并行遗传算法在模具型腔形状优化设计中的应用

针时挤压模具型腔形状的优化设计，提出了并行微观遗传优化方法，该方法采用多种群的并行微观遗传算法进行优化计算，利用BP神经网络的预测功能获得目标函数值，采用三次样条插值函数表达挤压模具型腔形状。训练BP神经网络模型的导师信号利用刚塑性有限元数值计算获得。以表面栽荷沿凹模型腔轮廓表面均匀分布为目标，建立了优化数学模型，对挤压模具型腔轮廓形状进行了优化设计。采用有限元软件MARC／AutoForge对优化结果进行了有限元仿真，仿真结果验证了优化结果的有效性。     

挤压模具型腔的等磨损优化设计

针对目前国内挤压模具寿命过低的情况,将有限元分析、神经网络和遗传算法结合起来应用到挤压模具型腔优化设计中。采用B样条函数插值描述凹模型腔轮廓形状,用有限元数值模拟获得型腔表面节点的应力场、速度场和温度场,基于修正Archard磨损模型计算型腔磨损深度,以此作为样本训练BP神经网络,建立模具型腔控制点与磨损深度之间的映射关系,再结合遗传算法以等磨损为目标,优化模具型腔轮廓形状。优化结果与序列二次规划法一致,可以降低模具磨损,提高模具寿命,结果与实际情况吻合,表明了这种设计方法是可行的。     

[成形过程仿真优化与集成计算材料工程]限定加热管布局的快速热循环注塑成形模具电加热系统优化

针对管道布局、最大允许能耗给定条件下快速热循环注塑成形（RHCM）注塑模具型腔表面快速均匀加热的问题，提出以单根加热棒热流密度为设计变量，以模具型腔表面升温效率和温度分布均匀性为目标，结合有限元模拟、响应面设计以及多目标粒子群优化技术来优化RHCM模具电加热系统。与优化前相比，加热系统优化后，模具型腔表面最大温差降低63.4%，加热系统总能耗降低9%。对比了不同注塑成形工艺条件下成形的平板塑件表面质量，结果表明，相对传统注塑成形（CIM）工艺，RHCM工艺将制品表面粗糙度Ra从320 nm降低到118 nm，并有效抑制了制品表面熔接痕、缩痕等缺陷；发现制品表面粗糙度与型腔表面对应点温度成负相关，说明优化后的型腔表面温度分布更有利于提升制品表面质量。     

基于Pro/E塑料端盖的一模多腔的模具设计

一套模具中有多个型腔,这种模具称为一模多腔模具。对于小尺寸塑件大多采用该类型模具。一模多腔模具有两种形式:一种是各个型腔尺寸相同并按规律排列,另一种是型腔尺寸或形状不同,组合在一套模具中。本文以端盖塑件为例利用Pro/E中模具设计分型面法来阐述型腔尺寸相同的一模多腔模具设计过程。     

衔铁零件挤压成形工艺理论与实验研究

继电器衔铁零件是一种非对称的Z形薄壁纯铁件,其挤压工艺的凹模设计是一个难点。在构造出坯料和成型零部件的有限元模型的基础上,利用DERORM-3D软件对其进行有限元分析,得到了最优模角和最佳工作带长度,优化型腔结构,为挤压模具结构设计提供了坚实的依据。实验研究结果表明,数值模拟分析准确,模具结构设计合理。     

锥形螺母冷镦挤数值模拟及模具设计

提出了锥形螺母一次冷镦挤复合成形新工艺,设计了采用管坯冷镦挤成形锥形螺母的模具结构,运用Deform-3D有限元软件,模拟分析了锥形螺母冷镦挤成形过程中坯料填充凹模型腔的流动速度场和等效应力场。结果表明:管坯各处的流动应力值均不超过其材料的流动应力极限,金属坯料可以流动到型腔的各个部位,此工艺能够获得形状完整的锥形螺母。     

基于神经网络与遗传算法的关节轴承挤压模具优化

针对实际生产中关节轴承内外圈间隙分布不均问题,以GEW12关节轴承为例,应用ABAQUS软件对关节轴承挤压装配过程进行了数值模拟。采用BP神经网络建立了挤压模具形状与内外圈最大间隙与最小间隙之差的映射关系。以关节轴承内外圈间隙均匀分布为目标,结合遗传算法,提出了一种集数值仿真、人工神经网络和遗传算法为一体的关节轴承挤压模具型腔优化设计方法。实验结果表明,模具型腔经过优化后,轴承内外圈间隙均匀性得到了很大的改善,轴承金属流动速度更加均匀。     

