Integration of a knowledge-based system, artificial neural networks and multimedia for gear design

Design is a complicated area consisting of a combination of rules, technical information and personal judgement. The quality of design depends highly on the designer's knowledge and experience. This system attempts to simulate the design process and to capture design expertise by combining artificial neural networks (ANNs) and knowledge-based system (KBS) together with multimedia (MM). It has been applied to the design of gears. Within the system, the KBS handles clearly defined design knowledge, the ANNs capture knowledge which is difficult to quantify and MM provides a user-friendly interface prompting the user to input information and to retrieve results during design process. The finished system illustrates how features of different artificial intelligence techniques, KBS, ANNs and MM, are combined in a hybrid manner to conduct complicated design tasks. (C) 2000 Elsevier Science B.V. All rights reserved.