Search

We describe a hybrid intelligent design retrieval and packaging system by utilizing techniques such as fuzzy associative memory, backpropagation neural networks, and adaptive resonance theory. As an illustrative example, a prototype of the proposed system has been developed to intelligently retrieve a design from a standard set of chair designs that can satisfy the required needs. The system then automatically passes the design to an intelligent packaging system which locates the parts needed from a designated area and packages the parts in the packaging area. This novel application of neural networks could establish the basic foundation of a true intelligent manufacturing system. [ABSTRACT FROM AUTHOR]

This article presents a self-adaptive, wasp-based control model for real-time part routing in a flexible manufacturing system (FMS). Inspired from the natural system of a wasp colony, the proposed control model is a multi-agent system that exhibits adaptive behaviour. It uses simple rules built on a decentralized architecture and hence it overcomes the drawbacks of traditional agent-based systems, such as long negotiation times among agents. The production problem, which has been previously studied in the literature, includes real-time routing of parts with the objective of minimizing average waiting times and average cycle times in a large FMS that consists of 40 machines. The proposed wasp-based control model is benchmarked via simulation under various experimental conditions against those previously published studies. The simulation study shows that it outperforms the previously reported studies when the production system is heavily loaded and prone to congestion. The self-adaptive nature of the proposed model makes it robust in the presence of such dynamic, unexpected changes occurring in the FMS. [ABSTRACT FROM AUTHOR]