The manufacturing constraint of topology optimization for finding structures composed primarily of plate cross sections with an automatically decided surface normal is discussed. The anisotropic partial differential equation filter for the sensitivity of the objective function is designed such that the eigenvalue-resolved stress tensor is converted to the anisotropic filter tensor. The user can obtain an optimal shape proposal with different degrees of plate formation by changing the influence radius of the ellipsoidal filter. Plate structure formation and stiffness compliance performance are discussed through three sample problems: a solid bar subjected to torsional loads, an L-shaped member subjected to multiple loads, and a vehicle body frame intended to be a complex frame. The finite element analysis with 3–300 million degrees of freedom is required to form a shell plate structure from a large ingot with a volume fraction constraint of 1%–5%. A voxel topology optimization software that utilizes the building cube method framework available in massively parallel environments is developed, and the parallel performance of the optimization routine, including the plate filtering, is measured.
讨论了拓扑优化的制造约束，以寻找主要由板截面组成的结构，并自动决定表面法线。设计了用于目标函数灵敏度的各向异性偏微分方程滤波器，将特征值解析应力张量转换为各向异性滤波器张量。用户可以通过改变椭圆滤波器的影响半径，获得不同板形成程度的最佳形状方案。通过三个示例问题讨论了板状结构的形成和刚度顺应性能：承受扭转载荷的实心杆、承受多重载荷的 L 形构件以及拟作为复杂框架的车身框架。要从体积分数限制为 1%-5%的大型钢锭中形成壳板结构，需要进行 3-3 亿自由度的有限元分析。利用大规模并行环境中可用的建筑立方体方法框架，开发了一个体素拓扑优化软件，并测量了包括板过滤在内的优化例程的并行性能。
{"title":"Plate Manufacturing Constraint in Topology Optimization Using Anisotropic Filter","authors":"Yuji Wada , Tokimasa Shimada , Koji Nishiguchi , Shigenobu Okazawa , Makoto Tsubokura","doi":"10.1016/j.cad.2024.103823","DOIUrl":"10.1016/j.cad.2024.103823","url":null,"abstract":"<div><div>The manufacturing constraint of topology optimization for finding structures composed primarily of plate cross sections with an automatically decided surface normal is discussed. The anisotropic partial differential equation filter for the sensitivity of the objective function is designed such that the eigenvalue-resolved stress tensor is converted to the anisotropic filter tensor. The user can obtain an optimal shape proposal with different degrees of plate formation by changing the influence radius of the ellipsoidal filter. Plate structure formation and stiffness compliance performance are discussed through three sample problems: a solid bar subjected to torsional loads, an L-shaped member subjected to multiple loads, and a vehicle body frame intended to be a complex frame. The finite element analysis with 3–300 million degrees of freedom is required to form a shell plate structure from a large ingot with a volume fraction constraint of 1%–5%. A voxel topology optimization software that utilizes the building cube method framework available in massively parallel environments is developed, and the parallel performance of the optimization routine, including the plate filtering, is measured.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"180 ","pages":"Article 103823"},"PeriodicalIF":3.0,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142722617","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}
Pub Date : 2024-11-19DOI: 10.1016/j.cad.2024.103824
Sebastian Bohm, Erich Runge
Correct mesh handling and in particular domain extraction is an important step of many simulation workflows. In the boundary element method, for example, only the surfaces of arbitrarily shaped domains have to be meshed. Here, an algorithm is presented that extracts all distinct spatial regions and domains from a given non-manifold three-dimensional surface triangulation without the need for a volume mesh. Only the coordinates of the mesh vertices and the connectivity matrix of the triangulation need to be given. The process is robust, easy to implement, and efficient. No geometric features such as edges or faces need to be detected or specified for the method to work. Thus, the method is suitable for mesh formats that do not contain information about the geometry partitioning. The algorithm is presented in detail, test cases are discussed, and an exemplary implementation is given.
