Project/Area Number |
05452316
|
Research Category |
Grant-in-Aid for General Scientific Research (B)
|
Allocation Type | Single-year Grants |
Research Field |
資源開発工学
|
Research Institution | University of Tokyo |
Principal Investigator |
OKANO Yasuhiko (1994) University of Tokyo, Faculty of Engineering, Associate professor, 工学部, 助教授 (30011092)
井上 外志雄 (1993) 東京大学, 工学部, 教授 (80010742)
|
Co-Investigator(Kenkyū-buntansha) |
OKAYA Katsunori University of Tokyo, Faculty of Engineering, Instructor, 工学部, 助手 (80134493)
NONAKA Michio University of Tokyo, Faculty of Engineering, Instructor, 工学部, 助手 (70010981)
岡野 靖彦 東京大学, 工学部, 助教授 (30011092)
|
Project Period (FY) |
1993 – 1994
|
Project Status |
Completed (Fiscal Year 1994)
|
Budget Amount *help |
¥7,000,000 (Direct Cost: ¥7,000,000)
Fiscal Year 1994: ¥1,300,000 (Direct Cost: ¥1,300,000)
Fiscal Year 1993: ¥5,700,000 (Direct Cost: ¥5,700,000)
|
Keywords | Optimal design / Expert system / Decoupled treatment / KJ法 / AI / ファジー推論法 / 資源開発プロジェクト |
Research Abstract |
The optimization is needed for capitals, materials, human abilities and terms in planning a resources development project. In this research work an expert system has been developed to support the planning of the project. The expert system is not only having a reasoning mechanism depending on the knowledge base but also is able to parallel execute subordinate programs in order to make sure the reasoning. The subordinate programs include a various kinds of stochastic treatments, simulations by models, data base searches and subsystems in the expert system, etc. It takes a much longer treatment time in the execution than the calculation time in a conventional reasoning process. These subprograms are heavily loaded in the calculating operation and are simultaneously executed in another multiple computers connected in a network, whilst the demanded results are returned to the main program. The system is possible to be realized relatively cheaply because it is constructed by a LAN-connected personal computer working with the operation system of DOS. Expert systems, knowledge regulation methods, simulation methods using the fuzzy theory and neural networks, software languages and networks, etc.have been evaluated and discussed in this research work. A communication system to be realized for a decoupled treatment and a decoupled treatment type expert system have been successfully developed.
|