基于非线性自适应度函数的遗传算法求取自由曲面最大主曲率研究  

Research in Calculation of Principal Curvature of Free-form Surface Based on Non-linear Automatic Fitness Function of Genetic Algorithm

作　　者：赵世田[1] 付莹莹[1] 曾勇[1] 郑雷[1] 周博[1] Zhao Shitian;Fu Yingying;Zeng Yong;Zheng Lei;Zhou Bo(School of Mechanical Engineering,UGS College,Yancheng Institute of Technology,Yancheng 224051,China)

机构地区：[1]盐城工学院机械工程学院优集学院,江苏盐城224051

出　　处：《南京师范大学学报（工程技术版）》2018年第3期19-24,共6页Journal of Nanjing Normal University(Engineering and Technology Edition)

基　　金：国家自然科学基金(51305379);江苏省"青蓝工程"项目

摘　　要：针对自由曲面最大主曲率求取问题及其主曲率的特点,设计了一种改进的遗传算法非线性自适应度函数,并给出了种群个体的选择及复制新规则.通过Schaffer函数进行测试,并用于自由曲面最大主曲率求取,实例验证表明算法可以稳定、准确地求取到自由曲面上的全局最大主曲率,比较曲面离散法的计算量不足1/3,极大地提高了计算效率.Improved genetic algorithm（IGA） is proposed aiming at the calculation of maximum principal curvature of freeform surface. A novel non-linear automatic fitness function is designed according to the features of the principal curvature, and new selection rules of the units to be selected are presented. The IGA is tested through the Sehaffer function and applied to the maximum principal curvature calculation of free-form surface. Verification example shows that the maximum principal curvature of the freeform surface can be calculated accurately and stably by the IGA. The number of calculation of the points is less than one third of that of the free-form surface discrete method. The efficiency of computation is improved greatly.

关 键 词：非线性自适应度函数 遗传算法 最大主曲率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]