Autonomous Generative Design System Using Digital Twin Graph
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current engineering design processes for complex systems like gas turbines, automobiles, and aircraft are labor-intensive and require significant manual effort, relying on human expertise, which limits efficiency and creativity due to the need for experienced engineers to generate design variants, analyze models, and create manufacturing plans.
Innovation Solution
An autonomous generative design system utilizing a digital twin graph that captures user interactions and imports requirements documents to synthesize and analyze design alternatives, leveraging AI and machine learning to automate the design process, reduce human intervention, and suggest optimal design solutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual engineering processes are used with human experts, then design quality and expertise are maintained, but productivity and time consumption deteriorate
Solution Approach 1:
The system enables self-service by capturing expert interactions and automatically generating design variants, analysis models, and manufacturing plans without requiring continuous human expert intervention. The digital twin and captured knowledge base allow the system to serve itself in generating design alternatives and performing analyses.
Solution Approach 2:
The patent replaces the mechanical system of human expert manual work with an automated digital system. Machine learning models and algorithms substitute for human cognitive processes in generating design variants, interpreting results, and creating manufacturing plans, thereby eliminating the bottleneck of human availability while maintaining design quality.
2Reliability
If more human experts are engaged, then design capability and knowledge application improve, but cost and resource requirements worsen
Solution Approach 1:
The system creates digital copies of expert knowledge by capturing and storing interactions between experts and design tools. These captured interactions are stored in a database and used to train machine learning models, effectively copying expert knowledge into a reusable digital format that can serve multiple design projects without requiring the original experts to be present.
Solution Approach 2:
The system performs preliminary action by pre-capturing and storing expert knowledge and interactions before they are needed for new design projects. The knowledge base is built in advance from historical expert work, allowing the system to automatically apply this pre-processed knowledge to generate design variants and analyze models without requiring real-time expert involvement.
3Productivity
If automated systems are implemented, then productivity and time efficiency improve, but design complexity and system sophistication worsen
Solution Approach 1:
The system segments the complex design process into distinct automated components: capturing user interactions, generating design variants, creating analysis models, interpreting results, and generating manufacturing plans. Each function is handled by specialized modules that work together through a standardized interface, making the overall complex system manageable through functional decomposition.
Data Source
AI summary
A system for autonomous generative design in a system having a digital twin graph a requirements distillation tool for receiving requirements documents of a system in human-readable format and importing useful information contained in the requirements documents into the digital twin graph, and a synthesis and analysis tool in communication with the digital twin graph, wherein the synthesis and analysis tool generates a set of design alternatives based on the captured interactions of the user with the design tool and the imported useful information from the requirements documents. The system may include includes a design tool with an observer for capturing interactions of a user with the design tool, In addition to the observer, an insighter in communication with the design tool and with the digital twin graph receives design alternatives from the digital twin graph and present the receive design alternatives to a user via design tool.