Modelling A Single-Rotor Wankel Engine Performance With Artificial Neural Network At Middle Speed Range
The researches on Wankel engines are very rare and considered new in modelling and prediction. Therefore this study deals with the artificial neural network (ANN) modelling of a Wankel engine to predict the power, volumetric efficiency and emissions, including nitrogen oxide, carbon dioxide, carbon...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Turkish Society of Automotive Engineers
2020-09-01
|
Series: | International Journal of Automotive Science and Technology |
Subjects: | |
Online Access: | https://dergipark.org.tr/en/pub/ijastech/issue/55251/771165 |
id |
doaj-b95d6c99b2f544d698334acacd32f8ae |
---|---|
record_format |
Article |
spelling |
doaj-b95d6c99b2f544d698334acacd32f8ae2021-02-08T21:31:14ZengTurkish Society of Automotive EngineersInternational Journal of Automotive Science and Technology2587-09632020-09-014315516310.30939/ijastech..77116558Modelling A Single-Rotor Wankel Engine Performance With Artificial Neural Network At Middle Speed RangeCemal Baykara0Osman Azmi Özsoysal1Akın Kutlar2Ömer Ci̇han3Mehmet İ̇lter Özmen4ISTANBUL TECHNICAL UNIVERSITYISTANBUL TECHNICAL UNIVERSITYISTANBUL TECHNICAL UNIVERSITYHAKKARI UNIVERSITYİSTANBUL TEKNİK ÜNİVERSİTESİThe researches on Wankel engines are very rare and considered new in modelling and prediction. Therefore this study deals with the artificial neural network (ANN) modelling of a Wankel engine to predict the power, volumetric efficiency and emissions, including nitrogen oxide, carbon dioxide, carbon monoxide and oxygen by using the change of mean effective pressure, intake manifold pressure, start of ignition angle and injection duration as inputs. The experiment results were taken from a research which is performed on a single-rotor, four stroke and port fuel injection 13B Wankel engine. The number of datas which are taken from experimental results were scarce and varied in six different data set (for example; mean effective pressure, from 1 to 6 bar) at 3000 rpm engine speed. The standard back-propagation (BPNN) Levenberg-Marquardt neural network algorithm is applied to evaluate the performance of middle speed range Wankel engine. The model performance was validated by comparing the prediction data sets with the measured experimental data. Results approved that the artificial neural network (ANN) model provided good agreement with the experimental data with good accuracy while the correlation coefficient R varies between 0.79 and 0.97.https://dergipark.org.tr/en/pub/ijastech/issue/55251/771165artificial neural networkengine performanceexhaust emissionsscarce datawankel engine |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Cemal Baykara Osman Azmi Özsoysal Akın Kutlar Ömer Ci̇han Mehmet İ̇lter Özmen |
spellingShingle |
Cemal Baykara Osman Azmi Özsoysal Akın Kutlar Ömer Ci̇han Mehmet İ̇lter Özmen Modelling A Single-Rotor Wankel Engine Performance With Artificial Neural Network At Middle Speed Range International Journal of Automotive Science and Technology artificial neural network engine performance exhaust emissions scarce data wankel engine |
author_facet |
Cemal Baykara Osman Azmi Özsoysal Akın Kutlar Ömer Ci̇han Mehmet İ̇lter Özmen |
author_sort |
Cemal Baykara |
title |
Modelling A Single-Rotor Wankel Engine Performance With Artificial Neural Network At Middle Speed Range |
title_short |
Modelling A Single-Rotor Wankel Engine Performance With Artificial Neural Network At Middle Speed Range |
title_full |
Modelling A Single-Rotor Wankel Engine Performance With Artificial Neural Network At Middle Speed Range |
title_fullStr |
Modelling A Single-Rotor Wankel Engine Performance With Artificial Neural Network At Middle Speed Range |
title_full_unstemmed |
Modelling A Single-Rotor Wankel Engine Performance With Artificial Neural Network At Middle Speed Range |
title_sort |
modelling a single-rotor wankel engine performance with artificial neural network at middle speed range |
publisher |
Turkish Society of Automotive Engineers |
series |
International Journal of Automotive Science and Technology |
issn |
2587-0963 |
publishDate |
2020-09-01 |
description |
The researches on Wankel engines are very rare and considered new in modelling and prediction. Therefore this study deals with the artificial neural network (ANN) modelling of a Wankel engine to predict the power, volumetric efficiency and emissions, including nitrogen oxide, carbon dioxide, carbon monoxide and oxygen by using the change of mean effective pressure, intake manifold pressure, start of ignition angle and injection duration as inputs. The experiment results were taken from a research which is performed on a single-rotor, four stroke and port fuel injection 13B Wankel engine. The number of datas which are taken from experimental results were scarce and varied in six different data set (for example; mean effective pressure, from 1 to 6 bar) at 3000 rpm engine speed. The standard back-propagation (BPNN) Levenberg-Marquardt neural network algorithm is applied to evaluate the performance of middle speed range Wankel engine. The model performance was validated by comparing the prediction data sets with the measured experimental data. Results approved that the artificial neural network (ANN) model provided good agreement with the experimental data with good accuracy while the correlation coefficient R varies between 0.79 and 0.97. |
topic |
artificial neural network engine performance exhaust emissions scarce data wankel engine |
url |
https://dergipark.org.tr/en/pub/ijastech/issue/55251/771165 |
work_keys_str_mv |
AT cemalbaykara modellingasinglerotorwankelengineperformancewithartificialneuralnetworkatmiddlespeedrange AT osmanazmiozsoysal modellingasinglerotorwankelengineperformancewithartificialneuralnetworkatmiddlespeedrange AT akınkutlar modellingasinglerotorwankelengineperformancewithartificialneuralnetworkatmiddlespeedrange AT omercihan modellingasinglerotorwankelengineperformancewithartificialneuralnetworkatmiddlespeedrange AT mehmetilterozmen modellingasinglerotorwankelengineperformancewithartificialneuralnetworkatmiddlespeedrange |
_version_ |
1724279211150016512 |