Application of Modified Genetic Algorithm to Optimal Design of Supporting Structure

The modified genetic algorithm was used for the optimal design of supporting structure in deep pits.Based on the common genetic algorithm, using niche technique and reserving the optimum individual the modified genetic algorithm was presented. By means of the practical engineering, the modified genetic algorithm not only has more expedient convergence, but also can enhance security and operation efficiency.

Aerodynamic design of transonic fan/compressor by 3D viscous RNS combined with genetic algorithms

This paper presents an aerodynamic design of a small transonic fan by 3D viscous RNS solver combined with genetic algorithms.The aerodynamic design system based on the 3D viscous RNS solver reduces the dependency on the design experience for designers.Furthermore the optimum with genetic algorithms is an effective method for improving the transonic fan performance as a part of the design system.The design result showed that the transonic fan designed by this method reaches the design requirement even with more efficiency value.

Optimal Building Frame Column Design Based on the Genetic Algorithm

Building structure is like the skeleton of the building,it bears the effects of various forces and forms a supporting system,which is the material basis on which the building depends.Hence building structure design is a vital part in architecture design,architects often explore novel applications of their technologies for building structure innovation.However,such searches relied on experiences,expertise or gut feeling.In this paper,a new design method for the optimal building frame column design based on the genetic algorithm is proposed.First of all,in order to construct the optimal model of the building frame column,building units are divided into three categories in general:building bottom,main building and building roof.Secondly,the genetic algorithm is introduced to optimize the building frame column.In the meantime,a PGA-Skeleton based concurrent genetic algorithm design plan is proposed to improve the optimization efficiency of the genetic algorithm.Finally,effectiveness of the mentioned algorithm is verified through the simulation experiment.

Structural Design Optimization of a Vertical Axis Wind Turbine for Seismic Qualification and Lightweight

Recently, there is a growing interest in seismic qualification of ridges, buildings and mechanical equipment worldwide due to increase of accidents caused by earthquake. Severe earthquake can bring serious problems in the wind turbines and eventually lead to an interruption to their electric power supply. To overcome and prevent these undesirable problems, structural design optimization of a small vertical axis wind turbine has performed, in this study, for seismic qualification and lightweight by using a Genetic Algorithm (GA) subject to some design constraints such as the maximum stress limit, maximum deformation limit, and seismic acceleration gain limit. Also, the structural design optimizations were conducted for the four different initial design variable sets to confirm robustness of the optimization algorithm used. As a result, all the optimization results for the 4 different initial designs showed good agreement with each other properly. Thus the structural design optimization of a small vertical-axis wind turbine could be successfully accomplished.

基于遗传算法的再生材料结构优化设计——以轻型木结构楼盖格栅为例

木材是一种典型的可再生材料,以其为主要建材的轻型木结构在双碳背景下拥有广阔前景。然而基于力学分析软件调整验算的轻型木结构楼盖格栅传统设计方法过分依赖主观工程经验,存在效率低、构件结构性能冗余,经济性不足的缺点;为实现轻型木结构楼盖格栅高效经济节材的设计,引入客观的遗传算法进行优化,通过Grasshopper搭建相关参数化几何模型与优化设计数学模型,调用Galapagos中的遗传算法模块以格栅总体积最小为目标执行优化,最后以某现代木结构幼儿园为优化算例,并通过MIDAS软件验证优化结果的可靠性。结果表明:轻木楼盖格栅节材优化变量均为离散数据,优化算例中班单元楼盖格栅工程量最大适应度个体在第5代已出现,优化效率整体可观;优化后的算例设计方案满足结构安全要求且相较于原方案节材6.4%。基于本方法所提出的各建筑功能类型轻型木结构楼盖格栅经济性设计方案能作为相关工程实践的有效参考。

