Search Sites

Tetsu-to-Hagané Vol. 97 (2011), No. 6

ISIJ International
belloff

Grid List Abstracts

ONLINE ISSN: 1883-2954
PRINT ISSN: 0021-1575
Publisher: The Iron and Steel Institute of Japan

Backnumber

  1. Vol. 110 (2024)

  2. Vol. 109 (2023)

  3. Vol. 108 (2022)

  4. Vol. 107 (2021)

  5. Vol. 106 (2020)

  6. Vol. 105 (2019)

  7. Vol. 104 (2018)

  8. Vol. 103 (2017)

  9. Vol. 102 (2016)

  10. Vol. 101 (2015)

  11. Vol. 100 (2014)

  12. Vol. 99 (2013)

  13. Vol. 98 (2012)

  14. Vol. 97 (2011)

  15. Vol. 96 (2010)

  16. Vol. 95 (2009)

  17. Vol. 94 (2008)

  18. Vol. 93 (2007)

  19. Vol. 92 (2006)

  20. Vol. 91 (2005)

  21. Vol. 90 (2004)

  22. Vol. 89 (2003)

  23. Vol. 88 (2002)

  24. Vol. 87 (2001)

  25. Vol. 86 (2000)

  26. Vol. 85 (1999)

  27. Vol. 84 (1998)

  28. Vol. 83 (1997)

  29. Vol. 82 (1996)

  30. Vol. 81 (1995)

  31. Vol. 80 (1994)

  32. Vol. 79 (1993)

  33. Vol. 78 (1992)

  34. Vol. 77 (1991)

  35. Vol. 76 (1990)

  36. Vol. 75 (1989)

  37. Vol. 74 (1988)

  38. Vol. 73 (1987)

  39. Vol. 72 (1986)

  40. Vol. 71 (1985)

  41. Vol. 70 (1984)

  42. Vol. 69 (1983)

  43. Vol. 68 (1982)

  44. Vol. 67 (1981)

  45. Vol. 66 (1980)

  46. Vol. 65 (1979)

  47. Vol. 64 (1978)

  48. Vol. 63 (1977)

  49. Vol. 62 (1976)

  50. Vol. 61 (1975)

  51. Vol. 60 (1974)

  52. Vol. 59 (1973)

  53. Vol. 58 (1972)

  54. Vol. 57 (1971)

  55. Vol. 56 (1970)

  56. Vol. 55 (1969)

  57. Vol. 54 (1968)

  58. Vol. 53 (1967)

  59. Vol. 52 (1966)

  60. Vol. 51 (1965)

  61. Vol. 50 (1964)

  62. Vol. 49 (1963)

  63. Vol. 48 (1962)

  64. Vol. 47 (1961)

  65. Vol. 46 (1960)

  66. Vol. 45 (1959)

  67. Vol. 44 (1958)

  68. Vol. 43 (1957)

  69. Vol. 42 (1956)

  70. Vol. 41 (1955)

Tetsu-to-Hagané Vol. 97 (2011), No. 6

Preface to the Special Issue on “Agent Technologies for Maintenance and Development of the ‘Field Force’ in Steel Plants”

Hisashi Tamaki, Hirokazu Kobayashi

pp. 315-315

Bookmark

Share it with SNS

Article Title

Preface to the Special Issue on “Agent Technologies for Maintenance and Development of the ‘Field Force’ in Steel Plants”

Field Force at Street Making Process-Scheduling

Toshiharu Iwatani

pp. 316-319

Abstract

In this report, the features of expert operators' skills in steelworks are discussed. Most of the skills cannot be substituted with a computer system and we name such skills ‘field forces’. Therefore, it can be said that Japanese steelworks have been supported by the field force. In domestic manufacturing plants, there still remain lots of operations which need field forces, for instance, machine control, fault diagnosis, plant maintenance and production scheduling operations. Here, we take a scheduling operation for an example. By describing the expert operator's tangible abilities which cannot be captured with a conventional scheduling system, we consider the essence of field forces. The outline of this report is as follows. After showing a brief introduction in Chap. 1, an example of a scheduling problem in a steel making process is presented in Chap. 2. The problem is used to describe the difference of the constraints and evaluation function between a human expert and a computer scheduler. In Chap. 3, several specific capabilities of scheduling experts are illustrated. When they deal with a scheduling problem, they always consider various viewpoints such as chronological change of plants. Moreover, some experts are able to even convert the problem drastically when a serious plant trouble happens in an upper process. In Chap. 4, we discuss the necessary system requirements for scheduling software to attain the human expert capabilities shown above and finish this report with a conclusion in Chap. 5.

