Ji yu pca-rbf shen jing wang luo de gong ye lie jie lu shou lv zai xian yu ce ruan ce liang fang fa

Translated title of the contribution: A soft-sensing approach to on-line predict the yields of industrial pyrolysis furnace based on PCA-RBF neural networks

Erfu Yang, Qiang Zhou, Yi Feng Hu, Yong Mao Xu

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The industrial pyrolysis furnace is a key equipment in ethylene process. It is very essential and important to on-line obtain the accurate yields of products not only for advanced control, process optimization, production evaluation, but also for performance monitoring, safety supervision, and fault diagnosis. However, it is usually difficult to on-line measure the product yields because of many practical reasons in some ethylene plants. In order to solve the problem on on-line yields prediction of industrial pyrolysis furnace, a soft-sensing approach with multi-inputs and multi-outputs (MIMO), and on-line correcting methods are investigated based on PCA(principal component analysis)-RBF(radial basis function) neural networks. The topology structure of this soft-sensing approach is as follows: the first unit is PCA, the second is RBF neural network, and the third is correcting unit. So the soft-sensing approach combines the abilities of PCA to de-correlate the variables and reduce the dimensionality of the data matrix with that of neural network to approximate any complex nonlinear function. The approach, which is of good real-time property, short modeling time, little calculations, and easily correcting, can be applied to on-line predict the yields of industrial pyrolysis furnace. The good performance of PCA-RBF soft-sensing approach for on-line yields prediction is illustrated by the example from a SRT-IV furnace. The results show that the soft-sensing approach to on-line predict the yields of industrial pyrolysis furnace based on PCA-RBF neural network is effective.

Original languageChinese
Pages (from-to)194-197
Number of pages4
JournalXitong Fangzhen Xuebao / Journal of System Simulation
Volume13
Issue numberS1
Publication statusPublished - 1 Dec 2001

Fingerprint

Soft-sensing
Pyrolysis
RBF Neural Network
Furnace
Principal component analysis
Principal Component Analysis
Furnaces
Neural networks
Predict
Ethylene
Performance Monitoring
Failure analysis
Unit
Radial Basis Function Neural Network
Prediction
Complex Functions
Process Optimization
Topology
Fault Diagnosis
Nonlinear Function

Keywords

  • ethylene process
  • neural networks
  • principal component analysis(PCA)
  • process modeling
  • pyrolysis furnace
  • soft-sensing

Cite this

@article{7b02824262a04103b995d686929e8c13,
title = "Ji yu pca-rbf shen jing wang luo de gong ye lie jie lu shou lv zai xian yu ce ruan ce liang fang fa",
abstract = "The industrial pyrolysis furnace is a key equipment in ethylene process. It is very essential and important to on-line obtain the accurate yields of products not only for advanced control, process optimization, production evaluation, but also for performance monitoring, safety supervision, and fault diagnosis. However, it is usually difficult to on-line measure the product yields because of many practical reasons in some ethylene plants. In order to solve the problem on on-line yields prediction of industrial pyrolysis furnace, a soft-sensing approach with multi-inputs and multi-outputs (MIMO), and on-line correcting methods are investigated based on PCA(principal component analysis)-RBF(radial basis function) neural networks. The topology structure of this soft-sensing approach is as follows: the first unit is PCA, the second is RBF neural network, and the third is correcting unit. So the soft-sensing approach combines the abilities of PCA to de-correlate the variables and reduce the dimensionality of the data matrix with that of neural network to approximate any complex nonlinear function. The approach, which is of good real-time property, short modeling time, little calculations, and easily correcting, can be applied to on-line predict the yields of industrial pyrolysis furnace. The good performance of PCA-RBF soft-sensing approach for on-line yields prediction is illustrated by the example from a SRT-IV furnace. The results show that the soft-sensing approach to on-line predict the yields of industrial pyrolysis furnace based on PCA-RBF neural network is effective.",
keywords = "ethylene process, neural networks, principal component analysis(PCA), process modeling, pyrolysis furnace, soft-sensing",
author = "Erfu Yang and Qiang Zhou and Hu, {Yi Feng} and Xu, {Yong Mao}",
year = "2001",
month = "12",
day = "1",
language = "Chinese",
volume = "13",
pages = "194--197",
journal = "Xitong Fangzhen Xuebao / Journal of System Simulation",
issn = "1004-731X",
number = "S1",

}

Ji yu pca-rbf shen jing wang luo de gong ye lie jie lu shou lv zai xian yu ce ruan ce liang fang fa. / Yang, Erfu; Zhou, Qiang; Hu, Yi Feng; Xu, Yong Mao.

