Acceptance Number.

The acceptance number is the maximum number of

defects or defective units in the sample that will permit acceptance lot or batch.

AQL has two different definitions due to standard changes.

MIL-STD-105E, ISO 2859-1 (1999)

Acceptable Quality Level. The acceptable level (AQL) is defined as the

maximum percent defective (or the maximum number of defects per hundred
units) that, for purpose of sampling inspection, can be considered satisfactory as
a process average. The sampling plans most frequently used by the department
of Defense are based on the AQL.

ANSI/ASQC Z1.4-2003

Acceptance Quality Limit. The AQL is the quality level that is the worst tolerable
process average when a continuing series of lots is submitted for acceptance
sampling.

The following note on the meaning of AQL was introduced with the ANSI/ASQ
Z1.4-2003 revision.

The concept of AQL only applies when an acceptance sampling scheme with
rules for switching between normal, tightened and reduced inspection and
discontinuance of sampling inspection is used. These rules are designed to
encourage suppliers to have process averages consistently better than the AQL.
If suppliers fail to do so, there is a high probability of being switched from normal
inspection to tightened inspection where lot acceptance becomes more difficult.
Once on tightened inspection, unless corrective action is taken to improve
product quality, it is very likely that the rule requiring discontinuance of sampling
inspection will be invoked.

Although individual lots with quality as bad as the AQL can be accepted with fairly
high probability, the designation of an AQL does not suggest that this is
necessarily a desirable quality level. The AQL is a parameter of the sampling
scheme and should not be confused with a process average which describes the
operating level of a manufacturing process. It is expected that the product quality
level will be less than the AQL to avoid excessive non accepted lots.

The AQL values are defined as percent nonconforming or defects or

nonconformities per hundred units.

Defects and Defectives. A defect is any nonconformance of the unit of product

with the specified requirements. A defective is a unit of product which contains

1
one or more defects. Failure to meet requirements with respect to quality
characteristics are usually described in terms of defects or defectives.

Critical - A critical defect is on that judgment and experience indicate is likely to:

a. result in hazardous or unsafe conditions for individuals using, maintaining,

or depending upon the products; or
b. prevent performance of the tactical function of a major end item. A critical
defective is a unit of product that contains one or more critical defects.

Major - A major defect is one, other than critical, that is likely to result in failure,
or to reduce materially the usability of the unit of product for its intended purpose.
A major defective is a unit of product that contains one or more major defects.

Minor - A minor defect is one that is not likely to reduce materially the usability of
the unit of product for its intended purpose, or is a departure from established
standards having little bearing on the effective use or operation of the unit of
product. A Minor defective is a unit of product that contains one or more defects.

Double Sampling Plan. A double sampling plan involves sampling inspection in

which the inspection of the first sample to a decision to accept, to reject or to take
a second sample. The inspection of a second sample, when required, lead to a
decision to accept or reject.

Drawing of Samples. Basic to sampling inspection is the assurance that the

sample selected from a quantity of units represents the quality of that quantity of
units. Hence, the procedure used to select units from a lot must be such that it
assures a sample free of bias.

Expression of Nonconformance. The extent of nonconformance of product

shall be expressed either in terms of percent defective or in terms of defects per
hundred units (DHU).

Defects per Hundred Units. The number of defects per hundred units of any
given quantity units of product is one hundred times the number of defects
contained therein (one or more defects being possible in any unit of product)
divided by the total number of units of product, i.e.:

number of defectives x 100

Defects per hundred units =
number of units inspected

Inspection. Inspection is the process of measuring, examining, testing, or

otherwise comparing the unit of product with the requirements.

2
Inspection by Attribute. Inspection by attributes is inspection where by either
the unit of product is classified simply as defective or non-defective, or the
number of defects in the unit of product is counted, with respect to a given
requirement or set of requirements.

Inspection Levels. The standards provides for three general inspection levels
and four special inspection levels. These seven levels permit the user to balance
the cost of inspection against the amount of protection required.

