Designing and learning are closely related activities in that design as an ill-structure problem
involves identifying the problem of the design as well as finding its solutions. A
knowledge-based design support system should support learning by capturing and reusing
design knowledge. This thesis addresses two fundamental problems in computational
support to design activities: the development of an intelligent design support system
architecture and the integration of inductive learning techniques in this architecture.
This research is motivated by the belief that (1) the early stage of the design process can
be modelled as an incremental learning process in which the structure of a design problem
or the product data model of an artefact is developed using inductive learning techniques,
and (2) the capability of a knowledge-based design support system can be enhanced by
accumulating and storing reusable design product and process information.
In order to incorporate inductive learning techniques into a knowledge-based design
model and an integrated knowledge-based design support system architecture, the
computational techniques for developing a knowledge-based design support system
architecture and the role of inductive learning in Al-based design are investigated. This
investigation gives a background to the development of an incremental learning model for
design suitable for a class of design tasks whose structures are not well known initially.
This incremental learning model for design is used as a basis to develop a knowledge-based
design support system architecture that can be used as a kernel for knowledge-based
design applications. This architecture integrates a number of computational techniques to
support the representation and reasoning of design knowledge. In particular, it integrates a
blackboard control system with an assumption-based truth maintenance system in an
object-oriented environment to support the exploration of multiple design solutions by
supporting the exploration and management of design contexts.
As an integral part of this knowledge-based design support architecture, a design
concept learning system utilising a number of unsupervised inductive learning techniques is
developed. This design concept learning system combines concept formation techniques
with design heuristics as background knowledge to build a design concept tree from raw
data or past design examples. The design concept tree is used as a conceptual structure for
the exploration of new designs.
The effectiveness of this knowledge-based design support architecture and the design
concept learning system is demonstrated through a realistic design domain, the design of
small-molecule drugs one of the key tasks of which is to identify a pharmacophore
description (the structure of a design problem) from known molecule examples.
In this thesis, knowledge-based design and inductive learning techniques are first
reviewed. Based on this review, an incremental learning model and an integrated
architecture for intelligent design support are presented. The implementation of this
architecture and a design concept learning system is then described. The application of the
architecture and the design concept learning system in the domain of small-molecule drug
design is then discussed. The evaluation of the architecture and the design concept learning
system within and beyond this particular domain, and future research directions are finally