CAD 3DA Annotation Prediction Using Physical Feature Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing CAD systems face challenges in efficiently assigning 3DA feature quantities such as annotations and attributes to CAD models, as they do not adequately consider physical features of faces and sides, making the process laborious and inefficient.
Innovation Solution
A learning model is constructed to predict 3DA feature quantities by learning the relationship between physical feature quantities and 3DA feature quantities, using a design assistance system that includes a learning unit, connecting unit, and 3DA predicting unit to automate the assignment process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual assignment of 3DA feature quantities is performed in existing CAD systems, then complete and accurate annotation information can be assigned, but the process requires significant time and labor effort
Solution Approach 1:
The system enables automatic self-assignment of 3DA feature quantities by learning from physical feature quantities of CAD model elements. The learning model autonomously predicts and assigns annotation information without requiring manual designer intervention, allowing the system to serve itself in the feature quantity assignment task.
Solution Approach 2:
The manual mechanical process of assigning 3DA feature quantities is replaced by an automated learning-based system. The learning model substitutes the manual operation with computational prediction, transitioning from mechanical human interaction to automated algorithmic processing.
2Productivity
If automated assignment of 3DA feature quantities is attempted without considering physical features, then time consumption is reduced, but assignment accuracy deteriorates due to lack of physical feature consideration
Solution Approach 1:
Physical feature quantities are extracted and prepared in advance as input data for the learning model. By performing this preliminary extraction of geometric and topological features before the prediction process, the system ensures that accurate physical characteristics are available to guide the automated assignment of 3DA feature quantities.
Solution Approach 2:
The learning model uses feedback from physical feature quantities to continuously improve prediction accuracy. The system learns the relationship between physical features and appropriate 3DA feature quantities, using this feedback loop to enhance assignment accuracy while maintaining automated operation.
3Extent of automation
If a learning model is constructed to predict 3DA feature quantities, then automation extent increases, but system complexity increases due to additional learning and prediction components
Solution Approach 1:
The learning model serves multiple functions: it learns from training data, predicts 3DA feature quantities, and adapts to different CAD model types. This multi-functionality reduces the need for separate specialized components for each task, thereby managing system complexity while maintaining high automation capability.
Data Source
AI summary
The number of processes at the time of performing design of assigning 3DA feature quantities to a CAD model such as a three-dimensional CAD model is decreased. Assignment errors and writing omissions of 3DA feature quantities for a CAD model are reduced. A design assistance device 10 predicting 3DA feature quantities which are defined on a CAD model and which are related information of a target object of design has: a learning unit 102 constructing a learning model 115 used for predicting the 3DA feature quantities using an assigned CAD model 113 that is a CAD model to which the 3DA feature quantities and physical feature quantities representing physical features have been assigned; a connecting unit 107 receiving a CAD model 114 of the target object; and a 3DA predicting unit 108 predicting 3DA feature quantities to be assigned to the received CAD model 114 using the learning model 115.