Extraction of geometric characteristics for manufacturability assessment

One of the advantages of feature-based design is that it provides data which are defined as parameters of features in readily available forms for tasks from design through manufacturing. It can thus facilitate the integration of CAD and CAM. However, not all design features are features required in down stream applications and not all parameters or data can be predefined in the features. One of the significant examples is property that is formed by feature interactions. For example, the interaction of a positive feature and a negative feature induces a wall thickness change that might cause defects in a part. Therefore, the identification of the wall thickness change by detecting the feature interaction is required in the moldability assessment.The work presented in this paper deals with the extraction of geometric characteristics in feature-based design for manufacturability assessment. We focus on the manufacturability assessment of discrete parts with emphasis on a net shape process—injection molding. The definition, derivation and representation of the spatial relationships between features are described. The geometric characteristics formed by feature interactions are generalized as significant items, such as “depth”, “thickness”, “height” etc. based on the generalization of feature shapes. Reasoning on feature interactions and extraction of geometric characteristics is treated as a refinement procedure. High-level spatial relationships—“is_in”, “adjacent_to” and “coplanar” as well as their geometric details are first derived. The significant items formed from feature interactions are then computed based on the detailed spatial relationships. This work was implemented in a computer-aided concurrent product and process development environment to support molding product design assessment.     

Knowledge-based manufacturability assessment: an object-oriented approach

To help the achievement of integrated product and process development, there is a need for tools that can assist designers in creating manufacturable parts with less design routines and tryouts. This paper presents a systematic approach to developing automated manufacturability assessment tools by identifying the functional and informational requirements and proposing an assessment model. The work presented in this paper includes: (1) identification of characteristics and tasks of design for the die-casting process; (2) determination of functional and informational requirements for automatic manufacturability assessment; (3) formalization and modularization of assessment knowledge; and (4) modeling of product definition data to support the assessment. Object-oriented techniques are employed to model the assessment knowledge and manage the complicated and diverse types of product definition data by taking advantage of data abstraction, modularity, inherent concurrence, and the concept of encapsulation and extendibility.     

基于深度学习的孔特征可制造性分析方法

针对传统基于知识库及规则库的零件可制造性分析方法柔性差,以及现有基于深度学习的可制造性分析方法无法给出零件具体不可制造原因的现状,提出一种基于深度学习的零件可制造性分析方法.首先,通过数字化建模技术构建大量带有具体可制造性类别标签的三维CAD模型,并进行点云提取,从而构建深度学习所需数据集;然后,基于PointNet网...     

Logic synthesis for manufacturability

Design optimization during synthesis is for area and/or performance while optimization for yield occurs at the layout level. To obtain abstraction level for yield optimization by introducing an interesting approach to yield-driven logic synthesis. Design for manufacturability denotes all techniques designers use to estimate and control yield and robustness during the design phase, prior to manufacturing.     

Feature based quality assessment of DNA sequencing chromatograms

Although next generation sequencing applications are getting dominant in molecular genetics, there are still many institutions that want to utilize their legacy sequencers as much as possible. An important concern in sequencing services is the quality of trace files presented to the customers. In this respect, the quality of the trace files should be screened and low quality files should be handled differently before reaching to customers. The quality scores already present in the trace files provide some useful information, however by incorporating auxiliary information we can improve to reliability of these scores. To this end, we used a feature based supervised classification strategy which requires a set of training and testing trace files qualities of which are determined manually. We tested several machine learning algorithms, namely k-nearest neighbors, Naive Bayes, Support Vector Machines and Random Forest, on a public DNA trace repository. Our results indicate that RF method with only 4 simple features provides a classification accuracy rate of 94.68% with a high level of reliability of concurrence (Kappa = 0.8679).     