Lot or Batch. The term lot or batch shall mean "inspection lot" or "inspection
batch" i.e., a collection of units of product from which a sample is to drawn and
inspected to determine conformance with the acceptance criteria, any may differ
from a collection of units designated as a lot or batch for other purposes (e.g.,
production, shipment, etc.).

Nonconformance. Nonconformance may be defined as the failure of a unit of

product to conform to specified requirements for any stated quality characteristic.
The extent of nonconformance of product to the required quality characteristics
shall be expressed either in terms of percent defective or in terms of defects per
hundred units (DHU).

Normal Inspection. Normal inspection is that which is used where there is no

evidence that the quality of product being submitted is better or poorer than the
specified quality level.

Percent Defective. The percent defective of any given quantity of units of

product is one hundred times the number of defective units of product contained
therein divided by the total number of units of product, i.e.: Percent defective =
number of defectives x100 / number of units inspected

Reduced Inspection. Reduced inspection under a sampling plan uses the same
quality level as for normal inspection, but requires a smaller sample for
inspection.

Rejection Number. The rejection number is the minimum number of defects or

defective units in the sample that will cause rejection of the lot represented by the
sample.

Representative Sampling. When appropriate, the number of units in the sample

shall be selected in proportion to the size of sub-lots or sub-batches, or parts or
the lot or batch, identified by some rational criterion. When representative
sampling is used, the units from each part of the lot or batch shall be selected at
random.

3
Resubmitted Lots or Batches. Lots or batches found unacceptable shall be
resubmitted for reinspection only after all units are re-examined or retested and
all defective units are removed or defects corrected. The responsible authority
shall determine whether normal or tightened inspection shall be used and
whether reinspection shall include all types or classes of defects or only the
particular types or classes of defects which caused initial rejection.

Sample. A sample consists of one or more units of product drawn from a lot or
batch, the units of the sample being selected at random without regard to their
quality. The number of product in the sample is the sample size.

Sampling Plans. A lot sampling plan is a statement of the sample size or sizes
to be used and the associated acceptance and rejection numbers.

Single Sample Plan. A single sampling plan is a type of sampling plan by which
the results of a single sample from an inspection lot are conclusive in determining
acceptability. The number of sample units inspected shall be equal to the sample
size given by the plan.

Severity of Inspection. The severity of inspection concerns the total amount,

kind and extent of inspection specified by the quality assurance provisions
established for the unit of product, or as dictated by quality history.

Unit of Production. The unit of product is the thing inspected in order to

determine its classification as defective or non-defective or to count the number
of defects. It may be a single article, a pair, a set, a length, an area, an operation,
a volume, a component of an end product, or the end product itself. The unit of
product may or may not be the same as the unit of purchase, supply, production,
or shipment.

Tightened Inspection. Tightened inspection under a sampling procedure plan

uses the quality level as for normal inspection, but requires more stringent
acceptance criteria.

Form OF Sampling

With each of these major sampling plans there may be

1. Single sampling that is , basing the acceptance or rejection of a lot

upon the units in one sample drawn from that lot
2. Double sampling, that is selecting one sample of units from a lot and
under certain conditions selecting a second sample before accepting or
rejecting a lot

4
 3. Multiple sampling, that is basing acceptance or rejection of a lot upon
the results of several samples of units drawn from that lot .
Of these three methods, double sampling has probably been the most popular for
reasons as the following:

Double Sampling As Compared With Single Sampling

1. Psychologically the idea of giving a lot of material a second chance before

rejecting it has popular appeal. Double sampling is therefore sometimes
easier to sell in the factory.
2. Double sampling plans permit a smaller for sample than is called for by
the sample size of the corresponding single sampling plan. When the
percent non-conformance is either low or high in material submitted for
inspection, it is frequently possible to accept or reject lots based upon the
results of the first sample. In these instances, therefore double sampling
permits lower sampling costs.

