基于代理模型的风机主轴疲劳优化  

Fatigue optimization of fan main shaft based on the surrogate model

作　　者：唐林 曾志 曾宇 马奔奔 杜宗亮[2] TANG Lin;ZENG Zhi;ZENG Yu;MA Benben;DU Zongliang(Research and Development Center,Dongfang Electric Wind Power Co.,Ltd.,Deyang 618000,Sichuan,China;State Key Laboratory of Structural Analysis for Industrial Equipment,Department of EngineeringMechanics,Dalian University of Technology,Dalian 116023,Liaoning,China)

机构地区：[1]东方电气风电股份有限公司风电研究设计院,四川德阳618000 [2]大连理工大学工程力学系工业装备结构分析国家重点实验室,辽宁大连116023

出　　处：《中国工程机械学报》2024年第6期767-772,共6页Chinese Journal of Construction Machinery

基　　金：中央高校研究基金资助项目(DUT20RC(3)020);大连人才创新计划资助项目(2020RQ099)。

摘　　要：主轴作为风力发电机组中的重要传动部件,合理的结构设计对于保证风机具有足够的运行寿命、可靠的载荷传递以及制造成本经济性有着至关重要的作用。在主轴设计中经常面临静强度满足要求,但局部区域疲劳寿命不足的难题。本文运用子模型技术,以主轴疲劳寿命为目标,以结构外形尺寸为约束条件,建立二阶响应面代理模型,并运用遗传算法对模型寻优求解。结果表明:经过局部优化后主轴疲劳寿命提高了将近30倍,节段重量下降了21.38%。本文提出的方法可以极大地提高主轴的疲劳性能优化效率,对同类结构疲劳优化及轻量化有一定的指导意义。Main shaft is an important driving component of wind turbine.A reasonable design of the main shaft plays a vital role in ensuring that the wind turbine has a sufficient operating life,reliable load transfer and economic manufacturing cost.The design of main shaft often faces the situation that the limit strength meets the requirements but the local fatigue life is insufficient.In this paper,the submodel technique is used to establish a second-order response surface surrogate model with the main shaft fatigue life as the goal and the structural configuration as the constraint condition,and the genetic algorithm is used to optimize the model.The results show that the fatigue life of the main shaft is increased by nearly 30 times and the segment weight is reduced by 21.38%in the optimized design.The method proposed in this paper can greatly improve the optimization efficiency of the fatigue performance of the main shaft,and has certain guiding significance for the fatigue optimization and lightweight of similar structures.

关 键 词：主轴 疲劳 子模型 优化设计 代理模型 遗传算法 

分 类 号：TH122[机械工程—机械设计及理论]