Pub Date : 2025-11-26DOI: 10.1016/j.cad.2025.104011
Nian-Ci Wu , Hong-Hong Cao , Chengzhi Liu
Geometric iterative methods form a distinct family of data-fitting techniques, distinguished by their progressive, iterative nature and endowed with clear geometric interpretations. Least-squares progressive iterative approximation (LSPIA), a prominent member of this family, enables efficient handling of large-scale point sets. In this work, we accelerate LSPIA by incorporating Polyak and Nesterov momentum together with random-sampling strategies. The resulting algorithms adaptively update control points via randomized index selection while exploiting historical information on both the control points and the gradients. We prove that the resulting algorithms converge in expectation to the least-squares fitting result of the given data points. We also derive explicit formulas for the momentum parameters. Numerical experiments demonstrate the improved efficiency and accuracy of the proposed methods compared to conventional approaches.
{"title":"Momentum-accelerated randomized geometric iterative methods for curve and surface approximation","authors":"Nian-Ci Wu , Hong-Hong Cao , Chengzhi Liu","doi":"10.1016/j.cad.2025.104011","DOIUrl":"10.1016/j.cad.2025.104011","url":null,"abstract":"<div><div>Geometric iterative methods form a distinct family of data-fitting techniques, distinguished by their progressive, iterative nature and endowed with clear geometric interpretations. Least-squares progressive iterative approximation (LSPIA), a prominent member of this family, enables efficient handling of large-scale point sets. In this work, we accelerate LSPIA by incorporating Polyak and Nesterov momentum together with random-sampling strategies. The resulting algorithms adaptively update control points via randomized index selection while exploiting historical information on both the control points and the gradients. We prove that the resulting algorithms converge in expectation to the least-squares fitting result of the given data points. We also derive explicit formulas for the momentum parameters. Numerical experiments demonstrate the improved efficiency and accuracy of the proposed methods compared to conventional approaches.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"192 ","pages":"Article 104011"},"PeriodicalIF":3.1,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145625307","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 : 2025-11-21DOI: 10.1016/j.cad.2025.104012
Chao Feng, Liang Gao, Hao Li
The enhanced geometric freedom in additive manufacturing has renewed interest in multiscale topology optimization. Nevertheless, multiscale design and additive manufacturing have yet to be sufficiently integrated to achieve multiple population, multiscale, lattice structures. In this study, we propose an STL-free method that unifies the design and manufacturing of spatially varying lattice structures via a novel functional representation of morphing strut-like microstructures with curved profiles. Specifically, a new morphing strut microstructure (MSM) is proposed and represented by a cluster of quadratic and planar half-spaces. Benefiting from the superior mechanical properties, the MSMs are integrated into the concurrent multiscale design for an optimized layout of a continuously smooth transition. To avoid prohibitively expensive surface representations and time-consuming intermediate conversion, we develop a direct slicing algorithm based on implicit representation, which is locally evaluated in an interval calculation manner. The resultant slices are directly embedded into the 3D printer without requiring intermediate data conversions such as triangulation, greatly improving additive manufacturing efficiency. The presented paradigm has been validated by some representative examples filled with different types of MSMs and demonstrated via digital light processing (DLP) 3D printing. The ideas are expected to provide a unified model data stream for solving the scalability and efficiency challenges of optimized design and additive manufacturing in engineering-scale applications.
