Generative Design Tool Functional Attribute Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Engineers face difficulties in specifying functional attributes for generative CAD tools, making it inefficient to generate a spectrum of designs without a starting point, as they often intuitively understand design requirements but struggle to articulate them.
Innovation Solution
A computer-implemented method that generates labels describing functional attributes of an exemplary design, allowing the system to identify similar system classes within a functional space, enabling the generation of design approaches without manual exploration of the vast design space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If generative design tools are used to create a spectrum of designs, then design productivity is improved, but the requirement for engineers to specify functional attributes accurately creates a barrier that worsens ease of operation
Solution Approach 1:
The patent introduces an intermediary system (the generative design tool with functional attribute extraction capability) that mediates between the engineer's intuitive understanding and the CAD system's requirements. The tool automatically extracts functional attributes from design specifications or existing designs, serving as a bridge that eliminates the need for engineers to manually specify complex functional attributes, thus resolving the contradiction between improved productivity and maintained ease of operation
Solution Approach 2:
The system enables self-service by allowing the generative design tool to automatically extract and process functional attributes without requiring manual input from engineers. The tool can analyze existing designs or specifications and autonomously identify relevant functional attributes, reducing the operational burden on engineers while maintaining high design generation efficiency
2Reliability
If engineers manually explore the design space to identify feasible design options, then design completeness is improved, but the time required increases significantly worsening loss of time
Solution Approach 1:
The patent replaces the mechanical process of manual design space exploration with an automated computational system. The generative design tool uses algorithms to systematically explore the design space, identifying feasible design options that meet specified criteria. This substitution eliminates the time-consuming manual exploration process while maintaining or improving the completeness of design options through more thorough and systematic search capabilities
Solution Approach 2:
The system changes the parameters of the design exploration process by using computational algorithms with adjustable parameters (such as search depth, constraint weights, and generation iterations) to efficiently navigate the design space. This allows the system to find comprehensive design options much faster than manual exploration, resolving the contradiction between design completeness and time consumption
3Ease of operation
If a single functional attribute is provided as a starting point for generative design, then the design generation process is simplified, but the quality and relevance of generated designs may deteriorate
Solution Approach 1:
The patent implements a multi-functional system that can process different types of input (single functional attributes, multiple attributes, or complete design specifications) and adaptively generate appropriate design spectra. The tool can extract additional relevant functional attributes automatically or accept various levels of user input, maintaining ease of operation while ensuring high design quality through flexible and comprehensive processing capabilities
Data Source
AI summary
A design application receives an exemplary design from an end-user having one or more functional attributes relevant to solving a design problem. The design application then generates a set of labels that describes the functional attributes of the exemplary design. Based on the set of labels, the design application explores a functional space to retrieve one or more system classes having functionally descriptive labels that are similar to the set of labels generated for the exemplary design. The one or more system classes include different approaches to solving the design problem, and represent systems having at least some functional attributes in common with the exemplary design.