In: Xitong Fangzhen Xuebao / Journal of System Simulation, Vol. 13, No. S1, 01.12.2001, p. 194-197.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Ji yu pca-rbf shen jing wang luo de gong ye lie jie lu shou lv zai xian yu ce ruan ce liang fang fa

AU - Yang, Erfu

AU - Zhou, Qiang

AU - Hu, Yi Feng

AU - Xu, Yong Mao

PY - 2001/12/1

Y1 - 2001/12/1

N2 - The industrial pyrolysis furnace is a key equipment in ethylene process. It is very essential and important to on-line obtain the accurate yields of products not only for advanced control, process optimization, production evaluation, but also for performance monitoring, safety supervision, and fault diagnosis. However, it is usually difficult to on-line measure the product yields because of many practical reasons in some ethylene plants. In order to solve the problem on on-line yields prediction of industrial pyrolysis furnace, a soft-sensing approach with multi-inputs and multi-outputs (MIMO), and on-line correcting methods are investigated based on PCA(principal component analysis)-RBF(radial basis function) neural networks. The topology structure of this soft-sensing approach is as follows: the first unit is PCA, the second is RBF neural network, and the third is correcting unit. So the soft-sensing approach combines the abilities of PCA to de-correlate the variables and reduce the dimensionality of the data matrix with that of neural network to approximate any complex nonlinear function. The approach, which is of good real-time property, short modeling time, little calculations, and easily correcting, can be applied to on-line predict the yields of industrial pyrolysis furnace. The good performance of PCA-RBF soft-sensing approach for on-line yields prediction is illustrated by the example from a SRT-IV furnace. The results show that the soft-sensing approach to on-line predict the yields of industrial pyrolysis furnace based on PCA-RBF neural network is effective.

AB - The industrial pyrolysis furnace is a key equipment in ethylene process. It is very essential and important to on-line obtain the accurate yields of products not only for advanced control, process optimization, production evaluation, but also for performance monitoring, safety supervision, and fault diagnosis. However, it is usually difficult to on-line measure the product yields because of many practical reasons in some ethylene plants. In order to solve the problem on on-line yields prediction of industrial pyrolysis furnace, a soft-sensing approach with multi-inputs and multi-outputs (MIMO), and on-line correcting methods are investigated based on PCA(principal component analysis)-RBF(radial basis function) neural networks. The topology structure of this soft-sensing approach is as follows: the first unit is PCA, the second is RBF neural network, and the third is correcting unit. So the soft-sensing approach combines the abilities of PCA to de-correlate the variables and reduce the dimensionality of the data matrix with that of neural network to approximate any complex nonlinear function. The approach, which is of good real-time property, short modeling time, little calculations, and easily correcting, can be applied to on-line predict the yields of industrial pyrolysis furnace. The good performance of PCA-RBF soft-sensing approach for on-line yields prediction is illustrated by the example from a SRT-IV furnace. The results show that the soft-sensing approach to on-line predict the yields of industrial pyrolysis furnace based on PCA-RBF neural network is effective.

KW - ethylene process

KW - neural networks

KW - principal component analysis(PCA)

KW - process modeling

KW - pyrolysis furnace

KW - soft-sensing

UR - http://www.scopus.com/inward/record.url?scp=4444379880&partnerID=8YFLogxK

UR - http://caod.oriprobe.com/articles/38766033/ji_yu_pca_rbf_shen_jing_wang_luo_de_gong_ye_lie_jie_lu_shou_lv_zai_xia.htm

M3 - Article

VL - 13

SP - 194

EP - 197

JO - Xitong Fangzhen Xuebao / Journal of System Simulation

JF - Xitong Fangzhen Xuebao / Journal of System Simulation

SN - 1004-731X

IS - S1

ER -