This paper develops a novel population-based evolutionary method called cooperation search algorithm (CSA) to address the complex global optimization problem. Inspired by the team cooperation behaviors in modern enterprise, the CSA method randomly generates a set of candidate solutions in the problem space, and then three operators are repeatedly executed until the stopping criterion is met: the team communication operator is used to improve the global exploration and determine the promising search area; the reflective learning operator is used to achieve a comprise between exploration and exploitation; the internal competition operator is used to choose solutions with better performances for the next cycle. Firstly, three kinds of mathematical optimization problems (including 24 famous test functions, 25 CEC2005 test problems and 30 CEC2014 test problems) are used to test the convergence speed and search accuracy of the CSA method. Then, several famous engineering optimization problems (like Gear train design, Welded beam design and Speed reducer design) are chosen to testify the engineering practicality of the CSA method. The results in different scenarios demonstrate that as compared with several existing evolutionary algorithms, the CSA method can effectively explore the decision space and produce competitive results in terms of various performance evaluation indicators. Taking the 23th CEC2005 function as the example, the best results obtained by the proposed method are improved by 23.03%, 31.64% and 36.83% compared with PSO, SCA and GSA. Thus, an effective tool is provided for solving the complex global optimization problems.

本文开发了一种新的基于种群的进化方法，称为合作搜索算法（CSA），以解决复杂的全局优化问题。受现代企业团队合作行为的启发，CSA方法在问题空间中随机生成一组候选解，然后重复执行三个操作员，直到满足停止准则为止：使用团队沟通操作员来改进全局探索并确定有前途的搜索区域；反射型学习算子用于实现探索与开发之间的包含；内部竞争运营商被用来为下一个周期选择性能更好的解决方案。首先，三种数学优化问题（包括24个著名的测试函数，使用25个CEC2005测试问题和30个CEC2014测试问题来测试CSA方法的收敛速度和搜索准确性。然后，选择了几个著名的工程优化问题（例如齿轮系设计，焊接梁设计和减速器设计）来证明CSA方法的工程实用性。在不同场景下的结果表明，与几种现有的进化算法相比，CSA方法可以有效地探索决策空间并在各种绩效评估指标方面产生竞争性结果。以第23届CEC2005为例，与PSO，SCA和GSA相比，该方法获得的最佳结果分别提高了23.03％，31.64％和36.83％。因此，提供了一种有效的工具来解决复杂的全局优化问题。