Generative Design Tradeoff Space Visualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Generative design systems produce overwhelming numbers of design options, leading to designers ignoring potentially good designs and differing opinions among designers complicating the selection process.
Innovation Solution
A computer-implemented method that generates a tradeoff space and filters design options using a GUI engine with tools like design explorer, composite explorer, and tradeoff explorer to visualize and analyze competing characteristics, allowing for effective cooperation among designers with differing opinions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If generative design systems generate numerous design options to meet design criteria, then the completeness of design exploration is improved, but the complexity of data analysis increases
Solution Approach 1:
The patent extracts and separates the analysis complexity from the design options by generating a Pareto frontier that identifies only the non-dominated designs. This extraction process removes inferior options from consideration, reducing the analysis burden while preserving all potentially optimal solutions.
Solution Approach 2:
The patent introduces a Pareto frontier analysis as an intermediary step between design generation and designer review. This intermediary structure organizes the large set of design options into a manageable subset of non-dominated solutions, facilitating easier analysis without losing important design alternatives.
2Ease of operation
If designers ignore a large fraction of generated design options to manage analysis complexity, then the ease of operation is improved, but the loss of information increases
Solution Approach 1:
The patent extracts only the non-dominated designs into a Pareto frontier subset, removing clearly inferior options while preserving all potentially optimal designs. This extraction maintains information integrity for important designs while reducing the overall analysis burden.
Solution Approach 2:
The patent changes the parameter of design option evaluation by introducing dominance relationships and Pareto optimality criteria. This parameter transformation allows designers to focus on designs that cannot be improved in one aspect without deteriorating in another, ensuring no potentially good designs are lost.
3Reliability
If designers consider only designs meeting commonly held standards to reduce analysis complexity, then the reliability of consensus is improved, but the loss of information increases
Solution Approach 1:
The patent segments the design evaluation process into two independent components: (1) automated Pareto frontier analysis that identifies non-dominated designs based on objective criteria, and (2) designer consensus on aesthetic and functional preferences. This segmentation allows reliable consensus-building on the Pareto subset without prematurely filtering out potentially good designs.
Solution Approach 2:
The Pareto frontier serves as an intermediary structure that enables reliable multi-designer consensus. By providing a standardized set of non-dominated options with clear trade-off relationships, it facilitates objective comparison and consensus-building while preserving all designs that could potentially meet diverse designer criteria.
4Adaptability or versatility
If multiple designers with differing opinions collaborate to evaluate design options, then the adaptability of design evaluation is improved, but the device complexity increases
Solution Approach 1:
The patent segments the collaborative evaluation process into independent preference expressions for each designer, which are then aggregated through Pareto analysis. Each designer evaluates designs independently based on their own criteria, and the system automatically synthesizes these into a unified Pareto frontier, reducing collaboration complexity while maintaining adaptability.
Solution Approach 2:
The Pareto frontier analysis provides a universal framework that accommodates multiple designers with differing opinions. The same Pareto optimality criteria apply regardless of individual designer preferences, creating a multi-functional evaluation system that handles diverse criteria through a unified analytical approach.
Data Source
AI summary
A design application is configured to visualize and explore large-scale generative design datasets. The design explorer includes a graphical user interface (GUI) engine that generates a design explorer, a composite explorer, and a tradeoff explorer. The design explorer displays a visualization of a multitude of design options included in a design space. The design explorer allows a user to filter the design space based on input parameters that influence a generative design process as well as various design characteristics associated with the different design options. The composite explorer displays a fully interactive composite of multiple different design options. The composite explorer exposes various tools that allow the user to filter the design space via interactions with the composite. The tradeoff explorer displays a tradeoff space based on different rankings of design options. The different rankings potentially correspond to competing design characteristics specified by different designers.