lexiara

PROCEDURE FOR PRODUCTION CONFORMITY TESTING WHEN STANDARD DEVIATION IS UNSATISFACTORY OR UNAVAILABLE

This Appendix describes the procedure to be used to verify production conformity for the emissions of pollutants when the manufacturer's production standard deviation is either unsatisfactory or unavailable. With a minimum sample size of three engines the sampling procedure is set so that the probability of a lot passing a test with 40 % of the engines defective is 0,95 (producer's risk = 5 %) while the probability of a lot being accepted with 65 % of the engines defective is 0,10 (consumer's risk = 10 %). The values of the pollutants given in Section 6.2.1 of Annex I are considered to be log normally distributed and should be transformed by taking their natural logarithms. Let m0 and m denote the minimum and maximum sample size respectively (m0 = 3 and m = 32) and let n denote the current sample number. If the natural logarithms of the values measured in the series are χ1, χ2, … χi and L is the natural logarithm of the limit value for the pollutant, then, define and Table 4 shows values of the pass (An) and fail (Bn) decision numbers against current sample number. The test statistic result is the ratio: and shall be used to determine whether the series has passed or failed as follows: for m0 ≤ n < m: pass the series if , fail the series if , take another measurement if . Remarks The following recursive formulae are useful for calculating successive values of the test statistic: Table 4 Pass and fail decision numbers of Appendix 2 sampling plan Minimum sample size: 3

· All articles ·

Source: EUR-Lex (Cellar) · retrieved 2026-11-01 · Text as adopted (Official Journal); later amendments are not incorporated in this text.