论文部分内容阅读
针对人工鱼群算法(AFSA)存在收敛速度慢和寻优精度低等问题,本文提出了一种改进人工鱼群算法(IAFSA).该算法中的人工鱼能够根据鱼群当前状态调整自身的视野和步长来平衡局部搜索和全局搜索.此外,算法中还加入了引导行为,即人工鱼在觅食行为未发现更优的位置时,当前人工鱼向最优人工鱼移动一步.仿真结果表明,改进人工鱼群算法在收敛速度、寻优精度和克服局部极值等方面有很大优势.本文将改进鱼群算法应用时滞系统的辨识中,辨识结果表明改进算法能获取被控对象的精准数学模型,并具有较强的抗干扰能力.
In order to solve the problem of low convergence rate and low precision of AFSA, an improved artificial fish school algorithm (IAFSA) is proposed in this paper. The artificial fish in this algorithm can adjust its own field of vision according to the current status of fish schools And step length to balance the local search and the global search.In addition, the algorithm also incorporates the guiding behavior that the artificial fish move to the optimal artificial fish when the artificial fish has not found a better position in the foraging behavior.The simulation results show , The improved artificial fish swarm algorithm has great advantages in terms of convergence speed, optimization accuracy and overcoming local extremum etc. In this paper, we will improve the identification of fish-swarm algorithm using time-delay system, and the recognition results show that the improved algorithm can obtain the controlled object Accurate mathematical model, and has strong anti-interference ability.