Generative Design Workflow for Exploring Feasible Solution Spectrums
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional CAD tools can only evaluate one design option at a time, limiting the exploration of feasible design solutions that meet design criteria, as they cannot assess multiple options simultaneously and human capabilities are insufficient to consider all possible outcomes.
Innovation Solution
A computer-readable medium with instructions that generate a spectrum of design solutions by synthesizing a problem specification, identifying promising approaches from a database, and producing three-dimensional geometry instances that satisfy design criteria, thereby alleviating the burden on the end-user to consider all possible approaches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional CAD tools are used to evaluate design options one at a time, then the evaluation process is simple and manageable, but the range of explored design solutions is limited
Solution Approach 1:
The patent creates virtual copies of design options through automated generation of multiple design variations. Instead of manually creating and evaluating each design option, the system automatically generates numerous design copies that satisfy the given design criteria, allowing comprehensive exploration of the design space without proportional increase in manual effort
Solution Approach 2:
The patent replaces the manual mechanical process of evaluating design options with an automated computational system. The computer automatically generates, evaluates, and compares multiple design options against the specified criteria, substituting human cognitive effort with algorithmic processing capability
2Adaptability or versatility
If the engineer manually considers all possible design outcomes, then comprehensive design exploration is achieved, but the cognitive burden on the engineer becomes unmanageable
Solution Approach 1:
The system performs self-service by automatically generating and evaluating design options without requiring human intervention for each individual option. The computer autonomously explores the design space, identifies viable solutions, and presents results to the engineer, freeing the engineer from the cognitive burden of manually considering all possible outcomes
Solution Approach 2:
The patent introduces a computer-based intermediary system that mediates between the design criteria and the final design solutions. This intermediary automatically processes the complex task of evaluating multiple design options, translating design criteria into actionable design solutions without requiring direct human cognitive engagement with each option
3Productivity
If conventional CAD tools are used for design iteration, then the design process follows a clear sequential workflow, but the time required to explore multiple design options increases significantly
Solution Approach 1:
The patent performs preliminary action by pre-generating multiple design options that satisfy the specified criteria before the engineer needs to make a selection. Instead of creating designs iteratively in response to evaluation feedback, the system proactively generates a comprehensive set of viable options in advance, significantly reducing the total time required for design exploration
Solution Approach 2:
The patent enables continuous useful action by automatically generating and evaluating design options without interruption or manual intervention. The computer continuously explores the design space, evaluating multiple options in parallel or rapid succession, maintaining productive action throughout the design exploration process rather than pausing for manual review at each step
Data Source
AI summary
A design application generates feasible engineering designs that satisfy criteria associated with a particular engineering problem. The design application receives input that outlines a specific engineering problem to be solved, and then synthesizes a problem specification based on this input. The design application then searches a database to identify different classes of approaches to solving the design problem set forth in the problem specification. The design application then selects one or more such classes of approaches, and generates a spectrum of potential design solutions for each such approach. The generated solutions may then be evaluated to determine the degree to which the problems specification has been met.