JaLCDOI 10.18926/46947
フルテキストURL mfe_38_1-2_005_014.pdf
著者 Ishimaru, Kazuhito| Konishi, Masami| Imai, Jun| Nishi, Tatsushi|
抄録 Temperature distribution in the reactor furnace is mainly operated by gas blowing from multiple tuyeres and material charge distribution. The objective of our research is obtain the optimal profile of gas flow to control temperature distribution in the reactor furnace in the shortest possible time. We formulated the optimization problem to reduce deviation of temperature distribution from its desired one in the reactor furnace. Based on the formulation, gas blow conditions are optimized by a sequential quadratic programming method to realize the desired temperature distribution. The validity of the method was checked through numerical experiments.
出版物タイトル Memoirs of the Faculty of Engineering, Okayama University
発行日 2004-03
38巻
1-2号
開始ページ 5
終了ページ 14
ISSN 0475-0071
言語 英語
論文のバージョン publisher
NAID 80016785933
JaLCDOI 10.18926/46948
フルテキストURL mfe_38_1-2_015_027.pdf
著者 Torigoe, Takashi| Konishi, Masami| Imai, Jun| Nishi, Tatsushi|
抄録 In these days, mechanical systems are becoming more complex and highly automated. So, there exist wide variety of demands for reliable diagnostic technology. A reliable data analysis and quantitative diagnosis method of mechanical system is necessary for the purpose. In this paper a quantitative diagnosis method for looper height control system has been developed based on neural network technologies. The wavelet transformation is used for pre-processing to analyze characteristics of looper height control system. And, self organizing map neural network is used for the purpose of classification based on the pre-processed data. After that, the classified results are used for quantitative diagnosis in hierarchical neural network.
出版物タイトル Memoirs of the Faculty of Engineering, Okayama University
発行日 2004-03
38巻
1-2号
開始ページ 15
終了ページ 27
ISSN 0475-0071
言語 英語
論文のバージョン publisher
NAID 80016785934