Intelligent Optimization Methods for the Design of an Overhead Travelling Crane

In design optimization of crane metal structures, present approaches are based on simple models and mixed variables, which are difficult to use in practice and usually lead to failure of optimized results for rounding variables. Crane metal structure optimal design（CMSOD） belongs to a constrained nonlinear optimization problem with discrete variables. A novel algorithm combining ant colony algorithm with a mutation-based local search（ACAM） is developed and used for a real CMSOD for the first time. In the algorithm model, the encoded mode of continuous array elements is introduced. This not only avoids the need to round optimization design variables during mixed variable optimization, but also facilitates the construction of heuristic information, and the storage and update of the ant colony pheromone. Together with the proposed ACAM, a genetic algorithm（GA） and particle swarm optimization（PSO） are used to optimize the metal structure of a crane. The optimization results show that the convergence speed of ACAM is approximately 20% of that of the GA and around 11% of that of the PSO. The objective function value given by ACAM is 22.23% less than the practical design value, a reduction of 16.42% over the GA and 3.27% over the PSO. The developed ACAM is an effective intelligent method for CMSOD and superior to other methods.

Structural Parameter Optimization of Multilayer Conductors in HTS Cable

In this paper, the design optimization of the structural parameters of multilayer conductors in high temperature superconducting （HTS） cable is reviewed. Various optimization methods, such as the particle swarm optimization （PSO）, the genetic algorithm （GA）, and a robust optimization method based on design for six sigma （DFSS）, have been applied to realize uniform current distribution among the multilayer HTS conductors. The continuous and discrete variables, such as the winding angle, radius, and winding direction of each layer, are chosen as the design parameters. Under the constraints of the mechanical properties and critical current, PSO is proven to be a more powerful tool than GA for structural parameter optimization, and DFSS can not only achieve a uniform current distribution, but also improve significantly the reliability and robustness of the HTS cable quality.

Structural Optimization of Concrete Slab Frame Bridges Considering Investment Cost

The present study investigates computer-antomated design and structural optimization of concrete slab frame bridges considering investment cost based on a complete 3D model. Thus, a computer code with several modules has been developed to produce parametric models of slab frame bridges. Design loads and load combinations are based on the Eurocode design standard and the Swedish design standard for bridges. The necessary reinforcement diagrams to satisfy the ultimate and serviceability limit states, including fatigue checks for the whole bridge, are calculated according to the aforementioned standards. Optimization techniques based on the genetic algorithm and the pattern search method are applied. A case study is presented to highlight the efficiency of the applied optimization algorithms. This methodology has been applied in the design process for the time-effective, material-efficient, and optimal design of concrete slab frame bridges.

基于多目标优化的箱梁渡槽结构设计研究

针对箱梁渡槽所受水荷载远大于同等跨径箱梁桥所受汽车荷载导致槽身纵向受力突出的问题,在渡槽结构设计中统筹考虑箱梁纵向应力储备和造价,构建了以截面尺寸、钢筋用量等6个参数为设计变量,以渡槽边缘正应力和造价为目标函数,以槽身挠度、法向应力等9个验算指标为约束条件的多目标优化模型,并基于支持向量机近似模型和NSGA2遗传算法求解多目标优化模型的Pareto最优解集,然后综合专家打分、COWA算子、博弈论综合赋权与TOPSIS法从Pareto最优解集中选出最佳方案。结果表明:与初始方案相比,最佳方案的渡槽边缘正应力储备提高了17.55%,渡槽上部结构总造价降低8.84%;与有限元分析相比,该方法在保持较高计算精度的同时节省了65.42%的计算时间成本。

