Prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data

Machine learning has received increased recognition for applications in engineering such as the thermal engineering discipline due to its abilities to circumvent thermodynamic simulation approaches and capture complex inter-dependencies. There have been recent headways to couple deep learning models...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Raidoo Renita, Laubscher Ryno
Formato:	article
Lenguaje:	EN FR
Publicado:	EDP Sciences 2021
Materias:	Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/b76e652d6a19446b98e88b5bd96da427
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b76e652d6a19446b98e88b5bd96da427
record_format	dspace
spelling	oai:doaj.org-article:b76e652d6a19446b98e88b5bd96da4272021-12-02T17:13:35ZPrediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data2261-236X10.1051/matecconf/202134700019https://doaj.org/article/b76e652d6a19446b98e88b5bd96da4272021-01-01T00:00:00Zhttps://www.matec-conferences.org/articles/matecconf/pdf/2021/16/matecconf_sacam21_00019.pdfhttps://doaj.org/toc/2261-236XMachine learning has received increased recognition for applications in engineering such as the thermal engineering discipline due to its abilities to circumvent thermodynamic simulation approaches and capture complex inter-dependencies. There have been recent headways to couple deep learning models to process simulations, given the deeper insight they can provide. The present study entails the development of a mixture density network (MDN) capable of predicting effective heat transfer coefficients for the various heat exchanger components of a utility scale boiler. Large boilers are susceptible to dead zones and other anomalous phenomena that influence performance and manifest as multimodalities in the measured data, which system-level 1D process models struggle to capture. The overall water-side heat load calculation, as well as mass and energy balances around the components were done to determine the heat transfer coefficients at each stage of the boiler using historic sensor data. The measured data was then used to train a deep learning model capable of outputting predicted heat transfer coefficients and local model uncertainty. The predictive model can be coupled to a water circuit process model which can be used to study aspects such as metal temperatures and operating philosophies at the different operating loads of the plant.Raidoo RenitaLaubscher RynoEDP SciencesarticleEngineering (General). Civil engineering (General)TA1-2040ENFRMATEC Web of Conferences, Vol 347, p 00019 (2021)
institution	DOAJ
collection	DOAJ
language	EN FR
topic	Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	Engineering (General). Civil engineering (General) TA1-2040 Raidoo Renita Laubscher Ryno Prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data
description	Machine learning has received increased recognition for applications in engineering such as the thermal engineering discipline due to its abilities to circumvent thermodynamic simulation approaches and capture complex inter-dependencies. There have been recent headways to couple deep learning models to process simulations, given the deeper insight they can provide. The present study entails the development of a mixture density network (MDN) capable of predicting effective heat transfer coefficients for the various heat exchanger components of a utility scale boiler. Large boilers are susceptible to dead zones and other anomalous phenomena that influence performance and manifest as multimodalities in the measured data, which system-level 1D process models struggle to capture. The overall water-side heat load calculation, as well as mass and energy balances around the components were done to determine the heat transfer coefficients at each stage of the boiler using historic sensor data. The measured data was then used to train a deep learning model capable of outputting predicted heat transfer coefficients and local model uncertainty. The predictive model can be coupled to a water circuit process model which can be used to study aspects such as metal temperatures and operating philosophies at the different operating loads of the plant.
format	article
author	Raidoo Renita Laubscher Ryno
author_facet	Raidoo Renita Laubscher Ryno
author_sort	Raidoo Renita
title	Prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data
title_short	Prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data
title_full	Prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data
title_fullStr	Prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data
title_full_unstemmed	Prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data
title_sort	prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data
publisher	EDP Sciences
publishDate	2021
url	https://doaj.org/article/b76e652d6a19446b98e88b5bd96da427
work_keys_str_mv	AT raidoorenita predictionofboilergassideeffectiveheattransfercoefficientsusingmixturedensitynetworksandhistoricplantdata AT laubscherryno predictionofboilergassideeffectiveheattransfercoefficientsusingmixturedensitynetworksandhistoricplantdata
_version_	1718381341366550528

Prediction of boiler gas side effective heat transfer coefficients using mixture density networks and historic plant data

Ejemplares similares