Double Sampling As Compared With Multiple Sampling

1. Double-sampling plans are often easier to administer than multiple

sampling plans. The need for selecting successive samples in the proper
fashions may require greater administrative control and more highly skilled
inspection operators.
2. In theory, multiple sampling may often permit lower total inspection than
double sampling for a given degree of protection because of the smaller
sample sizes required. In practice, however, the greater complexity of
multiple sampling may, in some cases, return the overall cost advantage
to double sampling. This is particularly true when the percent
nonconformance in submitted lots is low- say,0.1 percent-in these cases,
the amount of inspection required by single and double sampling plans
based upon process averages is much the same for that for multiple
sampling

Inspite of the popularity of double sampling, there are certain benefits unique
to both single and multiple sampling.

Single sampling

5
 1. Single sampling may be the only practical type of sampling plan under
conveyorized production conditions when it is physically possible to select
only one sample.
2. With lots of material whose percents nonconformance are close to the
AQL, single sampling may offer more economical inspection protection
than double sampling.

Multiple sampling

1. When administrative costs can be kept low, multiple sampling may permit
lower inspection costs for given degrees of protection than either single or
double sampling.
2. Newer methods to simplify multiple sampling, among them computer
based sampling, may result in greater improved efficiency in administering
these sampling plans.
3. Multiple sampling corresponds to the fashion in which an inspector
normally selects samples.

The type of product and the way the product is presented for sampling-on a
conveyor, in boxes piled on top of other, and so forth-are the factors that must
be taken into account.
Again, the choice of single, double, or multiple sampling depends upon the
particular conditions for which the sampling plan is to be used. None of the
three methods may be termed best; they may be merely best for certain
sampling conditions.

Procedure for Double Sampling Plan

Find the Sample Size Code Letter

Set the range covering the Batch or Lot Size being inspected in the window at
the top right corner on the front of the AQL Inspector's Rule. Then read the
Sample Size Code Letter, in the box, directly to the left of the Inspection Level.

Find the Sampling Plan

The Double Sampling Plan consists of two sets of Acceptance Numbers,

Rejection Numbers and Sample Sizes. Normal inspection is used until such time
as the results of inspection dictate the Tightened or Reduced inspection should
be employed as outlined in Switching Procedures on page 10. Double sampling
plans are found on the back of the AQL Inspector's Rule.

6
Set the required AQL level in the window above the Double Sampling Plans.
Locate the Sample Size Code Letter previously selected in step 1. If an arrow
show in the window directly below the Code Letter, follow the direction of the
arrow until a set of acceptance-rejection numbers are reached. Then read the
first Acceptance (in black) and Rejection (in color) Number in the window on the
'"1st" row.

The Acceptance and Rejection number pairs and the Sample Sizes directly
below them make up the Sample Plan.

Perform the First Inspection

Randomly select a group of "Sample Size" items from the lot and inspect them. If
the sample size equals or exceeds the lot size do 100% inspection. If the number
of defective items is equal to or less than the Acceptance Number accept the lot.
If the number of defective items is equal to or greater than the "Rejection
Number" reject the lot.

Perform The Second Inspection

If the lot was the accepted or rejected from the first inspection the second sample
inspection is not required, skip this step.

Read the Acceptance and Rejection Numbers and Sample size from the "2nd"
row under those used for the first inspection.

Randomly select a second group of "Sample Size" items from the lot and
inspection them. Combine the total number of defective items from the first and
second samples. If the total number of defective items is equal to or less than the
Acceptance Number accept the lot. If the total number of defective items is equal
to or greater than the "Rejection Number" reject the lot.

7
 Statistical Sampling Tables

Table # B.1 Sample Size Code Letters

Sample Size
Lot/Batch Size Code Letter

2 to 8 A
9 to15 B
16 to 25 C
26 to 50 D
51 to 90 E
91 to 150 F
151 to 280 G
281 to 500 H
501 to 1200 J
1201 to 3200 K
3201 to 10000 L
10001 to 35000 M
35001 to 150000 N
150001 to 500000 P
500001 & over Q
(Source-MIL- STD-105)

