Modular Design Optimization for Multi-Scale Construction Projects

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional multi-scale construction design approaches are limited by cascading dependencies between design stages, restricting the exploration and optimization of diverse design combinations across multiple goals and objectives, such as carbon emissions, habitability, and cost, due to computational resource constraints and the large number of possible permutations.

Innovation Solution

A modular design technique that generates and optimizes designs across multiple scales using a design optimization framework, which includes a site layout generator, building layout generator, design detail generator, and orchestrator, to reduce dependencies between smaller and larger-scale designs, employing modular representations and iterative optimization methods to explore a diverse range of design attributes and objectives.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If conventional sequential multi-scale design approaches are used, then design stages can be completed in a structured manner, but the exploration of diverse design combinations is restricted due to cascading dependencies

Engineering Contradiction:
Improvestructured design processVSAvoidexploration of design combinations
Core Design Contradiction:
Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent segments the design space into discrete modular units (e.g., spatial bins, design attributes) that can be independently varied. This allows the system to explore diverse design combinations by recombining modular units without being constrained by sequential dependencies, thus resolving the contradiction between structured process and design versatility

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts the design exploration process by iteratively generating and evaluating design combinations based on performance metrics. Rather than following a fixed sequential path, the system adapts its exploration strategy to balance structured progression with diverse combination generation, enabling both ease of manufacture and adaptability

Inventive Principle:
Principle #15Dynamics

2Reliability

If all possible design permutations are explored to optimize multiple goals, then comprehensive optimization is achieved, but computational resources are exceeded

Engineering Contradiction:
Improvecomprehensive optimizationVSAvoidcomputational resources
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The system performs partial exploration of the design space by focusing computational resources on generating and evaluating a representative subset of design combinations. Rather than exhaustively exploring all permutations, it uses performance metrics and diversity objectives to guide exploration toward the most promising regions, achieving comprehensive optimization of key goals without exceeding computational resources

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system changes parameters by varying design attributes (e.g., spatial configurations, building densities, unit types) within defined ranges and evaluating their impact on performance metrics. This parameter-based approach allows systematic exploration of design trade-offs while maintaining computational efficiency through targeted variation rather than full permutation enumeration

Inventive Principle:
Principle #35Parameter changes

3Stability of the object's composition

If cascading dependencies are enforced from larger to smaller design scales, then design consistency is maintained, but certain design combinations are excluded

Engineering Contradiction:
Improvedesign consistencyVSAvoiddesign combination diversity
Core Design Contradiction:
Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The patent adds a new dimension to design exploration by treating design attributes and spatial configurations as independent variables that can be varied simultaneously across multiple scales. This multi-dimensional approach allows the system to maintain design consistency through coordinated variation while excluding fewer combinations, as it can explore attribute-space rather than being constrained to sequential scale-based dependencies

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP4451161A1Diversity-based optimization of generative geometry systems
Publication Date: 2024.10.23 AUTODESK INC
  • EP4451161A1 patent drawingFigure 1
  • EP4451161A1 patent drawingFigure 2
  • EP4451161A1 patent drawingFigure 3A

AI summary

A method for generating a modular design for a construction project includes determining (414) a first set of candidate designs for the construction project. The method also includes for each candidate design included in the first set of candidate designs, generating (404) a set of design options based on one or more portions of the candidate design and determining (406, 410) a set of performance metrics and a set of attributes associated with the set of design options. The method further includes generating a second set of candidate designs for the construction project based on the sets of design options associated with the first set of candidate designs, the sets of performance metrics associated with the sets of design options, and the sets of attributes associated with the sets of design options.