MODELING A WOOD-CHIP REFINER USING ARTIFICIAL NEURAL NETWORKS

TitleMODELING A WOOD-CHIP REFINER USING ARTIFICIAL NEURAL NETWORKS
Publication TypeJournal Article
Year of Publication1995
AuthorsQIAN, Y., P. TESSIER, and G. A. Dumont
JournalTAPPI Journal
Volume78
Pagination167-174
Date PublishedJUN
Type of ArticleArticle
ISSN0734-1415
KeywordsArtificial Intelligence, CHIPS, Models, neural networks, optimization, quality, REFINERS, simulation
Abstract

The mechanism of the wood-chip refining process is still being studied, and no thorough model has yet been developed. Neural networks can be an attractive alternative to mathematical modeling of complex processes if a sufficient amount of input-output data is available. This article examines the use of a feed-forward neural network to model a wood-chip refiner. The network's predicted outputs compared faborably with industrial refiner data. It is also shown that the network structure can be modified to optimize refiner operation and product quality. Advantages and disadvantages of applying neural-networks models to simulate and optimize industrial processes are discussed.

a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949
Email:

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia