Generative Design System for Multi-Disciplinary Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional generative design techniques face challenges in optimizing complex 3D models with multiple interrelated components, as they require switching between CAD and physics simulation applications, necessitating additional operations like meshing and boundary condition setup, which is tedious and often leads to suboptimal designs.

Innovation Solution

A computer-implemented method that generates optimized designs by receiving user input for interdependent design variables and 3D shapes, defining design problems with associations between these variables and geometry, and iteratively performing operations to update the geometry, using a single user interface that integrates multi-disciplinary optimization (MDO) techniques, natural language interfaces, and free-form deformation methods.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a designer imports a 3D model from CAD to physics simulation application and performs meshing and boundary condition setup, then the model can be simulated, but the process becomes tedious and time-consuming requiring switching between applications

Engineering Contradiction:

Improvesimulation accuracyVSAvoidtime for model setup

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent merges the CAD modeling application and physics simulation application into a single integrated environment. The system allows direct execution of physics simulations on 3D models without exporting between applications, eliminating the tedious process of model setup while maintaining simulation accuracy through native support for complex geometries.

Inventive Principle:

Principle #5Merging (Combining)

2Adaptability or versatility

If a designer manually explores design spaces in conventional CAD applications, then design possibilities can be explored, but the process is inefficient compared to algorithm-driven approaches

Engineering Contradiction:

Improvedesign exploration capabilityVSAvoiddesign exploration efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system implements algorithm-driven generative design where the computer automatically explores design spaces by iteratively optimizing design variables. The system self-performs the exploration process through multi-disciplinary optimization, eliminating the need for manual designer intervention while maintaining comprehensive design exploration capability.

Inventive Principle:

Principle #25Self-service

3Ease of manufacture

If a designer uses pre-built components to approximate a complex 3D model, then the model can be created without external software, but the approximation is inaccurate especially for complex models like automobiles or airplanes

Engineering Contradiction:

Improveease of model creationVSAvoidmodel accuracy

Core Design Contradiction:

Ease of manufactureVSManufacturing precision

Solution Approach 1:

The patent creates a universal platform that handles both simple and complex 3D models uniformly. The system supports native import and simulation of complex geometries from external CAD files while maintaining ease of use. The multi-functional environment eliminates the need to choose between simplicity and complexity, allowing accurate representation of any model type.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Device complexity

If a designer optimizes only certain subsystems or components, then the optimization process is simplified, but the results are suboptimal because interrelated components are not considered

Engineering Contradiction:

Improveoptimization process complexityVSAvoiddesign optimization quality

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system segments the optimization process into manageable disciplinary domains (structural, aerodynamic, thermal, etc.) while maintaining integration through multi-disciplinary optimization. Each discipline can be optimized independently with appropriate complexity, then results are integrated to achieve optimal overall design considering all interrelated components.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250148171A1Techniques for generative design using multi-disciplinary optimization

Publication Date: 2025.05.08 AUTODESK INC

AI summary

In various embodiments, a generative design application can leverage multi-disciplinary optimization to solve a design problem associated with a 3D model and interdependent design variables. The generative design application includes an optimization engine that can solve the design problem, or portions thereof, by iteratively performing optimization techniques on the interdependent design variables to generate an 3D model that maximizes or minimizes one or more objectives and meets one or more constraints, while simultaneously considering the effect of each interdependency of the design variables. Furthermore, the generative design application can leverage a natural language interface to augment the creation of the design problem for optimization. The generative design application can also leverage free-form deformation during generative design to parameterize a portion of the 3D model as part of the design problem.