Generalized part family formation using neural network techniques

Abstract

The spontaneous generalization capability of neural network models has been exploited for solving the part family formation problem. Our approach combines the useful capacities of the neural network technique with the flexibility of the similarity coefficient method. Notably, the constraint satisfaction model of neural networks is adopted. In generalized part family formation, several practical factors such as sequence of operations, lot size, and multiple process plans are also considered. Our approach proves to be highly flexible in satisfying various requirements and efficient for integration with other manufacturing functions.