Search for: All records

Computer-aided design (CAD) tools empower designers to design and modify 3D models through a series of CAD operations, commonly referred to as a CAD sequence. In scenarios where digital CAD files are inaccessible, reverse engineering (RE) has been used to reconstruct 3D CAD models. Recent advances have seen the rise of data-driven approaches for RE, with a primary focus on converting 3D data, such as point clouds, into 3D models in boundary representation (B-rep) format. However, obtaining 3D data poses significant challenges, and B-rep models do not reveal knowledge about the 3D modeling process of designs. To this end, our research introduces a novel data-driven approach based on representation learning to infer CAD sequences from product images, coined as Image2CADSeq. These sequences can then be translated into B-rep models using a solid modeling kernel. Unlike B-rep models, CAD sequences offer enhanced flexibility to modify individual steps of model creation, providing a deeper understanding of the construction process of CAD models. One unique contribution of this paper is the development of a multi-level evaluation framework for model assessment, so the predictive performance of the Image2CADSeq model can be rigorously evaluated. The model was trained on a specially synthesized dataset, and various neural network architectures were explored to optimize the performance. The experimental and validation results show the great potential of our model in data-driven reverse engineering of 3D CAD models from 2D images. 

Despite the power of large language models (LLMs) in various cross-modal generation tasks, their ability to generate 3D computer-aided design (CAD) models from text remains underexplored due to the scarcity of suitable datasets. Additionally, there is a lack of multimodal CAD datasets that include both reconstruction parameters and text descriptions, which are essential for the quantitative evaluation of the CAD generation capabilities of multimodal LLMs. To address these challenges, we developed a dataset of CAD models, sketches, and image data for representative mechanical components such as gears, shafts, and springs, along with natural language descriptions collected via Amazon Mechanical Turk. By using CAD programs as a bridge, we facilitate the conversion of textual output from LLMs into precise 3D CAD designs. To enhance the text-to-CAD generation capabilities of GPT models and demonstrate the utility of our dataset, we developed a pipeline to generate fine-tuning training data for GPT-3.5. We fine-tuned four GPT-3.5 models with various data sampling strategies based on the length of a CAD program. We evaluated these models using parsing rate and intersection over union (IoU) metrics, comparing their performance to that of GPT-4 without fine-tuning. The new knowledge gained from the comparative study on the four different fine-tuned models provided us with guidance on the selection of sampling strategies to build training datasets in fine-tuning practices of LLMs for text-to-CAD generation, considering the trade-off between part complexity, model performance, and cost. 

The evolution of multimodal large language models (LLMs) capable of processing diverse input modalities (e.g., text and images) holds new prospects for their application in engineering design, such as the generation of 3D computer-aided design (CAD) models. However, little is known about the ability of multimodal LLMs to generate 3D design objects, and there is a lack of quantitative assessment. In this study, we develop an approach to enable LLMs to generate 3D CAD models (i.e., LLM4CAD) and perform experiments to evaluate their efficacy where GPT-4 and GPT-4V were employed as examples. To address the challenge of data scarcity for multimodal LLM studies, we created a data synthesis pipeline to generate CAD models, sketches, and image data of typical mechanical components (e.g., gears and springs) and collect their natural language descriptions with dimensional information using Amazon Mechanical Turk. We positioned the CAD program (programming script for CAD design) as a bridge, facilitating the conversion of LLMs’ textual output into tangible CAD design objects. We focus on two critical capabilities: the generation of syntactically correct CAD programs (Cap1) and the accuracy of the parsed 3D shapes (Cap2) quantified by intersection over union. The results show that both GPT-4 and GPT-4V demonstrate great potential in 3D CAD generation by just leveraging their zero-shot learning ability. Specifically, on average, GPT-4V outperforms when processing only text-based input, exceeding the results obtained using multimodal inputs, such as text with image, for Cap 1 and Cap 2. However, when examining category-specific results of mechanical components, the prominence of multimodal inputs is increasingly evident for more complex geometries (e.g., springs and gears) in both Cap 1 and Cap 2. The potential of multimodal LLMs to improve 3D CAD generation is clear, but their application must be carefully calibrated to the complexity of the target CAD models to be generated. 

The evolution of multimodal large language models (LLMs) capable of processing diverse input modalities (e.g., text and images) holds new prospects for their application in engineering design, such as the generation of 3D computer-aided design (CAD) models. However, little is known about the ability of multimodal LLMs to generate 3D design objects, and there is a lack of quantitative assessment. In this study, we develop an approach to enable two LLMs, GPT-4 and GPT-4V, to generate 3D CAD models (i.e., LLM4CAD) and perform experiments to evaluate their efficacy. To address the challenge of data scarcity for multimodal LLM studies, we created a data synthesis pipeline to generate CAD models, sketches, and image data of typical mechanical components (e.g., gears and springs) and collect their natural-language descriptions with dimensional information using Amazon Mechanical Turk. We positioned the CAD program (programming script for CAD design) as a bridge, facilitating the conversion of LLMs’ textual output into tangible CAD design objects. We focus on two critical capabilities: the generation of syntactically correct CAD programs (Cap1) and the accuracy of the parsed 3D shapes (Cap2) quantified by intersection over union. The results show that both GPT-4 and GPT-4V demonstrate potential in 3D CAD generation. Specifically, on average, GPT-4V outperforms when processing only text-based input, exceeding the results obtained using multimodal inputs, such as text with image, for Cap 1 and Cap 2. However, when examining category-specific results of mechanical components, while the same trend still holds for Cap 2, the prominence of multimodal inputs is increasingly evident for more complex geometries (e.g., springs and gears) in Cap 1. The potential of multimodal LLMs in enhancing 3D CAD generation is clear, but their application must be carefully calibrated to the complexity of the target CAD models to be generated. 

