3D Mechanical Part Segmentation for Geometric and Free-Form Surfaces

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for segmenting 3D modeled objects representing mechanical parts are inadequate, particularly in identifying and accurately separating simple geometric and free-form surfaces, leading to inefficiencies and reduced robustness in segmentation processes.

Innovation Solution

A hierarchical segmentation method that includes a first segmentation identifying simple geometric surfaces and a second segmentation identifying free-form surfaces, using specific distance metrics to quantify shape similarity and merge neighboring surfaces based on predefined thresholds, ensuring accurate and efficient partitioning of the 3D modeled object into geometrically coherent segments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a single segmentation approach is used for all surface types, then the method is simpler to implement, but the segmentation accuracy and robustness deteriorate due to inability to distinguish between simple geometric and free-form surfaces

Engineering Contradiction:
Improvesegmentation robustnessVSAvoidsegmentation method complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The segmentation method is divided into two distinct phases: a first segmentation phase for simple geometric surfaces and a second segmentation phase for free-form surfaces. This allows each phase to be optimized for its specific surface type, improving overall robustness while maintaining manageable complexity through structured division of labor.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different segmentation strategies are applied to different surface types based on their local geometric properties. Simple geometric surfaces use one set of criteria while free-form surfaces use another, allowing each region to receive tailored processing that maximizes segmentation accuracy for its specific characteristics.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If all surfaces are processed using the same segmentation algorithm, then the processing workflow is more efficient, but the measurement precision of shape similarity deteriorates due to inability to quantify different surface types accurately

Engineering Contradiction:
Improveshape similarity quantification accuracyVSAvoidsegmentation processing efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The method changes the segmentation parameters and distance metrics based on the surface type being processed. Different distance metrics are used for simple geometric surfaces versus free-form surfaces, allowing precise quantification of shape similarity appropriate to each surface type while maintaining efficient processing through automated type detection.

Inventive Principle:
Principle #35Parameter changes

3Manufacturing precision

If hierarchical segmentation is implemented with multiple passes, then the segmentation accuracy improves by systematically identifying different surface types, but the processing time increases

Engineering Contradiction:
Improvesegmentation accuracyVSAvoidsegmentation processing time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The first segmentation pass performs preliminary identification of simple geometric surfaces, which are then excluded from the second segmentation pass. This preliminary action optimizes the overall process by handling the easier-to-identify surface type first, reducing the computational burden on the second pass and improving total accuracy while managing processing time.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12511452B2Segmenting a 3D modeled object representing a mechanical part
Publication Date: 2025.12.30 DASSAULT SYSTEMES SA
  • US12511452B2 patent drawing
  • US12511452B2 patent drawing
  • US12511452B2 patent drawing

AI summary

A computer-implemented method for segmenting a 3D modeled object. The 3D modeled object represents a mechanical part. The method includes obtaining the 3D modeled object. The method further includes performing a hierarchical segmentation of the 3D modeled object. The hierarchical segmentation comprises a first segmentation. The first segmentation includes identifying, among surfaces of the 3D modeled object, first segments each corresponding to a simple geometric surface of the 3D modeled object. A simple geometric surface is a primitive exhibiting at least one slippable motion. The hierarchical segmentation includes then a second segmentation. The second segmentation includes identifying, among non-identified surfaces of the 3D modeled object, second segments each corresponding to a free-form surface of the 3D modeled object. This constitutes an improved method for segmenting a 3D modeled object representing a mechanical part.