Group-Orthogonal Supersaturated Design Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Supersaturated designs for experiments are underutilized due to difficulties in estimating all factors simultaneously and identifying active factors using current model selection techniques, which limits their application in experimental design.
Innovation Solution
A computer-program product is provided that generates a supersaturated design by distributing factors into groups, allowing for a greater number of factors than test cases, using a computing device to output an indication of the design based on input parameters such as the number of test cases, factors, and groups, enabling the creation of a group-orthogonal supersaturated design.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If supersaturated design is used to investigate more factors than test cases, then the number of factors that can be investigated is increased, but the ability to estimate all factors simultaneously and identify active factors deteriorates
Solution Approach 1:
The patent divides the set of factors into multiple groups, where each group can be estimated separately using orthogonal contrasts. This segmentation allows the experiment to handle more factors than test cases by processing them in manageable subsets, resolving the contradiction between investigating more factors and maintaining estimation accuracy.
Solution Approach 2:
The patent implements a design where the number of factors exceeds the number of test cases (supersaturated condition). Instead of requiring complete estimation of all factors simultaneously, the method accepts partial estimation of factor groups, allowing excessive action in terms of factor quantity while maintaining sufficient action for identifying active factors through group-based analysis.
2Ease of manufacture
If current model selection techniques are used for supersaturated designs, then the experimental setup is simple, but the difficulty in identifying active factors increases
Solution Approach 1:
By segmenting factors into groups and applying orthogonal contrasts within each group, the patent creates a systematic approach to identifying active factors. This segmentation transforms the difficult task of identifying active factors among many into a more manageable process of comparing group estimates, reducing the difficulty while preserving the simplicity of the supersaturated design setup.
Data Source
AI summary
A computing device receives a request for a design of an experiment. The design comprises test cases with test conditions for testing factors for the experiment. The device receives a value for a parameter of multiple parameters for the design. The multiple parameters indicate a total number of test cases for the design, a total number of factors for the design, and a total number of groups for grouping factors. The device generates a value for each of one or more other parameters of the multiple parameters such that the design is a supersaturated design. The device generates, based on the first value for the first parameter and the value for each of the one or more other parameters, the supersaturated design for the experiment that is a design that distributes each of the factors into one of the groups. The device outputs an indication of the supersaturated design.