Development of the visualizing information technique of blast furnace operation

Visualization of shaft pressure variations and spatial changes caused by slipping in the blast furnace has established by turning stave temperature and shaft pressure data into images distributed in two dimensions. In addition, combining the two-dimensional distribution of secondarily processed data of changes in space and time with the progress of operation data enables early detection of shaft pressure fluctuations. It has been also found that there exists a relationship between the cohesive zone root position, assumed by the visualized two-dimensional image of the stave temperature change over time, and the origins of shaft pressure fluctuations. It is extracted quantity of characteristic namely an independ-ent ingredient from a two-dimensional image using an independent component analysis. It will be expected that spatial image and time series order become easy by watching a change of time series of independent ingredient. We have developed "Large scale database Online Modeling" as the practical method based on the Just-In-Time modeling concept on blast furnace operation, which has very complicated physical phenomena and strong non-linear specific characteristics. The validity of the developed modeling method has been confirmed by the study with blast furnace operation data, then the past similar operation data have been searched and the prospective operation data have been estimated very quickly and precisely.