{"title":"Fast algorithm for extracting domains and regions from three-dimensional triangular surface meshes","authors":"Sebastian Bohm, Erich Runge","doi":"10.1016/j.cad.2024.103824","DOIUrl":"10.1016/j.cad.2024.103824","url":null,"abstract":"<div><div>Correct mesh handling and in particular domain extraction is an important step of many simulation workflows. In the boundary element method, for example, only the surfaces of arbitrarily shaped domains have to be meshed. Here, an algorithm is presented that extracts all distinct spatial regions and domains from a given non-manifold three-dimensional surface triangulation without the need for a volume mesh. Only the coordinates of the mesh vertices and the connectivity matrix of the triangulation need to be given. The process is robust, easy to implement, and efficient. No geometric features such as edges or faces need to be detected or specified for the method to work. Thus, the method is suitable for mesh formats that do not contain information about the geometry partitioning. The algorithm is presented in detail, test cases are discussed, and an exemplary implementation is given.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"180 ","pages":"Article 103824"},"PeriodicalIF":3.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142722618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-19DOI: 10.1016/j.cad.2024.103825
Xiaopeng Zheng, Junyi Duan, Na Lei, Zhongxuan Luo
Hexahedral (Hex) mesh topology optimization holds significant importance in various engineering and scientific applications. Most of the previous algorithms just use collapse operations in most cases, and less frequently use inflation operations, limited by the flexibility as well as the complexity of inflation operations in complex singularity structures, which restricts efficacy of methods. Furthermore, the singularities from previous optimization methods are located in the interior, which cannot be aligned to the features. In this paper, we verify that sheet collapse and inflation operations are capable of representing all hex mesh topology operations. Moreover, we introduce a feature-aware hex mesh optimization algorithm via sheet operations. The algorithm employs a greedy collapse strategy to simplify singularities, utilizes inflation operations to optimize high-degree singularities, and aligns singularities with feature lines. The sheet inflation algorithm we propose obtains the initial surface from an edge and is capable of generating simple surfaces even in complex topological structures. The experiments demonstrate the superior performance of our algorithm in feature preservation and optimization capability.
{"title":"Feature-aware Singularity Structure Optimization for Hex Mesh","authors":"Xiaopeng Zheng, Junyi Duan, Na Lei, Zhongxuan Luo","doi":"10.1016/j.cad.2024.103825","DOIUrl":"10.1016/j.cad.2024.103825","url":null,"abstract":"<div><div>Hexahedral (Hex) mesh topology optimization holds significant importance in various engineering and scientific applications. Most of the previous algorithms just use collapse operations in most cases, and less frequently use inflation operations, limited by the flexibility as well as the complexity of inflation operations in complex singularity structures, which restricts efficacy of methods. Furthermore, the singularities from previous optimization methods are located in the interior, which cannot be aligned to the features. In this paper, we verify that sheet collapse and inflation operations are capable of representing all hex mesh topology operations. Moreover, we introduce a feature-aware hex mesh optimization algorithm via sheet operations. The algorithm employs a greedy collapse strategy to simplify singularities, utilizes inflation operations to optimize high-degree singularities, and aligns singularities with feature lines. The sheet inflation algorithm we propose obtains the initial surface from an edge and is capable of generating simple surfaces even in complex topological structures. The experiments demonstrate the superior performance of our algorithm in feature preservation and optimization capability.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"180 ","pages":"Article 103825"},"PeriodicalIF":3.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697679","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}
Pub Date : 2024-11-15DOI: 10.1016/j.cad.2024.103822
Fangyuan Luo, Xin Li
Non-Uniform Rational B-splines Surfaces can be defined for any degrees and non-uniform knots, but existing subdivision surfaces are either uniform or of a fixed degree. The only existing non-uniform arbitrary degree subdivision is the scheme in Cashman et al. (2009). However, in order to improve the surface quality, the knot insertion strategy in Cashman et al. (2009) has the problem that the limit surface does not change continuously in terms of the perturbation of knot intervals. This paper solves this problem by introducing higher-degree hybrid non-uniform subdivision surfaces (HNUSS), where the first level refinement converts each valence extraordinary point (EP) into a valence face (Li et al., 2019). And then, the subdivision scheme can be defined with one step of splitting and several steps of averaging, where most rules are tensor-product of the arbitrary degree B-spline refinement rule with one double knot. We verify that higher-degree HNUSS limit surface is at the EPs if the knot intervals for the spoke edges of an EP are the same and has a higher order of continuity in other regions. In the absence of multiple knots at EPs, we provide a knot insertion strategy to create a uniform region around an EP. Additionally, numerical experiments show that the limit surface has satisfactory shape quality.
