Implicit Geometric Pattern Detection in CAD Models

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Many geometric models in CAD and PDM systems contain implicit patterns that are not explicitly labeled, which hinders their functionality, especially when data is imported from other systems or generated using unconventional methods.

Innovation Solution

A data processing system that automatically recognizes rectangular, circular, and linear patterns between features of geometric models by converting 3D features into 2D space, identifying nearest neighbors, and applying pattern indicators to detect and store pattern data, allowing for the identification of implicit patterns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If geometric models are imported from other systems or generated using unconventional methods, then data availability increases, but implicit patterns remain undetected reducing functionality

Engineering Contradiction:
Improvedata availabilityVSAvoidfunctionality
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary pattern recognition analysis on geometric model data before it is fully processed or used. By automatically detecting implicit patterns (rectangular, circular, linear, triangular) in advance, the system prepares the data for better functionality without requiring manual intervention or rework later in the workflow.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The geometric model data performs self-service by automatically revealing its own implicit patterns through the detection system. The patterns are inherently present in the data but remain undetected until the system analyzes them, allowing the data to self-identify its structural characteristics without external labeling or annotation.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If manual pattern labeling is performed, then pattern recognition accuracy improves, but processing time and complexity increase

Engineering Contradiction:
Improvepattern recognition accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system replaces the mechanical process of manual pattern labeling with an automated computational detection mechanism. By using algorithmic analysis to identify implicit patterns in geometric model data, the system eliminates the need for human operators to manually label patterns, significantly reducing processing time while maintaining or improving detection accuracy through consistent automated analysis.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated pattern detection is implemented, then productivity increases, but system complexity increases

Engineering Contradiction:
Improvepattern detection efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The automated pattern detection system is segmented into distinct functional modules that handle different pattern types (rectangular, circular, linear, triangular) and different stages of the detection process. This modular segmentation allows the system to achieve high productivity through automated parallel processing while managing complexity by organizing functions into separate, manageable components that can be independently developed and maintained.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3005237B1Automatic detection of regular patterns of features
Publication Date: 2022.12.28 SIEMENS INDUSTRY SOFTWARE INC
  • EP3005237B1 patent drawingFigure 1
  • EP3005237B1 patent drawingFigure 2
  • EP3005237B1 patent drawingFigure 3A~3B

AI summary

Methods for pattern recognition and corresponding systems and computer-readable mediums. A method includes receiving (205) a set of two-dimensional points (400). The method includes identifying (210) neighbor points for each of a plurality of points in the set and finding (215) at least one indicated pattern between points in the set. The indicated pattern can be one of a linear pattern (710), a rectangular pattern (702), a skew pattern, or a circular pattern (708, 712). The method includes storing (230) pattern data corresponding to the found indicated pattern.