面向壁厚均匀的液压成形三通管的坯料设计方法与参数优化

目的研究连续变厚度管液压成形过程中三通管的壁厚均匀性问题。方法首先,利用有限元软件分析得到了等厚管液压成形三通管过程中的成形规律,根据其成形规律,反向设计了用于液压成形三通管的连续变厚度管坯;其次,采用正交试验方法,研究了连续变厚度管厚区壁厚、过渡区长度对液压成形三通管成形质量的影响;最后,采用多岛遗传算法,对连续变厚度管的结构参数进行了优化验证,提高了液压成形三通管的成形质量。结果在等厚管液压成形三通管成形过程中,支管顶部壁厚值持续减小、轴向过渡圆角及直管底部中间位置处壁厚值持续增大;环向过渡圆角处等效应力最大,其他位置连续变化;轴向压应力使得三通管壁厚增大,拉应力使得壁厚减小;正交试验结果表明,当连续变厚度管厚区厚度、环向过渡区长度达到某一值时将出现较好的壁厚均匀性;在4种过渡区曲线线型中,直线型的壁厚均匀性最好;通过多目标优化得到最佳连续变厚度管结构参数,并通过有限元仿真进行验证,相对误差均在2%以内,使用优化后的连续变厚度管液压成形三通管相对于等厚管,壁厚均匀值减小了0.423 mm。结论可以采用厚度补偿或减薄的方式来提高成形三通管的壁厚均匀性;连续变厚度管坯相比于等厚管,显著提高了液压成形三通管的壁厚均匀性。

柔性立管限弯器高效设计方法

目的考虑聚氨酯材料非线性的影响,建立一种简单高效的柔性立管限弯器设计方法。方法首先确定限弯器的初始尺寸,在此基础上进行参数分析,并根据分析结果绘制设计图谱,然后通过插值获得最佳的设计尺寸。结果针对深水与浅水2种典型环境,分别采用本方法与基于遗传算法的优化设计方法进行限弯器设计,通过结果对比验证了方法的有效性。同时发现,深水环境条件设计出的限弯器相对短粗,而浅水条件设计出的限弯器则较为细长,且考虑材料非线性后,2种环境下限弯器的设计尺寸均有所减小。结论本文建立的限弯器设计方法具有广泛的适用性,且能够在确保得到理想设计方案的前提下,显著提高设计效率。与基于遗传算法的优化设计方法相比,采用线性材料和考虑材料非线性时的设计效率可分别提高约10倍和20倍。

基于智能优化算法的高频变压器电磁结构优化设计

高频变压器(HFT)作为电力电子变换器等功率变换装备的核心部件,其优化设计是实现高功率密度、高效率和高可靠性的重要环节。为有效解决高频条件下显著的涡流效应和复杂紧凑的结构使变压器损耗难以准确计算、针对绝缘设计裕量不足的问题,本文提出计及高频效应和结构效应的电磁场建模方法,构建了高频变压器多目标协同优化设计方案。首先建立了低成本与高效率兼备的磁心损耗计算模型。其次,根据面积等效原理推导了考虑绕组结构效应的近似Dowell模型,实现绕组损耗的高精度计算。然后提出了考虑绕组端部效应和频率影响的漏感计算模型,减小漏感对于结构和频率的依赖性。在此基础上,采用一种新型多重绝缘结构,提高绕组间的绝缘耐压水平。最后,基于改进的非支配排序遗传算法(INSGA-Ⅱ)和自由参数扫描法建立了高频变压器的优化设计流程,根据筛选的最优设计方案研制了一台高频变压器样机。

基于多种群遗传算法的钢框架结构优化设计

传统的基于力学分析软件的结构设计方法存在效率低下、依靠专家经验等局限性,采用智能算法能实现高效的结构自动优化设计。然而,由于随机搜索特征,优化结果和收敛性高度依赖于算法的参数设置,需要通过试算来确定其合理取值,该方法会造成优化效率低、计算量大等问题。引入多种群协作和信息共享机制来改善此类问题,并研究其在结构优化设计中的适用性。利用MSC.Marc软件建立钢框架结构有限元模型,采用底部剪力法将地震作用等效为水平荷载施加到结构上,搭建有限元软件与智能算法的自动优化过程,以结构的总体材料用量最低为目标,考虑了层间位移角、应力比、构件稳定性和宽厚比等多种约束条件,以遗传算法为基础,通过适应度尺度变换、基于方向的交叉算子、非均匀变异算子、自适应概率、精英保留策略、重复项替代机制、基于约束的策略对其进行改进,引入多种群思想,对比多种算法优化结果的差异。结果表明:基于多种群的遗传算法能有效改善优化结果对算法参数的依赖性,提高结构优化设计的效率。

