基于改进多元宇宙算法的零件平面度测量研究
DOI:
CSTR:
作者:
作者单位:

(成都工业职业技术学院装备制造学院,四川 成都 610218)

作者简介:

熊保玉(1980-),男,硕士,高级工程师/ 副教授,主要从事机械产品设计与制造、智能控制方面的研究.

通讯作者:

中图分类号:

基金项目:

四川省教育厅科研项目(18ZB0046)资助项目 (成都工业职业技术学院装备制造学院,四川 成都 610218)


Flatness measurement of parts based on improved multi verse optimization
Author:
Affiliation:

(Chengdu Vocational & Technical College of Industry Equipment Manufacturing Ins titute,Chengdu 610218,China)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了提高零件平面度测量结果,采用改进多元宇 宙算法。首先建立零件平面度测量 模型,设置非线性最优化问题的目标函数;接着基于对数函数对多元宇宙算法虫洞概率调整 , 调整后的虫洞概率随着迭代次数的增加,物体穿越虫洞的机会增加,从而加速了宇宙物体的 移动,提高了算法的搜索性能;然后基于指数函数对宇宙算法移动步长优化,在迭代初期具 有较大值使得宇宙能够以较快速度进行全局探索,迭代后期具有较小值使得宇宙能够慢速进 行局部开发,提升算法探索、开发能力;最后给出了算法流程。实例验证结果表明改进多元 宇宙算法测量误差平均值为 5.212μm,相比LSM、PSO、GA、DE、ANN 算法分别减少了37.63% 、33.61%、27.51%、19.41%、10.17%,测量所需时间为3.282 s,分 别减少了36.95%、30.33%、26.11%、18.52%、12.74%,明显优于 其它算法,测量效果较好。

    Abstract:

    In order to improve the flatness measurement results of parts,the imp roved multi universe algorithm is proposed.Firstly,the flatness measurement mo del of parts is established,and the objective function of nonlinear optimizatio n problem is set.Secondly,the wormhole probability of multi verse optimization is adjusted based on logarithmic function,with the iteration times,the probabili ty of objects crossing wormhole is increased,so that accelerating the movement of verse and improving the search performance.Thirdly,the moving step length of multi verse is optimized based on exponential function,the verse is explored glo bally fast at the beginning of the iteration using large value,while developed l ocally slowly using smaller value at the late stage,so that enhancing the abilit y of exploration and development.Finally,the process is given.The experimental r esults show that the average measurement error of the improved multi universe al gorithm is 5.212μ m,which is 37.63%,33.61%,27.51%,19.41% and 10.17% less t han LSM,PSO,GA,DE and ANN algorithm respectively.The measurement time is 3.282s,which is 36.95%,30.33%,26.11%,18.52% and 12.74% less than LSM,PSO,GA,DE an d ANN algorithm respectively,it is better than other algorithms obviously.

    参考文献
    相似文献
    引证文献
引用本文

熊保玉.基于改进多元宇宙算法的零件平面度测量研究[J].光电子激光,2021,32(3):251~256

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-10-15
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2021-03-11
  • 出版日期:
文章二维码