The use of knowledge based engineering in the mechatronic embodiment of intelligent machines and systems

Abstract

Conventional combinational design philosophies are, in many cases, proving inadequate for the sophisticated products and speed of response demanded by today's markets. Mechatronic design philosophies and concurrent practices for achieving the physical embodiment of the designers creative output are seen as an appropriate response to the challenge. Mechatronics is a holistic design philosophy which can yield intelligent machines (e.g. self-driving vehicles, robotic surgeons) for the benefit of mankind. The advent of new technologies has provided new possibilities for intelligent machines. The appropriate use of knowledge engineering has given much scope in this direction and this paper reports a number of applications across a range of industries from rock processing to food handling. It is clear that great benefit has been derived from the application of knowledge engineering and that techniques such as fuzzy logic and artificial neural networks have much to offer in complex systems where sensor data may be imprecise, where there may be a multiplicity of input data with possible conflicts or where it is not possible to generate precise algorithmic relationships or transfer functions. There is still, however, much research to be done regarding topologies of massively parallel systems, design rules for their creation, paradigms for sensor fusion and most importantly, reliability engineering and the concept of graceful degradation.