Expert system for blast furnace operation at Kimitsu works.

Amano, Shigeru; Takarabe, Tsuyoshi; Nakamori, Takashi; Oda, Hiroshi; Taira, Masamichi; Watanabe, Satoshi; Seki, Takatoshi

doi:10.2355/isijinternational.30.105

Cited by 26 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This system was configured of two subsystems, a furnace fault state diagnostic system and a furnace control expert system. The blast furnace operation control system ALIS 170) at Nippon Steel Kimitsu No. 4 blast furnace was also based on an expert system which used knowledge engineering, and during the 2003 revamp, incorporated distributed processing, web technologies, and visualization technologies.…”

Section: Artificial Intelligence (Ai) and Other Operationmentioning

confidence: 99%

Ironmaking Technology for the Last 100 Years: Deployment to Advanced Technologies from Introduction of Technological Know-how, and Evolution to Next-generation Process

Naito

Takeda²,

Matsui³

2015

ISIJ International

106

View full text Add to dashboard Cite

The 150 year history of the Japanese steel industry dates from the first western blast furnace, which was built by T. Ohashi in 1857. Modern blast furnace operation at integrated steel works in Japan started in 1901 with the first blow-in of Higashida No. 1 blast furnace at Yawata Steel Works. Throughout the prewar and postwar periods, the steel industry has supported the Japanese economy as a key industry which supplies basic materials for social infrastructure and development.After the period of recovery following the destruction caused by World War II, Chiba Works of Kawasaki Steel Corporation (now JFE Steel Corporation) was built and began operation in 1953 as the first integrated steel works in the Keiyo Industrial Region after the war. During Japan's period of high economic growth, many coastal steel works with large blast furnaces having inner volumes of more than 3 000 m 3 and even 5 000 m 3 were built to enable efficient marine transportation of raw materials and steel products. Japanese steel makers introduced and improved the most advanced technologies of the day, which included high pressure equipment, stave cooler systems, bell-less charging systems, etc. As a result, Japanese steel works now lead the world in low reducing agent rate (RAR) operation, energy saving, and long service life of blast furnaces and coke ovens.Following the Oil Crises of the 1970s, the Japanese steel industry changed energy sources from oil to coal and implemented cost-oriented operation design and technology. In 2012, the Japanese steel industry produced approximately 80 million tons of hot metal from 27 blast furnaces, including large-scale furnaces with inner volumes over 5 000 m 3 . During this period, the industry has faced many economic and social challenges, such as the high exchange rate of the yen, oligopoly in the mining industry, global warming, and the surge in iron ore and coal prices driven by the rapid growth of the BRICs. The industry has successfully responded to these challenges and maintained its international competitiveness by developing advanced technologies for pulverized coal injection, expanded use of low cost iron resources, recycling for environmental preservation, and CO2 mitigation.In this paper, the prospects for ironmaking technologies in the coming decades are described by reviewing published papers and looking back on the history of developments in ironmaking during the last 100 years.

show abstract

Section: Artificial Intelligence (Ai) and Other Operationmentioning

confidence: 99%

Ironmaking Technology for the Last 100 Years: Deployment to Advanced Technologies from Introduction of Technological Know-how, and Evolution to Next-generation Process

Naito

Takeda²,

Matsui³

2015

ISIJ International

106

View full text Add to dashboard Cite

show abstract

“…[5][6][7][8] However, the requirements of comprehensive rules and sufficient historical information about abnormalities, which are not always available, limit the application of these systems in many factories.…”

Section: Introductionmentioning

confidence: 99%

“…For Blast Furnace No. 5 at the Liuzhou Iron & Steel Co., Ltd., only historical data for three abnormalities were collected. Motivated by a study on predictive maintenance, 25) which fused the historical data of different aircraft engines all over the world to address the difficulty of insufficient historical faulty data for each engine, we fuse the historical data of three blast furnaces at the Liuzhou Iron & Steel Co., Ltd. to offer a more complete historical dataset for fault classification, which may cover more abnormality types and operating points than the historical data of each single blast furnace.…”

Section: Introductionmentioning

confidence: 99%

PCA-LMNN-Based Fault Diagnosis Method for Ironmaking Processes with Insufficient Faulty Data

Zhang

Hai-feng³

et al. 2016

ISIJ Int.

View full text Add to dashboard Cite

Fault detection and fault classification are important in the modern ironmaking process. Some studies based on principal component analysis (PCA) techniques have been performed for fault detection in the ironmaking process. However, studies on fault classification in the ironmaking process remain limited. In this paper, problems that are related to the classification of abnormalities in blast furnaces are considered. We fuse historical abnormal data that were collected from three real blast furnaces to address the problem of insufficient historical faulty data. To extract common features for the same type of abnormalities, which are not affected by different operation points or different blast furnaces, we propose the use of a contribution vector as a fault feature, which is calculated by the PCA-based technique. The large marginal nearest neighbor (LMNN) technique is employed to train a classifier with contribution vectors as inputs. Twentyone historical abnormalities in three different real blast furnaces are employed to validate the proposed method. The results indicate that this method achieves the desired performance.

show abstract

“…4,5) Moreover, the computer also developed, and the expert model by which the artificial intelligence was used was developed aggressively in the 1980's. [6][7][8][9] In addition, the predictive model by the neural network was developed as another use of the artificial intelligence. 10,11) Each model has strengths and limitations.…”

Section: Introductionmentioning

confidence: 99%

Application of Improved Local Models of Large Scale Database-based Online Modeling to Prediction of Molten Iron Temperature of Blast Furnace

et al. 2010

View full text Add to dashboard Cite

Expert system for blast furnace operation at Kimitsu works.

Cited by 26 publications

References 0 publications

Ironmaking Technology for the Last 100 Years: Deployment to Advanced Technologies from Introduction of Technological Know-how, and Evolution to Next-generation Process

Ironmaking Technology for the Last 100 Years: Deployment to Advanced Technologies from Introduction of Technological Know-how, and Evolution to Next-generation Process

PCA-LMNN-Based Fault Diagnosis Method for Ironmaking Processes with Insufficient Faulty Data

Application of Improved Local Models of Large Scale Database-based Online Modeling to Prediction of Molten Iron Temperature of Blast Furnace

Contact Info

Product

Resources

About