Digital Twin of a Reheating Furnace
In this thesis, a proof of concept of a digital twin of a type of reheating furnace, the walking beam furnace, is presented. It is created by using a machine learning concept called a neural network. The digital twin is trained using real data from a walking beam furnace located in Swerim AB, Luleå,...
Main Author: | |
---|---|
Format: | Bachelor Thesis |
Language: | English |
Published: |
Luleå tekniska universitet, Institutionen för system- och rymdteknik
2021
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87911 |
id |
ftluleatu:oai:DiVA.org:ltu-87911 |
---|---|
record_format |
openpolar |
spelling |
ftluleatu:oai:DiVA.org:ltu-87911 2023-05-15T17:09:11+02:00 Digital Twin of a Reheating Furnace Halme Ståhlberg, Daniel 2021 application/pdf http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87911 eng eng Luleå tekniska universitet, Institutionen för system- och rymdteknik http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87911 info:eu-repo/semantics/openAccess Machine Learning Digital Twin Reheating Furnace Steel Industry Tensorflow Neural Network Prediction Computer Engineering Datorteknik Student thesis info:eu-repo/semantics/bachelorThesis text 2021 ftluleatu 2022-10-25T20:58:01Z In this thesis, a proof of concept of a digital twin of a type of reheating furnace, the walking beam furnace, is presented. It is created by using a machine learning concept called a neural network. The digital twin is trained using real data from a walking beam furnace located in Swerim AB, Luleå, and is taught to predict the temperature in the furnace using air, fuel and pressure as inputs. The machine learning technique used is an artifical neural network in the form of a multilayer perceptron model. The resulting model consists of 3 layers, input, hidden and output layer. The hyperparameters is decided by using grid search cross validation. The hyperparameters chosen to use in this thesis was amount of epochs, optimizer, learning rate, batch size, activation function, regularizer and amount of neurons in the hidden layer. The final settings for these can be found in table. The digital twin is then evaluated comparing predicted temperatures and actual temperatures from the measured data. The end result shows that the twin performs reasonably well. The predictions differs from measured temperature with a percentage around 0.5% to 1.5%. Bachelor Thesis Luleå Luleå Luleå Luleå University of Technology Publications (DiVA) |
institution |
Open Polar |
collection |
Luleå University of Technology Publications (DiVA) |
op_collection_id |
ftluleatu |
language |
English |
topic |
Machine Learning Digital Twin Reheating Furnace Steel Industry Tensorflow Neural Network Prediction Computer Engineering Datorteknik |
spellingShingle |
Machine Learning Digital Twin Reheating Furnace Steel Industry Tensorflow Neural Network Prediction Computer Engineering Datorteknik Halme Ståhlberg, Daniel Digital Twin of a Reheating Furnace |
topic_facet |
Machine Learning Digital Twin Reheating Furnace Steel Industry Tensorflow Neural Network Prediction Computer Engineering Datorteknik |
description |
In this thesis, a proof of concept of a digital twin of a type of reheating furnace, the walking beam furnace, is presented. It is created by using a machine learning concept called a neural network. The digital twin is trained using real data from a walking beam furnace located in Swerim AB, Luleå, and is taught to predict the temperature in the furnace using air, fuel and pressure as inputs. The machine learning technique used is an artifical neural network in the form of a multilayer perceptron model. The resulting model consists of 3 layers, input, hidden and output layer. The hyperparameters is decided by using grid search cross validation. The hyperparameters chosen to use in this thesis was amount of epochs, optimizer, learning rate, batch size, activation function, regularizer and amount of neurons in the hidden layer. The final settings for these can be found in table. The digital twin is then evaluated comparing predicted temperatures and actual temperatures from the measured data. The end result shows that the twin performs reasonably well. The predictions differs from measured temperature with a percentage around 0.5% to 1.5%. |
format |
Bachelor Thesis |
author |
Halme Ståhlberg, Daniel |
author_facet |
Halme Ståhlberg, Daniel |
author_sort |
Halme Ståhlberg, Daniel |
title |
Digital Twin of a Reheating Furnace |
title_short |
Digital Twin of a Reheating Furnace |
title_full |
Digital Twin of a Reheating Furnace |
title_fullStr |
Digital Twin of a Reheating Furnace |
title_full_unstemmed |
Digital Twin of a Reheating Furnace |
title_sort |
digital twin of a reheating furnace |
publisher |
Luleå tekniska universitet, Institutionen för system- och rymdteknik |
publishDate |
2021 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87911 |
genre |
Luleå Luleå Luleå |
genre_facet |
Luleå Luleå Luleå |
op_relation |
http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87911 |
op_rights |
info:eu-repo/semantics/openAccess |
_version_ |
1766065155975675904 |