MYIGWO: A grey wolf optimizer with dual mutation and chaotic adaptive neighborhood for engineering problems and path planning

HY Zhao and K Zhang and XD Li and J Jin, ADVANCES IN ENGINEERING SOFTWARE, 211, 104044 (2025).

DOI: 10.1016/j.advengsoft.2025.104044

Metaheuristic algorithms are widely recognized as valuable optimization tools in numerous real-world applications due to their strong global search abilities, adaptability, and robustness. The grey wolf optimizer (GWO) is a widely adopted classical algorithm in this field, with IGWO representing a prominent improved version. To overcome the shortcomings of IGWO in global exploration, the imbalance between exploitation and exploration, and the static nature of neighbor selection in the DLH strategy, this paper introduces a novel metaheuristic algorithm called MYIGWO. The algorithm integrates a dual mutation strategy, adaptively selecting mutated individuals via differential random perturbations. By ranking individuals according to fitness, Cauchy mutation is applied to some lower performing individuals to strengthen global exploration, while the remaining selected individuals are subjected to polynomial mutation to enhance convergence speed and the ability to avoid local optima. Additionally, a directional correction is introduced to the mutated individuals to stabilize the mutation outcomes. Lastly, the DLH strategy's neighbor radius is dynamically adjusted using chaotic mapping, enabling flexible neighbor selection. The optimization performance of MYIGWO was systematically evaluated using multiple performance metrics, and MYIGWO was compared with eighteen advanced meta-heuristic algorithms on multiple benchmark test sets. Moreover, MYIGWO was applied to four classical engineering optimization problems and robot path planning task. The results show that MYIGWO exhibits significant performance advantages in all experiments. In particular, it showed significant improvements in the global optimal solution search capability over the original algorithm. We make the code publicly available at: https://github.com/zhy1109/MYIGWO.

Return to Publications page