Abstract
In this paper the case is presented that designers require different viewpoints from past designs and abstractions in order to facilitate the effective utilisation of past design knowledge. It highlights the need for a dynamic design tool capable of automating the rationalisation of past designs to suit a designer's particular needs. The rationalisation of past designs is motivated by the belief that, within the abundant explicit information of individual past designs, there exists a wealth of implicit knowledge which should be made explicitly available to the designer. Current approaches to utilising past design knowledge do not support the automatic generation of customised design perspectives. This is partly realised in this paper by the application of a clustering approach to rationalise past design examples into abstract groups. The results of this approach are compared with that of a case study and the paper concludes with a discussion on the utilisation of rationalisation in design.
Original language | English |
---|---|
Pages (from-to) | 183-199 |
Number of pages | 16 |
Journal | Artificial Intelligence in Engineering |
Volume | 8 |
Issue number | 3 |
DOIs | |
Publication status | Published - 1993 |
Keywords
- past design utilisation
- customised perspectives
- group rationalisation
- machine learning
- dynamic design tool