00311 40d919f08bfaaab16635561d62a741
314
McCarville & Montgomery
appropriate levels. These gage targets are called guard bands. This paper develops generał models for defect levels and gage losses for systems of gages and shows how response surface models can be used to optimize the system.
Introduction
Reduction of product and process variation has become a critical component of competitiveness in today's manufacturing industries. Morę recently, gage variability, and a thorough understanding of the components of gage variation, has also become significant. With quality levels measured in parts per million, and even parts per billion, the quality of measurement, especially at finał outgoing tests, must be high. However, for many high technology products accurate gages with Iow levels of variation are not yet available. Customers still expect perfection even when the industry has not yet developed capable gages to test critical product parameters.
In generał, the total observed variance for a product parameter can be decomposed into two components as follows:
CT^total = CT^product + CT^gage (1)
where cr^product *s the variability in the product distribution and a^gage is a variance component that represents the variability due to the gage. With the knowledge received from the analysis of the product and gage variation it is feasible that the defect level being sent on to the customer can be estimated. Once estimated, a proper setting for the gage, or the guard band, can be determined to achieve the desired quality level dictated by the manufacturer or the customer.
Many manufacturers use multiple gages in series to assure Iow defect levels for products reaching their customers. This is common in the semiconductor industry. Often the product is tested in wafer form before being sent on to the finał packaging processes where it is tested again at least once. In cases such as this, the guard bands shoułd be set at optimum levels such that the quality levels can be achieved and the minimum loss is encountered when good product is rejected due to errors in the gages.
To illustrate, suppose that a critical product parameter is normally distributed with a mean of 1130 and a standard deviation of 80. The customer's upper specification limit is 1250. The probability of having a unit outside of the specification is 0.06681. That is, the reject level is 6.681%. Because 6.6681% is an unacceptable level of rejects to be sending on to the customer, a
Wyszukiwarka
Podobne podstrony:
00005 ?c83d1e05ebea51ca527b5a4071b83a 4 Keats & Montgomery integration of these two generał cla
00317 ?8ddf873a508f535a2304aca8bc776b 320 McCarville & Montgomery units will be rejected due to
00323 ?85e6f46f7f32f30fdf82adebd3e7fe 326 McCarviIle & Montgomery Figurę 10. The Defect Level D
00325 ?437d425376f31708da407e970fe43f 328 McCarvilIe & Montgomery USL z = J[f
00327 271125d41fcbd8d7859983e972a0b77 330 McCarville & Montgomery P(good
00329 ?f4634893f39e8884db8751e17aa760 332 McCarville & Montgomery 0.136772. This becomes a pote
00331
00333 ]489b6074768ba52499a553f0da86cd 336 McCarville & Montgomery RasponM: Ln pnn(Daf) in trana
00335 g3b40dbbf66d5e5072621ad7f05eef6 33 8 McCarville & Montgomery Graphical Optimization When
00339 +06a963b1e1eb1e683a249968625de1 342 McCarville & Montgomery Additionał Considerations The
00315 ?2897da0df33ebfef7d49591ddf4696 318 McCarviIle & Montgomery Figurę 3. The Probabiiity of
00320 ?5cd1011755558fd005661a9b3cd8ed 323 Optimizing Defect Levels and Losses from Gage Errors Defe
00337 ?cc2c711f7435285954e5a4f8b72a11 340McCarville & Montgomery When applying the optimum guar
img025 The Letters K & L The K has a straight piece on the Ieft, and a bend on the right. These
2954e740d15dca50e64ed4e56a715ab9 Minister Pierre DeBane have spread the woed. to Burope and beyond,
28 1992). Due to their smali size, geographic spread, and high transportation costs, these civil wor
Looking for a Driving Course? Defensive Driving Courses These courses typically are for students who
69139 jff 096 TIPS TO THE TALL MAN Notę: These special instructions are the result
więcej podobnych podstron