Regularized level-set-based inverse lithography algorithm for IC mask synthesis

Inverse lithography technology(ILT)is one of the promising resolution enhancement techniques,as the advanced IC technology nodes still use the 193 nm light source.In ILT,optical proximity correction(OPC)is treated as an inverse imaging problem to find the optimal solution using a set of mathematical approaches.Among all the algorithms for ILT,the level-set-based ILT(LSB-ILT)is a feasible choice with good production in practice.However,the manufacturability of the optimized mask is one of the critical issues in ILT;that is,the topology of its result is usually too complicated to manufacture.We put forward a new algorithm with high pattern fidelity called regularized LSB-ILT implemented in partially coherent illumination(PCI),which has the advantage of reducing mask complexity by suppressing the isolated irregular holes and protrusions in the edges generated in the optimization process.A new regularization term named the Laplacian term is also proposed in the regularized LSB-ILT optimization process to further reduce mask complexity in contrast with the total variation(TV)term.Experimental results show that the new algorithm with the Laplacian term can reduce the complexity of mask by over 40%compared with the ordinary LSB-ILT.     

基于IPSO-Powell优化SVM的煤与瓦斯突出预测算法

针对基于支持向量机(SVM)的煤与瓦斯突出预测算法存在预测精度和可靠性不高,选择核函数时未考虑非线性数据的分类,对非线性分布的煤与瓦斯突出影响因素提取效果较差的问题,提出了一种将改进的粒子群(IPSO)算法与Powell算法相结合(IPSO-Powell)优化SVM的煤与瓦斯突出预测算法.首先通过灰色关联分析提取出煤与瓦斯突出主控因素,即瓦斯放散初速度、瓦斯压力、开采深度、瓦斯含量和煤体破坏类型,作为算法的输入样本;然后运用IPSO算法改善粒子群算法(PSO)的早熟收敛性,结合Powell算法进行局部搜索得到最优解,对SVM算法的惩罚系数和高斯核函数参数进行寻优,得到SVM的最优参数组合;最后将煤与瓦斯突出的主控因素输入到SVM中进行分类,并将其与实际测试集分类结果进行对比,实现煤与瓦斯突出预测.仿真结果表明:与SVM算法、GA-SVM算法、PSO-SVM算法相比,利用IPSO-Powell优化SVM算法进行煤与瓦斯突出预测,具有更高的预测精度,同时提高了SVM求解过程的运算效率,能同时满足煤与瓦斯突出预测的精度和可靠性要求,准确率达到95.9%.     

Structure quality in deep X-ray lithography applying commercial polyimide-based masks

The structure quality of deep X-ray lithography components strongly depends on the quality of the applied X-ray mask. In this article we compare the results obtained with two different mask types. Sophisticated working masks generated by e-beam lithography, soft X-ray lithography and electroplating of gold absorbers on a titanium mask membrane have been fabricated at the Institute for Microstructure Technology, Research Center, Karlsruhe (FZK/IMT), Germany. Prototype masks generated by e-beam lithography, optical lithography and electroplating of gold absorbers on a polyimide mask membrane have been fabricated by Optnics Precision, Japan, with the aim to offer commercially available low cost masks. Both mask types were applied to pattern PMMA resist layers of 300–750 μm thickness at the 2.5 GeV electron storage ring ANKA, Germany, using comparable process parameters. FZK/IMT masks provide microstructures with significantly better structure quality. The layout area, however, is currently limited to 12 cm², and the Ti mask membrane tends to lead to a slight resist surface attack, such as rounding of the resist edges. Optnics masks provide microstructures with reduced structure quality due to sidewall striations (sidewall roughness up to 2 μm) and thermal distortions (of up to 3–5 μm) which limit the potential scope of applications. They could nevertheless potentially be applied as low quality, low cost X-ray masks. High resolution and high accuracy applications, however, require more sophisticated but also more expensive masks, like the Ti-masks from FZK/IMT.     