Abstract Computer-aided design (CAD) is a standard design tool used in engineering practice and by students. CAD has become increasingly analytic and inventive in incorporating artificial intelligence (AI) approaches to design, e.g., generative design (GD), to help expand designers' divergent thinking. However, generative design technologies are relatively new, we know little about generative design thinking in students. This research aims to advance our understanding of the relationship between aspects of generative design thinking and traditional design thinking. This study was set in an introductory graphics and design course where student designers used Fusion 360 to optimize a bicycle wheel frame. We collected the following data from the sample: divergent and convergent psychological tests and an open-ended response to a generative design prompt (called the generative design reasoning elicitation problem). A Spearman's rank correlation showed no statistically significant relationship between generative design reasoning and divergent thinking. However, an analysis of variance found a significant difference in generative design reasoning and convergent thinking between groups with moderate GD reasoning and low GD reasoning. This study shows that new computational tools might present the same challenges to beginning designers as conventional tools. Instructors should be aware of informed design practices and encourage students to grow into informed designers by introducing them to new technology, such as generative design. 

Conceptual design is the foundational stage of a design process that translates ill-defined design problems into low-fidelity design concepts and prototypes through design search, creation, and integration. In this stage, product shape design is one of the most paramount aspects. When applying deep learning-based methods to product shape design, two major challenges exist: (1) design data exhibit in multiple modalities and (2) an increasing demand for creativity. With recent advances in deep learning of cross-modal tasks (DLCMTs), which can transfer one design modality to another, we see opportunities to develop artificial intelligence (AI) to assist the design of product shapes in a new paradigm. In this paper, we conduct a systematic review of the retrieval, generation, and manipulation methods for DLCMT that involve three cross-modal types: text-to-3D shape, text-to-sketch, and sketch-to-3D shape. The review identifies 50 articles from a pool of 1341 papers in the fields of computer graphics, computer vision, and engineering design. We review (1) state-of-the-art DLCMT methods that can be applied to product shape design and (2) identify the key challenges, such as lack of consideration of engineering performance in the early design phase that need to be addressed when applying DLCMT methods. In the end, we discuss the potential solutions to these challenges and propose a list of research questions that point to future directions of data-driven conceptual design. 

Abstract Data-driven generative design (DDGD) methods utilize deep neural networks to create novel designs based on existing data. The structure-aware DDGD method can handle complex geometries and automate the assembly of separate components into systems, showing promise in facilitating creative designs. However, determining the appropriate vectorized design representation (VDR) to evaluate 3D shapes generated from the structure-aware DDGD model remains largely unexplored. To that end, we conducted a comparative analysis of surrogate models’ performance in predicting the engineering performance of 3D shapes using VDRs from two sources: the trained latent space of structure-aware DDGD models encoding structural and geometric information and an embedding method encoding only geometric information. We conducted two case studies: one involving 3D car models focusing on drag coefficients and the other involving 3D aircraft models considering both drag and lift coefficients. Our results demonstrate that using latent vectors as VDRs can significantly deteriorate surrogate models’ predictions. Moreover, increasing the dimensionality of the VDRs in the embedding method may not necessarily improve the prediction, especially when the VDRs contain more information irrelevant to the engineering performance. Therefore, when selecting VDRs for surrogate modeling, the latent vectors obtained from training structure-aware DDGD models must be used with caution, although they are more accessible once training is complete. The underlying physics associated with the engineering performance should be paid attention. This paper provides empirical evidence for the effectiveness of different types of VDRs of structure-aware DDGD for surrogate modeling, thus facilitating the construction of better surrogate models for AI-generated designs. 

Abstract In this paper, we present a predictive and generative design approach for supporting the conceptual design of product shapes in 3D meshes. We develop a target-embedding variational autoencoder (TEVAE) neural network architecture, which consists of two modules: (1) a training module with two encoders and one decoder (E2D network) and (2) an application module performing the generative design of new 3D shapes and the prediction of a 3D shape from its silhouette. We demonstrate the utility and effectiveness of the proposed approach in the design of 3D car body and mugs. The results show that our approach can generate a large number of novel 3D shapes and successfully predict a 3D shape based on a single silhouette sketch. The resulting 3D shapes are watertight polygon meshes with high-quality surface details, which have better visualization than voxels and point clouds, and are ready for downstream engineering evaluation (e.g., drag coefficient) and prototyping (e.g., 3D printing).