| Project/Area Number |
01460105
|
|---|
| Research Category |
Grant-in-Aid for General Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
機械工作
|
|---|
| Research Institution | Keio University, Faculty of Science and Technology |
|---|
Principal Investigator |
INASAKI Ichiro KEIO University, Faculty of Science and Technology, Professor, 理工学部, 教授 (30051650)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
AOYAMA Tojiro KEIO University, Faculty of Science and Technology, Associate Professor, 理工学部, 助教授 (70129302)
|
|---|
| Project Period (FY) |
1989 – 1990
|
| Project Status |
Completed (Fiscal Year 1990)
|
| Budget Amount *help |
¥6,500,000 (Direct Cost: ¥6,500,000)
Fiscal Year 1990: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 1989: ¥5,400,000 (Direct Cost: ¥5,400,000)
|
|---|
| Keywords | Grinding / Expert system / Grinding wheel / Grinding conditions / Frame systems / Production system / Fuzzy theory / 加工条件 / 異常診断 |
|---|
| Research Abstract |
This research report has presented an architecture and basic strategy for grinding expert system. We have suggested an effective mechanism for knowledge-base based on fuzzy set theory. This system can handle vague and uncertain knowledge, and presents a scheme for integrating data with various kinds
of grinding knowledge knowledge-base. The knowledge-base establishes the three parts so as to functionally cope with various knowledge. The developed system performed in using the KBMS and engineering work station (Apollo DN4000).
1. The hybrid model based on frames and production rules is utilized to represent domain specific knowledge such as experiences and intuitions. Also, a default theory and fuzzy logic based on fuzzy set theory are adopted to utilize the vague grinding knowledge.
2. The developed system is composed of inter face, inference engine, grinding knowledge-base, actual grinding operation database, grinding trouble knowledge-base management system, and several temporary frames.
3. The procedures which are necessary to determine the grinding conditions are separated into modules which are accumulated to the grinding knowledge-base. The grinding data are used to calculate coefficient factors of experimental equations stored in the grinding actual operation database.
|
