改进KnEA的二级斜齿圆柱齿轮减速器优化设计  

Optimum Design of Improved KnEA Two-Stage Helical Cylindrical Gear Reducer

作　　者：高淑芝[1] 仰雷雨 张义民[1] GAO Shu-zhi;YANG Lei-yu;ZHANG Yi-min(Institute of Equipment Reliability,Shenyang University of Chemical Technology,Liaoning Shenyang 110142,China;College of Information Engineering,Shenyang University of Chemical Technology,Liaoning Shenyang 110142,China)

机构地区：[1]沈阳化工大学装备可靠性研究所,辽宁沈阳110142 [2]沈阳化工大学信息工程学院,辽宁沈阳110142

出　　处：《机械设计与制造》2024年第5期257-261,共5页Machinery Design & Manufacture

基　　金：NSFC-国家自然科学重点基金—辽宁联合基金(U1708254);辽宁省特聘教授(No.[2018]3533)。

摘　　要：在实际工程中,复杂的多目标问题是导致优化结果收敛性和多样性损失的重要因素。为了提高优化算法在复杂问题中维持解多样性和收敛性平衡的能力,提出了基于KnEA(A Knee Point Driven Evolutionary Algorithm)的辅助点进化算法。首先,该算法借助进化过程中有明显趋势的拐点作为邻域空间的中心;其次,通过分析邻域空间中的拐点与上一代拐点之间的关系,从侧面来定量分析了邻域空间的潜力;再次,为了解决对复杂问题优化过程中收敛性不足的缺陷,提出了根据邻域空间的进化潜力来增加辅助点的策略,进一步地提高了进化过程中的空间搜索能力。在种群的环境选择中,优先选择拐点和辅助点进化下一代,以此平衡种群的收敛性和多样性。将该算法在多目标测试问题上与流行的算法进行了比较,实验结果表明提出的算法在多目标问题优化中有明显优势。最后,将该算法应用到二级斜齿圆柱齿轮减速器优化设计当中。In practical engineering,the complex multi-objective problem is an important factor leading to the loss of convergence and diversity of optimization results.In order to improve the ability of optimization algorithm to maintain the balance of solution diversity and convergence in complex problems,an auxiliary point evolutionary algorithm based on KnEA(A Knee Point Driven Evolutionary Algorithm)is proposed.Firstly,the inflection point with obvious trend in the evolution process is used as the center of neighborhood space;Secondly,by analyzing the relationship between the inflection points in neighborhood space and the in-flection points of the previous generation,the potential of neighborhood space is quantitatively analyzed;Thirdly,in order to solve the problem of insufficient convergence in the optimization process of complex problems,the strategy of increasing auxiliary points according to the evolution potential of neighborhood space is proposed,which further improves the spatial search ability in the evolution process.In order to balance the convergence and diversity of the population,the inflection point and auxiliary point are preferred to evolve the next generation.The experimental results show that the proposed algorithm has obvious advantages in multi-objective optimization.Finally,the algorithm is applied to the optimal design of two-stage helical cylindrical gear reducer.

关 键 词：多目标优化 收敛性 拐点 齿轮减速器 

分 类 号：TH16[机械工程—机械制造及自动化] TP18[自动化与计算机技术—控制理论与控制工程]