The current study proposes a new metaheuristic algorithm based on the clan behavior of elephants, called elephant clan optimization (ECO), to solve structural optimization problems. This method is a new version of the previously developed algorithm; namely, the elephant herding optimization (EHO). While the EHO algorithm has been inspired by the behavior of elephants, the theory behind this method is based on the herding behavior of the elephants, and also the selection of random members to replace the worst members, which is far from the real-life behavior of this animal. Since elephants are animals with powerful memories and a high capability for learning, it seems that by accurately modeling the real-life behavior of this animal, a more powerful algorithm can be developed. The proposed ECO algorithm attempts to simulate the most essential individual and collective behaviors of elephants. The performance of the ECO method is evaluated by solving several structural optimization problems, including the size optimization of truss structures. The findings of the study confirm the reliable performance of the proposed ECO algorithm to expedite the convergence rate and achieve superior solutions in comparison with the EHO. Moreover, the ECO method produces better or very competitive results by consuming less computational effort compared to well-known metaheuristic methods.

目前的研究提出了一种基于大象氏族行为的新元启发式算法，称为大象氏族优化（ECO），以解决结构优化问题。该方法是之前开发的算法的新版本；即大象放牧优化（EHO）。虽然 EHO 算法的灵感来自大象的行为，但该方法背后的理论是基于大象的放牧行为，并且随机选择成员来替换最差的成员，这与现实生活中的行为相去甚远这种动物的。由于大象是具有强大记忆力和高学习能力的动物，似乎通过对这种动物的现实行为进行准确建模，可以开发出更强大的算法。提议的 ECO 算法试图模拟大象最重要的个人和集体行为。ECO 方法的性能是通过解决几个结构优化问题来评估的，包括桁架结构的尺寸优化。研究结果证实了所提出的 ECO 算法的可靠性能，与 EHO 相比，可以加快收敛速度​​并获得更好的解决方案。此外，与众所周知的元启发式方法相比，ECO 方法通过消耗更少的计算工作产生更好或非常有竞争力的结果。研究结果证实了所提出的 ECO 算法的可靠性能，与 EHO 相比，可以加快收敛速度​​并获得更好的解决方案。此外，与众所周知的元启发式方法相比，ECO 方法通过消耗更少的计算工作产生更好或非常有竞争力的结果。研究结果证实了所提出的 ECO 算法的可靠性能，与 EHO 相比，可以加快收敛速度​​并获得更好的解决方案。此外，与众所周知的元启发式方法相比，ECO 方法通过消耗更少的计算工作产生更好或非常有竞争力的结果。