Giter Site home page Giter Site logo

feliperamosoliveira / dissertation Goto Github PK

View Code? Open in Web Editor NEW
3.0 2.0 0.0 5.34 MB

Optimization Of Cold-formed Steel Lipped Channel Columns Using Metaheuristic Algorithms

MATLAB 22.88% Jupyter Notebook 77.12%
cold-formed-steel thin-walled structural-engineering metaheuristics optimization-algorithms

dissertation's Introduction

Abstract

OPTIMIZATION OF COLD-FORMED STEEL LIPPED CHANNEL COLUMNS WITH MANUFACTURING CONSTRAINTS USING METAHEURISTIC ALGORITHMS

Cold-formed steel (CFS) cross-sections can be optimized to increase their load-carrying capacity, leading to more efficient and economical structural systems. This dissertation aims to provide a practical methodology that would enable the development of optimized CFS lipped channel columns sections with maximum compressive strength for practical applications. The optimized sections are designed to comply with the NBR 14762 geometrical specifications and a certain number of manufacturing and practical constraints. The compressive strengths of the sections are determined based on the Direct Strength Method (DSM) adopted in the Brazilian guide, while the optimization process is performed using four distinct metaheuristic algorithms (Genetic Algorithms, Differential Evolution, Particle Swarm Optimization, and Artificial Bee Colony). In total, five different CFS lipped channel prototypes are considered in the optimization process. The critical buckling loads, required by DSM, are determined using Finite Strip Method (FSM) analysis and Machine Learning techniques (ML). The results indicate optimized sections providing a compressive capacity, which is up to 217% higher than standard shapes with the same amount of material.

Repository files

The present repository has the follwing filles:

  • The CFS optimizer code (in portuguse Otimizador, all content is also in portuguese)
  • The trained GPR predictor (all content is in portuguese)
  • The raw results (in portuguse Resultado bruto, all content is also in portuguese)
  • Pair plot PNG image and IPYNB notebook

-

Resumo

OTIMIZAÇÃO VIA ALGORITMOS META-HEURÍSTICOS DE PERFIS U ENRIJECIDOS FORMADOS A FRIO SUBMETIDOS À COMPRESSÃO AXIAL E CONSIDERANDO RESTRIÇÕES DE FABRICAÇÃO

Perfis de aço formado a frio (PFF) podem ser otimizadas para aumentar sua capacidade de carga, levando a sistemas estruturais mais eficientes e econômicos. Esta dissertação tem como objetivo fornecer uma metodologia prática que permita o desenvolvimento de seções otimizadas de colunas de PFF tipo U enrijecido com resistência à compressão máxima para aplicações práticas. As seções otimizadas foram projetadas para atender aos requisitos geométricos da NBR 14762, além de diversas restrições práticas e de fabricação. A resistência à compressão das seções é determinada com base no Método de Resistência Direta (MRD) adotado na norma Brasileira, enquanto o processo de otimização é realizado usando quatro algoritmos meta-heurísticos distintos (Algoritmos Genéticos, Evolução Diferencial, Otimização de Enxame de Partículas e Colônia Artificial de Abelhas). No total, cinco protótipos U enrijecido diferentes são considerados no processo de otimização. As cargas críticas de flambagem, exigidas pelo MRD, são determinadas usando o Método de Faixas Finitas (MFF) e técnicas de aprendizado de máquina. Os resultados apresentam seções otimizadas com resistência à compressão até 217% maior que o protótipo com a mesma quantidade de material.

Arquivos do repositório

Este repositório contem os seguintes arquivos:

  • O otimizador de PFF
  • O preditor GPR treinado
  • O resultado bruto
  • Pair plot nas versões PNG e IPYNB

dissertation's People

Contributors

feliperamosoliveira avatar

Stargazers

 avatar  avatar  avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.