控制变形力的锻造预成形优化设计研究

以刚黏塑性有限元为基础,采用基于灵敏度分析的正向模拟优化法,以直接设计预成形模具形状为目标,提出并建立了一种控制变形力的灵敏度分析理论和模具形状优化设计方法。给出了目标函数的表达形式,确定了优化设计变量,推导了目标函数对优化设计变量的灵敏度,利用FORTRAN语言开发了变形力预成形优化设计程序,并对一平面应变变形的H形锻件进行了预成形优化设计,得到了目标函数及终锻件y向应力分布随优化迭代次数的变化情况。     

控制变形力的锻造预成形优化设计研究

以刚黏塑性有限元为基础,采用基于灵敏度分析的正向模拟优化法,以直接设计预成形模具形状为目标,提出并建立了一种控制变形力的灵敏度分析理论和模具形状优化设计方法。给出了目标函数的表达形式,确定了优化设计变量,推导了目标函数对优化设计变量的灵敏度,利用FORTRAN语言开发了变形力预成形优化设计程序,并对一平面应变变形的H形锻件进行了预成形优化设计,得到了目标函数及终锻件Y向应力分布随优化迭代次数的变化情况。     

基于修正Archard磨损理论的挤压模具磨损分析

基于修正的Archard磨损理论,应用有限元数值模拟软件计算模具挤压成形阶段每个节点的瞬时温度、压力和速度场,以此计算锥形和弧形两种挤压模具型腔的磨损。计算结果表明:挤压模具磨损集中在入口,弧形凹模磨损较锥形凹模磨损大,但弧形凹模磨损均匀,模具寿命较高。磨损计算结果与实际情况较吻合,为预测模具寿命和优化模具型腔奠定了基础。     

Multiobjective optimization design of porthole extrusion die using Pareto-based genetic algorithm

The extrusion die plays a crucial role in aluminum alloy profile production, which influences product quality and service life of extrusion die directly. In this paper, a profile with irregular shape was taken as an analysis example, and multiobjective optimization for porthole extrusion die based on modern intelligence algorithm was carried out. Aiming at achieving the uniform velocity distribution in the cross-section of the profile as well as decreasing the maximum stress on the extrusion die and the deflection of the mandrel, the angle between port bridges, the position of die orifice, and the height of welding chamber were considered as the design variables. Then Kriging model was established on the basis of Latin hypercube samplings, and above design variables were optimized using Pareto-based genetic algorithm. Finally, an optimal die structure is gained. Compared with the initial scheme, the velocity distribution in the extrudate was more even, and the stress on the die and the deflection of the mandrel were decreased obviously in the optimal scheme. The optimal design method for porthole die has strong commonality, thus, it could give useful guidelines for practical production of the same kind of aluminum profile.     

型材挤压过程工艺参数优化模型

提出了一种集数值仿真、人工神经网络和遗传算法为一体的工艺参数优化模型,用于型材挤压成形过程工艺参数优化,合理配置了非对称角铝型材模模孔位置。通过现场试验,验证了提出的工艺参数优化模型是行之有效和正确的。并在模孔位置优化配置结果基础上对其挤压成形过程进行数值仿真,分析了挤压成形过程中各阶段网格畸变情况,给出了挤压变形时应力和应变分布,对指导型材挤压工艺和模具优化设计具有重要意义。     

基于热力耦合的热挤压模具结构参数优化设计

利用基于有限变形理论的热力耦合基本方程，对方管铝型材平面分流组合模进行了三维热力耦合计算。分析发现应力集中明显，且其部位与模桥裂纹位置相吻合。为改善模具体内应力分布，对该模具的主要结构参数进行了优化设计。经过21次迭代计算，获得最优结构尺寸，使最大应力下降32．2％，从而延长了模具的使用寿命。     

Optimal Shape Design of an Extrusion Die Using Polynomial Networks and Genetic Algorithms

