Artificial neural network-based approach for design of parts for cellular manufacturing

An artificial neural network approach is applied to the problem of integrating design and manufacturing engineering. The self organising map neural network recognises products and parts which are modelled as boundary representation solids using a modified face complexity code scheme adopted, and forms the necessary feature families. Based on the part-features, machines, tools and fixtures are selected. These information are then fed into a four layer feed-forward neural network that provides a designer with the desired features that meet the current manufacturing constraints for design of a new product or part. The proposed methodology does not involve training of the neural networks used and is seen to be a significant potential for application in concurrent engineering where design and manufacturing are integrated. The main advantages of the neural network approach over the rule-based systems are high recognition speed, ease of computation, minimal memory storage, and ability to recognise partial and complex features encountered in design.