Bookmark

Share it with SNS

Article Title

Field Force at Street Making Process-Scheduling

A Scenario for the Image Enhancement of Agent Technologies for Development of the “Field Force”

Hirokazu Kobayashi, Shigeto Hojo, Ken Iwamura, Kuniharu Ito

pp. 320-325

Abstract

Systematization and automation have been promoted and achieved big results for iron and steel industries in Japan. On the other hand, enough result is not achieved for the duties experienced personnel are in charge. Under such situation, a large amount of the retirement of experienced personnel is worried about. So it is one of the most pressing issues how to maintain and also to enlarge the technical predominance. As an approach to resolve this issue, agent technology-based approaches which can deal with knowledge of experienced personnel are expected.
In this work, a scenario has been written to enhance the image of agent technologies, and we discuss the functions which are needed for agent technologies.

Bookmark

Share it with SNS

Article Title

A Scenario for the Image Enhancement of Agent Technologies for Development of the “Field Force”

Methods of Diagnosis and Intervention for Agent of Hot Rolling Operation Support

Masami Konishi, Koichi Nakano, Jun Imai

pp. 326-333

Abstract

In the last two decades, it becomes possible to automate operations of various steel plants especially in rolling mills. As the results, stabilization of productivity and improvement of product quality have been attained. On the while, in these years, many skilled engineers and operators who actively promoted economical growth of steel industries will retire due to their age limits. Thus, the inheritance of the high level technology and know-how has becomes a serious problem. To overcome the problem, it is necessary to extract knowledge of the skilled persons and make technical textbook reducing tacit knowledge. In this paper, rules are extracted from the operation data of hot strip rolling applicable to the operation diagnosis and intervention during operation. To attain the object, agent based simulator of hot strip rolling has been developed to prepare various rolling data for extraction of diagnosis and intervention rules in rolling operations. As for the selection of normal and abnormal data, SVM algorithm is tested before rules extraction. Rules are written in Fuzzy logic forms and its parameters are optimized by GA algorithm. These technologies are involved in the operation support agent system of hot strip rolling mills together with RNN for automatic gain tuning of mill controller.

Bookmark

Share it with SNS

Article Title

Methods of Diagnosis and Intervention for Agent of Hot Rolling Operation Support

Acquiring Plant Operation Knowledge through Learning Classifier Systems

Takao Terano, Hasnat Elias Mohammad Abu, Mhd Irvan

pp. 334-340

Abstract

We are conducting a research and development project on agent technologies to enrich “Field Forces” in steel industries under the support of the Iron and Steel Institute of Japan. The objective of the project is to explore the applicability of recent software agent technologies to practical task domains performed by both human experts and plant systems. Under the support, this paper proposes a new method to extract plant operation knowledge from time varying plant data. The method is characterized by the use of Learning Classifier Systems (LCSs), which is one of machine learning methods with rule generation, modification by evolutionary algorithms. We have equipped plural learning components, each of which consists of XCS (eXtended Classifier System), a recent advanced version of LCSs. We have designed each XCS as a software agent with communication capabilities among the other agents and the operation environments. This paper describes the basic principles and implementation of the method, then explains how the proposed method can be applied to plant operation tasks for hot strip mills of a steel plant. In our methodological frame work, we do not use any plant specific knowledge but only rely on the plant operation data virtually generated by the simulator of hot strip mills operations developed by Konishi et al. The objective of the proposed method is, therefore, to explore the feasibility of the data oriented method with XCS agents. The proposed method is combined with the simulator of hot strip mills operation and shows the effectiveness.

