人工知能
Online ISSN : 2435-8614
Print ISSN : 2188-2266
人工知能学会誌(1986~2013, Print ISSN:0912-8085)
製造を考慮した対話型設計支援システム : エア駆動型ボンプ設計への適用
西岡 靖之中須賀 真一堀 浩一
著者情報
解説誌・一般情報誌 フリー

1998 年 13 巻 2 号 p. 300-311

詳細
抄録

This paper applies a concurrent problem solving (CPS) framework to a practical design of a mechanical pump: CPS is a new concept in which both spatial and temporal structures are dealt with in ill-defined problems. The system named PICCSS is developed on the framework, and used in this research to investigate applicability to a practical design. The objective of this paper is to evaluate the CPS framework by demonstrating an industrial application. The system consists of calculation modules, graphical user-interfaces and knowledge-base. In this system, every kind of knowledge is represented by primitives and their connections. Primitives are ontology which defines the problem domain as basic vocabulary in the system. Therefore, the system has to have domain-specific information of design and manufacturing as primitives in advance. Consequently, this paper, firstt, illustrates primitives of mechanical design knowledge. A product model and a production model can correspond to a spatial structure of primitives and a temporal structure of primitives respectively. Connections between these two structures are established according to templates which represent reusable patterns in the past. Secondly, this paper demonstrates an application of the system to an aired bump design. Using the proposed system, a designer solves his design problem in the computer interactively. The system supports the designer clarifying the problem itself and verifying it in terms of consistency of constraints and causality. After that, the system provides visualized charts such as product drafts and production plans. This paper concludes that the proposed system and the CPS framework are quite appropriate in supporting designers. Furthermore, it can be expected that decrease of a span of product development, elimination of human error in the design, and effective management of design and manufacturing knowledge are achieved.

著者関連情報
© 1998 人工知能学会
前の記事 次の記事
feedback
Top