Potential of Reduced Experimental Designs in Object-Oriented Modeling of a Manufacturing Department for Film Production
From Proceeding of European Simulation Multiconference,ESS94, Barcelona, June 1-3 1994
Agostino G.Bruzzone

CONCLUSIONS

The experimental methods, which are based on major fractioning though defined by the conditions imposed by the minimum aberration, are valid results and can be used to reproduce plant behavior. The same can be said about the polynomial models obtained from the small composite design which generated similar performances.
An important innovative method obtained from this work was the superimposition of the two polynomial meta-models. Considering the common base of the tests required by both designs (34 runs and therefore about half of the total), it was very profitable to operate with a compendium of the two models not only to obtain mutual validation, but above all to choose the most suitable model within the same experimental range.
Looking at what are industrially more concrete results, an analysis of the meta-models has clearly shown the best possible lines of action to strengthen the plant while remaining within the budget limits.
For the sake of brevity, we will only mention some of the other suggestions which can be extrapolated from the analysis performed: determination of the "optimum" number of skilled technicians, minor influence of transports on general productivity compared with other possibilities and the effect of retooling times of several machines (indicating therefore that they should be updated).

Return to the Title