B-Rep Face Classification via AI Parametric Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Boundary Representation (B-Rep) models, used in mechanical part design, cannot be directly passed to Machine Learning algorithms due to their graph structure format, necessitating a transformation into a tabular format for effective face classification.
Innovation Solution
A method and system that extract topological information from B-Rep models, determining sets of surface, edge, and connectivity parameters, and transforming them into a parametric data table for classification using supervised learning algorithms based on AI models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If B-Rep model is used to represent mechanical parts, then the model can store topological information and enable computer-based analysis, but the model cannot be directly passed to Machine Learning algorithms due to its graph structure format
Solution Approach 1:
The patent introduces an intermediary transformation layer that converts B-Rep graph structure into tabular format. This intermediary step includes extracting topological information (nodes, edges, faces) and converting it into a tabular representation with features like face area, edge count, and connectivity matrices, which can then be consumed by ML algorithms.
Solution Approach 2:
The patent changes the data representation parameters from a graph-structured format (nodes, edges, faces) to a tabular format with specific parameters (surface parameters, edge parameters, connectivity parameters). This parameter transformation enables the data to be compatible with machine learning algorithms while preserving the essential topological information.
2Productivity
If topological information is extracted and transformed into tabular format, then the data can be processed by supervised learning algorithms, but the transformation process adds complexity to the system
Solution Approach 1:
The patent segments the transformation process into distinct modules: extracting topological information (nodes, edges, faces), determining parameters (surface, edge, connectivity parameters), and transforming into tabular format. This segmentation makes the complex transformation process more manageable and reusable.
Solution Approach 2:
The patent performs preliminary extraction and transformation of topological information into a standardized tabular format before the actual classification task. This preliminary action prepares the data in advance, making the subsequent supervised learning process more efficient and the overall system more productive.
Data Source
AI summary
The invention relates to method and system for classifying faces of a Boundary Representation (B-Rep) model using Artificial Intelligence (AI). The method includes extracting topological information corresponding to each of a plurality of data points of a B-Rep model of a product; determining a set of parameters based on the topological information corresponding to each of the plurality of data points; transforming the set of parameters corresponding to each of the plurality of data points of the B-Rep model into a tabular format to obtain a parametric data table; and assigning each of the plurality of faces of the B-Rep model a category from a plurality of categories based on the parametric data table using an AI model.