摘要
随着现有工程问题高非线性、高计算复杂度、高维度等特征的凸显和对低成本高保真度仿真模型的要求,基于多学科耦合的工程结构多目标优化设计求解难度显著提高,且计算量大,这一问题引起了广泛的研究。针对这一挑战,本文提出了一种基于混合指标自适应采样代理模型实现工程结构多目标优化设计的方法。为降低优化设计成本,综合考虑了优化设计空间的全局探索与局部开发特征,提出了一种基于Voronoi区域划分的混合指标自适应采样方法,用于全局代理模型构建,经与不同案例及方法对比测试,在保证精度的前提下显著降低了样本数量;为实现工程结构多目标优化问题的求解,提出了一种基于优势面旋转投影和区域划分新型拥挤度算子的多目标优化设计NSGA-Ⅱ-RD(Improvednon-dominatedsortinggenetic algorithmⅡbased on a rotation and density operator,NSGA-Ⅱ-RD)算法,经与不同算法对比测试,该方法求解收敛速度更快且计算结果准确。最后,将提出的混合指标采样代理模型构建方法与NSGA-Ⅱ-RD算法结合,在绝缘栅双极晶体管母排的结构设计上进行应用,针对母排的质量、电路压降与疲劳损伤进行多目标优化设计。结果表明,该方法不仅保证了母排的轻量化与良好导电性能,还使其具备了更好的抗超声焊接疲劳性能。同时,验证了该方法在保证低成本与高精度仿真模型的前提下,能够有效解决实际工程中的多目标优化设计问题。
The high nonlinearity,computational complexity,and dimensionality of existing engineering problems,along with the demand for low-cost and high-fidelity simulation models,have increased the difficulty of solving multi-objective optimization designs of engineering structures based on multidisciplinary coupling effects.This has led to extensive research in this field due to the large computational volume involved.To address this challenge,this paper proposes a method to realize the multi-objective optimization design of engineering structures based on a new hybrid metric adaptive sampling surrogate model.Firstly,to reduce the cost of optimization design,a new hybrid metric adaptive sampling method based on the Voronoi tessellation is proposed by comprehensively considering the characteristics of global exploration and local exploitation of the entire design space.It is used for constructing a global surrogate model.After comparative testing with different cases and methods,the proposed hybrid metric adaptive sampling method can significantly reduce the required samples while ensuring the same accuracy.And then,to realize the multi-objective optimization design of engineering structure,a new NSGA-II-RD(Improved non-dominated sorting genetic algorithm II based on a rotation and density operator,NSGA-II-RD)multi-objective optimization design algorithm based on the new congestion operator of dominant surface rotational projection and Voronoi tessellation is proposed,which is tested in comparison with different algorithms and shows faster convergence speed and accurate calculation results.Finally,the proposed hybrid metric adaptive sampling surrogate modeling method is combined with the NSGA-II-RD algorithm and applied to the design of busbar structures for insulated-gate bipolar transistors to perform multi-objective optimization design considering the quality,circuit voltage drops,and fatigue damage of the busbars.The results demonstrate that the optimization design method ensures excellent lightweight and conductivity
作者
赵峰
胡伟飞
李光
邓晓豫
刘振宇
郭云飞
谭建荣
ZHAO Feng;HU Weifei;LI Guang;DENG Xiaoyu;LIU Zhenyu;GUO Yunfei;TAN Jianrong(State Key Laboratory of Fluid Power and Mechatronic Systems,Zhejiang University,Hangzhou 310058;Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province,Hangzhou 310058;Taizhou Institute of Zhejiang University,Taizhou 318000;State Key Laboratory of Intelligent Mining Equipment Technology,Taiyuan 030024)
出处
《机械工程学报》
EI
CAS
CSCD
北大核心
2024年第13期81-91,共11页
Journal of Mechanical Engineering
基金
国家自然科学基金(52275275,52111540267)
浙江省自然科学基金(LZ22E050006)
浙江省‘尖兵’‘领雁’研发攻关计划(2023C01008)资助项目。