非均匀有理 B 样条曲面可定义为任意度和非均匀结，但现有的细分曲面要么是均匀的，要么是固定度的。现有的唯一非均匀任意度细分是 Cashman 等人（2009 年）的方案。然而，为了提高曲面质量，Cashman 等人（2009）的节点插入策略存在一个问题，即极限曲面不会随着节点间隔的扰动而连续变化。本文通过引入高阶混合非均匀细分曲面（HNUSS）解决了这一问题，其中第一级细化将每个第 n 价非常点（EP）转换为第 n 价面（李等人，2019）。然后，细分方案可以通过一步分割和几步平均来定义，其中大多数规则都是带有一个双结的任意度 B 样条细化规则的张量乘积。我们验证了，如果一个 EP 的辐边的节点间隔相同，则高阶 HNUSS 极限曲面在 EP 上是 G1，并且在其他区域具有更高阶的连续性。在 EP 上没有多个节点的情况下，我们提供了一种节点插入策略，以在 EP 周围创建一个均匀区域。此外，数值实验表明，极限曲面的形状质量令人满意。
{"title":"Higher-degrees Hybrid Non-uniform Subdivision Surfaces","authors":"Fangyuan Luo, Xin Li","doi":"10.1016/j.cad.2024.103822","DOIUrl":"10.1016/j.cad.2024.103822","url":null,"abstract":"<div><div>Non-Uniform Rational B-splines Surfaces can be defined for any degrees and non-uniform knots, but existing subdivision surfaces are either uniform or of a fixed degree. The only existing non-uniform arbitrary degree subdivision is the scheme in Cashman et al. (2009). However, in order to improve the surface quality, the knot insertion strategy in Cashman et al. (2009) has the problem that the limit surface does not change continuously in terms of the perturbation of knot intervals. This paper solves this problem by introducing higher-degree hybrid non-uniform subdivision surfaces (HNUSS), where the first level refinement converts each valence <span><math><mi>n</mi></math></span> extraordinary point (EP) into a valence <span><math><mi>n</mi></math></span> face (Li et al., 2019). And then, the subdivision scheme can be defined with one step of splitting and several steps of averaging, where most rules are tensor-product of the arbitrary degree B-spline refinement rule with one double knot. We verify that higher-degree HNUSS limit surface is <span><math><msup><mrow><mi>G</mi></mrow><mrow><mn>1</mn></mrow></msup></math></span> at the EPs if the knot intervals for the spoke edges of an EP are the same and has a higher order of continuity in other regions. In the absence of multiple knots at EPs, we provide a knot insertion strategy to create a uniform region around an EP. Additionally, numerical experiments show that the limit surface has satisfactory shape quality.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"179 ","pages":"Article 103822"},"PeriodicalIF":3.0,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142699329","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}
Pub Date : 2024-11-13DOI: 10.1016/j.cad.2024.103820
Carlos Andrés Restrepo García , Yann Ledoux , Nabil Anwer , Vincent Delos , Laurent Pierre , Denis Teissandier
Contact modeling is an important activity in the geometrical and tolerancing management. The research on contact modeling using methods based on sets of constraints has focused on the stack-up functions or graph reductions for the accumulation of geometric variations. Even when the Skin Model paradigm is used to simulate form deviations on mating surfaces, the impact of disregarding those deviations has not been formally discriminated. In this paper, an enriched polyhedral-based approach for the contact modeling of mechanisms is proposed. The contact is simulated through a rigid body model with no frictional forces based on the screw theory. In this method, the external loadings on the mechanism are translated into an additional half-space in the polyhedron that imposes an additional restriction to the polyhedron operand. By explicitly including the external mechanical loadings, the impact of the form deviations on a functional condition can be discriminated precisely. In this paper, a case study of a sliding contact between two mating parts of a spectrometer is presented to further illustrate the method advantages.
