論文検索サイト

ISIJ International Vol. 30 (1990), No. 2

ISIJ International
belloff

Grid List Abstracts

オンライン版ISSN: 1347-5460
冊子版ISSN: 0915-1559
発行機関: The Iron and Steel Institute of Japan

Backnumber

  1. Vol. 64 (2024)

  2. Vol. 63 (2023)

  3. Vol. 62 (2022)

  4. Vol. 61 (2021)

  5. Vol. 60 (2020)

  6. Vol. 59 (2019)

  7. Vol. 58 (2018)

  8. Vol. 57 (2017)

  9. Vol. 56 (2016)

  10. Vol. 55 (2015)

  11. Vol. 54 (2014)

  12. Vol. 53 (2013)

  13. Vol. 52 (2012)

  14. Vol. 51 (2011)

  15. Vol. 50 (2010)

  16. Vol. 49 (2009)

  17. Vol. 48 (2008)

  18. Vol. 47 (2007)

  19. Vol. 46 (2006)

  20. Vol. 45 (2005)

  21. Vol. 44 (2004)

  22. Vol. 43 (2003)

  23. Vol. 42 (2002)

  24. Vol. 41 (2001)

  25. Vol. 40 (2000)

  26. Vol. 39 (1999)

  27. Vol. 38 (1998)

  28. Vol. 37 (1997)

  29. Vol. 36 (1996)

  30. Vol. 35 (1995)

  31. Vol. 34 (1994)

  32. Vol. 33 (1993)

  33. Vol. 32 (1992)

  34. Vol. 31 (1991)

  35. Vol. 30 (1990)

  36. Vol. 29 (1989)

ISIJ International Vol. 30 (1990), No. 2

Artificial Intelligence in Materials Processing Operations: A Review and Future Directions

Stavros A. Argyropoulos

pp. 83-89

抄録

The evolution of Artificial Intelligence from its early days to the present is reviewed, the various concepts currently utilized are defined, and the software and hardware tools in existence surveyed. The strides that have been made in recent years in applying expert systems to numerous engineering problems, and most notably in the area of Materials Processing Operations, are reviewed. The rate of new applications of Artificial Intelligence to engineering problems is constantly increasing, as it becomes more feasible to build on earlier theoretical research. Ultimately, we can expect that Artificial Intelligence will be applied in all areas of human endeavor, as its benefits in terms of cost/effectiveness becomes more apparent. For the near future, however, one's expectations need to be more circumspect. Areas in Materials Processing Operations that are most promising for expansion into Al in the near future are considered.

他の人はこちらも検索

ブックマーク

SNSによる共有

論文タイトル

Rapid Prototyping Tools for Real-time Expert Systems in the Steel Industry

L. G. Lock Lee, A. R. McNamara, K. C. Teh, H. M. Lie, B. J. Orenstein, D. J. H. Brown

pp. 90-97

抄録

The application of artificial intelligence (AI) and expert systems techniques to process management tasks within the Iron and Steel Industry is now gaining wide acceptance. This paper describes the development and application of software tools which have been successful in significantly reducing the time required to produce real-time expert system prototypes.
BHP's SHERPA (System for HEuristic Real-time Process Assistance) is a facility which integrates modules for knowledge base development, signal processing, operator displays, on-line numerical models and data base storage. TABLEAUX, is a decision table based knowledge acquisition tool which can be used in combination with SHERPA for developing real-time expert system applications. Three examples of prototypes being developed for sinter plants, blast furnaces and continuous casters, using SHERPA, are described.
The use of the SHERPA and TABLEAUX facilities has enabled real-time expert system prototypes to be built over periods of weeks. In a number of cases the resultant prototype has shown sufficient functionality to attract requests for immediate implementation as production systems.