{"title":"An STL-free method for concurrent optimization and fabrication of morphing strut-based lattice structures","authors":"Chao Feng, Liang Gao, Hao Li","doi":"10.1016/j.cad.2025.104012","DOIUrl":"10.1016/j.cad.2025.104012","url":null,"abstract":"<div><div>The enhanced geometric freedom in additive manufacturing has renewed interest in multiscale topology optimization. Nevertheless, multiscale design and additive manufacturing have yet to be sufficiently integrated to achieve multiple population, multiscale, lattice structures. In this study, we propose an STL-free method that unifies the design and manufacturing of spatially varying lattice structures via a novel functional representation of morphing strut-like microstructures with curved profiles. Specifically, a new morphing strut microstructure (MSM) is proposed and represented by a cluster of quadratic and planar half-spaces. Benefiting from the superior mechanical properties, the MSMs are integrated into the concurrent multiscale design for an optimized layout of a continuously smooth transition. To avoid prohibitively expensive surface representations and time-consuming intermediate conversion, we develop a direct slicing algorithm based on implicit representation, which is locally evaluated in an interval calculation manner. The resultant slices are directly embedded into the 3D printer without requiring intermediate data conversions such as triangulation, greatly improving additive manufacturing efficiency. The presented paradigm has been validated by some representative examples filled with different types of MSMs and demonstrated via digital light processing (DLP) 3D printing. The ideas are expected to provide a unified model data stream for solving the scalability and efficiency challenges of optimized design and additive manufacturing in engineering-scale applications.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"192 ","pages":"Article 104012"},"PeriodicalIF":3.1,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685268","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 : 2025-11-20DOI: 10.1016/j.cad.2025.104008
Yan Zhao , Qingyue Liu , Yinglei Wei
Origami patterns enable the transformation of two-dimensional flat sheet materials into three-dimensional target surfaces through folding. However, existing origami patterns exhibit limitations in both diversity and performance when applied to inverse design problems. In this paper, we focus on a novel Kresling variant pattern and demonstrate its flexibility in approximating target surfaces with freeform shapes and varying curvatures. Given a standard Kresling pattern, the upper and lower edges of each unit are expanded into four small triangles to obtain the Kresling variant pattern. This variant pattern inherits the developability and flat-foldability of the original Kresling pattern while providing more flexibility for inverse design. We then tile the partially folded Kresling variant pattern onto the target surface and solve the inverse-origami-design problem through optimization. In the optimization process, unknown variables can be selected and residuals of origami geometric constraints can be eliminated without relaxation. In addition, we demonstrate that origami approximations are capable of fitting between two target surfaces with or without developability. To improve mesh quality, we incorporate additional constraints on the aspect ratio and area of each triangular facet. These constraints supplement the origami geometric constraints for improving the regularity and stability of the final approximations. Paper fabrications and folding simulations confirm the validity and flexibility of our approach. Our work reveals the potential of the Kresling variant pattern for inverse origami design and opens up novel avenues for applications across diverse fields, including architecture, aerospace, and robotics.
{"title":"Novel Kresling variant patterns for inverse origami design","authors":"Yan Zhao , Qingyue Liu , Yinglei Wei","doi":"10.1016/j.cad.2025.104008","DOIUrl":"10.1016/j.cad.2025.104008","url":null,"abstract":"<div><div>Origami patterns enable the transformation of two-dimensional flat sheet materials into three-dimensional target surfaces through folding. However, existing origami patterns exhibit limitations in both diversity and performance when applied to inverse design problems. In this paper, we focus on a novel Kresling variant pattern and demonstrate its flexibility in approximating target surfaces with freeform shapes and varying curvatures. Given a standard Kresling pattern, the upper and lower edges of each unit are expanded into four small triangles to obtain the Kresling variant pattern. This variant pattern inherits the developability and flat-foldability of the original Kresling pattern while providing more flexibility for inverse design. We then tile the partially folded Kresling variant pattern onto the target surface and solve the inverse-origami-design problem through optimization. In the optimization process, unknown variables can be selected and residuals of origami geometric constraints can be eliminated without relaxation. In addition, we demonstrate that origami approximations are capable of fitting between two target surfaces with or without developability. To improve mesh quality, we incorporate additional constraints on the aspect ratio and area of each triangular facet. These constraints supplement the origami geometric constraints for improving the regularity and stability of the final approximations. Paper fabrications and folding simulations confirm the validity and flexibility of our approach. Our work reveals the potential of the Kresling variant pattern for inverse origami design and opens up novel avenues for applications across diverse fields, including architecture, aerospace, and robotics.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 104008"},"PeriodicalIF":3.1,"publicationDate":"2025-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579685","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 : 2025-11-17DOI: 10.1016/j.cad.2025.104010
Henriette Lipschütz , Ulrich Reitebuch , Konrad Polthier , Martin Skrodzki
Point clouds and polygonal meshes are widely used when modeling real-world scenarios. Here, point clouds arise, for instance, from acquisition processes applied in various surroundings, such as reverse engineering, rapid prototyping, or cultural preservation. Based on these raw data, polygonal meshes are created to, for example, run various simulations. For such applications, the utilized meshes must be of high quality. This paper presents an algorithm to derive triangle meshes from unstructured point clouds. The occurring edges have a close to uniform length and their lengths are bounded from below. Theoretical results guarantee the output to be manifold, provided suitable input and parameter choices. Further, the paper presents several experiments establishing that the algorithms can compete with widely used competitors in terms of quality of the output and timing and the output is stable under moderate levels of noise. Additionally, we expand the algorithm to detect and respect features on point clouds as well as to remesh polyhedral surfaces, possibly with features.
