01 - Acceptance Sampling
01 - Acceptance Sampling
01 - Acceptance Sampling
Acceptance Sampling
15 - 1
Acceptance Sampling
Acceptance Sampling is very useful when
15 - 2
Sampling Plans
Sampling Plans specify the lot size, sample size, number of samples
and acceptance/rejection criteria. Sampling plans involve
. Single sampling
. Double sampling
. Multiple sampling
Lot
Random
sample
15 - 3
Single Sampling Plan
A Single Sampling Plan is one where
. A representative sample of n items is drawn from a lot size
of N items.
. Each item in the sample is examined and classified as
good/defective
. If the number of defective exceeds a specified rejection
number (C - cut off point) the whole lot is rejected; otherwise
the whole lot is accepted
Lot (N Random Lot (N Random
items) sample items) sample
(n items) (n items)
15 - 4
Double Sampling Plan
A Double Sampling Plan allows the opportunity to take a second
sample if the results of the original sample are inconclusive.
. Specifies the lot size, size of the initial sample, the
accept/reject/inconclusive criteria for the initial sample
(CL - lower level of defectives, CU - upper level of
defectives)
. Specifies the size of the second sample and the acceptance
rejection criteria based on the total number of defective
observed in both the first and second sample (CT- total
allowable defectives)
15 - 5
Double Sampling Plan
CL CU
Compare number of defective found in the first random sample to CL
and CU and make appropriate decision.
15 - 6
Double Sampling Plan
Lot First Random sample
CT
Compare the total number of defective in both lots to CT and make the
appropriate decision
15 - 7
Multiple Sampling Plan
A Multiple Sampling Plan is similar to the double sampling plan in that
successive trials are made, each of which has acceptance, rejection
and inconclusive options.
15 - 8
Acceptance Sampling
Purposes
Determine quality level
Ensure quality is within predetermined level
Advantages Disadvantages
Economy Risks of accepting “bad” lots and
Less handling damage rejecting “good” lots
Fewer inspectors Added planning and documentation
Upgrading of the inspection job Sample provides less information
Applicability to destructive testing than 100-percent inspection
Entire lot rejection (motivation for
improvement)
15 - 9
Operating Characteristic Curve (OCC)
An Operating Characteristic Curve (OCC) is a probability curve for a
sampling plan that shows the probabilities of accepting lots with various
lot quality levels (% defectives).
1
0.9 Under this sampling plan, if the lot has 3% defective
Probability of accepting lot
0.8
. the probability of
accepting the lot is 90% . the probability of
0.7
rejecting the lot is 10%
0.6
0.5 If the lot has 20% defective
0.4 . it has a small probability (5%) of being accepted
0.3 . the probability of rejecting the lot is 95%
0.2
0.1
0
0 .05 .10 .15 .20 Lot quality (% defective)
15 - 10
Operating Characteristic Curve (OCC)
Under this sampling plan what is the probability of accepting a lot that
has 5% defectives?
1
0.9
Probability of accepting lot
The Lot Tolerance Percent Defective (LTPD) is the upper limit on the
percentage of defectives that a customer is willing to accept.
Customers want lots with quality better than or equal to the AQL but are
willing to live with some lots with quality as poor as the LTPD, but prefer
not to accept lots with quality levels worse than the LTPD.
15 - 12
Customer Acceptance Levels
Therefore the sampling plan must be designed to assure the customer
that they will be receiving the required AQL and LTPD.
The AQL and LTPD are dependent on many things (reliability, liability,
competitor quality levels, etc.) and will vary by industry and by customer.
Typically industry standards are set because suppliers have more than
one customer and customers have more than one supplier.
The Producer’s Risk is the probability that a “good” lot will be rejected.
15 - 13
OCC, AQL & Producer’s Risk
1
0.9 Producer’s Risk = probability acceptable lot is rejected
0.8
Probability of accepting lot
0.7
0.6
0.5 AQL - percentage level of defects at which
0.4 a customer is willing to accept
0.3
0.2
0.1
0
0 .05 .10 .15 .20 Lot quality (% defective)
“Acceptable Lot”
15 - 14
OCC, LTPD & Consumer’s Risk
1
0.9
0.8
Probability of accepting lot
0.7
LTPD - upper limit on the percentage of
0.6 defectives that a customer is willing to
0.5 accept.
0.4
0.3
0.2
0.1 Consumer’s Risk = probability unacceptable is accepted
0
0 .05 .10 .15 .20 Lot quality (% defective)
“Unacceptable Lot”
15 - 15
Average Quality Of Inspected Lots
The result of acceptance sampling (assuming rejected lots are 100%
inspected) is that the level of inspection automatically adjusts to the
quality of the lots being inspected.
15 - 17
15 - 18
Operating Characteristic Curves
15 - 19
Operating Characteristic Curves
15 - 20
Operating Characteristic Curves
15 - 21
Operating Characteristic Curves
15 - 22
Homework
Read and understand all material in the chapter.
15 - 23