Computer-Aided Design最新文献_第10页

Extending Point-Based Deep Learning Approaches for Better Semantic Segmentation in CAD 基于扩展点的深度学习方法在CAD中实现更好的语义分割

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-10 DOI: 10.1016/j.cad.2023.103629

Gerico Vidanes , David Toal , Xu Zhang , Andy Keane , Jon Gregory , Marco Nunez

{"title":"Extending Point-Based Deep Learning Approaches for Better Semantic Segmentation in CAD","authors":"Gerico Vidanes , David Toal , Xu Zhang , Andy Keane , Jon Gregory , Marco Nunez","doi":"10.1016/j.cad.2023.103629","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103629","url":null,"abstract":"<div><p>Geometry understanding is a core concept of computer-aided design and engineering (CAD/CAE). Deep neural networks have increasingly shown success as a method of processing complex inputs to achieve abstract tasks. This work revisits a generic and relatively simple approach to 3D deep learning – a point-based graph neural network – and develops best-practices and modifications to alleviate traditional drawbacks. It is shown that these methods should not be discounted for CAD tasks; with proper implementation, they can be competitive with more specifically designed approaches. Through an additive study, this work investigates how the boundary representation data can be fully utilised by leveraging the flexibility of point-based graph networks. The final configuration significantly improves on the predictive accuracy of a standard <em>PointNet++</em> network across multiple CAD model segmentation datasets and achieves state-of-the-art performance on the <em>MFCAD++</em> machining features dataset. The proposed modifications leave the core neural network unchanged and results also suggest that they can be applied to other point-based approaches.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49711218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multicomponent Topology Optimization Method Considering Stepwise Linear Assemblability with a Fictitious Physical Model 考虑虚拟物理模型分步线性可装配性的多部件拓扑优化方法

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-06 DOI: 10.1016/j.cad.2023.103628

R. Hirosawa , M. Noda , K. Matsushima , Y. Noguchi , T. Yamada

引用次数: 0

Simplification of 3D CAD Model in Voxel Form for Mechanical Parts Using Generative Adversarial Networks 用生成对抗性网络简化机械零件的体素形式三维CAD模型

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-01 DOI: 10.1016/j.cad.2023.103577

Hyunoh Lee , Jinwon Lee , Soonjo Kwon , Karthik Ramani , Hyung-gun Chi , Duhwan Mun

{"title":"Simplification of 3D CAD Model in Voxel Form for Mechanical Parts Using Generative Adversarial Networks","authors":"Hyunoh Lee , Jinwon Lee , Soonjo Kwon , Karthik Ramani , Hyung-gun Chi , Duhwan Mun","doi":"10.1016/j.cad.2023.103577","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103577","url":null,"abstract":"<div><p>Most three-dimensional (3D) computer-aided design (CAD) models of mechanical parts, created during the design stage, have high shape complexity. The shape complexity required of CAD models reduces according to the field of application. Therefore, it is necessary to simplify the shapes of 3D CAD models, depending on their applications. Traditional simplification methods recognize simplification target shape based on a pre-defined algorithm. Such algorithm-based methods have difficulty processing unusual partial shapes not considered in the CAD model. This paper proposes a method that uses a network based on a generative adversarial network (GAN) to simplify the 3D CAD models of mechanical parts. The proposed network recognizes and removes simplification target shapes included in the 3D CAD models of mechanical parts. A 3D CAD model dataset was constructed to train the 3D CAD model simplification network. 3D CAD models are represented in voxel form in the dataset. Next, the constructed training dataset was used to train the proposed network. Finally, a 3D voxel simplification experiment was performed to evaluate the performance of the trained network. The experiment results showed that the network had an average error rate of 3.38% for the total area of the mechanical part and an average error rate of 14.61% for the simplification target area.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49711094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Region-growing GradNormal Algorithm for Geometrically and Topologically Accurate Mesh Extraction 一种用于几何和拓扑精确网格提取的区域增长GradNormal算法

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-01 DOI: 10.1016/j.cad.2023.103559

Chen Zong , Jinhui Zhao , Pengfei Wang , Shuangmin Chen , Shiqing Xin , Yuanfeng Zhou , Changhe Tu , Wenping Wang

{"title":"A Region-growing GradNormal Algorithm for Geometrically and Topologically Accurate Mesh Extraction","authors":"Chen Zong , Jinhui Zhao , Pengfei Wang , Shuangmin Chen , Shiqing Xin , Yuanfeng Zhou , Changhe Tu , Wenping Wang","doi":"10.1016/j.cad.2023.103559","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103559","url":null,"abstract":"<div><p>With the prevalence of implicit shape processing and reconstruction, extracting a polygonal mesh of an isosurface from volume data, which plays an important role in these tasks, is receiving more and more attention. GradNormal, a recently proposed marching tetrahedra method, can effectively extract high-quality meshes from analytic functional shapes but suffers from detail loss and computational inefficiency issues. In this paper, we improve GradNormal from four aspects. First, we extend GradNormal from an analytic function to an arbitrary geometric domain equipped with the projection operation. Second, we select a seed tetrahedron and find only the tetrahedra intersecting the implicit surface, in a region-growing style, which helps save memory and accelerate calculation. Third, we invent a hierarchical tiling mechanism to enhance the recovery accuracy of the resulting mesh, unlike the uniform tiling used in GradNormal. Finally, we propose to accurately predict how the underlying surface goes through a tetrahedral element so that complicated topological structures such as thin plates and gaps can be well captured. Extensive experimental results on challenging shapes show that the improved GradNormal is able to quickly produce a feature-adapted triangle mesh that is more topologically and geometrically accurate than the state-of-the-art.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49761553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Simple Point-based Iso-Scallop Tool Path Planning Method for Noisy Point Clouds with High Robustness and Controlled Errors 一种基于简单点的高鲁棒性、误差可控的噪声点云等距扇贝刀具路径规划方法

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-01 DOI: 10.1016/j.cad.2023.103560

Guoyue Luo, Qiang Zou

{"title":"A Simple Point-based Iso-Scallop Tool Path Planning Method for Noisy Point Clouds with High Robustness and Controlled Errors","authors":"Guoyue Luo, Qiang Zou","doi":"10.1016/j.cad.2023.103560","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103560","url":null,"abstract":"<div><p>With the rapid advances in 3D scanning and vision technologies, point clouds have seen a significant increase in their application to CNC machining. As an important way to generate tool paths from point clouds, point-based direct planning methods are, however, now restricted to high-quality point clouds. Most existing methods would have robustness issues if a noisy point cloud is given due to their reliance on the noise-sensitive estimation of differential properties from point clouds. Error control under noisy point clouds is also rarely considered. This paper presents a robust and error-controlled point-based iso-scallop tool path planning method for CNC machining with ball-nosed cutters. It casts the problem of searching for scallop/CL points to another problem of finding circle-sphere intersection points and the maximum/minimum among them. Both circle-sphere intersections and <strong><em>max/min</em></strong> comparisons are easy to implement and robust. It has also been theoretically proved that the intersections and comparisons can ensure an error bound of <span><math><mrow><mn>2</mn><mi>ϵ</mi></mrow></math></span> on the final results if two conditions called <span><math><mi>ϵ</mi></math></span>-sampling and <span><math><mi>ϵ</mi></math></span>-covering are met. The effectiveness of the method has been demonstrated by a series of examples and comparisons.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49761556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Towards G1-Continuous Multi-Strip Path-Planning for 5-Axis Flank CNC Machining of Free-Form Surfaces Using Conical Cutting Tools 面向G1连续多条路径规划的五轴平面数控加工自由曲面的锥形刀具

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-01 DOI: 10.1016/j.cad.2023.103555

Kanika Rajain , Michal Bizzarri , Miroslav Lávička , Jiří Kosinka , Michael Bartoň