Supplementary material, an extended preprint, a link to a previously published version of the article, utilized models, and implementation details are made available online.
{"title":"Feature-aware manifold meshing and remeshing of point clouds and polyhedral surfaces with guaranteed smallest edge length","authors":"Henriette Lipschütz , Ulrich Reitebuch , Konrad Polthier , Martin Skrodzki","doi":"10.1016/j.cad.2025.104010","DOIUrl":"10.1016/j.cad.2025.104010","url":null,"abstract":"<div><div>Point clouds and polygonal meshes are widely used when modeling real-world scenarios. Here, point clouds arise, for instance, from acquisition processes applied in various surroundings, such as reverse engineering, rapid prototyping, or cultural preservation. Based on these raw data, polygonal meshes are created to, for example, run various simulations. For such applications, the utilized meshes must be of high quality. This paper presents an algorithm to derive triangle meshes from unstructured point clouds. The occurring edges have a close to uniform length and their lengths are bounded from below. Theoretical results guarantee the output to be manifold, provided suitable input and parameter choices. Further, the paper presents several experiments establishing that the algorithms can compete with widely used competitors in terms of quality of the output and timing and the output is stable under moderate levels of noise. Additionally, we expand the algorithm to detect and respect features on point clouds as well as to remesh polyhedral surfaces, possibly with features.</div><div>Supplementary material, an extended preprint, a link to a previously published version of the article, utilized models, and implementation details are made <span><span>available online</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"192 ","pages":"Article 104010"},"PeriodicalIF":3.1,"publicationDate":"2025-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145600401","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 : 2025-11-08DOI: 10.1016/j.cad.2025.104007
Caleb B. Goates, Kendrick M. Shepherd
Harmonic maps are important in generating parameterizations for various domains, particularly in two and three dimensions. General extensions of two-dimensional harmonic parameterization methods to volumetric parameterizations are known to fail in a variety of contexts, though more specialized volumetric parameterizations have been proposed. This work provides and contextualizes a counterexample to various proposed proofs that employ harmonic maps to sweep a parameterization from a base surface, , to the entire domain of a geometry that is homeomorphic to or . The existence of a counterexample clarifies that these swept parameterizations come with no inherent guarantees of bijectivity, as they may in two dimensions.