他の人はこちらも検索

ブックマーク

SNSによる共有

論文タイトル

An AI Tool and Its Applications to Diagnosis Problems

Hiroshi Narazaki, Toshiharu Iwatani, Kayako Omura, Yoshihisa Otsuka, Masami Konishi

pp. 98-104

抄録

An expert system shell is developed for a personal computer using C language. It is designed for diagnosis problems such as fault diagnosis and process operation guidance. The tool is suitable for the knowledge that is represented in the form of the hierarchical tree and causal relationship matrix. Further by using the tool it is easy to build expert systems which cooperatively work with the existing software by passing or receiving data, and which evokes or is evoked by external programs. Therefore the tool is appropriate to construct on-line expert systems. Application examples are shown to prove the usefulness of the tool.

他の人はこちらも検索

ブックマーク

SNSによる共有

論文タイトル

Expert System for Blast Furnace Operation at Kimitsu Works

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

pp. 105-110

抄録

The experience and knowledge of operators are important for operation control of blast furnaces. A knowledge engineering or expert system that can represent this empirical knowledge was practically applied to Nos. 3 and 4 blast furnaces at Kimitsu Works, Nippon Steel Corp. In the development of the knowledge base for the expert system, the knowledge of the most experienced operators was represented by a hypothetical inference method composed of the sensor information judgement, interim judgement, final judgement and action stages. The expert system was implemented with emphasis placed on its maintainability by operators. Among the measures taken to this end are the adoption of a Japanese production language, augmentation of indication of inferred result, and installation of off-line terminals for modifying and test running the knowledge base. As a result of these efforts, the expert system can be largely operated and controlled by the field personnel. Since the expert system was brought on-line, periodic study meetings have been evaluating its performance and updating the knowledge base. The expert system is utilized in the actual operation control of the two blast furnaces at a high rate and the blast furnaces are stably operated.

ブックマーク

SNSによる共有

論文タイトル

Application of a Self-learning Function to an Expert System for Blast Furnace Heat Control

Yasuo Niwa, Takashi Sumigama, Masaaki Sakurai, Taichi Aoki

pp. 111-117

抄録

A self-learning function, in which the statistical methods and production rules were effectively combined, was applied to an expert system for blast furnace heat control to improve controllability of temperature and chemical composition of hot metal and to improve mentenance of the system.
This self-learning function consists of a short term self-learning function and a long term self-learning function. The former has been in operation since the expert system for blast furnace heat control, which was named BAISYS, was started and the latter has been utilized since March, 1988.
In the short term self-learning function, the reference values of sensor data, hot metal temperature differences among tapholes and rising patterns of hot metal temperature in the casting are periodically judged and automatically processed.
In the long term self-learning function, the guidance to modify the three-dimensional membership functions and the weight coefficients of all sensors is performed. Through the test application of the self-learning function, the followings were confirmed.
(1) Guidance by the self-learning function is very effective for the evaluation of weight coefficients of various sensors.
(2) The three-dimensional membership functions for all sensor data, which are made by self-learning function, are applicable.
(3) The standard deviations of hot metal temperature and silicon content in hot metal have been decreased and the application ratio of the expert system has been kept at high level by the introduction of the self-learning function.

ブックマーク

SNSによる共有

論文タイトル

A Hybrid Expert System Combined with a Mathematical Model for Blast Furnace Operation

Koichi Otsuka, Yoshiyuki Matoba, Yoshimasa Kajiwara, Masateru Kojima, Masaaki Yoshida

pp. 118-127

抄録

For the establishment of completely automatic and most intelligent control system, a hybrid expert system composed of both a mathematical model (the TS model) and experiential rules was developed as the application of artificial intelligence.
The selection of control method either by the TS model or by experiential rules is appropriately performed by furnace state judgment rules which are actually experiential rules.
In the normal furnace state, the control by the TS model is performed to minimize hot metal temperature for the reduction of energy cost. In the abnormal furnace state, the control by experiential rules is performed to achieve stable furnace operation for the prevention of significant reduction of hot metal production.
Further, diagnosis rules are provided in the system to determine the cause of abnormality and to select necessary actions for the long term control. The necessary actions indicated by diagnosis rules are performed manually through the final decision of operators or staffs.
The system was introduced into Kashima No. 1 blast furnace of Sumitomo Metal Industries, Ltd. in October of 1988. The hybrid expert system is successfully applied in actual short term control. The establishment of the complete diagnosis rule for long term control is one of the main future tasks of the system.