{"title":"An Enriched Polyhedral-based Simulation for the Contact Modeling with Form Defects and Mechanical Loads","authors":"Carlos Andrés Restrepo García , Yann Ledoux , Nabil Anwer , Vincent Delos , Laurent Pierre , Denis Teissandier","doi":"10.1016/j.cad.2024.103820","DOIUrl":"10.1016/j.cad.2024.103820","url":null,"abstract":"<div><div>Contact modeling is an important activity in the geometrical and tolerancing management. The research on contact modeling using methods based on sets of constraints has focused on the stack-up functions or graph reductions for the accumulation of geometric variations. Even when the Skin Model paradigm is used to simulate form deviations on mating surfaces, the impact of disregarding those deviations has not been formally discriminated. In this paper, an enriched polyhedral-based approach for the contact modeling of mechanisms is proposed. The contact is simulated through a rigid body model with no frictional forces based on the screw theory. In this method, the external loadings on the mechanism are translated into an additional half-space in the polyhedron that imposes an additional restriction to the polyhedron operand. By explicitly including the external mechanical loadings, the impact of the form deviations on a functional condition can be discriminated precisely. In this paper, a case study of a sliding contact between two mating parts of a spectrometer is presented to further illustrate the method advantages.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"180 ","pages":"Article 103820"},"PeriodicalIF":3.0,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142748666","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}
Pub Date : 2024-11-01DOI: 10.1016/j.cad.2024.103821
Xinming Li, Lujie Ma, Bowen Ji, Kuan Fan, Zhengdong Huang
This paper presents a novel approach for extracting fiber paths from the optimized lamination parameters (LPs) of variable stiffness laminated shells, utilizing the framework of physics-informed neural network (PINN). In this methodology, each fiber layer is associated with a specific stream function, which is approximated by an independent neural network. The stream function is governed by a partial differential equation (PDE) derived from the fiber orientation field in the parameter space. Moreover, the isocontours of the stream function are transformed into the actual fiber paths in the physical space. To account for manufacturing constraints, Riemannian geometry serves as a computational tool to determine the intrinsic distance between adjacent fiber paths and the geodesic curvature of the isocontours. By incorporating regularization terms into the loss function based on the physical relationships, the constrained optimization problem is converted into an unconstrained one, making it more suitable for neural network training. Meanwhile, a fiber path extraction (FPE) algorithm is used to minimize the loss function at randomly sampled points through gradient descent. The numerical results suggest that the extraction of fiber paths using PINN can achieve satisfactory levels of accuracy while effectively satisfying the imposed constraints.
{"title":"Extracting fiber paths from the optimized lamination parameters of variable-stiffness laminated shells based on physic-informed neural network","authors":"Xinming Li, Lujie Ma, Bowen Ji, Kuan Fan, Zhengdong Huang","doi":"10.1016/j.cad.2024.103821","DOIUrl":"10.1016/j.cad.2024.103821","url":null,"abstract":"<div><div>This paper presents a novel approach for extracting fiber paths from the optimized lamination parameters (LPs) of variable stiffness laminated shells, utilizing the framework of physics-informed neural network (PINN). In this methodology, each fiber layer is associated with a specific stream function, which is approximated by an independent neural network. The stream function is governed by a partial differential equation (PDE) derived from the fiber orientation field in the parameter space. Moreover, the isocontours of the stream function are transformed into the actual fiber paths in the physical space. To account for manufacturing constraints, Riemannian geometry serves as a computational tool to determine the intrinsic distance between adjacent fiber paths and the geodesic curvature of the isocontours. By incorporating regularization terms into the loss function based on the physical relationships, the constrained optimization problem is converted into an unconstrained one, making it more suitable for neural network training. Meanwhile, a fiber path extraction (FPE) algorithm is used to minimize the loss function at randomly sampled points through gradient descent. The numerical results suggest that the extraction of fiber paths using PINN can achieve satisfactory levels of accuracy while effectively satisfying the imposed constraints.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"179 ","pages":"Article 103821"},"PeriodicalIF":3.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657976","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}
Pub Date : 2024-11-01DOI: 10.1016/j.cad.2024.103813
Jianping Yang , Qiaoyun Wu , Yuan Zhang , Jiajia Dai , Jun Wang
