AI-Generated 3D CAD Completion from 2D Assembly Drawings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manufacturing and production companies face challenges in transitioning from traditional drafting drawings to Model-Based Design (MBD) and Model-Based Instruction (MBI) due to the lack of fully defined 3D representations of components in their CAD models, particularly in aerospace and manufacturing parts.
Innovation Solution
A method and system utilizing Generative Artificial Intelligence to extract content from 2D engineering drawings, compare it to a 3D CAD model's bill of materials, and generate missing component representations, incorporating them into the 3D CAD model with metadata and textual information, and control manufacturing processes based on the complete model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If companies transition from traditional drafting drawings to Model-Based Design (MBD), then manufacturing precision and model completeness are improved, but the complexity of the system increases due to the need for fully defined 3D representations
Solution Approach 1:
The patent introduces an AI-based system as an intermediary between 2D drawings and 3D CAD models. This intermediary automatically generates missing 3D components by interpreting 2D drawing data, thereby achieving complete MBD without requiring manual intervention for every component, thus managing system complexity while improving model completeness
Solution Approach 2:
The system enables self-service by automatically detecting missing components in 3D models by comparing them with 2D drawing data and bill of materials, then generating the missing components autonomously. This automation reduces the need for manual modeling operations while ensuring complete MBD representation
2Manufacturing precision
If manual creation of 3D models from 2D drawings is performed, then manufacturing precision is maintained, but productivity decreases due to time-consuming manual processes
Solution Approach 1:
The patent replaces the mechanical manual process of creating 3D models from 2D drawings with an AI-based automated system. The system uses machine learning models that automatically interpret 2D drawing data, extract geometric information, and generate corresponding 3D representations, thereby dramatically increasing productivity while maintaining manufacturing precision
Solution Approach 2:
The system changes the fundamental parameters of the modeling process by transitioning from manual parameter input to automated parameter extraction. The AI system automatically extracts geometric, dimensional, and topological parameters from 2D drawings and converts them into 3D model parameters, eliminating manual operations while preserving accuracy
3Manufacturing precision
If AI models are trained on diverse 2D drawing data, then the ability to generate accurate 3D representations improves, but the training data requirements and computational resources increase
Solution Approach 1:
The patent applies partial action by training AI models on a curated subset of diverse 2D drawing data that represents the most common engineering drawing types and geometries. This selective training approach achieves sufficient accuracy for practical applications without requiring exhaustive training on all possible drawing variations, thereby reducing computational resource consumption while maintaining generation accuracy
Data Source
AI summary
Generating a 3D model from 2D drawings is provided. The method comprises extracting, by a design parser, content from 2D engineering drawings of an assembly and comparing the extracted content to a bill of materials corresponding to a 3D computer assisted design (CAD) model of the assembly to identify missing components from the 3D CAD model. Responsive to identifying missing components, 3D representations of the missing components are modeled based on the 2D engineering drawings, and metadata and textual information related to the 2D engineering drawings. The 3D representations of the missing components are incorporated into the 3D CAD model of the assembly to create a complete 3D CAD model. A manufacturing process for the assembly is then controlled according to the complete 3D CAD model.