Generative 3D Shape Optimization Under Part Reliability Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing CAD software lacks the ability to automatically generate 3D geometry for physical structures with a target part reliability, requiring manual editing and simulation post-design, which is time-consuming and prone to over-engineering.
Innovation Solution
The implementation of a generative design process that uses a reliability constraint to optimize the shape and topology of 3D models, integrating a statistical model to translate acceptable component probabilities of failure into structural performance metrics, allowing for iterative modification of the design within the CAD program.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If generative design is used to automatically generate 3D geometry, then design time is reduced and productivity is improved, but the ability to ensure target part reliability is lost
Solution Approach 1:
The patent incorporates reliability constraints into the generative design process before the design is finalized. By pre-defining reliability requirements and integrating them into the optimization algorithm, the system ensures that reliability considerations are built into the design from the outset rather than requiring post-design verification and manual editing.
Solution Approach 2:
The patent implements a feedback mechanism where reliability analysis results are fed back into the generative design optimization loop. The system performs reliability assessment on generated designs, uses the results to guide further optimization iterations, and continuously improves designs until reliability targets are met, enabling automatic reliability assurance throughout the design process.
2Reliability
If manual editing and post-design simulation are performed to ensure reliability, then part reliability is improved, but design time and complexity increase
Solution Approach 1:
The patent merges the generative design process, reliability analysis, and optimization into a single integrated workflow. Instead of performing manual editing and simulation as separate post-design steps, the system combines these functions into the generative design loop itself, allowing designs to be automatically optimized for reliability during the generation process rather than requiring time-consuming post-processing.
Solution Approach 2:
The patent enables the generative design system to self-correct and self-optimize for reliability without requiring manual intervention. The automated system performs reliability assessment, identifies deficiencies, and iteratively improves designs autonomously, eliminating the need for manual editing and reducing design time while maintaining high reliability standards.
3Manufacturing precision
If manual editing is performed to meet reliability constraints, then manufacturing precision is improved, but device complexity and ease of operation worsen
Solution Approach 1:
The patent replaces manual design processes with an automated computational system. Instead of relying on engineers to manually edit designs and perform iterative simulations, the system uses computer algorithms to automatically generate, assess, and optimize designs for reliability constraints, reducing procedural complexity while maintaining precision.
Solution Approach 2:
The patent transforms reliability constraints from post-design verification parameters into design-stage optimization parameters. By changing the role of reliability constraints from checklists to be completed after design to active parameters guiding the generative process, the system achieves manufacturing precision automatically without increasing operational complexity.
Data Source
AI summary
Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design of physical structures using generative design processes. A method includes: obtaining a design space and design criteria for a modeled object including a design constraint on an acceptable likelihood of failure, wherein a statistical model that relates a structural performance metric to specific likelihoods of failure for material(s) is used to translate between the acceptable likelihood of failure and a value for the structural performance metric; iteratively modifying a generatively designed shape of the modeled object in the design space in accordance with the design criteria including the design constraint to stay under the acceptable likelihood of failure for the physical structure, wherein the numerical simulation includes computing the structural performance metric, which is evaluated against the design constraint; and providing the generatively designed shape of the modeled object for use in manufacturing a physical structure.