封闭周转轮系动态优化设计.pdfVIP

23 9 Vol. 23 No.9 2004 9 MECHANICAL SCIENCE AND T ECHNOLOGY September 2004 : 1003-8728(2004) 09-1131-04 1, 2 2 韩继光 , 王贵成 1 2 ( , 221116; , 212013) :利用 P 神经网络极强的非线性映射功能, 成功地建立了封闭周转轮 的设计变量与模态柔度之间非线性 映射的3 层 P 神经网络模型, 解决了动态优化设计时目标函数难以建立的难题, 使非常复杂的动态优化问题变得 十分简单利用本文所提出的混合离散变量遗传算法对封闭周转轮 进行了动态优化设计, 并对优化后的设计方 案进行了动态特性分析,通过对比可以看出,优化后的设计方案不但动态特性有了较大提高, 其重量也有所下降 :封闭周转轮 ; 动态优化设计; 神经网络;遗传算法 :TH112 :A Dynamics Optimization Design of Closed Epicyclic Gear Trains 1,2 2 HAN J-i guang , WANG Gu-i cheng 1 2 ( Xuzhou Normal University, Xuzhou 221116; Jiangsu University, Zhenjiang 212013) Abstract: T he intensive nonlinear mapping function of P neural net is applied successfully in establish- ing the nonlinear mapping three-layer P neural net relationship between the design variables and mode flexibility of closed epicyclic gear trains. So, the problem that objective function is hard to establish in dynamic optimization is solved, and this makes some complex dynamic optimization very simple. A closed epicyclic gear train is dynamically optimized by means of the genetic algorithm with mixing dis- crete variables. The dynamic characteristics of the optimized design are analyzed. It is obvious that in the optimized design not only the dynamic characteristics are improved remarkably but also its weight is reduced. Key words: Closed epicyclic gear trains; Dynamics optimization design; Neural net; Genetic algorithm , , [ 2] ,