Detail Identification and Computer Control of a Fermentor using Neural Networks   Oleh:  Meszaros, A. ; Andrasik, A. ; Sperka, L. Jenis: Article from Article Dalam koleksi: Final Program and Book of Abstracts: The 4th Asian Control Conference, September 25-27, 2002 (Sep. 2002), page 220-224. Topik: Computer Control; Fermentor; Neural Networks Fulltext: AC021328.PDF (268.98KB) Isi artikel The advantages of the artificial neural network strategies in process identification and control are demonstrated, hereinafter, for a highly non-linear, random behavior process, represented by a laboratory-scale biochemical reactor. A PC supported, fully automatically operating, multi-task control system has been designed and built up by the authors. Forward and inverse neural process models are proposed to identify and control the pH as well as the dissolved oxygen concentration in the fermentor, operating on the Saccharomyces cerevisiae based culture. The models are trained off-line, using a modified back-propagation algorithm, based on conjugate gradients. Opini Anda Klik untuk menuliskan opini Anda tentang koleksi ini! Kembali

Copyright © 2006, 2007 Unika Atma Jaya, all rights reserved