{"title":"Harmonic-based sweeps need not yield volumetric parameterizations","authors":"Caleb B. Goates, Kendrick M. Shepherd","doi":"10.1016/j.cad.2025.104007","DOIUrl":"10.1016/j.cad.2025.104007","url":null,"abstract":"<div><div>Harmonic maps are important in generating parameterizations for various domains, particularly in two and three dimensions. General extensions of two-dimensional harmonic parameterization methods to volumetric parameterizations are known to fail in a variety of contexts, though more specialized volumetric parameterizations have been proposed. This work provides and contextualizes a counterexample to various proposed proofs that employ harmonic maps to sweep a parameterization from a base surface, <span><math><msub><mrow><mi>Γ</mi></mrow><mrow><mn>0</mn></mrow></msub></math></span>, to the entire domain of a geometry that is homeomorphic to <span><math><mrow><msub><mrow><mi>Γ</mi></mrow><mrow><mn>0</mn></mrow></msub><mo>×</mo><mrow><mo>[</mo><mn>0</mn><mo>,</mo><mn>1</mn><mo>]</mo></mrow></mrow></math></span> or <span><math><mrow><msub><mrow><mi>Γ</mi></mrow><mrow><mn>0</mn></mrow></msub><mo>×</mo><msup><mrow><mi>S</mi></mrow><mrow><mn>1</mn></mrow></msup></mrow></math></span>. The existence of a counterexample clarifies that these swept parameterizations come with no inherent guarantees of bijectivity, as they may in two dimensions.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 104007"},"PeriodicalIF":3.1,"publicationDate":"2025-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145528381","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 : 2025-11-06DOI: 10.1016/j.cad.2025.104004
Olivier Coulaud
The present article studies the problem of approximating 3D surface models with meshes composed of curved triangles of arbitrary order. The considered process derives from a high-order solution-based mesh adaptation method called log-simplex method. In this case, it is locally applied on a specific 2D high-order solution, which is built from the features of the model and is defined on the tangent plane to the surface. This way, for a given mesh complexity, an optimal metric field is computed, which then drives the mesh adaptation procedure.
{"title":"High-order CAD-based surface mesh adaptation with the log-simplex method","authors":"Olivier Coulaud","doi":"10.1016/j.cad.2025.104004","DOIUrl":"10.1016/j.cad.2025.104004","url":null,"abstract":"<div><div>The present article studies the problem of approximating 3D surface models with meshes composed of curved triangles of arbitrary order. The considered process derives from a high-order solution-based mesh adaptation method called log-simplex method. In this case, it is locally applied on a specific 2D high-order solution, which is built from the features of the model and is defined on the tangent plane to the surface. This way, for a given mesh complexity, an optimal metric field is computed, which then drives the mesh adaptation procedure.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 104004"},"PeriodicalIF":3.1,"publicationDate":"2025-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145474712","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 : 2025-11-03DOI: 10.1016/j.cad.2025.104005
Min Song, Chao Li, Xiao-Wei Guo, Qing-Yang Zhang, Jie Liu, Xiang Gao
This paper introduces a physics-driven approach to improve fluid dynamics simulations of multi-body geometries with non-matching interfaces. Conventional methods often suffer from inaccuracies due to the lack of robust physical models. Our solution integrates Computational Fluid Dynamics (CFD) techniques and proposes a conservative interpolation algorithm that resolves interface mismatches without mesh modification. By using a dual-weighting scheme based on overlapping face areas, the algorithm ensures flux consistency across subdomains while maintaining high computational efficiency. Applicable to both structured and unstructured meshes, this simple yet robust method has been implemented in general-purpose CFD software and validated through complex cases. Specifically, in Couette flow between concentric cylinders, it shows a maximum 1.556% relative error in velocity distribution against analytical solutions, outperforming continuous mesh methods in accuracy. In reactor pressure vessel simulations, it achieves a pressure distribution error of 0.586% and a maximum flow distribution error of 1.645% compared to continuous mesh solutions. These results validate the method’s high accuracy and reliability in simulating diverse flow regimes, thus facilitating precise analyses for complex engineering problems.
