AN IMPROVED NEURAL-NETWORK LEADER ALGORITHM FOR PART-MACHINE GROUPINGIN-GROUP TECHNOLOGY

In this paper, a robust neural network-based leader algorithm is propo sed for the part-machine grouping problem in group technology. This cl ustering method involves a modification to the normal use of Carpenter and Grossberg's ART1 neural network. The robustness of the modified a lgorithm to random ordering of the input data is tested using three da ta sets. The data sets include an industry-size problem consisting of 10000 parts and 100 machine types. The experiments revealed that the m ethod results in the identification of clusters and block diagonal str uctures rapidly and to a good degree of perfection, even for large, in dustry-size data sets. The solutions obtained were also found to be ro bust to the order of presentation of the input data. The proposed meth od offers a promising solution to a cellular manufacturing problem tha t is yet to be solved satisfactorily.