A simulation-based optimization approach for a semiconductor photobay with automated material handling system

This study addressed the issue of automated material handling systems (AMHS) in the photolithography zone of a 300 mm (12-in.) wafer fab facility. The lithography process accounts for 40–50% of the time required to produce wafers. Therefore, managing the AMHS in the photolithography zone is a challenging task. This paper examines the dispatching rule and the number of vehicles in variable wafer input cases. With a stochastic and complex manufacturing process, a photobay simulation may lead to excessive iterations and wasted computation time. The most frequently used approach for process management in the literature is performance analysis with a model that simulates each alternative for N times. However, this approach becomes time consuming as the number of variables and iterations increases. To address this issue, we use Optimal Computing Budget Allocation (OCBA) and extend OCBA by adding particle swarm optimization (PSO). With this combined approached, the number of iterations of each alternative is determined by OCBA, and the optimal solution in the domain of feasible solutions is identified through PSO. This research provides a useful reference to optimally allocate lithographical resources and the number of iterations with random parameters for both scholars and practitioners. Results demonstrate the superiority of PSO_OCBA in terms of searching quality and robustness.     

Retargeting 3D Objects and Scenes with a General Framework

In this paper, we introduce an interactive method suitable for retargeting both 3D objects and scenes. Initially, the input object or scene is decomposed into a collection of constituent components enclosed by corresponding control bounding volumes which capture the intra‐structures of the object or semantic grouping of objects in the 3D scene. The overall retargeting is accomplished through a constrained optimization by manipulating the control bounding volumes. Without inferring the intricate dependencies between the components, we define a minimal set of constraints that maintain the spatial arrangement and connectivity between the components to regularize the valid retargeting results. The default retargeting behavior can then be easily altered by additional semantic constraints imposed by users. This strategy makes the proposed method highly flexible to process a wide variety of 3D objects and scenes under an unified framework. In addition, the proposed method achieved more general structure‐preserving pattern synthesis in both object and scene levels. We demonstrate the effectiveness of our method by applying it to several complicated 3D objects and scenes.     

Banner layout retargeting with hierarchical reinforcement learning and variational autoencoder

In many advertising areas, banners are often generated with different display sizes, so designers have to make huge efforts to retarget their designs to each size. Automating such retargeting process can greatly save time for designers and let them put creativity on new ads. This paper proposes a hierarchical reinforcement learning-based (HRL-based) method and a variational autoencoder-based (VAE-based) method by treating the automated banner retargeting problem as a layout retargeting task. The HRL and VAE models are trained separately to learn the scaling and positioning policy of the design elements from an original (base) layout. Hence, the proposed method can generate appropriate layouts for different target banner sizes. Meanwhile, evaluation metrics are proposed to assess the quality of generated layouts and are also reward conditions during the training process. To evaluate performances of the two models, SOTA methods such as Non-linear Inverse Optimization (NIO), Triangle Interpolation (TI), and Layout GAN (LGAN) are implemented and compared. Experimental results show that both HRL- and VAE-based methods retarget design layouts effectively, and the VAE model achieves better performance than the HRL model.

     

面向反馈运动控制器的多目标求解

目的 基于物理模拟的人体运动生成方法由于能够合成符合自然规律的运动片段,可实时响应环境的变化,且生成的物理运动不是机械性的重复,因此是近年来计算机动画和虚拟现实领域中最活跃的研究方向之一。然而人体物理模型具有高维、非线性及关节间强耦合性等特点,求解人体物理运动十分困难。反馈控制器常用于人体物理运动控制,求解时通常需要对多个目标函数加权求和,然而权重的设置需多次试验,烦杂耗时。针对运动控制器求解困难的问题,本文提出了一种面向反馈运动控制器的多目标求解方法。方法 首先,对运动数据进行预处理并提取关键帧求解初始控制器,并设计一种改进的反馈控制机制;在此基础上,种群父代个体变异产生子代,采用禁选区域预筛选策略去除不满足约束的个体,并通过重采样获取新解;然后,通过物理仿真获得多目标适应度值,采用区域密度多层取优选取分布均匀的优秀个体作为下一代父代,并通过基于剪枝的多阶段物理求解算法决定是否进入下一阶段优化;经过多次迭代后获得物理控制器,从而生成具有反馈的人体物理运动。结果 针对提出的方法,本文针对多个测试函数和物理运动分别进行实验：在测试函数实验中,本文分别采用经典的测试函数进行实验对比,在相同的迭代次数下,相比之前算法,本文算法中满足约束的优秀个体命中率更高,反转世距离更小,且最优解集的分布更加均匀;物理运动生成实验中,分别针对走路、跑步和翻滚等运动进行物理运动生成,与之前算法进行对比,本文算法可以更早地完成收敛,同时目标函数值更小,表明生成的运动效果更好。结论 本文提出的进化求解方法可以生成不同运动的控制器,该控制器不仅可以生成物理运动,而且还具备外力干扰下保持平衡的能力,解决了运动控制器求解中多目标权重设置困难、优化时间长的问题;除此之外,本文算法还对具有约束的多目标问题具有较好的求解效果。     

