Predicting wind-driven rain catch ratios in building simulation using machine learning techniques

Research output: Contribution to conferencePaper

Abstract

Wind-driven rain catch-ratios are an important boundary condition for the study of the hygrothermal behaviour and durability of building envelopes. Measurements are time-consuming, expensive and of limited applicability to other facades of other buildings and sites. CFD simulations are accurate, but time consuming and simplified calculation have large uncertainty. This work focuses on improving the use of WDR catch-ratios in building simulation using artificial neural networks (ANNs). Results obtained indicate that an ANN can predict WDR catch-ratio with an uncertainty of 0:07 for a confidence interval of 95%. ANNs have the ability to combine results from multiple experiments/simulations to provide catch ratios at any position at the facade and extrapolate them to a range of facade's aspect ratios.
LanguageEnglish
Number of pages7
Publication statusPublished - 2 Sep 2019
EventBuilding Simulation 2019 - Rome, Italy
Duration: 2 Sep 20194 Sep 2019
http://buildingsimulation2019.org/

Conference

ConferenceBuilding Simulation 2019
CountryItaly
CityRome
Period2/09/194/09/19
Internet address

Fingerprint

Facades
Rain
Learning systems
Neural networks
Time measurement
Aspect ratio
Computational fluid dynamics
Durability
Boundary conditions
Experiments
Uncertainty

Keywords

  • wind-driven rain catch-ratios
  • hygrothermal behaviour
  • machine learning
  • artificial neural network

Cite this

@conference{0ed092435a474647bed0ef578c7d437e,
title = "Predicting wind-driven rain catch ratios in building simulation using machine learning techniques",
abstract = "Wind-driven rain catch-ratios are an important boundary condition for the study of the hygrothermal behaviour and durability of building envelopes. Measurements are time-consuming, expensive and of limited applicability to other facades of other buildings and sites. CFD simulations are accurate, but time consuming and simplified calculation have large uncertainty. This work focuses on improving the use of WDR catch-ratios in building simulation using artificial neural networks (ANNs). Results obtained indicate that an ANN can predict WDR catch-ratio with an uncertainty of 0:07 for a confidence interval of 95{\%}. ANNs have the ability to combine results from multiple experiments/simulations to provide catch ratios at any position at the facade and extrapolate them to a range of facade's aspect ratios.",
keywords = "wind-driven rain catch-ratios, hygrothermal behaviour, machine learning, artificial neural network",
author = "Ioanna Vrachimi and Daniel C{\'o}stola",
year = "2019",
month = "9",
day = "2",
language = "English",
note = "Building Simulation 2019 ; Conference date: 02-09-2019 Through 04-09-2019",
url = "http://buildingsimulation2019.org/",

}

Vrachimi, I & Cóstola, D 2019, 'Predicting wind-driven rain catch ratios in building simulation using machine learning techniques' Paper presented at Building Simulation 2019, Rome, Italy, 2/09/19 - 4/09/19, .

Predicting wind-driven rain catch ratios in building simulation using machine learning techniques. / Vrachimi, Ioanna; Cóstola, Daniel.

2019. Paper presented at Building Simulation 2019, Rome, Italy.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Predicting wind-driven rain catch ratios in building simulation using machine learning techniques

AU - Vrachimi, Ioanna

AU - Cóstola, Daniel

PY - 2019/9/2

Y1 - 2019/9/2

N2 - Wind-driven rain catch-ratios are an important boundary condition for the study of the hygrothermal behaviour and durability of building envelopes. Measurements are time-consuming, expensive and of limited applicability to other facades of other buildings and sites. CFD simulations are accurate, but time consuming and simplified calculation have large uncertainty. This work focuses on improving the use of WDR catch-ratios in building simulation using artificial neural networks (ANNs). Results obtained indicate that an ANN can predict WDR catch-ratio with an uncertainty of 0:07 for a confidence interval of 95%. ANNs have the ability to combine results from multiple experiments/simulations to provide catch ratios at any position at the facade and extrapolate them to a range of facade's aspect ratios.

AB - Wind-driven rain catch-ratios are an important boundary condition for the study of the hygrothermal behaviour and durability of building envelopes. Measurements are time-consuming, expensive and of limited applicability to other facades of other buildings and sites. CFD simulations are accurate, but time consuming and simplified calculation have large uncertainty. This work focuses on improving the use of WDR catch-ratios in building simulation using artificial neural networks (ANNs). Results obtained indicate that an ANN can predict WDR catch-ratio with an uncertainty of 0:07 for a confidence interval of 95%. ANNs have the ability to combine results from multiple experiments/simulations to provide catch ratios at any position at the facade and extrapolate them to a range of facade's aspect ratios.

KW - wind-driven rain catch-ratios

KW - hygrothermal behaviour

KW - machine learning

KW - artificial neural network

M3 - Paper

ER -