A Nonlinear Programming and Artificial Neural Network Approach for Optimizing the Performance of a Job Dispatching Rule in a Wafer Fabrication Factory : Table 1

Table 1: The differences between the proposed methodology and the previous methods.


Rule	Number of objectives	Objectives	Number of adjustable parameters	Optimized?	How to derive the rule?

NFSMCT	1	Average cycle time	1	No	(i) Generalizing FSMCT
1f-TNFSVCT	1	Cycle time standard variation	1	No	(i) Generalizing FSVCT (ii) Adding adjustable parameters
1f-TNFSMCT	1	Average cycle time	1	No	(i) Generalizing FSMCT (ii) Adding adjustable parameters
2f-TNFSVCT	1	Cycle time standard deviation	2	No	(i) Generalizing FSVCT (ii) Adding adjustable parameters
4f-biNFS	2	Average cycle time, cycle time standard deviation	2	Yes	(i) Fusing FSVCT and FSMCT (ii) Adding adjustable parameters
The proposed methodology	2	Average cycle time, cycle time standard deviation	2	Yes	(i) Fusing 2f-TFSMCT and 2f-TNFSVCT (ii) Nonlinear programming