Machine Learning Optimization for Fiber Reinforced Polymer Building Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The construction industry faces challenges in reducing design time for new building components and assemblies, particularly in optimizing structural designs while adhering to various design constraints and performance objectives.
Innovation Solution
The implementation of machine learning (ML) techniques, specifically using artificial neural networks (ANNs), to analyze and optimize structural designs for building systems and components made from Fiber Reinforced Polymer (FRP). This involves configuring ML to learn complex relationships between design variables and performance characteristics, thereby tuning designs to optimize objectives while satisfying constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional design methods are used for FRP building systems, then design expertise and manual optimization are maintained, but design time is excessive and productivity is low
Solution Approach 1:
The patent replaces manual mechanical design processes with an automated computational system comprising a database of FRP components, a performance evaluation module, and an optimization engine that automatically iterates through design configurations to meet performance criteria, eliminating the need for manual trial-and-error optimization
Solution Approach 2:
The design system performs self-optimization by automatically evaluating design configurations against performance criteria, selecting optimal components from the database, and iteratively refining designs without requiring continuous human intervention or expertise
2Reliability
If manual design optimization is performed, then design quality and constraint satisfaction are maintained, but the complexity and time required for design increases
Solution Approach 1:
The patent replaces complex manual design processes with a computational optimization system that systematically evaluates design configurations against performance criteria and constraints, ensuring reliable constraint satisfaction while reducing process complexity through automation
Solution Approach 2:
The design system incorporates feedback loops where the performance evaluation module assesses design configurations against performance criteria, and the optimization engine uses this feedback to iteratively refine designs, ensuring constraints are satisfied while systematically reducing design space complexity
Data Source
AI summary
A method comprises configuring machine learning to generate an architectural model; configuring machine learning to adapt the architectural model to satisfy structural design constraints and optimize at least one objective function; configuring machine learning to select structural components for use in the architectural model; and configuring a machine for manufacturing or assembling the structural components. The architectural model can comprise fiber reinforced polymer (FRP) elements that are selected based on their performance characteristics in order to satisfy the structural design constraints and optimize the at least one objective function.