Bookmark

Share it with SNS

Article Title

Acquiring Plant Operation Knowledge through Learning Classifier Systems

An Approach for Designing Expert Agent Based on Mathematical Programming Model

Hisashi Tamaki, Satoshi Sugikawa

pp. 341-346

Abstract

Due to a large amount of the retirement of experienced personnel, it is one of the most serious issues how the technical predominance of manufacturing industries, such as iron and steel industries in Japan, can be maintained. Here, from the viewpoint of problem-solving by experienced personnel, the acquisition and the utilization of some additional and essential information might be crucial. According to this observation, in the paper, a kind of scheduling problems, i.e., a scheduling problem of the flexible flow shop type with uncertainty in set-up operations, is taken as an example of the problem-solving in manufacturing industries. Then, a mathematical programming-based approach is investigated, where two kinds of optimization models are formulated: One is the model of the solution by unskillful personnel in which only the normal (or common) data is used, whereas the other is the solution model by experienced personnel in which some additional information is available. Furthermore, through some computational examples for the simplified scheduling problem of the flexible flow shop type, the potential of the experienced personnel model, i.e., the robustness of the obtained schedule for uncertain situations, has been confirmed.

Bookmark

Share it with SNS

Article Title

An Approach for Designing Expert Agent Based on Mathematical Programming Model

A Study on Machine Learning Based Modeling of Skilled Worker Agents for Production Planing Laerning Support Systems in Street Production

Itsuo Hatono, Katsutoshi Yokota, Shifumi Fukunaga

pp. 347-351

Abstract

This paper deals with machine learning based modelling of skilled worker agents for production planing learning support systems in steel production. In this paper, a try-and-error process in generating a schedule is assumed to consist of three steps: (1) select appropriate priority rules and evaluation items, (2) generate a schedule by using the priority rules, (3) evaluate of the generated schedule and revise the priority rules based on the evacuation. The scheduling generation processis modelledby using Stochastic Learning Automata, whichisakindof reinforcement learning method, to obtain thee.ective ‘know-how’ fora production planning learning support system. Asimulation experiment has been carried out in order to evaluate the model. The simulation results suggested that the know-hows obtained in the simulation experiments may be able to apply them into a production planning learning support system.

Bookmark

Share it with SNS

Article Title

A Study on Machine Learning Based Modeling of Skilled Worker Agents for Production Planing Laerning Support Systems in Street Production

A TZBM-Based Algorithm for Flow Shop Scheduling Problem Considering the Decision Maker's Preference

Tetsuo Sawaragi, He Xu, Yajie Tian, Yukio Horiguchi, Jidong Ren

pp. 352-359

Abstract

Nowadays steel manufacturing pays a critical attention to on-time delivery and inventory reduction. In our study, we propose a heuristic algorithm to solve the hybrid flow shop scheduling problem (HFSP) considering reducing total tardiness and inventory time. In order to achieve a feasible solution in limited computational time, the algorithm is based on Three-zone Buffer Management (TZBM) approach. TZBM approach combines the Drum Buffer Rope (DBR) method proposed in theory of constraints (TOC), with a contract net protocol in multi-agent system (MAS). The effectiveness of the proposed algorithm is shown by simulation results comparing with the results obtained by a Tabu search (TS) algorithm. In the production field, a shipment buffer is set between the due date and the shipping time in order to avoid possible late shipment. The size of shipment buffer is always decided according to the experience of a system operator who has responsibility to draw up a production schedule. Wherein, an operator needs to take a decision considering trade-off between on-time delivery and inventory reduction. Therefore, a new interactive decision support system is proposed which is based on the two-stage TZBM approach. The operator needs to make his/her judgment whether an optimal solution shown by the system is preferable or not, then to change the trade-off between the two conflicting objectives. The system needs to compute another optimal solution according to judgment given by the operator. Under the result of numerical experiments, to integrate the experience of operators with the computational intelligence of systems proves to be an effective scheduling method.

Bookmark

Share it with SNS

Article Title

A TZBM-Based Algorithm for Flow Shop Scheduling Problem Considering the Decision Maker's Preference

You can use this feature after you logged into the site.
Please click the button below.

Advanced Search

Article Title

Author

Abstract

Journal Title

Year

Please enter the publication date
with Christian era
(4 digits).

Please enter your search criteria.