Full-IC manufacturability check based on dense silicon imaging

State of the art IC manufacturing process is witnessing the situation that the wave- length of stepper is more than twice the minimum feature size (193 nm wavelength vs. 90 nm/65 nm/45 nm feature size). According to the International Technology Roadmap for Semiconductors, this reality of “sub-wavelength lithography” will continue for the next several technology nodes. Optical Proximity Effect (OPE), as a technical terminol- ogy, usually refers to all of the undesired pattern vs. layout d…     

Feature sensitive deformation for triangular mesh models

Shape deformation is a useful tool for shape modeling and animation in computer graphics. In this paper, we propose a novel surface deformation method based on a feature sensitive (FS) metric. Firstly, taking unit normal vectors into account, we derive a FS Laplacian operator, which is more sensitive to featured regions of mesh models than existing operators. Secondly, we use the 1‐ring tetrahedron in the dual mesh, a volumetric structure, to encode geometric details. To preserve the shape of the tetrahedron, we introduce linear tetrahedron constraints minimizing both the distortion of the base triangle and the change of the corresponding height. These ensure that geometric details are accurately preserved during deformation. The time complexity of our new method is similar to that of existing linear Laplacian methods. Examples are included to show that our FS deformation method better preserves mesh details, especially features, than existing Laplacian methods. Copyright © 2010 John Wiley & Sons, Ltd.     

Feature weighting heuristics for analogy-based effort estimation models

Software cost estimation is one of the critical tasks in project management. In a highly demanding and competitive market environment, software project managers need robust models and methodologies to accurately predict the cost of a new project. Analogy-based cost estimation is one of the widely used models that rely on historical project data. It checks the similarity of features between past and current projects, and it approximates current project cost from past ones. One shortcoming of analogy-based cost estimation is that it assumes all project features as equal. However, these features may have different impacts on project cost based on their relevance. In this research, we present two feature weight assignment heuristics for cost estimation. We assign weights to the project features by benefiting from a statistical technique, namely principal components analysis (PCA) that is used for extracting optimal linear patterns of high dimensional data. We test our proposed heuristics on public datasets and conclude that the prediction performance in terms of MMRE and Pred(25) increases with a statistical-based assignment technique rather than random assignment approach.     

基于隐马尔可夫的网络实时风险评估

在基于隐马尔可夫模型的网络安全实时风险评估中,状态转移概率矩阵的确定是关键一步,目前基本上都是依据经验给出,具有很大主观性,不能客观反映网络安全的风险状况.为此,引入了攻击难度系数的概念,通过对数据集的统计学习,给出了状态转移概率矩阵.此外,通过对威胁进行分类,根据各类威胁的影响,给出了相应的权重.实验结果表明,该方法使得网络安全实时风险评估更加客观,为网络安全的风险管理提供了决策支持.     

New test paradigms for yield and manufacturability

As CMOS technology continues its trend down the technology nodes through 90 nm to 14 nm, our industry faces the challenge of achieving necessary yield as we integrate more on-chip circuitry having more complex, advanced process technologies. These technologies are generally less scalable than in the past, which means we're involved in a completely new yield ramp almost every two years. Closing the loop from semiconductor manufacturing back to design and process development is crucial. The author explored the nanometer-era semiconductor yield challenges, classified the yield limiting problems, and discussed how to close the loop back to design and process development. This analysis, summarized in this perspectives, reveals the key role of test and the data it generates to optimize semiconductor yield for the next generation.     

A knowledge-based approach to design for manufacturability

In the light of growing global competition, organizations around the world today are constantly under pressure to produce high-quality products at an economical price. The integration of design and manufacturing activities into one common engineering effort has been recognized as a key strategy for survival and growth. Design for manufacturability (DFM) is an approach to design that fosters the simultaneous involvement of product design and process design. The implementation of the DFM approach requires the collaboration of both the design and manufacturing functions within an organization. Many reasons can be cited for the inability to implement the DFM approach effectively, including: lack of interdisciplinary expertise of designers; inflexibility in organizational structure, which hinders interaction between design and manufacturing functions; lack of manufacturing cost information at the design phase; and absence of integrated engineering effort intended to maximize functional and manufacturability objectives. The purpose of this research is to show how expert systems methodology could be used to provide manufacturability expertise during the design phase of a product. An object- and rule-based expert system has been developed that has the capability: (1) to make process selection decisions based on a set of design and production parameters to achieve cost-effective manufacture; and (2) to estimate manufacturing cost based on the identified processes. The expertise for primary process selection is developed for casting and forging processes. The specialized processes considered are die casting, investment casting, sand casting, precision forging, open die forging and conventional die forging. The processes considered for secondary process selection are end milling and drilling. The cost estimation expertise is developed for the die casting process, the milling and drilling operations, and the manual assembly operations. The results obtained from the application of the expert system suggest that the use of expert systems methodology is a feasible method for implementing the DFM approach.     