ブックマーク

SNSによる共有

論文タイトル

An Application of Expert System to LD Converter Processes

Michitaka Kanemoto, Hiroshi Yamane, Tooru Yoshida, Hideo Tottori

pp. 128-135

抄録

Superior blowing control system is required for stable operation and saving manpower in LD converter process. To investigate the possibility of future advances in blowing control system, a prototype expert system for blowing control has been developed.
This system is successful in applying the expert system to on-line real-time process control and applying the fuzzy reasoning to represent the ill-structured problem. As a test result, the high blowing controllability like a skilled operator has been achieved to prove the effectiveness of application of knowledge engineering to the blowing control.

他の人はこちらも検索

ブックマーク

SNSによる共有

論文タイトル

Real-time Expert System Applied to Mold Bath Level Control of Continuous Caster

Yukihiro Sasabe, Sadao Kubota, Asayoshi Koyama, Hirotaka Miki

pp. 136-141

抄録

Fluctuation of the mold bath level of continuous caster greatly influences the surface quality of cast slabs or billets. It is difficult to maintain an optimal bath level by a PID controller and a slide gate vibration controller with fixed parameters, because the characteristics of casting condition fluctuate during operation. To solve this problem, an expert system method has been applied to the mold bath level control system. In this expert system operator know-how regarding control parameter adjustment is represented in the form of a knowledge base, and that knowledge base is driven by inference engine when a significant fluctuation of the mold bath level occurs. This system has been applied to a continuous round caster, and has effectively regulated the mold bath level fluctuation by adjusting the controlling parameters to optimize the state of operation when the fluctuation occurred.

ブックマーク

SNSによる共有

論文タイトル

Computer Aided Simulation of Universal Rolling Processes

Manabu Kiuchi, Jun Yanagimoto

pp. 142-149

抄録

An advanced computer aided simulation technique for three-dimensional rolling processes, named complex element method (CEM), has been developed. It is based on functional combination of the rigid-plastic FEM and the slab method. It has capability to analyze various rolling processes very effectively and economically and calculate strain, stress and contact pressure distributions, rolling load, rolling torque and dimension of rolled product.
In this paper, firstly, mathematical formulation of the extended CEM is explained, where non-uniformity of longitudinal velocity distribution on every cross section of workpiece is taken into consideration. Then it is applied to the universal rolling processes of H-beams. Calculated results on rolling load, rolling torque, induced back tension and compression, strain distribution in workpiece and geometry of rolled product are found reasonable and acceptable. It is concluded that the extended CEM can be an effective tool for the design and diagnosis of roll profiles and pass-schedules.

ブックマーク

SNSによる共有

論文タイトル

Expert System for Determining Welding Condition for a Pressure Vessel

Shuichi Fukuda, Hideki Morita, Yoshihisa Yamauchi, Isao Nagasawa, Shuichi Tsuji

pp. 150-154

抄録

This paper describes the outline of the expert system for producing a Welding Procedure Specification for a pressure vessel which was developed with the grant from the Ministry of International Trade and Industry for Nagasaki Prefecture. What is stressed in this paper is that as welding calls for a broad range and wide variety of knowledge from many different engineering fields, it is very difficult to get familiar with each chunk of different kinds of knowledge and that it is no exaggeration to say that it is more important how to manipulate these different kinds of knowledge. Object oriented programing environment provides a really workable basis for developing a welding expert system because we can construct a meta rule system without any detailed knowledge about the content of each particular rule. Thus we may be able to construct a system which permits a very flexible reasoning that corresponds to the actual trial and error way of decision making of welding engineers.

