| Project/Area Number |
01850156
|
|---|
| Research Category |
Grant-in-Aid for Developmental Scientific Research
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
金属加工(含鋳造)
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
OSAKADA Kozo Osaka University, Faculty of Engineering Science, Professor, 基礎工学部, 教授 (50031109)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KATO Takasi Government Industrial Research Institute, NAGOYA, Mechanical Engineering Divisio, 機械部, 主任研究官 (90093012)
KUDO Hideaki Tokyo Denki University, Faculty of Engineering, Professor, 工学部, 教授 (90017848)
NAKAMURA Simesu Teikyo University, Faculty of Science and Engineering, Professor, 理工学部, 教授 (10029431)
SHINAGAWA Kazunari Osaka University, Faculty of Engineering Science, Research Associate, 基礎工学部, 助手 (30215983)
MORI Ken-ichro Osaka University, Faculty of Engineering Science, Associate Professor, 基礎工学部, 助教授 (80127167)
|
|---|
| Project Period (FY) |
1989 – 1991
|
| Project Status |
Completed (Fiscal Year 1991)
|
| Budget Amount *help |
¥6,100,000 (Direct Cost: ¥6,100,000)
Fiscal Year 1991: ¥700,000 (Direct Cost: ¥700,000)
Fiscal Year 1990: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 1989: ¥4,300,000 (Direct Cost: ¥4,300,000)
|
|---|
| Keywords | Forging / Process Design / Expert System / Simulation / FEM / AI / Neural Network / Fuzzy |
|---|
| Research Abstract |
An expert system has been developed to assist the cold forging engineers in planning the forming process by utilizing various innovative technologies. The primary functions of the system can be enumerated as knowledge acquisition, product registration, process generation, determination of order of evaluation, process evaluation, process visualization, and verification of metal flow of process in the order of their successive implementations in the system.
Process candidates of any given product are generated efficiently with either the variant-and-generative approach or the neural network system for process generation. The process evaluation strategy to evaluate each process according to the order of evaluation determined significantly reduces the time spent for evaluation, and the metal flow simulation carried out at the end of the process evaluation ensures only a pretty feasible process is adopted as the actual process. The combination of FEM simulation and neural networks is found effective to acquire knowledge to compensate the deficiency of the knowledge base of the system.
Although the prototype of the system has been established, there is a lot of work that needs to be accomplished in the future to complete the expert system for process planning of cold forging.
(1) At the present stage, only four forming methods are considered in the system. Other combined cold-forming methods should be taken into account.
(2) The knowledge base of the system is still not sufficient to enable quantitative evaluation of various operations. The applicability of the system should be broadened in the future.
(3) Occurrence of the internal ductile fracture and the surface crack of the product should be predicted by the evaluation system. Fatigue crack, tribology, etc. of the tool have to be considered in a system to predict tool life.
(4) Energy consumption, cost, and other economical factors should also be accounted in process selection.
|