Table # B.2 Normal Inspection Plan: Single

Sampling
Acceptable Quality Levels AQL -Normal Inspection
Sample Size Code
Letter Sample Size 1.0 1.5 2.5 4.0 6.5
Ac Re Ac Re Ac Re Ac Re Ac Re
A 2 0 1 0 1 0 1 0 1 0 1
B 3 0 1 0 1 0 1 0 1 0 1
C 5 0 1 0 1 0 1 0 1 1 2
D 8 0 1 0 1 0 1 1 2 1 2
E 13 0 1 0 1 1 2 1 2 2 3
F 20 0 1 1 2 1 2 2 3 3 4
G 32 1 2 1 2 2 3 3 4 5 6
H 50 1 2 2 3 3 4 5 6 7 8
J 80 2 3 3 4 5 6 7 8 10 11
K 125 3 4 5 6 7 8 10 11 14 15
L 200 5 6 7 8 10 11 14 15 21 22
M 315 7 8 10 11 14 15 21 22 21 22
N 500 10 11 14 15 14 15 21 22 21 22
P 800 14 15 21 22 21 22 21 22 21 22

8
 Q 1250 21 22 21 22 21 22 21 22 21 22
(Source-MIL- STD- 105)

Table # B.3 Normal Inspection Plan: Double Sampling

Acceptable Quality Levels AQL -Normal Inspection
Sample Sample Sampl Cumulati 1.0 1.5 2.5 4.0 6.5
Size e Size ve
Code Sample
Size
Ac Re Ac Re Ac Re Ac Re Ac Re
First 0 1 0 1 0 1 0 1 0 1
A Second 0 1 0 1 0 1 0 1 0 1
First 2 2 0 1 0 1 0 1 0 1 0 1
B Second 2 4 0 1 0 1 0 1 0 1 0 1
First 3 3 0 1 0 1 0 1 0 1 0 2
C Second 3 6 0 1 0 1 0 1 0 1 1 2
First 5 5 0 1 0 1 0 1 0 2 0 2
D Second 5 10 0 1 0 1 0 1 1 2 1 2
First 8 8 0 1 0 1 0 2 0 2 0 3
E Second 8 16 0 1 0 1 1 2 1 2 3 4
First 13 13 0 1 0 2 0 2 0 3 1 4
F Second 13 26 0 1 1 2 1 2 3 4 4 5
First 20 20 0 2 0 2 0 3 1 4 2 5
G Second 20 40 1 2 1 2 3 4 4 5 6 7
First 32 32 0 2 0 3 1 4 2 5 3 7
H Second 32 64 1 2 3 4 4 5 6 7 8 9
First 50 50 0 3 1 4 2 5 3 7 5 9
J Second 50 100 3 4 4 5 6 7 8 9 12 13
First 80 80 1 4 2 5 3 7 5 9 7 11
K Second 80 160 4 5 6 7 8 9 12 13 18 19
First 125 125 2 5 3 7 5 9 7 11 11 16
L Second 125 250 6 7 8 9 12 13 18 19 26 27

First 200 200 3 7 5 9 7 11 11 16 11 16

M Second 200 400 8 9 12 13 18 19 26 27 26 27
First 315 315 5 9 7 11 11 16 11 16 11 16
N Second 315 630 12 13 18 19 26 27 26 27 26 27
First 500 500 7 11 11 16 11 16 11 16 11 16

9
P Second 500 1000 18 19 26 27 26 27 26 27 26 27
First 800 800 11 16 11 16 11 16 11 16 11 16
Q Second 800 1600 26 27 26 27 26 27 26 27 26 27
(Source-MIL- STD-105)

Normal, reduced, and tightened inspection

The standard form of, many sampling tables is generally called

normaltables. Many well conceived acceptance-sampling procedures,
such as MIL-STD-105D, also provide for reduced sampling and in some
cases tightened sampling plans for use to supplant normal sampling under
certain circumstances. This is provided for in what is called the switching
rule of the plan in technical sampling terms.

