cad model conversion

This study addresses the persistent challenges of version control in modern computer-aided design (CAD), where data complexity and strong interdependencies hinder effective implementation, thereby limiting design traceability, variant management, and team collaboration. Through qualitative content analysis, the authors systematically coded and synthesized insights from 170 online forum posts, revealing recurring sociotechnical challenges that CAD users face in version management, continuity, scoping, and distribution. The work introduces “infrastructural reflexivity” as a novel design principle for CAD tools, emphasizing support for coordinated work and cross-boundary collaboration. This concept offers actionable guidance for software developers and opens new research avenues for reimagining version control systems in complex design environments.

Existing mesh-based generative methods for mechanical engineering lack the precision and parametric editability required for high-fidelity CAD design. Method: We propose the first end-to-end, natural language–driven framework for generating constructive solid geometry (CSG) code tailored to CAD workflows—bypassing low-fidelity mesh representations to directly produce syntactically correct, geometrically valid, and CAD-importable parametric CSG scripts in Python. Contribution/Results: Our approach introduces three key innovations: (1) the first application of large language models (LLMs) to CSG code generation; (2) the construction of the first publicly available Python dataset mapping boundary representation (BREP) geometries to CSG programs, annotated with natural language descriptions (validated by GPT-4 and refined manually); and (3) a pipeline integrating BREP geometric parsing, CSG compilation, and supervised fine-tuning (SFT) to map semantic descriptions and spatial constraints to executable geometric code. Experiments demonstrate substantial improvements in both automation capability and modeling accuracy for mechanical design.

Existing CAD generation methods struggle to simultaneously preserve modeling history, topological reference stability, and feature-level editability in cross-platform scenarios. This work proposes CADIR—an agent-oriented, executable intermediate representation that explicitly constructs a procedural graph encompassing operation sequences, parameter dependencies, constraints, and topological selections based on the OpenCASCADE (OCCT) geometric kernel. To enable faithful cross-platform model reconstruction, CADIR introduces a geometric signature matching mechanism. It is the first approach to support explicit procedural graph representations that allow editing across heterogeneous CAD backends. By integrating text- or image-driven procedural graph retrieval, CADIR demonstrates high-fidelity, editable reuse of complete models and substructures across FreeCAD, SolidWorks, and Fusion 360, enabling seamless subsequent modifications.

Existing text-to-CAD generation methods struggle to produce mechanical assemblies that are engineering-compliant, physically consistent, and reusable due to their inadequate modeling of multi-part协同 relationships and underlying engineering principles. This work proposes the first axiom-driven assembly generation framework, which translates natural language instructions into structured specifications comprising typed components, geometric ports, executable mating relations, and formal engineering axioms. By leveraging deterministic geometric solvers, the framework generates production-grade CAD assemblies that are verifiable, reusable, and explicitly grounded in engineering principles. The approach enables interpretable and generalizable parametric component synthesis by directly linking engineering intent with geometric realization, significantly outperforming current code-centric methods on the AssemBench benchmark in terms of assembly fidelity, physical validity, and cross-model generalization.

Early implicit assumptions about materials and fabrication processes in CAD design often lead to late-stage design lock-in that is difficult to rectify. To address this, we propose a modular, extensible, interactive workflow exploration architecture that enables designers to execute, preview, and compare multiple fabrication processes in real time during CAD modeling. Methodologically, we unify empirical craft practices with academic manufacturing knowledge for the first time—via abstract workflow interfaces, CAD-model-driven process simulation, and collaborative design research. Our implementation reproduces five representative fabrication techniques, captures practices from six expert artisans, and extends three literature-based workflows. A design workshop evaluation demonstrates that the tool significantly broadens creative exploration and deepens procedural understanding of fabrication. By embedding fabrication awareness directly into the CAD environment, our approach advances co-design paradigms toward manufacturability-aware design.

Existing CAD generation models struggle to emulate engineers’ iterative design processes and lack the capability to validate physical and structural compliance. This work proposes an industry-native CAD generation framework that produces complete multi-part STEP files from engineering text and, for the first time, integrates finite element analysis (FEA) into the generative loop to verify structural plausibility. The approach leverages structured blueprint descriptions and 21-view image renderings as dual supervisory signals to guide large language model agents—such as GPT-5.5 and Claude Code—toward self-improving generation. Evaluated on the S2O and Fusion360 datasets, the method significantly enhances geometric reconstruction quality and engineering compliance, improving Box-IoU from 0.444 to 0.592 and from 0.397 to 0.505, respectively.

This work addresses the persistent challenges in fused deposition modeling (FDM) printing—such as poor printability, insufficient mechanical strength, and complex post-processing caused by geometric defects like steep overhangs—by introducing the first end-to-end multi-agent system capable of automatically repairing original CAD models. The proposed framework integrates B-Rep parsing, graph neural network–based semantic recognition, and multimodal large language model reasoning to detect manufacturability issues and generate optimized STEP files along with detailed modification reports. By constructing face adjacency topological graphs, applying GraphSAGE for semantic labeling, leveraging Claude Sonnet for design suggestions, and validating modifications via GPT-4o’s visual reasoning, the system automates the entire pipeline from geometric analysis to natural-language design recommendations. Evaluated on a birdhouse model, it accurately identified overhang regions and effectively proposed corrective strategies such as chamfering, filleting, or part reorientation, substantially overcoming the reliance on manual intervention inherent in traditional design-for-manufacturing approaches.

Automatically generating editable, kinematically functional parametric CAD assemblies from high-level text or image inputs remains a significant challenge. This work proposes the first training-free multi-agent system that coordinates four specialized agents—design, generation, assembly, and review—to explicitly predict assembly relationships during the design phase via a connector-based mechanism. The framework incorporates multi-stage verification, cross-phase rollback, and a self-evolving experience repository to ensure output fidelity. By circumventing the spatial reasoning limitations of large language models, the approach supports code generation, joint definition, and experience reuse. Validated on ArtiCAD-Bench, CADPrompt, and ACD datasets, the method demonstrates effectiveness in conceptual design and physical prototyping, and can export URDF files for embodied AI training.

In three-dimensional graphic statics, editing complex polyhedral graphs often compromises their symmetry, thereby undermining engineering applicability. This work introduces crystallographic point group theory into the field for the first time and establishes length consistency among equivalent edge sets as a necessary and sufficient condition for preserving symmetry. By integrating symmetry detection algorithms from spglib and pymatgen, the authors develop an efficient fingerprinting method to automatically classify equivalent edges and enforce corresponding constraints. Implemented in the PolyFrame 2 plugin, this approach significantly reduces the dimensionality of the solution space while effectively maintaining the symmetry of polyhedral graphs, thereby enhancing both design feasibility and computational efficiency.