关键词: 足球队训练算法, 动态适应度-距离平衡策略, 非独占搜索, FADs扰动, 工程设计

Abstract: A multi-strategy Football team training algorithm (MSFTTA) is proposed to address the problems of imbalance between global search and local exploitation capabilities and the tendency to fall into local optimization of Football team training algorithm. First, a dynamic fitness-distance balancing strategy is proposed to strike a balance between exploration and exploitation by guiding the training process through candidate solution scores. Second, the implementation of non-monopolize superiority and inferiority cointegration search in the individual extra training phase promotes individual independent exploration and improves the convergence accuracy of the algorithm in the later stages. Finally, the FADs perturbation strategy inspired by the ocean predator algorithm is introduced to simulate the unexpected situation of the race, increase the randomness and enhance the ability of the algorithm to escape from local extremes. By applying the CEC2017 function for experimental simulation, the results show that the proposed algorithm presents a significant improvement in both the optimization performance and search accuracy. In addition, the practicality and effectiveness of the improved algorithm are further verified by optimization analysis for two engineering examples. 

Key words: Football team training algorithm, dynamic fitness-distance balancing strategy, non-monopolize search, FADs perturbation, engineering design