Browsing by Subject "Computer integrated manufacturing systems."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Joint lot sizing and tool management in a single CNC environment(Bilkent University, 1996) Önen, Siraceddin111 most of the studies on tool management, lot sizes are taken as pi'edetermined input while deciding on tool allocations and machining |)arameters. In this study, we considered the integration of lot sizing and tool rnaricigement problems for single and multi i:>eriod cases. For the single period case, we proposed a new algorithm. By this algorithm we not only improved the overall solution by exploiting interactions, but also prevented any infeasibility that might occur lor the tool management problem due to the decisions made at the lot sizing level. The computational experiments showed that in a set of randomly generated problems 22.5% of solutions found by a. traditional approach were infeasible and the proposed joint approach improved the overall solution by 6.8%. For the multi period case, we proposed live new algorithms. Among these algorithms, the most promising one was tlie Look Atiea.d-LUC algorithm, which improved the overall solution on the average by 6.5% compared to the best known algorithm, Wa.gner-Whitin, used in traditional approcich, over a set of randomly generated problems.Item Open Access Simulation metamodeling with neural networks(Bilkent University, 1997) Touhami, SouheylModern manufacturing environments increasingly call for more sophisticated cind fast decision aiding systems for their management. Artificial neural networks have been proposed as an alternative cipproach for formalizing various quantitative and qualitative aspects of manufacturing systems. This research attempts to lay down the motivation behind using neural networks as a simulation metamodeling approach. This research can be classified under the major headings of simulation metamodeling for the purpose of estimating system performance. Steiidy state perfornuince of non-terminating type systems and transient state performance of terminating tyj^e systems are examined under job shop environments by applying Back Propagation neural networks. We attempt to study the peribrrnance of neural metamodels with respect to estimating two performance measures (mean machine utilization and mean job tardiness), with respect to system complexity, with different types of system configurations (deterministic cuid stochastic), with respect to multiple metamodel accuracy assessment criteria and various metamodel design settings. The objective of this analysis is to investigate the potential application of neural metamodeling.