{"title":"Towards G1-Continuous Multi-Strip Path-Planning for 5-Axis Flank CNC Machining of Free-Form Surfaces Using Conical Cutting Tools","authors":"Kanika Rajain , Michal Bizzarri , Miroslav Lávička , Jiří Kosinka , Michael Bartoň","doi":"10.1016/j.cad.2023.103555","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103555","url":null,"abstract":"<div><p>Existing flank milling path-planning methods typically lead to tiny gaps or overlaps between neighboring paths, which causes artifacts and imperfections in the workpiece. We propose a new multi-strip path-planning method for 5-axis flank milling of free-form surfaces which targets <span><math><msup><mrow><mi>G</mi></mrow><mrow><mn>1</mn></mrow></msup></math></span> (tangent-plane) continuity of the neighboring strips along shared boundaries. While for some geometries one cannot achieve <span><math><msup><mrow><mi>G</mi></mrow><mrow><mn>1</mn></mrow></msup></math></span> continuity and high approximation quality at the same time, our optimization framework offers a good trade-off between machining accuracy in terms of distance error and the <span><math><msup><mrow><mi>G</mi></mrow><mrow><mn>1</mn></mrow></msup></math></span> connection of neighboring strips. We demonstrate our algorithm on synthetic free-form surfaces as well as on industrial benchmark datasets, showing that we are able to meet fine industrial tolerances and simultaneously significantly reduce the kink angle of adjacent strips, and consequently to improve the surface finish in terms of smoothness.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49710976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Partition-based Print Sequence Planning and Adaptive Slicing for Scalar Field-based Multi-axis Additive Manufacturing 基于标量场的多轴增材制造中基于分区的打印序列规划和自适应切片

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-01 DOI: 10.1016/j.cad.2023.103576

Tak Yu Lau , Li Chen , Dong He , Zhaoyu Li , Kai Tang

{"title":"Partition-based Print Sequence Planning and Adaptive Slicing for Scalar Field-based Multi-axis Additive Manufacturing","authors":"Tak Yu Lau , Li Chen , Dong He , Zhaoyu Li , Kai Tang","doi":"10.1016/j.cad.2023.103576","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103576","url":null,"abstract":"<div><p>While multi-axis additive manufacturing is found to be a good solution to the inherent limitations of conventional 2.5D additive manufacturing, it is a much more sophisticated process. Among different existing multi-axis process planning algorithms, we are interested in those based on a scalar field, in which print slices are the iso-surfaces of a scalar field embedded in the 3D model. In this paper, we propose a partitioned-based print sequence planning algorithm and an adaptive slicing algorithm, which together determine a complete multi-axis printing process for an arbitrary solid model. The first algorithm iteratively subdivides the model into a set of components such that a collision-free print sequence can be established among the components. The second algorithm then extracts print slices from each component such that all these slices satisfy the self-support condition. Since an arbitrary model may not satisfy both the self-support and collision-free requirements, we also define certain critical printability rules at the beginning to check whether a given input model with its associated scalar field is printable. The generated print slices and print sequence by the proposed two algorithms are guaranteed to be printable. Furthermore, a shorter total fabrication time and a better surface quality are achieved. Physical experiments of four test models are performed on a homebuilt multi-axis FDM printer, whose results verify the capabilities of the proposed algorithms.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49711092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Review of a B-spline based Volumetric Representation: Design, Analysis and Fabrication of Porous and/or Heterogeneous Geometries 基于b样条的体积表示:多孔和/或非均质几何的设计、分析和制造综述

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-01 DOI: 10.1016/j.cad.2023.103587

Gershon Elber

{"title":"A Review of a B-spline based Volumetric Representation: Design, Analysis and Fabrication of Porous and/or Heterogeneous Geometries","authors":"Gershon Elber","doi":"10.1016/j.cad.2023.103587","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103587","url":null,"abstract":"<div><p>The needs of modern (additive) manufacturing (AM) technologies can no longer be satisfied by geometric modeling tools that are based on boundary representations (B-reps) - AM requires the representation and manipulation of interior heterogeneous fields and materials. Further, while the need for a tight coupling between design and analysis has been recognized as crucial almost since geometric modeling (GM) was conceived, contemporary GM systems only offer a loose link between the two, if at all.</p><p>For more than half a century, the (trimmed) Non-Uniform Rational B-spline (NURBs) surface representation has been the B-rep of choice for virtually all the GM industry. Fundamentally, B-rep GM has evolved little during this period. In this work, we review almost a decade of research and development in extending this boundary representation to a B-spline based, volumetric representation (V-rep) that successfully confronts the existing and anticipated design, analysis, and manufacturing foreseen challenges. We have extended all fundamental B-rep GM operations, such as primitive and surface constructors, and Boolean operations, to trimmed trivariate V-reps. This enables the much-needed tight link between the designed geometry and (iso-geometric) analysis on one hand and the full support of (additive) manufacturing of porous, (graded-) heterogeneous and anisotropic geometries, on the other. Examples and applications of V-rep GM, that span design, analysis and optimization, and AM, of lattice- and micro-structure synthesis as well as graded-heterogeneity, are demonstrated, with emphasis on AM.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49733278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Co-design Optimization of Moving Parts for Compliance and Collision Avoidance 运动部件顺应性与避碰协同设计优化

