Reference : Kraft RB : recurrent neural network prediction of steam production

	Document type :	Scientific congresses and symposiums : Poster
	Discipline(s) :	Engineering, computing & technology : Energy
	To cite this reference:	http://hdl.handle.net/2268/94245

Title :	Kraft RB : recurrent neural network prediction of steam production
Language :	English
Author, co-author :	Sainlez, Matthieu [Université de Liège - ULg > > > Form.doct. sc. ingé. (chim. appl. - Bologne)]
	Heyen, Georges [Université de Liège - ULg > Département de chimie appliquée > LASSC (Labo d'analyse et synthèse des systèmes chimiques) >]
Publication date :	30-May-2011
Page number :	A0
Peer reviewed :	Yes
On invitation :	No
Audience :	International
Event name :	ESCAPE21
Event date :	May 29 - June 1, 2011
Event organizer :	EFCE - European Federation of Chemical Engineering
Event place (city) :	Chalkidiki
Event country :	Greece
Abstract :	[en] In this study, neural networks approaches are compared for predicting the high pressure (HP) steam flow rate from a Kraft recovery boiler. We apply two types of neural networks: a static multilayer perceptron and a dynamic Elman’s recurrent neural network. Starting from a one-day database of raw process data related to the boiler, the goal is to model and predict the next 12-hours of HP steam flow production from the boiler to the steam turbine. The results illustrate the potential of the dynamic approach in this task.
Permalink :	http://hdl.handle.net/2268/94245

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Restricted access Poster_Escape21.pdf Author postprint 2.89 MB Request copy

All documents in ORBi are protected by a user license.

 

© ULg Library Network |  Feedback |  ORBi legal notices

Dspace v1.5