{"title":"A physics conservation-based mesh patching algorithm for multi-body modeling and simulation","authors":"Min Song, Chao Li, Xiao-Wei Guo, Qing-Yang Zhang, Jie Liu, Xiang Gao","doi":"10.1016/j.cad.2025.104005","DOIUrl":"10.1016/j.cad.2025.104005","url":null,"abstract":"<div><div>This paper introduces a physics-driven approach to improve fluid dynamics simulations of multi-body geometries with non-matching interfaces. Conventional methods often suffer from inaccuracies due to the lack of robust physical models. Our solution integrates Computational Fluid Dynamics (CFD) techniques and proposes a conservative interpolation algorithm that resolves interface mismatches without mesh modification. By using a dual-weighting scheme based on overlapping face areas, the algorithm ensures flux consistency across subdomains while maintaining high computational efficiency. Applicable to both structured and unstructured meshes, this simple yet robust method has been implemented in general-purpose CFD software and validated through complex cases. Specifically, in Couette flow between concentric cylinders, it shows a maximum 1.556% relative error in velocity distribution against analytical solutions, outperforming continuous mesh methods in accuracy. In reactor pressure vessel simulations, it achieves a pressure distribution error of 0.586% and a maximum flow distribution error of 1.645% compared to continuous mesh solutions. These results validate the method’s high accuracy and reliability in simulating diverse flow regimes, thus facilitating precise analyses for complex engineering problems.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 104005"},"PeriodicalIF":3.1,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145474710","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 : 2025-10-30DOI: 10.1016/j.cad.2025.104003
Martin Roth , Jan Kopatsch , Kristina Wärmefjord , Rikard Söderberg , Stefan Goetz
Computer-Aided Tolerancing (CAT) software has become the standard for statistically analyzing the effects of geometrical part variations on product quality. Irrespective of CAT’s scope and technical depth, Finite Element Analysis (FEA) software, used to simulate the physical product behavior for ideal part geometry in the first place, is also often used for studies with geometrical shapes deviating from their nominal. However, this requires a manual translation of the tolerances specified in the design phase into geometrical variations represented by Finite Element (FE) meshes and their transfer to the FEA software. The method presented in this article exploits the potential of Model-Based Definition by establishing a link between Computer-Aided Design and FEA software to empower the latter for variation simulation based on semantic Geometric Dimensioning and Tolerancing (GD&T) information. To transfer this information exchanged via the Quality Information Framework (QIF) standard, a new mapping algorithm is presented that automatically decomposes FE meshes into geometrical face elements and creates a semantic link with the GD&T information carried in QIF. As a result, geometrical features are simultaneously described through meshes with nodes in the 3D Euclidean space and mathematical geometrical faces in the 2D parameter space. Exploiting this duality, mesh deviations are modeled indirectly by adjusting the mapped feature descriptions. An exemplary implementation in ANSYS® and its usage for non-intrusive structural simulations illustrates that sharing tolerancing information via QIF enables an automated, GD&T standards-compliant variation simulation within FEA software environments and is one step closer to a seamless digital thread for geometry assurance.
{"title":"Linking Model-Based Definition and Non-Intrusive Finite Element Analysis for Automated Variation Simulation","authors":"Martin Roth , Jan Kopatsch , Kristina Wärmefjord , Rikard Söderberg , Stefan Goetz","doi":"10.1016/j.cad.2025.104003","DOIUrl":"10.1016/j.cad.2025.104003","url":null,"abstract":"<div><div>Computer-Aided Tolerancing (CAT) software has become the standard for statistically analyzing the effects of geometrical part variations on product quality. Irrespective of CAT’s scope and technical depth, Finite Element Analysis (FEA) software, used to simulate the physical product behavior for ideal part geometry in the first place, is also often used for studies with geometrical shapes deviating from their nominal. However, this requires a manual translation of the tolerances specified in the design phase into geometrical variations represented by Finite Element (FE) meshes and their transfer to the FEA software. The method presented in this article exploits the potential of Model-Based Definition by establishing a link between Computer-Aided Design and FEA software to empower the latter for variation simulation based on semantic Geometric Dimensioning and Tolerancing (GD&T) information. To transfer this information exchanged via the Quality Information Framework (QIF) standard, a new mapping algorithm is presented that automatically decomposes FE meshes into geometrical face elements and creates a semantic link with the GD&T information carried in QIF. As a result, geometrical features are simultaneously described through meshes with nodes in the 3D Euclidean space and mathematical geometrical faces in the 2D parameter space. Exploiting this duality, mesh deviations are modeled indirectly by adjusting the mapped feature descriptions. An exemplary implementation in ANSYS® and its usage for non-intrusive structural simulations illustrates that sharing tolerancing information via QIF enables an automated, GD&T standards-compliant variation simulation within FEA software environments and is one step closer to a seamless digital thread for geometry assurance.