A hybrid optimization approach for layout design of unequal-area facilities

A hybrid optimization approach is presented for the layout design of unequal-area facilities. Simulated annealing is used to optimize a randomly generated initial placement on an “extended plane” considering the unequal-area facilities enclosed in magnified envelop blocks. An analytical method is then applied to obtain the optimum placement of each envelop block in the direction of steepest descent. Stepwise reduction of the sizes of the envelop blocks allows controlled convergence in a multi-phase optimization process. The presented test problems include two large size benchmark problems of 50 and 100 facilities of unequal areas. The results indicate that although the computational cost is relatively quite high, the technique is a significant improvement over previously published techniques for unequal-area facilities and can yield solutions of the same quality as obtained by PLANOPT, a general-purpose layout optimization program based on pseudo-exhaustive search.     

在原始空间用Rosenbrock算法训练线性支持向量机

为了加快并行下降方法（ＣＤ）用于线性支持向量机（ＳＶＭ）时的最终收敛速度,将Ｒｏｓｅｎｂｒｏｃｋ算法（Ｒ）用于线性ＳＶＭ．在内循环,Ｒ 通过解一个单变量子问题来更新狑的一个分量,并同时固定其他分量不变;在外循环,采用Ｇｒａｍ-ｓｃｈｍｉｄｔ过程构建新的搜索方向．实验结果表明,与ＣＤ 相比,Ｒ 加快了最终的收敛,在分类中能更快地获得更高的测试精度．     

网络入侵检测中的自动决定聚类数算法

针对模糊C均值算法(fuzzy C-means algorithm,简称FCM)在入侵检测中需要预先指定聚类数的问题,提出了一种自动决定聚类数算法(fuzzy C-means and support vector machine algorithm,简称F-CMSVM).它首先用模糊C均值算法把目标数据集分为两类,然后使用带有模糊成员函数的支持向量机(support vector machihe,简称SVM)算法对结果进行评估以确定目标数据集是否可分,再迭代计算,最终得到聚类结果.支持向量机算法引入模糊C均值算法得出的隶属矩阵作为模糊成员函数,使得不同的输入样本可以得到不同的惩罚值,从而得到最优的分类超平面.该算法既不需要对训练数据集进行标记,也不需要指定聚类数,因此是一种真正的无监督算法.在对KDD CUP 1999数据集的仿真实验结果表明,该算法不仅能够得到最佳聚类数,而且对入侵有较好的检测效果.     

Topology optimization with design-dependent pressure loading

In this paper, the layout of structures under design-dependent pressure loading is optimized using a topology optimization approach. In contrast to topology optimization problems with conventional static external loading, the position and direction of pressure loading are changing with topology of structure during optimization iterations. In order to model the changing structural surface boundaries under design-dependent pressure loading, a pseudo equal-potential function is introduced. Design sensitivity analysis is derived from the adjoint method. Three examples solved by the proposed method are presented.     

