EIA-555 2015 Edition, August 1, 2015
Lot Acceptance Procedure for Verifying Compliance with the Specified Quality Levels (SQL) in PPM
Includes all amendments and changes through Stabilization Notice (No longer revised / updated) , August 2015
Additional Comments: FORMERLY TECHAMERICA -EIA-555
Published By:SAE International (SAE)
This Specification covers a statistical sampling plan for lot inspection by attributes. It verifies that the customer's specified quality level (SQL) is not being exceeded. The estimate of fraction nonconforming determined by EIA Interim Standard No. EIA-554 is used to select the optimum sample plan for verifying that a given lot meets the specified quality level (SQL).
This specification is applicable to components:
Whose overall manufacturing processes are in statistical control;
Whose manufacturing processes have a distribution of nonconformances that can be approximated by a binomial probability distribution;
Whose manufacturing processes have manufacturing fraction nonconforming (F) levels of approximately 30 ppm to 5000 ppm. While there is no mathematical basis for limiting the application of this specification, when F is less than 30 ppm, sample inspection may not be economically feasible. When F is greater than 5000 ppm other lot by lot inspection techniques may be more appropriate. The SQL range corresponding to this F range falls between 500 ppm and 75000 ppm since the SQL is likely to be on the order of 15 times the manufacturing fraction nonconforming:
Those production process output per lot is "large" compared to the sample size. (For a lot size that is three times the sample size the alpha error is approximately 6% instead of the 10% stated and the beta error is approximately 14% instead of the 20% stated.); and
Whose production process produces more than five lots per year.
This sampling plan provides confirmation that steps in a process, following prior in-process inspection, have not introduced excessive nonconformances and that the prior in-process inspection has not passed an excessive number of nonconformances.
Both the Type I (alpha) and Type II (beta) errors are fixed.
An estimate of the fraction of nonconforming components that reach the inspection point is established.