This paper presents a nature-inspired metaheuristic called Marine Predators Algorithm (MPA) and its application in engineering. The main inspiration of MPA is the widespread foraging strategy namely Lévy and Brownian movements in ocean predators along with optimal encounter rate policy in biological interaction between predator and prey. MPA follows the rules that naturally govern in optimal foraging strategy and encounters rate policy between predator and prey in marine ecosystems. This paper evaluates the MPA's performance on twenty-nine test functions, test suite of CEC-BC-2017, randomly generated landscape, three engineering benchmarks, and two real-world engineering design problems in the areas of ventilation and building energy performance. MPA is compared with three classes of existing optimization methods, including (1) GA and PSO as the most well-studied metaheuristics, (2) GSA, CS and SSA as almost recently developed algorithms and (3) CMA-ES, SHADE and LSHADE-cnEpSin as high performance optimizers and winners of IEEE CEC competition. Among all methods, MPA gained the second rank and demonstrated very competitive results compared to LSHADE-cnEpSin as the best performing method and one of the winners of CEC 2017 competition. The statistical post hoc analysis revealed that MPA can be nominated as a high-performance optimizer and is a significantly superior algorithm than GA, PSO, GSA, CS, SSA and CMA-ES while its performance is statistically similar to SHADE and LSHADE-cnEpSin. The source code is publicly available at: https://github.com/afshinfaramarzi/Marine-Predators-Algorithm, http://built-envi.com/portfolio/marine-predators-algorithm/, https://www.mathworks.com/matlabcentral/fileexchange/74578-marine-predators-algorithm-mpa, and http://www.alimirjalili.com/MPA.html.

本文介绍了一种自然启发式的元启发式方法，称为海洋捕食者算法（MPA）及其在工程中的应用。MPA的主要灵感是广泛的觅食策略，即海洋捕食者中的Lévy和Brownian运动，以及捕食者与猎物之间生物相互作用中的最佳遭遇率策略。MPA遵循在最佳觅食策略中自然支配的规则，并在海洋生态系统中的捕食者与猎物之间遇到速率策略。本文评估了MPA在29个测试功能，CEC-BC-2017测试套件，随机生成的景观，三个工程基准以及两个在通风和建筑节能方面的实际工程设计问题中的性能。将MPA与三类现有的优化方法进行了比较，包括（1）GA和PSO是研究最深入的元启发式算法；（2）GSA，CS和SSA是最近开发的算法；（3）CMA-ES，SHADE和LSHADE-cnEpSin是高性能优化器和IEEE CEC获奖者竞争。在所有方法中，与LSHADE-cnEpSin相比，MPA获得了第二名，并表现出非常具有竞争力的结果，LSHADE-cnEpSin是表现最好的方法，并且是CEC 2017竞赛的获胜者之一。事后统计分析表明，MPA可以被提名为高性能优化器，并且是一种比GA，PSO，GSA，CS，SSA和CMA-ES更好的算法，而统计上的性能类似于SHADE和LSHADE-cnEpSin。源代码可在以下位置公开获得：https：//github.com/afshinfaramarzi/Marine-Predators-Algorithm，http：//built-envi.com/portfolio/marine-predators-algorithm/，https：