00339 +06a963b1e1eb1e683a249968625de1

342

McCarville & Montgomery

Additionał Considerations

The examples in this paper described the case where there is an upper specification limit. Obviously, with minor modifications, models for situations where a lower specification limit is employed can easily be developed. Situations with both upper and lower specification limits can be approximated by summing the results of the upper and lower specification models.

Many manufacturers have gages staged at different process steps throughout the manufacturing operation. This allows for the removal of defective units prior to adding any additionał manufacturing costs to the product. It is common in the semiconductor industry to have a gage at the completion of the wafer processing so as to remove the defective chips prior to being assembled into the finał packages. After the package assembly, a finał test gage is utilized prior to shipping to the customer. Therefore, rather than minimizing the yield loss due to gage error, it might be morę advantageous to minimize the costs due to the gage error.

A useful modification to the Gage Loss model generated in this paper would be to consider formally the cost of the product at the point of testing. Then a cost model could be minimized.

Business conditions may dictate a yield loss goal for the company such that the quality level would need to be minimized while guaranteeing a maximum yield loss. The only difference between this situation and that shown in the example in this paper would be in the optimization procedurę. The example in this paper held the ppm(Def) = 100 as a constraint and minimized the Gage Loss. In this new scenario the Gage Loss would become the constraint while the ppm(Def) is minimized.

References

Box, G. E. P. and Draper, N. R. (1987). Empirical Model Building and Response Surfaces. John Wiley and Sons, Inc., New York, NY.

Derringer, G. C. and Suich, R. (1980). "Simultaneous Optimization of Several Response Variables." Journal of Quality Technology 12, pp. 214-219.

Design-Expert User's Manuał Version 3.0 (1992). Stat Ease, Inc., Minneapolis, MN.

Eagle, A. R. (1954). "A Method for Handling Errors in Testing and Measuring." Industrial Quality Control March, pp. 10-15.