Designing the optimal shape for an extrusion die to produce a high-quality extrusion product is often required by industry. Design from experience is unsatisfactory for achieving the flexibility and precision requirements in die design. In this paper, a design method has been developed for the optimum shape design of extrusion die. The extrusion process was modelled and analysed by using the finite-element method to obtain the extrusion force and effective strain for different die shapes. A polynomial network was applied to identify the force and strain models in terms of the geometric parameters of the extrusion die. An improved genetic algorithm was used to optimise the identified model for optimal shape with minimum force and strain. It has been verified that the modelling error is extremely small. The designer can quickly and accurately access the optimal shape of an extrusion die through this new approach. RID=" ID=" <E5>Correspondence and offprint requests to</E5>: Dr Y.-C. Hsu, Department of Mechanical Manufacturing Engineering, National Huwei Institute of Technology, 64 Wun-Hua Road, Huwei, Yunlin, Taiwan. E-mail: jasonych&commat;sunws.nhit.edt.tw     

基于多目标优化的扁挤压筒结构设计

在组合式扁挤压筒的结构尺寸设计中，为确保挤压筒最佳工作性能的同时，最大程度地减少过盈装配后内腔产生的变形，提出了多目标优化的概念。结合有限元模拟技术和BP神经网络方法，建立了变过盈量下三层组合式扁挤压筒结构尺寸与各层等效应力分布、内腔位移之间的非线性映射模型，采用多目标遗传算法对其进行优化。优化时，采用了向量评价法、最佳个体保存策略和小生境技术，得到了均匀分布的Pareto最优解，根据定义的满意度函数，选出了最终的满意解。结果表明，在该满意解下，扁挤压筒既实现了等强度设计，又保证了内腔的尺寸精度。     

An optimization strategy for die design in the low-density polyethylene annular extrusion process based on FES/BPNN/NSGA-II

An optimization strategy for die design in the polymer extrusion process is proposed in the study based on the finite element simulation, the back-propagation neural network, and the non-dominated sorting genetic algorithm II (NSGA-II). The three-dimensional simulation of polymer melts flow in the extrusion process is conducted using the penalty finite element method. The model for predicting the flow patterns in the extrusion process is established with the artificial neural network based on the simulated results. The non-dominated sorting genetic algorithm II is performed for the search of globally optimal design variables with its objective functions evaluated by the established neural network model. The proposed optimization strategy is successfully applied to the die design in low-density polyethylene (LDPE) annular extrusion process. A constrained multi-objective optimization model is established according to the characteristics of annular extrusion process. The minimum of velocity relative difference, δu, and the minimum of swell ratio, S _w, that, respectively, ensure the extrinsic feature, mechanical property, and dimensional precision of the final products are taken as optimization objectives with a constrained condition on the maximum shear stress. Three important die structure parameters, including the die contraction angle α, the ratio of parallel length to inner radius L/R _i, and the ratio of outer to inner radius R _o /R _i, are taken as design variables. The Phan-Thien–Tanner constitutive model is adopted to describe the viscoelastic rheological characteristics of LDPE whose parameters are fitted by the distributions of material functions detected on the strain-controlled rheometer. The penalty finite element model of polymer melts flowing through out of the extrusion die is derived. A decoupled method is employed to solve the viscoelastic flow problem with the discrete elastic-viscous split-stress algorithm. The simulated results are selected and extracted to constitute the learning samples according to the orthogonal experimental design method. The back propagation algorithm is adopted for the training and the establishment of the predicting model for the optimization objective. A Pareto-optimal set for the constrained multi-objective optimization is obtained using the constrained NSGA-II, and the optimal solution is extracted based on the fuzzy set theory. The optimization for die parameters in the annular extrusion process of low-density polyethylene is performed and the optimization objective is successfully achieved.     

Numerical and experimental study on the three-dimensional extrusion of square section from square billet through a polynomial shaped curved die

The geometry of die profile plays a major role in reducing the extrusion pressure and ensuring the smooth flow of material. In general, the extrusion process is mostly affected by billet geometry, die geometry, and interface frictional force at the die billet geometry. In the present investigation, an analysis using three-dimensional upper bound method using fifth-order die profile function has been carried out for extrusion of square sections from square billet. The extrusion pressure and optimum die length have been computed by multivariable optimization technique. The present die shape profile is found to be superior to many other profiles. The results obtained will help in design of optimum die profile and investigation of its performance.