星载二维转台U型架结构轻量化与优化设计

星载二维转台是空间相机等光电设备的主要承载机构,U型架是转台的关键支撑部件。为了对星载二维转台U型架进行结构优化与轻量化设计,研制高承载比和轻量化的星载二维转台,本文设计了一种用于星载二维转台的碳纤维复合材料U型架。首先,利用碳纤维复合材料代替钛合金材料,结合考虑工艺性,设计了一种变截面管状结构U型架。接着,按照基于铺层工艺的有限元建模方法对碳纤维U型架进行有限元建模与仿真分析。然后,试制U型架样机并通过模态试验验证有限元模型的准确性。最后,提出一种理论分析法、遗传算法、有限元法相结合的三级优化方法对碳纤维U型架铺层角度、铺层厚度与铺层顺序进行优化设计。结果表明:模态试验与仿真得到的U型架振型完全一致,频率相差在5%以内。初始设计的碳纤维U型架比钛合金U型架质量减少了45.7%,通过对复合材料铺层的优化设计,使U型架质量进一步减少了13.8%,固有频率提升了10.14%。本文所采用的复合材料建模与优化方法正确,设计的碳纤维U型架满足星载二维转台轻量化设计需求。

基于加速遗传算法的钢板组合梁桥设计优化研究

针对公路简支钢板组合梁桥用钢量优化问题,提出基于加速遗传算法的组合梁截面优化方法,该方法以钢主梁用钢量为目标函数、以钢主梁截面参数为设计变量、以组合梁承载力和变形为约束条件对截面尺寸进行优化求解。以武穴长江公路大桥南引桥为背景,基于不同钢主梁间距下内力计算结果采用加速遗传算法求解钢主梁最优截面,获得钢主梁每延米最小用钢量和整桥每延米最小总用钢量随梁高变化趋势;结合优化结果提出了最小用钢量设计方案,并建立有限元模型进行优化后结构力学性能验算。结果表明:基于加速遗传算法的组合梁截面优化方法具有较好的收敛性和极值寻优能力;随钢主梁间距的增大,钢主梁截面尺寸及用钢量随之增大,但整桥总用钢量随之减小;钢主梁设计存在用钢量最为节约的最优梁高,该梁高随钢主梁间距的增大而增大;提出的桥梁最小用钢量设计方案计算挠度、应力小于规范限值,且具有足够的安全储备,可较好满足结构受力要求。

U形截面包容环优化设计方法研究

U形结构包容环是涡轮起动机通常采用的保护装置。在满足涡轮转子被包容的条件下,对U形截面包容环进行结构优化以获得一个轻便且包容的结构,有利于提高飞机的安全性和推重比。提出了一种U形截面包容环的优化设计方法,该方法采用最优拉丁超立方设计、数值模拟、响应面建模、多岛遗传算法实现包容环截面多参数的优化设计。并通过仿真和试验相结合的方法,分析了不同结构参数对碎片剩余动能和包容环体积的影响权重,研究了U形包容环的不同结构参数对包容结果的影响,并对优化设计后的包容环进行包容性试验验证。结果表明,包容环厚度参数对碎片剩余动能的影响最大,权重比为38%;且影响包容效果主要结构参数是厚度和槽深。仿真与试验结果对比中包容环变形量的误差小于2%,提出的优化设计方法合理可靠。可为U形包容环结构的质量减轻提供先验知识和优化方法。