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-01 DOI: 10.1016/j.cad.2023.103547

Amir M. Mirzendehdel, Morad Behandish

{"title":"Co-design Optimization of Moving Parts for Compliance and Collision Avoidance","authors":"Amir M. Mirzendehdel, Morad Behandish","doi":"10.1016/j.cad.2023.103547","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103547","url":null,"abstract":"<div><p>Design requirements for moving parts in mechanical assemblies are typically specified in terms of interactions with other parts. Some are purely kinematic (e.g., pairwise collision avoidance) while others depend on physics and material properties (e.g., deformation under loads). Kinematic design methods and physics-based shape/topology optimization (SO/TO) deal separately with these requirements. They rarely talk to each other as the former uses set algebra and group theory while the latter requires discretizing and solving differential equations. Hence, optimizing a moving part based on physics typically relies on either neglecting or pruning kinematic constraints in advance, e.g., by restricting the design domain to a collision-free space using an unsweep operation. In this paper, we show that TO can be used to co-design two or more parts in relative motion to simultaneously satisfy physics-based criteria and collision avoidance. We restrict our attention to maximizing linear-elastic stiffness while penalizing collision measures aggregated in time. We couple the TO loops for two parts in relative motion so that the evolution of each part’s shape is accounted for when penalizing collision for the other part. The collision measures are computed by a correlation functional that can be discretized by left- and right-multiplying the shape design variables by a pre-computed matrix that depends solely on the motion. This decoupling is key to making the computations scalable for TO iterations. We demonstrate the effectiveness of the approach with 2D and 3D examples.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49733487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Symmetrization of 2D Polygonal Shapes Using Mixed-Integer Programming 用混合整数规划实现二维多边形的对称化

IF 4.3 3区计算机科学

Computer-Aided Design Pub Date : 2023-10-01 DOI: 10.1016/j.cad.2023.103572

Jin Huang, Jantien Stoter, Liangliang Nan

{"title":"Symmetrization of 2D Polygonal Shapes Using Mixed-Integer Programming","authors":"Jin Huang, Jantien Stoter, Liangliang Nan","doi":"10.1016/j.cad.2023.103572","DOIUrl":"https://doi.org/10.1016/j.cad.2023.103572","url":null,"abstract":"<div><p>Symmetry widely exists in nature and man-made shapes, but it is unavoidably distorted during the process of growth, design, digitalization, and reconstruction steps. To enhance symmetry, traditional methods follow the <em>detect-then-symmetrize</em> paradigm, which is sensitive to noise in the detection phase, resulting in ambiguities for the subsequent symmetrization step. In this work, we propose a novel optimization-based framework that jointly detects and optimizes symmetry for 2D shapes represented as polygons. Our method can detect and optimize symmetry using a single objective function. Specifically, we formulate symmetry detection and optimization as a mixed-integer program. Our method first generates a set of candidate symmetric edge pairs, which are then encoded as binary variables in our optimization. The geometry of the shape is expressed as continuous variables, which are then optimized together with the binary variables. The symmetry of the shape is enforced by the designed hard constraints. After the optimization, both the optimal symmetric edge correspondences and the geometry are obtained. Our method simultaneously detects all the symmetric primitive pairs and enhances the symmetry of a model while minimally altering its geometry. We have tested our method on a variety of shapes from designs and vectorizations, and the results have demonstrated its effectiveness.</p></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":null,"pages":null},"PeriodicalIF":4.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49711116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0