Sheet Part Selection Using Geometric Compatibility Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating cutting plans to minimize material waste when cutting parts from sheet materials do not allow for flexible selection of parts, leading to inefficiencies in material usage.
Innovation Solution
A method that encodes geometric features of each part into a geometric information vector, generates a graph where each part is represented as a node, and estimates geometrical compatibility indices (GCI) for pairs of parts to optimize their placement on sheets, using an optimization method to determine the optimal arrangement of parts on sheets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of substance
If traditional cutting plan methods are used, then material waste is reduced through nesting, but part selection flexibility is limited
Solution Approach 1:
The patent transforms the part selection and arrangement problem into a parameter optimization problem by defining geometric compatibility indices and using machine learning models to predict optimal configurations. This allows flexible part selection while maintaining material efficiency through computational optimization of geometric parameters.
Solution Approach 2:
The patent replaces traditional mechanical nesting methods with an information-based system using graph neural networks and machine learning algorithms. The system processes geometric information vectors and compatibility indices computationally to determine optimal part arrangements, substituting manual or rule-based mechanical approaches with intelligent algorithms.
2Loss of substance
If complex optimization methods are used to optimize part placement, then material waste is reduced, but computational time increases
Solution Approach 1:
The patent performs preliminary encoding of geometric features into information vectors and pre-calculates geometric compatibility indices for all part pairs before optimization. This preprocessing allows the main optimization algorithm to work with pre-computed parameters, significantly reducing computational time during the actual optimization process while maintaining material efficiency.
Solution Approach 2:
The patent introduces geometric compatibility indices as intermediary parameters that mediate between part geometry and optimization objectives. These indices serve as pre-computed features that capture geometric relationships, allowing the optimization algorithm to make efficient decisions without directly processing complex geometric calculations during optimization.
3Manufacturing precision
If geometric compatibility indices are calculated for all part pairs, then part placement accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the complex geometric analysis into distinct components: geometric feature extraction, information vector encoding, and compatibility index calculation. This segmentation allows each component to be processed independently and efficiently, reducing overall computational complexity while maintaining placement accuracy through systematic breakdown of the problem.
Solution Approach 2:
The patent creates simplified representations (geometric information vectors) that copy essential geometric features without requiring full geometric models. These vector representations capture necessary spatial relationships in a compact format, enabling accurate compatibility assessment with reduced computational complexity compared to using complete geometric models.
Data Source
AI summary
A method for selecting parts to be placed on sheets includes encoding geometric features of each part in a respective geometric information vector, generating a graph in which the geometric features of each part are assigned to one node of the graph, estimating geometrical compatibility indices (GCI) for all pairs of parts, assigning each GCI to a respective edge of the graph, which passes through two nodes representing the pair of parts, determining weights of the edges of the graph depending on the GCI associated with the edges, and assigning the parts to a respective sheet by determining subgraphs through the nodes of the graph by an optimization method. The nodes through which a respective subgraph passes represent the parts to be placed on the respective sheet. A sum of the projected areas of the parts on each subgraph is at most equal to a size of the respective sheet.