When, for example, the quality of lots submitted for inspection is consistently
better than the specified quality index value, which may be demonstrated by the
fact that no lots are being rejected then a reduced sampling schedule may be
used in place of normal sampling under certain acceptance plans. These
reduced schedules are usually similar in form to the normal schedules, except
that the first sample sizes , which correspond to a given lot size, are smaller.
Such tables may have for example a first reduced sample one-fifth the size of the
first normal sample.

Reduced sampling permits a decrease in inspection cost. This type of sampling

can be continued until the quality of the material were to become poorer and call
for returns to normal sampling.

When the quality of lots submitted for inspection is consistently poorer than the
quality target aimed for, a tightened sampling schedule is called for. This
tightened schedule is usually similar to the normal schedule, except that the
allowable number of defectives for a given sample size is reduced.

When tightened inspection is in effect, normal inspection should be instituted

when 5 consecutive lots or batches have been considered acceptable and
original inspection. After tightened inspection has been in effect for 10
consecutive lots, sampling inspection under the standard is terminated until
action is taken to improve the process.

Acceptance criteria under tightened inspection

10
 Code normal tightened
letter
n c n c

E 13 0 20 0

H 50 1 80 1

K 125 3 125 2

N 500 10 500 8

In the first three cases the criteria under tightened inspection for a 1% AQL are
the same as the criteria under normal inspection for the stated code letter for the
next lower AQL, namely , .65% . in most cases in the ABC standard , the
tightened criteria are identical with the normal criteria for the next lower AQL
class, although there are a number of exceptions.

Criteria for qualification and loss of qualification for reduced inspection

Generally speaking, eligibility for reduced inspection should be based on recent

quality history indicating average quality considerably better than the AQL.
Moreover, it should seem likely that the product to be inspected under reduced
inspection will be produced under the same conditions that gave rise to the
recent good quality history.

The ABC standard states the following conditions for a shift from normal to
reduced inspection :
The preceding 10 lots or batches (or more,) have been on normal inspection and
none has been rejected on original inspection; and

The total number of the defectives (or defects ) in the samples from the
preceding 10 lots or batches (or such other number as was used for
conditions a above ) is equal to or less than the applicable number given in
table 16. If double or multiple sampling is in use , all samples inspected
should be included , not firstsamples only; and

Production is a steady rate ; and

Reduced inspection is considered desirable by the responsible authority.

11
Normal inspection must be reinstated whenever a lot or batch is rejected or
production becomes irregular or delayed, or other conditions warrant that normal
inspection shall be instituted.

Acceptance criteria under reduced inspection

In all the military AQL systems using sample size code letters, the code letter in
reduced inspection has been determined just as in normal inspection.. The
relationship between the criteria under normal and reduced inspection may be
illustrated with reference to the single sampling normal plans for a 1% .

Code normal reduced

letter
n accept reject n accep reject
t
E 13 0 1 5 0 1

H 50 1 2 20 0 2

K 125 3 4 50 1 4
N 500 10 11 200 5 8

It is clear that the acceptance criteria shown for code letters H, K, and N under
reduced inspection all have an area of indecision in which the lot is neither
accepted nor rejected. The standard states that, whenever the number of
defectives falls in this indecision region (for example, if there should be exactly 1
defective in the sample of 20 with code letter H), the lot in question shall be
accepted but reduced inspection shall be continued and normal inspection
reinstated.

General comments on reduced inspection in acceptance/rejection plans

A provision for reduced inspection is not a necessary part of an

acceptance/rejection plan. Nevertheless, such a provision is based on a principle
that is economically sound. The principle is to concentrate inspection on those
products and quality characteristics where the quality history is doubtful and to
give less attention where the quality history is very good.

12
The consumers savings in inspection costs under reduced inspection are
apparent. The producers advantages are not quite so obvious. However,
because the acceptance criteria in reduced inspection are not so stringent, the
producer receives added protection against lot rejection. The producer may also
have a real sense of accomplishment in having qualified for reduced inspection.
Hence, from the consumers point of view point, the provisions for reduced
inspection in any acceptance program may provide a useful nonfinancial
incentive to the producer to improve quality.

13