A process oriented approach to an intelligent design aid

Abstract

The paper reports an approach to intelligent design aiding which differs radically from both conventional CAD systems and also from expert system approaches which aim to automate features of the design process. Current electronic tools are scarcely more than draughting aids and provide little or no support for the cognitive processes involved in the task of design. Conventional knowledge engineering involves attempts to elicit the content of a human expert's knowledge but makes little attempt to understand the psychological processes involved. By contrast, the present system is designed to work with engineers, helping them to optimise their thinking in the early, high-level stages of design. This requires knowledge of the cognitive processes of design which can only be achieved by systematic psychological studies. We report on a multi-disciplinary project involving experimental psychologists, computer scientists and electronic engineers jointly engaged in the development of a prototype design aid (PEDA) to assist in the early stages of design. The analysis of data obtainedfrom two psychological studies, one using undergraduate designers and another based on a controlled laboratory study in which expert design engineers were engaged on specific design tasks, have been used to accurately model the design process. The model has strongly influenced the construction of the design aid both in its funtionality and in the specification of the user interface. A designer is able to interact with the tool via a direct manipulation interface which offers a drawing board metaphor. Any part of the evolving hierarchical design representation can be accessed and it supports a range of funtionality from user specified mathematical function to individual electronic components. Multiple versions of all or part of the design are maintained by the system and a history of the design steps and decisions establishes a model of the designers' use of the tool. The initial system has been implemented using some of the facilities provided by the Automatic Reasoning Tool (ART) from Inference Corporation within an object-oriented framework. The limitations of these tools are addressed and the future direction of the work discussed.