For the highly interacting machining features, Layered Projection Decomposition Method presents inferior recognition efficiency and accuracy, due to its high-cost 3D projection and failures in determining projection faces for internal occluded faces. To address these issues, we propose a potential hybrid recognition framework. We first introduce a straightforward adjacent projection wire (APW) over UV wires, automatically restoring the full projection wires from highly interacting features. Building on APWs, an efficient hybrid boundary representation and its corresponding unambiguous primitive definitions are proposed by combining with graph-based boundary representations. Subsequently, we design an efficient primitive decomposition method by introducing primitive boundary matching to decide the initial projection faces, and introducing iterative projection boundary expansion to complete the full primitives from occluded faces. Moreover, we establish an efficient Graph Neural Network to learn the distinguishable distributions over the decomposed primitives. Specifically, an Adjacency Attention Unit is proposed to automatically perceive the influence weight of adjacent nodes, leading to more discriminative self-adaptive shape embedding for efficient primitive recognition. Finally, we summarize convenient reconstruction rules to correct the wrong predictions of feature faces with indistinguishable adjacent relationships. To evaluate the effectiveness of the proposed recognition framework, CAD models of complex aircraft structural parts are collected to present a challenging machining feature dataset. Extensive numerical experiments demonstrate that the proposed hybrid recognition framework enables significant improvements over the state-of-the-art machining feature recognition techniques.
{"title":"A Hybrid Recognition Framework for Highly Interacting Machining Features Based on Primitive Decomposition, Learning and Reconstruction","authors":"Jianping Yang , Qiaoyun Wu , Yuan Zhang , Jiajia Dai , Jun Wang","doi":"10.1016/j.cad.2024.103813","DOIUrl":"10.1016/j.cad.2024.103813","url":null,"abstract":"<div><div>For the highly interacting machining features, Layered Projection Decomposition Method presents inferior recognition efficiency and accuracy, due to its high-cost 3D projection and failures in determining projection faces for internal occluded faces. To address these issues, we propose a potential hybrid recognition framework. We first introduce a straightforward adjacent projection wire (APW) over UV wires, automatically restoring the full projection wires from highly interacting features. Building on APWs, an efficient hybrid boundary representation and its corresponding unambiguous primitive definitions are proposed by combining with graph-based boundary representations. Subsequently, we design an efficient primitive decomposition method by introducing primitive boundary matching to decide the initial projection faces, and introducing iterative projection boundary expansion to complete the full primitives from occluded faces. Moreover, we establish an efficient Graph Neural Network to learn the distinguishable distributions over the decomposed primitives. Specifically, an Adjacency Attention Unit is proposed to automatically perceive the influence weight of adjacent nodes, leading to more discriminative self-adaptive shape embedding for efficient primitive recognition. Finally, we summarize convenient reconstruction rules to correct the wrong predictions of feature faces with indistinguishable adjacent relationships. To evaluate the effectiveness of the proposed recognition framework, CAD models of complex aircraft structural parts are collected to present a challenging machining feature dataset. Extensive numerical experiments demonstrate that the proposed hybrid recognition framework enables significant improvements over the state-of-the-art machining feature recognition techniques.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"179 ","pages":"Article 103813"},"PeriodicalIF":3.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657977","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}
Pub Date : 2024-10-18DOI: 10.1016/j.cad.2024.103812
Zhiyong Su , Changchang Wang , Kun Jiang , Kai Jiang , Weiqing Li
Despite existing supervised point cloud denoising methods having made great progress, they require paired ideal noisy-clean datasets for training which is expensive and impractical in real-world applications. Moreover, they may perform the denoising process multiple times with fixed network parameters for better denoising results at test time. To address above issues, this paper proposes a self-supervised iterative training framework (SITF) for point cloud denoising, which only requires single noisy point clouds and a noise model. Given an off-the-shelf denoising network and original noisy point clouds, firstly, an intermediate noisier-noisy dataset is created by adding additional noises from the known noise model to noisy point clouds (i.e. learning targets). Secondly, after training on the noisier-noisy dataset, the denoising network is employed to denoise the original noisy point clouds to obtain the learning targets for the next iteration. The above two steps are iteratively and alternatively performed to get a better and better trained denoising network. Furthermore, to get better learning targets for the next round, this paper also proposes a novel iterative denoising network (IDN) architecture of stacked source attention denoising modules. The IDN explicitly models the iterative denoising process internally within a single network via reforming the given denoising network. Experimental results show that existing supervised networks trained through the SITF can achieve competitive denoising results and even outperform supervised networks under high noise conditions. The source code can be found at: https://github.com/VCG-NJUST/SITF.
