This study proposed an improved sine–cosine algorithm (SCA) for global optimization tasks. The SCA is a meta-heuristic method ground on sine and cosine functions. It has found its application in many fields. However, SCA still has some shortcomings such as weak global search ability and low solution quality. In this study, the chaotic local search strategy and the opposition-based learning strategy are utilized to strengthen the exploration and exploitation capability of the basic SCA, and the improved algorithm is called chaotic oppositional SCA (COSCA). The COSCA was validated on a comprehensive set of 22 benchmark functions from classical 23 functions and CEC2014. Simulation experiments suggest that COSCA’s global optimization ability is significantly improved and superior to other algorithms. Moreover, COSCA is evaluated on three complex engineering problems with constraints. Experimental results show that COSCA can solve such problems more effectively than different algorithms.

中文翻译：

---

求解全局优化问题的混沌对立正余弦方法

本研究为全局优化任务提出了一种改进的正弦-余弦算法（SCA）。SCA 是一种基于正弦和余弦函数的元启发式方法。它已在许多领域得到应用。然而，SCA 仍然存在全局搜索能力弱、解质量低等缺点。本研究利用混沌局部搜索策略和基于对立的学习策略来加强对基本SCA的探索和开发能力，改进后的算法称为混沌对立SCA（COSCA）。COSCA 在来自经典 23 个函数和 CEC2014 的 22 个基准函数的综合集上进行了验证。仿真实验表明，COSCA 的全局优化能力显着提高，优于其他算法。而且，COSCA 针对三个具有约束的复杂工程问题进行评估。实验结果表明，COSCA 可以比不同的算法更有效地解决此类问题。