Carpenter Optimization Algorithm: A Human-inspired Metaheuristic for Robust and Efficient Constrained Optimization

Abstract

This paper introduces the Carpenter Optimization Algorithm (COA), a novel human-inspired metaheuristic designed to efficiently solve complex, high-dimensional, and constrained optimization problems. COA draws direct inspiration from the systematic behaviors of skilled carpenters, who initially perform broad cuts to explore raw materials and subsequently execute precise refinements to achieve high-quality outcomes. These behaviors are mathematically mapped into exploration and exploitation phases, where stochastic global modifications mimic broad exploratory actions, and targeted incremental adjustments refine promising solutions. Unlike traditional metaheuristics, COA achieves a robust balance between exploration and exploitation while requiring minimal control parameters, enhancing both adaptability and computational efficiency. The algorithm was rigorously evaluated on 22 constrained benchmark functions from the CEC 2011 suite and compared against nine well-established metaheuristics. The results demonstrate that COA consistently outperforms all competitors in terms of solution quality, convergence speed, stability, and robustness, achieving the best mean, median, and best values across all test problems. Statistical analyses, including standard deviation, rank-based evaluation, and pairwise Wilcoxon tests, confirm the significance and reproducibility of these results, while boxplot visualizations highlight controlled variability and narrow interquartile ranges, even for large-scale and multimodal problems. The findings suggest that COA’s behaviorally grounded design provides a practical and explainable framework for real-world optimization tasks. Future research directions include extending COA to multi-objective, dynamic, and large-scale industrial problems, integrating hybrid strategies or adaptive mechanisms, and conducting theoretical analyses of convergence and parameter sensitivity. Overall, COA represents a promising addition to the metaheuristic optimization landscape, offering both conceptual clarity and high practical performance. This article is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. License details: https://creativecommons.org/licenses/by-sa/4.0/