛效率。然而，GWOA增加了计算复杂度，在处理大规模问题时可能导致计算时间变长。在高维情况下它也可能陷入局部最优。进行了多项实验以验证GWOA的有效性。首先，测试了23个经典基准函数，涵盖单峰、多峰和组合优化问题。将GWOA与其他基本元启发式算法、优秀的WOA变体以及最新算法进行了比较。然后，对GWOA进行了比较扩展性实验。实验结果表明，在大多数测试函数中，GWOA比其他算法具有更好的收敛速度和求解精度，尤其是在多峰和组合优化问题中，总体效率（OE）值为74.46%。在压力容器设计和弹簧设计等工程优化问题中，GWOA有效降低了成本并满足了约束条件，展现出更强的稳定性和优化能力。总之，GWOA通过多策略集成显著提高了全局搜索能力、收敛速度和求解稳定性。它在解决复杂优化问题方面显示出巨大潜力，并为工程优化应用提供了一种高效工具。
