Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks
The Crude Preheat Train (CPT) in a petroleum refinery recovers waste heat from product streams to preheat the crude oil. Due to high fouling nature of the fluids that flow through the exchangers, the performance deteriorates significantly over time as less heat can be transferred through the fouli...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Book Section |
Published: |
World Scientific and Engineering Academy and Society Press
2007
|
Subjects: | |
Online Access: | http://eprints.utp.edu.my/3851/1/le-no-ee-2007.pdf http://www.wseas.org http://eprints.utp.edu.my/3851/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Teknologi Petronas |
id |
my.utp.eprints.3851 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.38512017-01-19T08:27:06Z Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks M., Ramasamy H., Zabiri N. T. , Thanh Ha N. M. , Ramli TP Chemical technology The Crude Preheat Train (CPT) in a petroleum refinery recovers waste heat from product streams to preheat the crude oil. Due to high fouling nature of the fluids that flow through the exchangers, the performance deteriorates significantly over time as less heat can be transferred through the fouling layers. Prediction of the performance for optimal scheduling of the CPT operations requires a reasonably accurate mathematical model. There are no guidelines for selecting relevant input variables and correct functional forms for building theoretical models for such nonlinear systems. Neural Network (NN) offers the flexibility to model complex and nonlinear systems with good prediction capabilities. In this paper, prediction models using two different types of NNs are developed and compared for a heat exchanger to predict the change in the outlet temperatures over time. The data required for model building were collected from plant historian in a refinery. The data were processed for removal of outliers through Principal Component Analysis (PCA) and the important input variables (predictors) were selected using Projection to Latent Structures (PLS). A nonlinear auto-regression with exogenous inputs (NARX) type neural network model demonstrates its superior prediction capabilities with a root mean square error of less than 2.5 oC in the outlet temperatures and possesses a correct directional change index of more than 90%. World Scientific and Engineering Academy and Society Press Helmis, C. Celikyay, S. 2007 Book Section PeerReviewed application/pdf http://eprints.utp.edu.my/3851/1/le-no-ee-2007.pdf http://www.wseas.org M., Ramasamy and H., Zabiri and N. T. , Thanh Ha and N. M. , Ramli (2007) Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks. In: Lecture Notes on Energy and Environment. Energy and Environmental Engineering Series (ISSN: ). World Scientific and Engineering Academy and Society Press, pp. 202-207. ISBN 978-960-6766-09-1 http://eprints.utp.edu.my/3851/ |
institution |
Universiti Teknologi Petronas |
building |
UTP Resource Centre |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Petronas |
content_source |
UTP Institutional Repository |
url_provider |
http://eprints.utp.edu.my/ |
topic |
TP Chemical technology |
spellingShingle |
TP Chemical technology M., Ramasamy H., Zabiri N. T. , Thanh Ha N. M. , Ramli Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks |
description |
The Crude Preheat Train (CPT) in a petroleum refinery recovers waste heat from product streams
to preheat the crude oil. Due to high fouling nature of the fluids that flow through the exchangers, the
performance deteriorates significantly over time as less heat can be transferred through the fouling layers.
Prediction of the performance for optimal scheduling of the CPT operations requires a reasonably accurate
mathematical model. There are no guidelines for selecting relevant input variables and correct functional
forms for building theoretical models for such nonlinear systems. Neural Network (NN) offers the flexibility
to model complex and nonlinear systems with good prediction capabilities. In this paper, prediction models
using two different types of NNs are developed and compared for a heat exchanger to predict the change in the
outlet temperatures over time. The data required for model building were collected from plant historian in a
refinery. The data were processed for removal of outliers through Principal Component Analysis (PCA) and
the important input variables (predictors) were selected using Projection to Latent Structures (PLS). A
nonlinear auto-regression with exogenous inputs (NARX) type neural network model demonstrates its superior
prediction capabilities with a root mean square error of less than 2.5 oC in the outlet temperatures and
possesses a correct directional change index of more than 90%. |
author2 |
Helmis, C. |
author_facet |
Helmis, C. M., Ramasamy H., Zabiri N. T. , Thanh Ha N. M. , Ramli |
format |
Book Section |
author |
M., Ramasamy H., Zabiri N. T. , Thanh Ha N. M. , Ramli |
author_sort |
M., Ramasamy |
title |
Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks |
title_short |
Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks |
title_full |
Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks |
title_fullStr |
Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks |
title_full_unstemmed |
Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks |
title_sort |
heat exchanger performance prediction modeling using narx-type neural networks |
publisher |
World Scientific and Engineering Academy and Society Press |
publishDate |
2007 |
url |
http://eprints.utp.edu.my/3851/1/le-no-ee-2007.pdf http://www.wseas.org http://eprints.utp.edu.my/3851/ |
_version_ |
1738655300949377024 |