计算机集成制造系统 ›› 2020, Vol. 26 ›› Issue (8): 2060-2072.DOI: 10.13196/j.cims.2020.08.006

• 当期目次 • 上一篇    下一篇

碳排放约束下基于特征的刀具选配与切削参数集成优化

田长乐1,周光辉1,2,张俊杰1,王闯3   

  1. 1.西安交通大学机械工程学院
    2.西安交通大学机械制造系统工程国家重点实验室
    3.西安邮电大学物联网与两化融合研究院
  • 出版日期:2020-08-31 发布日期:2020-08-31
  • 基金资助:
    国家自然科学基金资助项目(51575435)。

Integration optimization of tool selection and cutting parameters based on machining features considering carbon emissions

  • Online:2020-08-31 Published:2020-08-31
  • Supported by:
    Project supported by the National Natural Science Foundation,China(No.51575435).

摘要: 针对传统选择刀具与切削参数采用的分阶段串行决策方法,因忽略其内在关联导致选择出的刀具和切削参数优化程度不高的问题,以加工碳排放和加工成本为综合优化目标,引入刀具磨损对切削参数和碳排放的影响,提出一种基于加工特征的刀具选配与切削参数集成优化模型。为有效解算该模型,设计了基于K近邻和多目标粒子群混合优化算法,得到了优化的切削刀具与切削参数。采用企业实际加工案例验证了所提模型与算法的正确性和有效性。所提集成优化方法可为低碳制造环境下合理选择零部件加工的切削刀具和切削参数提供理论和方法支持。

关键词: 刀具选配, 切削参数优化, 集成优化, K近邻算法, 多目标粒子群优化算法

Abstract: Reasonable selections of cutting tools and cutting parameters are one of the key factors to determine the carbon emissions and costs of parts.Aiming at the problem that the traditional researches ignored the complex relationships between tool selection and cutting parameters optimization,which resulted in local optimal solutions,the carbon emissions and costs were taken as the optimization objectives,and an integrated optimization model of tool selection and cutting parameters based on machining features was proposed by introducing the influence factors of tool wear on cutting parameters and carbon emissions.To solve the model effectively,a bi-level hybrid algorithm based on K-nearest neighbor and multi-objective particle swarm optimization was designed,and the optimized cutting tool and cutting parameters were obtained.The correctness and validity of the proposed method were verified by an actual manufacturing case.The proposed integrated optimization method could provide theoretical and methodological support for the rational selection of cutting tools and cutting parameters in low carbon manufacturing environment.

Key words: tool selection, cutting parameters optimization, integration optimization, K-nearest neighbor algorithm, multi-objective particle swarm optimization

中图分类号: