Open Access

ARTICLE

MCPSFOA: Multi-Strategy Enhanced Crested Porcupine-Starfish Optimization Algorithm for Global Optimization and Engineering Design

Hao Chen¹, Tong Xu¹, Yutian Huang², Dabo Xin^1,*, Changting Zhong^1,3,*

1 School of Civil Engineering and Architecture, Hainan University, Haikou, China
2 Engineering Management Department, Hainan Provincial Water Conservancy and Hydropower Group Co., Ltd., Haikou, China
3 Department of Engineering Mechanics, State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment, Dalian University of Technology, Dalian, China

* Corresponding Authors: Dabo Xin. Email: ; Changting Zhong. Email:

(This article belongs to the Special Issue: AI-Enhanced Computational Mechanics and Structural Optimization Methods)

Computer Modeling in Engineering & Sciences 2026, 146(1), 16 https://doi.org/10.32604/cmes.2026.075792

Received 08 November 2025; Accepted 31 December 2025; Issue published 29 January 2026

Abstract

Optimization problems are prevalent in various fields of science and engineering, with several real-world applications characterized by high dimensionality and complex search landscapes. Starfish optimization algorithm (SFOA) is a recently optimizer inspired by swarm intelligence, which is effective for numerical optimization, but it may encounter premature and local convergence for complex optimization problems. To address these challenges, this paper proposes the multi-strategy enhanced crested porcupine-starfish optimization algorithm (MCPSFOA). The core innovation of MCPSFOA lies in employing a hybrid strategy to improve SFOA, which integrates the exploratory mechanisms of SFOA with the diverse search capacity of the Crested Porcupine Optimizer (CPO). This synergy enhances MCPSFOA’s ability to navigate complex and multimodal search spaces. To further prevent premature convergence, MCPSFOA incorporates Lévy flight, leveraging its characteristic long and short jump patterns to enable large-scale exploration and escape from local optima. Subsequently, Gaussian mutation is applied for precise solution tuning, introducing controlled perturbations that enhance accuracy and mitigate the risk of insufficient exploitation. Notably, the population diversity enhancement mechanism periodically identifies and resets stagnant individuals, thereby consistently revitalizing population variety throughout the optimization process. MCPSFOA is rigorously evaluated on 24 classical benchmark functions (including high-dimensional cases), the CEC2017 suite, and the CEC2022 suite. MCPSFOA achieves superior overall performance with Friedman mean ranks of 2.208, 2.310 and 2.417 on these benchmark functions, outperforming 11 state-of-the-art algorithms. Furthermore, the practical applicability of MCPSFOA is confirmed through its successful application to five engineering optimization cases, where it also yields excellent results. In conclusion, MCPSFOA is not only a highly effective and reliable optimizer for benchmark functions, but also a practical tool for solving real-world optimization problems.

---

Keywords

---