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 104003"},"PeriodicalIF":3.1,"publicationDate":"2025-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145474711","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 : 2025-10-28DOI: 10.1016/j.cad.2025.104006
Jiwei Zhou , Jorge D. Camba , Pedro Company
Recent advances in generative Artificial Intelligence (AI)—particularly Large Language Models (LLMs)—offer a new paradigm for CAD interaction by enabling natural and intuitive input through texts, images, and context-aware selections. In this study, we present CADialogue, a multimodal LLM-powered conversational assistant to enable intuitive parametric CAD modeling through natural language, speech, image, and selection-based geometry interactions. Built on a general-purpose large language model, CADialogue translates user prompts into executable code to support geometry creation and context-aware editing. The system features a modular architecture that decouples prompt handling, refinement logic, and execution—allowing seamless model replacement as LLMs develop—and includes caching for rapid reuse of validated designs. We evaluate the system on 70 modeling and 10 editing tasks across varying difficulty levels, assessing performance in terms of accuracy, refinement behavior, and execution time. Results show an overall success rate of 95.71%, combining a 91.43% baseline under Text-Only input with additional recoveries enabled by Text + Image input, with robust recovery from failure via self-correction and human-in-the-loop refinement. Comparative analysis reveals that image input improves success in semantically complex prompts but introduces additional processing time. Furthermore, caching confirmed macros yields over 85.71% speedup in repeated executions. These findings highlight the potential of general-purpose LLMs for enabling accessible, iterative, and accurate CAD modeling workflows without domain-specific fine-tuning. The source code and dataset for CADialogue are available at https://github.com/Hiram31/CADialogue.
{"title":"CADialogue: A multimodal LLM-powered conversational assistant for intuitive parametric CAD modeling","authors":"Jiwei Zhou , Jorge D. Camba , Pedro Company","doi":"10.1016/j.cad.2025.104006","DOIUrl":"10.1016/j.cad.2025.104006","url":null,"abstract":"<div><div>Recent advances in generative Artificial Intelligence (AI)—particularly Large Language Models (LLMs)—offer a new paradigm for CAD interaction by enabling natural and intuitive input through texts, images, and context-aware selections. In this study, we present CADialogue, a multimodal LLM-powered conversational assistant to enable intuitive parametric CAD modeling through natural language, speech, image, and selection-based geometry interactions. Built on a general-purpose large language model, CADialogue translates user prompts into executable code to support geometry creation and context-aware editing. The system features a modular architecture that decouples prompt handling, refinement logic, and execution—allowing seamless model replacement as LLMs develop—and includes caching for rapid reuse of validated designs. We evaluate the system on 70 modeling and 10 editing tasks across varying difficulty levels, assessing performance in terms of accuracy, refinement behavior, and execution time. Results show an overall success rate of 95.71%, combining a 91.43% baseline under Text-Only input with additional recoveries enabled by Text + Image input, with robust recovery from failure via self-correction and human-in-the-loop refinement. Comparative analysis reveals that image input improves success in semantically complex prompts but introduces additional processing time. Furthermore, caching confirmed macros yields over 85.71% speedup in repeated executions. These findings highlight the potential of general-purpose LLMs for enabling accessible, iterative, and accurate CAD modeling workflows without domain-specific fine-tuning. The source code and dataset for CADialogue are available at <span><span>https://github.com/Hiram31/CADialogue</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 104006"},"PeriodicalIF":3.1,"publicationDate":"2025-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145425278","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