Soft Sensor for Ammonia Concentration at the Ammonia Converter Outlet Based on an Improved Group Search Optimization and BP Neural Network

The ammonia synthesis reactor is the core unit in the whole ammonia synthesis production. The ammo- nia concentration at the ammonia converter outlet is a significant process variable, which reflects directly the pro- duction efficiency. However, it is hard to be measured reliably online in real app...

Full description

Saved in:
Bibliographic Details
Published inChinese journal of chemical engineering Vol. 20; no. 6; pp. 1184 - 1190
Main Author 阎兴頔 杨文 马贺贺 侍洪波
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.12.2012
Subjects
Ammonia
ammonia concentration
ammonia synthesis
Artificial neural networks
Back propagation
BP神经网络
group search optimization
Mathematical models
Outlets
Searching
Sensors
soft sensor
Synthesis
优化
出口
应用程序
搜索
氨合成塔
氨浓度
软测量模型
soft sensor
group search optimization
ammonia concentration
ammonia synthesis
Online AccessGet full text
ISSN1004-9541
2210-321X
DOI10.1016/S1004-9541(12)60606-5

Cover

More Information
Summary:The ammonia synthesis reactor is the core unit in the whole ammonia synthesis production. The ammo- nia concentration at the ammonia converter outlet is a significant process variable, which reflects directly the pro- duction efficiency. However, it is hard to be measured reliably online in real applications. In this paper, a soft sensor based on BP neural network （BPNN） is applied to estimate the ammonia concentration. A modified group search optimization with nearest neighborhood （GSO-NH） is proposed to optimize the weights and thresholds of BPNN. GSO-NH is integrated with BPNN to build a soft sensor model. Finally, the soft sensor model based on BPNN and GSO-NH （GSO-NH-NN） is used to infer the outlet ammonia concentration in a real-world application. Three other modeling methods are applied for comparison with GSO-NH-NN. The results show that the soft sensor based on GSO-NH-NN has a good prediction performance with high accuracy. Moreover, the GSO-NH-NN also provides good generalization ability to other modeling problems in ammonia synthesis production.
Bibliography:YAN Xingdi , YANG Wen , MA Hehe, SHI Hongbo （Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, Shanghai 200237, China）
The ammonia synthesis reactor is the core unit in the whole ammonia synthesis production. The ammo- nia concentration at the ammonia converter outlet is a significant process variable, which reflects directly the pro- duction efficiency. However, it is hard to be measured reliably online in real applications. In this paper, a soft sensor based on BP neural network （BPNN） is applied to estimate the ammonia concentration. A modified group search optimization with nearest neighborhood （GSO-NH） is proposed to optimize the weights and thresholds of BPNN. GSO-NH is integrated with BPNN to build a soft sensor model. Finally, the soft sensor model based on BPNN and GSO-NH （GSO-NH-NN） is used to infer the outlet ammonia concentration in a real-world application. Three other modeling methods are applied for comparison with GSO-NH-NN. The results show that the soft sensor based on GSO-NH-NN has a good prediction performance with high accuracy. Moreover, the GSO-NH-NN also provides good generalization ability to other modeling problems in ammonia synthesis production.
11-3270/TQ
ammonia synthesis, ammonia concentration, soft sensor, group search optimization
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1004-9541
2210-321X
DOI:10.1016/S1004-9541(12)60606-5