DYNAMIC GROUPING OF PARTS IN FLEXIBLE MANUFACTURING SYSTEMS - A SELF-ORGANIZING NEURAL NETWORKS APPROACH

Artificial Intelligence (AI) has recently been recognized as a worthwh ile tool for supporting manufacturing operations. This paper reviews A I-related approaches to Group Technology (GT) and presents the Self-Or ganizing Map (SOM) network, a special type of neural networks, as an i ntelligent tool for grouping parts and machines. SOM can learn from co mplex, multi-dimensional data and transform them into visually deciphe rable clusters. What sets this technique apart from others in GT is th at SOM offers the flexibility of choosing from multiple grouping alter natives. SOM can be used in a dynamic situation where quick response t o changes in part designs, process plans, or manufacturing conditions is essential, and thus it can be more easily integrated into a Flexibl e Manufacturing System. The paper proposes a framework of an intellige nt system that integrates the neural networks approach and a knowledge -based system to provide decision supporting functions.