Feature recognition from CAD models

This article presents a system dubbed IF² (Integrated Incremental Feature Finder), which functions as a feature recognizer or a feature model converter depending on whether the input CAD data contains design features. IF² recognizes three types of machining features: holes, slots and pockets. This article discusses recognition algorithms for slots and pockets. Recognition algorithms for holes are similar to those of slots (Han, 1996)     

产品概念设计可制造性评价方法研究

随着新产品开发技术的发展,人们对产品使用性能和外观艺术的要求越来越高。但概念设计不仅仅体现艺术性,更应符合工业产品的制造特点和使用特性。认为产品概念设计方案的可制造性决定于概念设计的工业设计阶段,并针对工业设计因素建立概念设计评价体系。认为产品概念设计可制造性评价是一个多层次、多属性的决策问题,建立概念设计评价模型,并基于多属性决策的理论知识给予了解决。     

Feature selection in single and ensemble learning‐based bankruptcy prediction models

Feature selection is an important data preprocessing step for the construction of an effective bankruptcy prediction model. The prediction performance can be affected by the employed feature selection and classification techniques. However, there have been very few studies of bankruptcy prediction that identify the best combination of feature selection and classification techniques. In this study, two types of feature selection methods, including filter‐ and wrapper‐based methods, are considered, and two types of classification techniques, including statistical and machine learning techniques, are employed in the development of the prediction methods. In addition, bagging and boosting ensemble classifiers are also constructed for comparison. The experimental results based on three related datasets that contain different numbers of input features show that the genetic algorithm as the wrapper‐based feature selection method performs better than the filter‐based one by information gain. It is also shown that the lowest prediction error rates for the three datasets are provided by combining the genetic algorithm with the naïve Bayes and support vector machine classifiers without bagging and boosting.     

Feature based volumes for implicit intersections

The automatic generation of volumes bounding the intersection of two implicit surfaces (isosurfaces of real functions of 3D point coordinates) or feature based volumes (FBV) is presented. Such FBVs are defined by constructive operations, function normalization and offsetting. By applying various offset operations to the intersection of two surfaces, we can obtain variations in the shape of an FBV. The resulting volume can be used as a boundary for blending operations applied to two corresponding volumes, and also for visualization of feature curves and modeling of surface based structures including microstructures.     

Design for manufacturability and reliability in extreme-scaling VLSI

In the last five decades, the number of transistors on a chip has increased exponentially in accordance with the Moore’s law, and the semiconductor industry has followed this law as long-term planning and targeting for research and development. However, as the transistor feature size is further shrunk to sub-14nm nanometer regime, modern integrated circuit (IC) designs are challenged by exacerbated manufacturability and reliability issues. To overcome these grand challenges, full-chip modeling and physical design tools are imperative to achieve high manufacturability and reliability. In this paper, we will discuss some key process technology and VLSI design co-optimization issues in nanometer VLSI.     

Development of a fuzzy decision model for manufacturability evaluation

A manufacturability evaluation decision model is formulated and analyzed based on fuzzy logic and multiple attribute decision-making under the concurrent engineering environment. The study emphasizes on the treatment of the linguistic and vagueness at the early product development stage. The study also considers the function integration of the total life cycle of a product. Hence, the integrated decision model covers the multi-level, multi-goal requirements of the products. Multiple criteria such as the goal space, the decision space, the function space, the development (i.e., product & process design) space, and the activity space, are then applied under different analysis of decision-making methods. For instances, the fuzzy multiple attribute decision-making (FMADM) combined with activity-based costing (ABC) can be used in the activity decision space. The fuzzy logic decision model can be applied in the goal decision space. The results of this study point out the importance of early decision making capability. An example of a high-pressure vessel is provided to demonstrate the proposed model for evaluating the manufacturability.     

基于粒子群优化的KPCA暂态稳定评估模型的特征提取

提出一种核主成分分析法(KPCA),用于电力系统暂态稳定评估(TSA)模型中的输入向量特征提取,并利用粒子群优化算法(PSO)对核函数参数进行优化设置.以EPRI36系统为例,对基于支持向量机(SVM)分类的暂态稳定评估模型进行仿真,结果表明该方法不仅得到了良好的预测精度,而且大大降低了输入空间的维数.