Genetic Algorithm for Building Frame System Design Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional CAD applications are inefficient in exploring the overall design space for structural systems, leading to suboptimal designs due to the complexity and size of building projects, where only a handful of baseline designs can be generated and refined, often resulting in conservative decisions that neglect weight minimization objectives.

Innovation Solution

A computer-implemented method that uses a genetic algorithm to determine frame locations and sizes based on a building load centroid, breaking down the design optimization problem into simpler aspects, allowing for systematic exploration of the design space to identify optimized structural systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional CAD applications are used to generate structural system designs, then the design process can be completed with manual refinement, but the design space exploration is insufficient and leads to suboptimal designs

Engineering Contradiction:

Improvedesign space exploration capabilityVSAvoiddesign optimization quality

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system performs automatic design space exploration and optimization without requiring manual intervention. The computer executes algorithms that automatically generate, evaluate, and refine structural system designs, allowing the system to serve itself in exploring the design space comprehensively while maintaining high optimization quality

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical design refinement with automated computational algorithms. Instead of structural engineers manually refining designs in CAD applications, the system uses computer-executable algorithms to automatically explore design spaces and optimize structural configurations, substituting human mechanical processes with automated computational mechanisms

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If only a handful of baseline designs are generated and refined manually, then the design process remains manageable, but the likelihood of achieving optimized designs decreases

Engineering Contradiction:

Improvedesign process complexityVSAvoidnumber of designs evaluated

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The system dynamically adapts the design exploration process based on computational resources and objectives. It can adjust the number of designs generated, the depth of refinement, and the computational algorithms used, allowing the design process complexity to vary dynamically rather than being fixed, thereby enabling comprehensive evaluation of numerous designs without overwhelming complexity

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent segments the overall design optimization problem into smaller, manageable components that can be processed systematically. By dividing the design space exploration into discrete evaluable units, the system can efficiently evaluate a large number of designs without requiring excessive computational resources for each individual design, thus increasing productivity while controlling complexity

Inventive Principle:

Principle #1Segmentation

3Loss of time

If structural engineers make conservative design decisions to reduce design time, then the design process becomes faster, but weight minimization objectives are neglected

Engineering Contradiction:

Improvedesign timeVSAvoidstructural system weight

Core Design Contradiction:

Loss of timeVSWeight of moving object

Solution Approach 1:

The system automatically varies design parameters such as structural member sizes, materials, and configurations to explore the design space for optimal solutions. By systematically changing parameters rather than using conservative fixed values, the system can identify lightweight designs that meet all requirements, eliminating the need for conservative overdesign while maintaining compliance with design constraints

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent implements feedback mechanisms where design evaluations inform subsequent design iterations. The system uses performance feedback from structural analysis to automatically refine designs, learning from each evaluation to improve subsequent designs. This feedback loop enables the system to quickly converge on optimized designs without conservative assumptions, reducing both weight and design time

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20220198095A1Techniques for automatically designing frame systems associated with buildings

Publication Date: 2022.06.23 AUTODESK INC

AI summary

In various embodiments, a frame system application generates a design of a frame system associated with a building. The frame system application determines potential frame locations based on a frame grid for a structural system and a computer-aided design of the structural system and then bifurcates the potential frame locations based on a building load centroid to generate frame groups. Based on the frame groups, the frame system application generates a genetic algorithm that determines values for location counts associated with the frame groups based on an objective function that quantifies design objective(s). The frame system application executes the genetic algorithm on a value for the objective function that is associated with first values for the location counts to determine second values for the location counts. Based on the frame groups and the second values for the location counts, the frame system application generates the design of the frame system.