基于自适应的细菌觅食算法

摘要

针对细菌觅食（BFO）算法存在容易陷入局部最优、求解精度不高、收敛速度慢等问题，提出一种新的基于自适应的算法。算法主要对趋化和复制两个关键步骤进行改进，自适应地调整游动步长，并在复制操作中引入轮盘赌选择机制，使算法快速收敛到全局最优解以改善细菌觅食算法的性能。实验结果表明，提出的算法不仅收敛速度快，且求解精度高。%There are some problems in bacteria foraging optimization (BFO) algorithm, it is easy to fall in local optimum and it has relatively low accuracy and slow convergence speed. A new algorithm based on self-adaptative method was proposed to solve these problems. This paper mainly focused on improving two key steps of BFO, chemotaxis and reproduction. The swimming stepsize was adaptively adjusted to make the algorithm rapidly converge to the global optimum, and the roulette wheel selection was introduced into the reproduction step. Experimental results show that the proposed algorithm has high convergence speed and accuracy.