{"title":"SITF: A Self-Supervised Iterative Training Framework for Point Cloud Denoising","authors":"Zhiyong Su , Changchang Wang , Kun Jiang , Kai Jiang , Weiqing Li","doi":"10.1016/j.cad.2024.103812","DOIUrl":"10.1016/j.cad.2024.103812","url":null,"abstract":"<div><div>Despite existing supervised point cloud denoising methods having made great progress, they require paired ideal noisy-clean datasets for training which is expensive and impractical in real-world applications. Moreover, they may perform the denoising process multiple times with fixed network parameters for better denoising results at test time. To address above issues, this paper proposes a self-supervised iterative training framework (SITF) for point cloud denoising, which only requires single noisy point clouds and a noise model. Given an off-the-shelf denoising network and original noisy point clouds, firstly, an intermediate noisier-noisy dataset is created by adding additional noises from the known noise model to noisy point clouds (i.e. learning targets). Secondly, after training on the noisier-noisy dataset, the denoising network is employed to denoise the original noisy point clouds to obtain the learning targets for the next iteration. The above two steps are iteratively and alternatively performed to get a better and better trained denoising network. Furthermore, to get better learning targets for the next round, this paper also proposes a novel iterative denoising network (IDN) architecture of stacked source attention denoising modules. The IDN explicitly models the iterative denoising process internally within a single network via reforming the given denoising network. Experimental results show that existing supervised networks trained through the SITF can achieve competitive denoising results and even outperform supervised networks under high noise conditions. The source code can be found at: <span><span>https://github.com/VCG-NJUST/SITF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"179 ","pages":"Article 103812"},"PeriodicalIF":3.0,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142528272","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}
Pub Date : 2024-10-17DOI: 10.1016/j.cad.2024.103811
Rafael Merli , Antolín Martínez-Martínez , Juan José Ródenas , Marc Bosch-Galera , Enrique Nadal
In today’s industry, the rapid evolution in the design and development of optimized mechanical components to meet customer requirements represents a significant challenge for companies. These companies seek efficient solutions to enhance their products in terms of stiffness and strength. One powerful approach is Topology Optimization, which aims to determine the optimal material distribution within a predefined domain to maximize the overall component’s stiffness. Achieving high-resolution solutions is also crucial for accurately defining the final material distribution. While standard Topology Optimization tools can propose optimal solutions for entire components, they struggle with small-scale details (such as trabecular structures) due to prohibitive computational costs. To address this issue, our proposed approach introduces a two-level topology optimization methodology considering density-based techniques. The proposed methodology includes three steps: The first one subdivides the whole component in cells and generates a coarse optimized low-definition material distribution, assigning a different density to each cell. Since the output stresses from the coarse problem are not equilibrated into each cell, they must not be directly used in the fine level. Thus, the second step uses the equilibrating traction recovery approach to convert the cell nodal forces into equilibrated lateral tractions over the cell boundary. Finally, taking as input data the densities from the coarse optimization and imposing these lateral tractions as Neumann boundary conditions, each cell is optimized at fine level. The main goal of this work is to efficiently solve high-resolution topology optimization problems using a two-level mechanically-continuous method, which would be unaffordable with standard computing facilities and the current techniques.
