论文部分内容阅读
提出了一种改进单目标自适应遗传算法(MSAGA)。针对自适应搜索遗传算法(ASNSGA)遗传代数设置不合理与单目标非支配排序自适应遗传算法(SONSAGA)因非均匀种群而引起拟合新误差的缺陷,MSAGA算法通过临界遗传代数与变量取值区间的自适应调整,同时提高了计算精度与计算速度。将MSAGA算法应用于车削优化,实例结果显示不仅优于标准遗传算法(GA)与SONSAGA算法的优选值,而且计算速度比SONSAGA算法提高了75.9669%。结果证明MSAGA算法用于车削用量参数的优化是有效的。MSAGA算法能快速自适应获得满足给定精度的变量优选值,为车削优化提出了新思路。
An improved single-objective adaptive genetic algorithm (MSAGA) is proposed. Aiming at the defect of fitting new error due to non-uniform population by setting unreasonable and single-objective non-dominated adaptive genetic algorithm (ASNSGA) for genetic algorithm of adaptive search genetic algorithm (ASNSGA), MSAGA algorithm uses the critical genetic algebra and variable value Interval adaptive adjustment, while improving the calculation accuracy and speed. The MSAGA algorithm is applied to turning optimization. The results show that the proposed algorithm not only outperforms the standard genetic algorithm (GA) and SONSAGA algorithm, but also increases the computational speed by 75.9669% compared with SONSAGA algorithm. The results show that the MSAGA algorithm is effective in optimizing the turning parameters. The MSAGA algorithm can quickly get the optimal value of variable to meet the given precision and brings forward a new idea for turning optimization.