Change point determination for a multivariate process using a two-stage hybrid scheme

Effective identification of the change point of a multivariate process is an important research issue since it is associated with the determination of assignable causes which may seriously affect the underlying process. Most existing studies either use the maximum likelihood estimator (MLE) method or the machine learning (ML) method to estimate or identify the change point of a process. Typically, the MLE method may be criticized for its assumption that the process distribution is known, and the ML method may have the deficiency of using a large number of input variables in the modeling procedure. Diverging from existing approaches, this study proposes an integrated hybrid scheme to mitigate the difficulties of the MLE and ML methods. The proposed scheme includes four components: the logistic regression (LR) model, the multivariate adaptive regression splines (MARS) model, the support vector machine (SVM) classifier and the change point identification strategy. It performs three tasks in order to effectively identify the change point in a multivariate process. The initial task is to use the LR and MARS models to reduce and refine the whole set of input or explanatory variables. The remaining variables are then served as input variables to the SVM in the second task. The last task is to integrate use of the SVM outputs with our proposed identification strategy to determine the change point in a multivariate process. Experimental simulation results reveal that the proposed hybrid scheme is able to effectively identify the change point and outperform the typical statistical process control (SPC) chart alone and the single stage SVM methods.     

基于GA和FEM的夹具布局和变夹紧力优化设计

通过夹具布局和夹紧力大小的优化可以提高薄壁件加工精度．建立了夹具布局和变夹紧力分层优化模型．首先,以工件加工变形最小化和变形最均匀化为目标函数,对夹具布局进行优化设计;其次,基于优化的夹具布局对变夹紧力进行设计．采用有限元法计算工件的加工变形,加工变形求解时综合考虑了接触力、摩擦力、切削力、夹紧力和切屑的影响．采用遗传算法求解优化模型,获得优化的夹具布局和变夹紧力．通过实例分析,验证了分层优化设计方法可以进一步减小工件加工变形,提高加工变形均匀度．     

基于工艺特征约束的改进遗传算法

为提高飞机装配的精度,减小定位的误差,优化具有复杂工艺特征的机身框件的支撑序列.针对优化中工艺特征约束处理问题,建立了工艺特征约束的广义数学模型,从理论角度提出了一种针对此类约束的不可行解修补算法,并基于此算法设计一种改进的遗传算法.使用改进的遗传算法优化某型飞机机身框在可重构柔性工装上的支撑序列,优化过程稳定,最优序列下框的柔性定位误差减小93.08%,保证了飞机装配的精度.理论基础分析和仿真结果分析表明,改进的遗传算法通用性强,适用于各种约束优化问题;收敛速度快且稳定,具备可行性.     

基于粒子群与支持向量机的隧道变形预测模型

针对粒子群算法易早熟且在算法后期易在全局最优解附近产生振荡现象,提出一种自适应调整惯性权重的优化粒子群算法。该算法引入双曲线正切函数的非线性变化思想,使惯性权重随着迭代次数的增加产生自适应调整,有利于增强粒子搜索能力及收敛速度,不易陷入局部极值点。将该算法应用于基于支持向量机的隧道变形预测模型中,对预测模型的超参数进行优化,并利用稳态与非稳态两组实测工况数据对组合算法进行工程测试,结果表明采用SaωPSO＋SVM算法可有效提高预测模型的计算精度,增强其鲁棒性,有助于隧道变形的工程建模。     

基于SQP局部搜索的多子群果蝇优化算法

针对基本果蝇优化算法在寻优过程中种群多样性降低导致算法易陷入早熟收敛的问题,提出了基于序列二次规划（SQP）局部搜索的多子群果蝇优化算法（MFOA-SQP）。新算法将果蝇种群均匀划分为多个子群,并引入粒子群算法中的惯性权重和学习因子,协同调节果蝇移动方向和步长;每隔一定迭代次数重新划分子群,避免种群单一化,使算法更易跳出局部最优;对子群最优个体进行SQP搜索,提高局部寻优性能。通过6个测试函数和优化广义回归神经网络对银行客户进行分类的实验结果表明,算法在寻优精度和速度方面性能优越,能够有效提高广义回归神经网络的分类准确率。     

非规则三维建筑模型的保结构变形

为了快速生成大量与输入风格一致的三维建筑模型,提出一种针对非规则三维建筑模型的保结构交互式变形技术.该技术以一般的三维网格模型作为输入,经过若干预处理操作形成带标记的包围盒层次结构,以此作为变形操作的分析基础.变形算法的核心思想是将原始的复杂结构分解为一组一维的结构序列,然后逐条对一维结构序列施加变形操作.在对一维结构序列的变形过程中尽可能以可重复的元素来填充变形空间,实现对输入结构特点的保持.实验结果表明,该技术可用于各种不同风格的建筑模型.