A Kohonen self-organizing map approach to addressing a multiple objective, mixed-model just in time sequencing system

A Kohonen self-organizing map approach to addressing a multiple objective, mixed-model just in time sequencing system

0.00 Avg rating0 Votes
Article ID: iaor2002178
Country: Netherlands
Volume: 72
Issue: 1
Start Page Number: 59
End Page Number: 71
Publication Date: Jan 2001
Journal: International Journal of Production Economics
Authors:
Keywords: neural networks, heuristics
Abstract:

A technique is presented which addresses a JIT production-scheduling problem where two objectives are present – minimization of setups between differing products and optimization of schedule flexibility. These two objectives are inversely related to each other, and, as a result, simultaneously obtaining desirable results for both is problematic. An efficient frontier approach is employed to address this situation, where the most desirable sequences in terms of both objectives are found. Finding the efficient frontier requires addressing the combinatorial complexity of sequencing problems. The artificial neural network approach of a Kohonen self-organizing map (SOM) is used to find sequences which are desirable in terms of both the number of setups and flexibility. The Kohonen SOM was used to find sequences for several problems from the literature. Experimental results suggest that the SOM approach provides near-optimal solutions in terms of the two objectives, in addition to comparing formidably with other search heuristics. Results also show, however, that the SOM approach performs poorly with regard to CPU time.

Reviews

Required fields are marked *. Your email address will not be published.