Design Optimization in Gas Turbines using Machine Learning : A study performed for Siemens Energy AB
In this thesis, the authors investigate how machine learning can be utilized for speeding up the design optimization process of gas turbines. The Finite Element Analysis (FEA) steps of the design process are examined if they can be replaced with machine learning algorithms. The study is done using a...
Main Authors: | , |
---|---|
Format: | Others |
Language: | English |
Published: |
Linköpings universitet, Programvara och system
2021
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-173920 |
id |
ndltd-UPSALLA1-oai-DiVA.org-liu-173920 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-liu-1739202021-03-13T05:27:17ZDesign Optimization in Gas Turbines using Machine Learning : A study performed for Siemens Energy ABengDesignoptimisering i gasturbiner med hjälp av maskininlärningMathias, BerggrenDaniel, SonessonLinköpings universitet, Programvara och systemLinköpings universitet, Programvara och system2021Computer ScienceDesign OptimizationDOMDOSurrogate ModelsSurrogatesResponse Surface MethodsMetamodelsMetamodelingMachine LearningMLFEAFinite Element AnalysisFEMFinite Element MethodComputer SciencesDatavetenskap (datalogi)In this thesis, the authors investigate how machine learning can be utilized for speeding up the design optimization process of gas turbines. The Finite Element Analysis (FEA) steps of the design process are examined if they can be replaced with machine learning algorithms. The study is done using a component with given constraints that are provided by Siemens Energy AB. With this component, two approaches to using machine learning are tested. One utilizes design parameters, i.e. raw floating-point numbers, such as the height and width. The other technique uses a high dimensional mesh as input. It is concluded that using design parameters with surrogate models is a viable way of performing design optimization while mesh input is currently not. Results from using different amount of data samples are presented and evaluated. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-173920application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Computer Science Design Optimization DO MDO Surrogate Models Surrogates Response Surface Methods Metamodels Metamodeling Machine Learning ML FEA Finite Element Analysis FEM Finite Element Method Computer Sciences Datavetenskap (datalogi) |
spellingShingle |
Computer Science Design Optimization DO MDO Surrogate Models Surrogates Response Surface Methods Metamodels Metamodeling Machine Learning ML FEA Finite Element Analysis FEM Finite Element Method Computer Sciences Datavetenskap (datalogi) Mathias, Berggren Daniel, Sonesson Design Optimization in Gas Turbines using Machine Learning : A study performed for Siemens Energy AB |
description |
In this thesis, the authors investigate how machine learning can be utilized for speeding up the design optimization process of gas turbines. The Finite Element Analysis (FEA) steps of the design process are examined if they can be replaced with machine learning algorithms. The study is done using a component with given constraints that are provided by Siemens Energy AB. With this component, two approaches to using machine learning are tested. One utilizes design parameters, i.e. raw floating-point numbers, such as the height and width. The other technique uses a high dimensional mesh as input. It is concluded that using design parameters with surrogate models is a viable way of performing design optimization while mesh input is currently not. Results from using different amount of data samples are presented and evaluated. |
author |
Mathias, Berggren Daniel, Sonesson |
author_facet |
Mathias, Berggren Daniel, Sonesson |
author_sort |
Mathias, Berggren |
title |
Design Optimization in Gas Turbines using Machine Learning : A study performed for Siemens Energy AB |
title_short |
Design Optimization in Gas Turbines using Machine Learning : A study performed for Siemens Energy AB |
title_full |
Design Optimization in Gas Turbines using Machine Learning : A study performed for Siemens Energy AB |
title_fullStr |
Design Optimization in Gas Turbines using Machine Learning : A study performed for Siemens Energy AB |
title_full_unstemmed |
Design Optimization in Gas Turbines using Machine Learning : A study performed for Siemens Energy AB |
title_sort |
design optimization in gas turbines using machine learning : a study performed for siemens energy ab |
publisher |
Linköpings universitet, Programvara och system |
publishDate |
2021 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-173920 |
work_keys_str_mv |
AT mathiasberggren designoptimizationingasturbinesusingmachinelearningastudyperformedforsiemensenergyab AT danielsonesson designoptimizationingasturbinesusingmachinelearningastudyperformedforsiemensenergyab AT mathiasberggren designoptimiseringigasturbinermedhjalpavmaskininlarning AT danielsonesson designoptimiseringigasturbinermedhjalpavmaskininlarning |
_version_ |
1719383520693977088 |