Forecasting Heat Levels in Blast Furnaces Using a Neural Network Model.

• Otsuka Yoshihisa

  Process Technology Research Laboratory, Kobe Steel, Ltd.

• Konishi Masami

  Process Technology Research Laboratory, Kobe Steel, Ltd.

• Hanaoka Kunihiro

  Electronics & Information Technology Laboratory, Kobe Steel, Ltd.

• Maki Takeshi

  Kakogawa Works, Kobe Steel, Ltd.

Abstract

Heat level is one of the important factors influencing the stable operation of blast furnaces, and it is especially important to accurately forecast decreasing heat levels in order to stabilize the heat level.<br> A forecasting model for decreasing heat levels which occur accompanied with a sudden rising of wall temperatures has been developed using neural network technology. Wall temperatures are measured at various points in the vertical and circular directions. Temperature rising points are measured as a distributed pattern, and neural network technology is used in order to recognize this distributed pattern.<br>Neural network models are classified into two groups according to their learning style, one is called the supervised learning model and the other, the unsupervised learning model. The operators notice that a decrease in heat level sometimes occurs after a rise in wall temperature, but there is no knowledge of what patterns cause the heat level decrease, which means there is no teaching data for the supervised model. The forecasting model is built using one of the unsupervised neural network models, the self organization feature maps model, which recognizes and classifies the wall temperature rising patterns. A new method of shift invariant recognition has been developed in order to put circularly shifted wall temperature rising patterns together in a class.<br>It has been established that the heat level forecasting model using the classified wall temperature pattern gives better forecasting accuracy for heat level decrease than a forecasting model using the total amount of wall temperature rising points. Furthermore, this heat level forecasting model, which uses a classified wall temperature pattern and solution loss C, has sufficient accuracy for heat level operation guidance.

Journal

• ISIJ International

  ISIJ International 39 (10), 1047-1052, 1999

  The Iron and Steel Institute of Japan

Keywords

• blast furnace
• heat level forecasting
• wall temperature
• neural network
• unsupervised learning

Details

• CRID: 1390282681429645312
• NII Article ID: 10002555846
• NII Book ID: AA10680712
• DOI: 10.2355/isijinternational.39.1047
• COI: 1:CAS:528:DyaK1MXns1Grtro%3D
• ISSN: 13475460
• ISSN: 09151559
• Web Site: http://www.jstage.jst.go.jp/article/isijinternational1989/39/10/39_10_1047/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed