浮点数编码改进遗传算法在平面度误差评定中的研究

发布时间：2019-05-19 18:41

【摘要】：随着智能制造系统的迅猛发展,应用元启发模式计算方法快速、准确地求解平面度误差值凸显出重大现实意义。为进一步提高平面度误差计算精度,研究了一种基于浮点数编码的改进遗传算法,在原有遗传算法的交叉变异基础之上,引入模拟退火思想,建立最小包容区域法的数学模型,通过计算机仿真获得了最佳适应度收敛曲线和平均适应度收敛曲线,优化结果表明相比传统遗传算法,平面度误差计算精度提高了33.67%。本算法采用浮点数编码、三段式交叉、转轮式选择和最优保存策略,借助模拟退火算法的局部搜索优势,提升了算法的整体性能,且更便于计算机编程,可进一步推广应用到智能测量仪器的其他高精度形位尺寸计算问题领域。
[Abstract]:With the rapid development of intelligent manufacturing system, it is of great practical significance to solve the flatness error accurately by using meta-heuristic mode calculation method. In order to further improve the accuracy of flatness error calculation, an improved genetic algorithm based on floating point coding is studied. on the basis of the cross variation of the original genetic algorithm, the simulated annealing idea is introduced to establish the mathematical model of the minimum inclusive region method. The optimal fitness convergence curve and the average fitness convergence curve are obtained by computer simulation. The optimization results show that the accuracy of flatness error calculation is 33.67% higher than that of the traditional genetic algorithm. The algorithm adopts floating-point coding, three-segment intersection, wheel selection and optimal preservation strategy. With the help of the local search advantages of simulated annealing algorithm, the overall performance of the algorithm is improved, and it is more convenient for computer programming. It can be further extended to other high precision form and position size calculation fields of intelligent measuring instruments.
【作者单位】：成都理工大学核技术与自动化工程学院;
【基金】：机器人,国家高技术863-809专题专家组成都理工大学机械工程创新团队(No.10912-JXTD201501)
【分类号】：TG83;TP18

【相似文献】