改进蜂群算法及其在圆度误差评定中的应用

Research on Roundness Error Evaluation Based on the Improved Artificial Bee Colony Algorithm

针对基本人工蜂群算法(Artificial bee colony algorithm,ABC)的缺点,提出一种改进人工蜂群算法(Improved artificial bee colony algorithm,IABC),并应用于圆度误差最小区域评定中。该改进算法利用信息熵初始化种群,增强种群的多样性,并在引领蜂和跟随蜂搜索阶段,提出一种新的搜索策略,平衡算法的探索与开发能力。详细阐述IABC算法的基本原理与实现步骤,给出圆度误差满足最小包容区域条件的优化目标函数和收益度函数。通过基准测试函数验证IABC算法的有效性和准确性;通过对由三坐标机测得的多组测量数据进行圆度误差评定试验,结果表明IABC算法的评定精度优于最小二乘法、遗传算法以及粒子群算法等其他优化算法,且在求解质量和稳定性上优于ABC算法,验证了IABC算法不仅正确,而且适用于圆度误差的评定优化。

According to the weakness of artificial bee colony algorithm（ABC）, a new improved artificial bee colony algorithm（IABC） is presented and is applied to evaluate roundness error in minimum zone. The improved algorithm use information entropy to initialize population to enhance diversity, besides, a new search strategy is proposed in the stage of employed bees and onlookers. The fundamentals and implementation techniques of IABC are discussed. The optimal target function for roundness error evaluation and the fitness function of IABC are introduced. A series of classical test functions are selected in the experiments, the simulation results verifies the feasibility of IABC. Through several algorithms to measure some same sets of data for roundness error evaluation experiment, the results show that the evaluation precision of IABC is better than least square method（LSM）、genetic algorithm（GA）、particle swarm optimization（PSO） and some other algorithms, and it is superior to ABC in optimization of efficiency, quality and stability, the experiment results also show that IABC is correct and is a unified approach for roundness error evaluations.