基于LightGBM和遗传算法的二维层状声子晶体结构设计

声子晶体具有周期性人工复合结构,以其带隙特性在波传播控制上的应用潜力而广受关注,为工程减振降噪提供了新的解决思路,这类材料的设计问题是当下研究的焦点。本研究以二维层状声子晶体结构为例,提出了一种利用LightGBM和改进遗传算法设计的创新方法。首先在声子晶体的带隙预测上选用LightGBM算法,对结构的排列向量进行类别特征处理,并结合模拟退火算法进行超参数调优,在传统有限元法计算时间的1/3134内,达到了整体误差不超过2%的预测精度;其次在设计方法上集成了一种基于精英保留策略的遗传算法,以地铁运行造成的环境振动问题为例,确定以带隙宽度为优化的适应度函数,得到了对应结构带隙覆盖30~40 Hz频段的种群;最后,对优化结构进行有限元分析,其带隙特征与预期基本吻合。本研究为声子晶体结构高效优化设计提供了一种新的解决方案。

Cost Optimization Method of Large-scale Prestressed Wire Winded Framework on Multiple-island Genetic Algorithm

Prestressed wire winded framework （PWWF） is an advanced structure and the most expensive part in the large-scale equip- ment. The traditional design of PWWF is complicated, highly iterative and cost uncontrolable, because PWWF is a variable stiffness multi-agent structure, with non-linear loading and deformation coordination. In this paper, cost optimization method of large-scale PWWF by multiple-island genetic algorithm （MIGA） is presented. Optimization design flow and optimization model are proposed based on variable-tension wire winding theory. An example of the PWWF cost optimization of isostatic equipment with axial load 6 000 kN is given. The optimization cost is reduced by 21.6% compared with traditional design. It has also been verified by the finite-element analysis and successfully applied to an actual PWWF design of isostatic press. The results show that this method is efficient and reliable. This method can also provide a guide for optimal design for ultra-large dimension muti-frame structure of 546 MN and 907 MN isostatic press equipment.

基于聚类算法的自动变速箱装配模块划分研究

自动变速箱可实现换挡变速功能,是车辆系统中传递动力的关键部件。由于其结构狭窄紧凑、零件数量繁多,导致装配复杂度大大增加。模块划分是产品模块化设计的关键步骤,可以将系统整体拆分形成若干个高内聚低耦合的模块,从而达到降低产品装配难度的目的。模糊C-均值聚类算法(FCM)是实现模块划分的传统方法,然而其对初值敏感,容易收敛到局部极值点。FCM与优化算法的结合有利于避免陷入局部最优解的情况,因此提出使用基于遗传模拟退火算法的FCM方法进行装配模块划分以获取自动变速箱模块的最佳划分方案。以重庆铁马变速箱有限公司的自动变速箱为例,使用所提方法对其进行装配模块划分,将所得模块划分结果与实际方案进行对比,证明了方法的准确性和有效性。

基于多保真代理模型的塔机臂架结构优化

起重臂架是动臂式塔机的关键工作部件,负责提升运输建筑材料,其制造成本和工作耗能与自身重量成正比,需要对臂架的重量优化展开研究,因此提出了一种针对动臂式塔机臂架的高效优化设计方法。首先,基于有限元法,计算了不同臂架幅度下的极限工况应力及变形,确定了最危险工况,并以此工况作为优化设计的基础工况;然后,选定了臂架上12个结构参数为设计变量,进行了参数化建模,利用拉丁超立方采样(LHS)选取了样本点,基于有限元仿真数据,构建了三种基于径向基函数(RBF)的代理模型并对其精度进行了评估;最后,基于精度高的多保真代理模型(MFS),以臂架重量最小为优化目标,构建了臂架优化问题的数学模型,使用遗传算法(GA)完成了优化设计。研究结果表明:优化后的臂架满足强度、刚度要求,整个臂架不会发生断裂和失稳,而且臂架重量减轻了25.03%;同时,多保真代理模型的预测结果和仿真结果误差小于3%,证明了多保真代理模型的准确性,进而证明了基于多保真代理模型的臂架优化方法的有效性。