ブックマーク

SNSによる共有

論文タイトル

An Expert System of Automatic Slab Assignment for Hot Strip Mill

Yoshihiro Jimichi, Akihiro Hori, Hiroshi Ishihara, Tsuyoshi Odaira

pp. 155-160

抄録

A fully automatic assignment system of slabs for hot strip mill has been developed by using an expert system building tool SMI/Marks-II. This tool is an original software by Sumitomo Metals and has some types of linkage function. The linkage functions are very useful to develop a hybrid computer system, where ordinary language systems and an expert system can cooperate effectively. The automatic slab assignment system is installed in a mainframe IBM 3090, as an alternative to the conventional system which consists of the ordinary language system and the manual assignment job by an expert. Selection or assignment of stocked slabs for the products orders can be performed automatically. As the result of evaluation, this system has the following capabilities.
(1) The number of assigned pairs is almost equal to that by the expert.
(2) Assignments of slabs with excessive upper grades can be eliminated.
(3) Job time is reduced from 6 to 1 h.
This expert system can be easily maintained for environmental changes. The development period is reduced by the prototyping method.

他の人はこちらも検索

ブックマーク

SNSによる共有

論文タイトル

Fully Automated Bar Mill Pacing Control System Incorporating Artificial Intelligence

Shinji Sasaka, Yoshimitsu Kozaki, Yuji Chida, Takayuki Kotake, Fumio Fukuda, Tomoichi Satoh

pp. 161-166

抄録

The fully automated mill pacing control system in the bar mill at Muroran Works of Nippon Steel Corporation is a control type expert system developed to determine and to control automatically the material discharge pitch from the reheating furnace. The material discharge pitch is a dominating factor affecting productivity and operating efficiency. Until now, it has been difficult to establish a mathematical model for determining the optimal discharge pitch because of the following:
1) complex material flow caused by variations in processing and production capacity, and
2) variations in flow due to differences in material quality and size of the steel bar being produced.
The fully automated discharge system was realized by developing an expert system based on the most suitable inference of productivity in each process of steel bar flow. The production capacity of mill and finishing line is determined from a knowledge base. How the expert system achieves on-line and real-time control and how the mill pacing control is performed are described in this paper. The fully automated mill pacing control expert system for the bar mill at Muroran Works achieved following production improvements:
1) Improvement in rolling tons per hour due to minimization of discharge pitch, and
2) Improvement in production efficiency by avoiding discharge interruption caused by line jam.

他の人はこちらも検索

ブックマーク

SNSによる共有

論文タイトル

An Expert System for Efficient Coil Transfer in Finishing Line of Hot Strip Mill

Fumiki Hirao, Kazuki Takenaka, Takashi Kuribayashi, Mitsuji Hosoda

pp. 167-172

抄録

Coils of hot rolled steel are transferred by conveyors, cranes or coil cars in the finishing lines. An expert system has been developed for efficient transfer of coils and is now in real time operation as a part of the finishing control system. The expert system has two main functions; selection of a coil to be transferred and a point of loading or unloading of the coil to a coil car in a looped track. This expert system consists of 309 rules and the rules for selecting a coil occupy the main part. The expert system was successfully developed within 10 months.

ブックマーク

SNSによる共有

論文タイトル

An Expert System for Quality Diagnosis of Glass Films on Silicon Steels

Harutoshi Ogai, Takatugu Ueyama, Hiroshi Sato, Yoichi Mishima, Shinichi Itonaga

pp. 173-181

抄録

Knowledge acquisition and modification methods are described for building a quality diagnosis expert system. Knowledge of a quality diagnosis expert is represented in a tabular form. The final quality properties are predicted from the operating conditions of the intermediate process and are compared with the target values. A pattern of deviations of the final quality properties from the target values is summarized in a table.
A data file in the form of knowledge table is created or revised by an editor in an actual quality diagnosis system, and a knowledge base in an if-then format is created by a knowledge generation program.
The practical application of this procedure and the architecture and human interface of a silicon steel glass film quality diagnosis expert system are described.

ブックマーク

SNSによる共有

論文タイトル

この機能はログイン後に利用できます。
下のボタンをクリックしてください。

詳細検索

論文タイトル

著者

抄録

ジャーナル名

出版日を西暦で入力してください(4桁の数字)。

検索したいキーワードを入力して下さい