{"title":"Two-Level High-Resolution Structural Topology Optimization with Equilibrated Cells","authors":"Rafael Merli , Antolín Martínez-Martínez , Juan José Ródenas , Marc Bosch-Galera , Enrique Nadal","doi":"10.1016/j.cad.2024.103811","DOIUrl":"10.1016/j.cad.2024.103811","url":null,"abstract":"<div><div>In today’s industry, the rapid evolution in the design and development of optimized mechanical components to meet customer requirements represents a significant challenge for companies. These companies seek efficient solutions to enhance their products in terms of stiffness and strength. One powerful approach is Topology Optimization, which aims to determine the optimal material distribution within a predefined domain to maximize the overall component’s stiffness. Achieving high-resolution solutions is also crucial for accurately defining the final material distribution. While standard Topology Optimization tools can propose optimal solutions for entire components, they struggle with small-scale details (such as trabecular structures) due to prohibitive computational costs. To address this issue, our proposed approach introduces a two-level topology optimization methodology considering density-based techniques. The proposed methodology includes three steps: The first one subdivides the whole component in cells and generates a coarse optimized low-definition material distribution, assigning a different density to each cell. Since the output stresses from the coarse problem are not equilibrated into each cell, they must not be directly used in the fine level. Thus, the second step uses the equilibrating traction recovery approach to convert the cell nodal forces into equilibrated lateral tractions over the cell boundary. Finally, taking as input data the densities from the coarse optimization and imposing these lateral tractions as Neumann boundary conditions, each cell is optimized at fine level. The main goal of this work is to efficiently solve high-resolution topology optimization problems using a two-level mechanically-continuous method, which would be unaffordable with standard computing facilities and the current techniques.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"179 ","pages":"Article 103811"},"PeriodicalIF":3.0,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142528347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-10DOI: 10.1016/j.cad.2024.103809
Qiang Zou, Lizhen Zhu, Jiayu Wu, Zhijie Yang
This paper presents a learning-based method to solve the traditional parameterization and knot placement problems in B-spline approximation. Different from conventional heuristic methods or recent AI-based methods, the proposed method does not assume ordered or fixed-size data points as input. There is also no need for manually setting the number of knots. Parameters and knots are generated in an associative way to attain better parameter-knot alignment, and therefore a higher approximation accuracy. These features are attained by using a new generative model SplineGen, which casts the parameterization and knot placement problems as a sequence-to-sequence translation problem. It first adopts a shared autoencoder model to learn a 512-D embedding for each input point, which has the local neighborhood information implicitly captured. Then these embeddings are autoregressively decoded into parameters and knots by two associative decoders, a generative process automatically determining the number of knots, their placement, parameter values, and their ordering. The two decoders are made to work in a coordinated manner by a new network module called internal cross-attention. Once trained, SplineGen demonstrates a notable improvement over existing methods, with one to two orders of magnitude increase in approximation accuracy on test data.
{"title":"SplineGen: Approximating unorganized points through generative AI","authors":"Qiang Zou, Lizhen Zhu, Jiayu Wu, Zhijie Yang","doi":"10.1016/j.cad.2024.103809","DOIUrl":"10.1016/j.cad.2024.103809","url":null,"abstract":"<div><div>This paper presents a learning-based method to solve the traditional parameterization and knot placement problems in B-spline approximation. Different from conventional heuristic methods or recent AI-based methods, the proposed method does not assume ordered or fixed-size data points as input. There is also no need for manually setting the number of knots. Parameters and knots are generated in an associative way to attain better parameter-knot alignment, and therefore a higher approximation accuracy. These features are attained by using a new generative model SplineGen, which casts the parameterization and knot placement problems as a sequence-to-sequence translation problem. It first adopts a shared autoencoder model to learn a 512-D embedding for each input point, which has the local neighborhood information implicitly captured. Then these embeddings are autoregressively decoded into parameters and knots by two associative decoders, a generative process automatically determining the number of knots, their placement, parameter values, and their ordering. The two decoders are made to work in a coordinated manner by a new network module called internal cross-attention. Once trained, SplineGen demonstrates a notable improvement over existing methods, with one to two orders of magnitude increase in approximation accuracy on test data.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"178 ","pages":"Article 103809"},"PeriodicalIF":3.0,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142433629","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号