Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm

The Nitrogen Oxides (NOx) from engines aggravate natural environment and human health. Institutional regulations have attempted to protect the human body from them, while car manufacturers have tried to make NOx free vehicles. The formation of NOx emissions is highly dependent on the engine operatin...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim Jongmyung, Park Jihwan, Shin Seunghyup, Lee Yongjoo, Min Kyoungdoug, Lee Sangyul, Kim Minjae
Formato:	article
Lenguaje:	EN FR
Publicado:	EDP Sciences 2021
Materias:	Chemical technology TP1-1185 Energy industries. Energy policy. Fuel trade HD9502-9502.5
Acceso en línea:	https://doaj.org/article/9550429c66f341bab52f003e3dae2ebf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9550429c66f341bab52f003e3dae2ebf
record_format	dspace
spelling	oai:doaj.org-article:9550429c66f341bab52f003e3dae2ebf2021-12-02T17:14:51ZPrediction of engine NOx for virtual sensor using deep neural network and genetic algorithm1294-44751953-818910.2516/ogst/2021054https://doaj.org/article/9550429c66f341bab52f003e3dae2ebf2021-01-01T00:00:00Zhttps://ogst.ifpenergiesnouvelles.fr/articles/ogst/full_html/2021/01/ogst200187/ogst200187.htmlhttps://doaj.org/toc/1294-4475https://doaj.org/toc/1953-8189The Nitrogen Oxides (NOx) from engines aggravate natural environment and human health. Institutional regulations have attempted to protect the human body from them, while car manufacturers have tried to make NOx free vehicles. The formation of NOx emissions is highly dependent on the engine operating conditions and being able to predict NOx emissions would significantly help in enabling their reduction. This study investigates advanced method of predicting vehicle NOx emissions in pursuit of the sensorless engine. Sensors inside the engine are required to measure the operating condition. However, they can be removed or reduced if the sensing object such as the engine NOx emissions can be accurately predicted with a virtual model. This would result in cost reductions and overcome the sensor durability problem. To achieve such a goal, researchers have studied numerical analysis for the relationship between emissions and engine operating conditions. Also, a Deep Neural Network (DNN) is applied recently as a solution. However, the prediction accuracies were often not satisfactory where hyperparameter optimization was either overlooked or conducted manually. Therefore, this study proposes a virtual NOx sensor model based on the hyperparameter optimization. A Genetic Algorithm (GA) was adopted to establish a global optimum with DNN. Epoch size and learning rate are employed as the design variables, and R-squared based user defined function is adopted as the object function of GA. As a result, a more accurate and reliable virtual NOx sensor with the possibility of a sensorless engine could be developed and verified.Kim JongmyungPark JihwanShin SeunghyupLee YongjooMin KyoungdougLee SangyulKim MinjaeEDP SciencesarticleChemical technologyTP1-1185Energy industries. Energy policy. Fuel tradeHD9502-9502.5ENFROil & Gas Science and Technology, Vol 76, p 72 (2021)
institution	DOAJ
collection	DOAJ
language	EN FR
topic	Chemical technology TP1-1185 Energy industries. Energy policy. Fuel trade HD9502-9502.5
spellingShingle	Chemical technology TP1-1185 Energy industries. Energy policy. Fuel trade HD9502-9502.5 Kim Jongmyung Park Jihwan Shin Seunghyup Lee Yongjoo Min Kyoungdoug Lee Sangyul Kim Minjae Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm
description	The Nitrogen Oxides (NOx) from engines aggravate natural environment and human health. Institutional regulations have attempted to protect the human body from them, while car manufacturers have tried to make NOx free vehicles. The formation of NOx emissions is highly dependent on the engine operating conditions and being able to predict NOx emissions would significantly help in enabling their reduction. This study investigates advanced method of predicting vehicle NOx emissions in pursuit of the sensorless engine. Sensors inside the engine are required to measure the operating condition. However, they can be removed or reduced if the sensing object such as the engine NOx emissions can be accurately predicted with a virtual model. This would result in cost reductions and overcome the sensor durability problem. To achieve such a goal, researchers have studied numerical analysis for the relationship between emissions and engine operating conditions. Also, a Deep Neural Network (DNN) is applied recently as a solution. However, the prediction accuracies were often not satisfactory where hyperparameter optimization was either overlooked or conducted manually. Therefore, this study proposes a virtual NOx sensor model based on the hyperparameter optimization. A Genetic Algorithm (GA) was adopted to establish a global optimum with DNN. Epoch size and learning rate are employed as the design variables, and R-squared based user defined function is adopted as the object function of GA. As a result, a more accurate and reliable virtual NOx sensor with the possibility of a sensorless engine could be developed and verified.
format	article
author	Kim Jongmyung Park Jihwan Shin Seunghyup Lee Yongjoo Min Kyoungdoug Lee Sangyul Kim Minjae
author_facet	Kim Jongmyung Park Jihwan Shin Seunghyup Lee Yongjoo Min Kyoungdoug Lee Sangyul Kim Minjae
author_sort	Kim Jongmyung
title	Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm
title_short	Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm
title_full	Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm
title_fullStr	Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm
title_full_unstemmed	Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm
title_sort	prediction of engine nox for virtual sensor using deep neural network and genetic algorithm
publisher	EDP Sciences
publishDate	2021
url	https://doaj.org/article/9550429c66f341bab52f003e3dae2ebf
work_keys_str_mv	AT kimjongmyung predictionofenginenoxforvirtualsensorusingdeepneuralnetworkandgeneticalgorithm AT parkjihwan predictionofenginenoxforvirtualsensorusingdeepneuralnetworkandgeneticalgorithm AT shinseunghyup predictionofenginenoxforvirtualsensorusingdeepneuralnetworkandgeneticalgorithm AT leeyongjoo predictionofenginenoxforvirtualsensorusingdeepneuralnetworkandgeneticalgorithm AT minkyoungdoug predictionofenginenoxforvirtualsensorusingdeepneuralnetworkandgeneticalgorithm AT leesangyul predictionofenginenoxforvirtualsensorusingdeepneuralnetworkandgeneticalgorithm AT kimminjae predictionofenginenoxforvirtualsensorusingdeepneuralnetworkandgeneticalgorithm
_version_	1718381273555140608

Prediction of engine NOx for virtual sensor using deep neural network and genetic algorithm

Ejemplares similares