Introduction to

Acceptance Sampling
Assoc. Prof. Ir. Dr. Cheong Kuan Yew
School of Materials & Mineral Resources Engineering
Engineering Campus
Universiti Sains Malaysia

1
 Topic Outcome:
At the end of this topic, student are able to:
 Discuss the importance of acceptance
sampling (AS) in modern QC system.
 List down the advantages and disadvantages
of AS.
 Distinguish between AS by attributes and
variables.

2
 Topic Outline:
I] Introduction
II] Some Definitions
III] Areas where Inspection & Sampling are needed
IV] Methods used in performing the task of Inspection
V] Types of Sampling.
VI] Formation of Lots.
VII] Sample Selection.
VIII] Non-Accepted Lots.

3
 Introduction
 Sampling, Inspection & decision making of products.
Sampling?
Inspection?
Decision making  disposition?
Products?

4
 Some Definitions
I] Inspection
 Inspection
It is a process of measuring, examining, testing,or
otherwise comparing a unit of product with requirements.

2] Products
 Unit of product
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.

5
3] Sampling
 Sampling
Randomly drawing of sample(s).

4] Decision making
Lot disposition
Lot sentencing (accept or reject)

6
Areas where inspection &
sampling are needed:
 (1) Incoming, supplier inspection:
QC where raw materials are moving from supplier
(vendor) to purchaser. (components & raw materials)
Incoming
Raw Materials Accept
Ship
Process Inspection Customer

Reject

Disposition of lots

7
  (2) Process inspection
 where work-in-progress is moving from one process to
another for further processing. (operation, materials in
process, maintenance operations, data, or records)

Accept Ship
Process Inspection Customer
Reject

Scrap Rework
Disposition of lots

8
  (3) Final inspection
 where finished product is moving from the final process
to the warehouse or customer. (end items, supplies in
storage).

Accept Ship
Process Inspection Customer
Reject

Scrap Rework
Disposition of lots

9
Methods used in performing
the task of inspection
A. 100% inspection (every item produced is examined)

B. Sampling inspection (based on mathematical theory

of probability) – by attributes or by variables

C. Ad hoc sampling (not based on theory of

probability,e.g. the inspection of a fixed percentage or
spot checking).

D. No inspection

10
A) 100% Inspection
 This is used to eliminate the nonconformities that have
been produced from:
 A process unable to meet product specification.
 A process in control but not capable (with
manufacturing difficulties).
 Commonly used in new processes.
 This form of inspection is very costly especially if every
batch (British) or lot (US) that needs to be screened.

Lot or batch: It means “inspection lot/batch” a collection of units

of product from which a sample is to be drawn and inspected to
determine conformance with the acceptability criteria, and may
differ from a collection of units designated as a lot or batch for
other purposes (e.g. production, shipment,etc.)

11
 It cannot eliminate all (100%) nonconformities
presented. This could be due to
 Operator fatigue
 Operator training 80-90% Human error
 Inspection criteria
 Inspection method

12
B) Acceptance Sampling
 A system by which a lot is accepted or rejected based
on the results of inspecting samples in that lot.
Lot Size of N

Sample of n pieces inspected

Number of nonconformities < Number of nonconformities >

Acceptance number, c Acceptance number, c

Accept the lot, Ac Reject the lot, Re

Screening (100% Inspection) /

Rework / Scrap Entire lot

13
 One of the oldest aspect of QA (1930s)
 This method is most likely to be used in one of five
situations:
When test is destructive.
When cost of 100% inspection is high in relation to
the cost of passing a nonconforming unit.
When there are many similar units to be
inspected.
When information concerning producer’s quality is
available.
When automated inspection in not available.

14
 Advantages of Acceptance Sampling:
• Economy – key advantages.
• Less handling damage during inspection.
• Applies to destructive testing.
• Upgrades inspection job from monotonous piece-by-
piece decisions to lot-by-lot decisions.
• Indirectly motivate improvement with rejection of
entire lots instead of mere return of nonconformities.
[Put responsibility of Quality in the hands of Operating
organization and not the inspectors]

15
 Disadvantages of Acceptance Sampling:
• Risk of accepting “bad” lots and rejecting “good”
lots.
• Increases documentation and planning time.
• Less information is provided about the product.
• No assurance is given to the entire lot conforms to
specifications.

16
 Acceptance sampling is NOT a
substitute for adequate process
monitoring and control and use of
other statistical methods to drive
variability reduction.

17
Important Aspects of Acceptance Sampling (AS)
 It is the purpose of AS to sentence lots, not to estimate
the lot quality.
 AS plans do not provide any direct form of QC. Even if all
lots are of the same quality, sampling will accept some
lots and reject others. Process controls are used to
control and systematically improve quality, but AS is not.
 The most effective use of AS is not to ‘inspect quality into
the product’, but rather as an audit tool to ensure that the
output of a process conforms to requirements.

18
How many samples to be drawn?
 Based on “good” sampling plan.
 A Sampling Plan indicates the number of units of
product from each lot that are to be inspected (sample
size or series of sample size) and the criteria for
determining the acceptability of the lot (acceptance and
rejection numbers).
 Characteristics of a “Good” Sampling Plan:
 Protect producer against having “good” lots rejected.
 Protect consumer against accepting “bad” lots.
 Encourage producer to keep process in control.
 Minimize sampling cost.
 Provide information on product quality.
19
 Lot-by-lot acceptance sampling plans.

20
II] Types of Sampling Plans
Attribute Sampling Plans Variable Sampling Plans

Variables = measurement
Attributes = Quality characteristics
information (Quality characteristics
expressed on a go-no go basis.
measured on a numerical scale)
A sample is taken from a lot and A sample is taken and a
each unit is classified as GOOD or measurement of a specified
NO-GOOD. parameter is made on each unit.
The measurements are then
The number of NO-GOOD is summarized into a simple statistic
compared with the acceptance (e.g. Mean). The observed value is
number in the plan. compared to the allowable value
defined in the plan.
Decision is made to accept or
Decision is made to accept or reject the lot
reject the lot

21
Comparison of Attributes and Variables Sampling Plan
Features Attributes Variables
Each item would be
Each item is
Inspection measured at the specified
1 classified as good or
required parameter. Higher inspection
no-good
skill would be required.
Any number of
Type of One plan,one type of
2 nonconforming
nonconforming nonconforming.
under one plan
Large – depends on
3 Sample size the protection Smaller sample size.
required.
Distribution of
4 None Usually assumed Normal.
measurements
Valuable information on
Process Percent
5 process average and
information Nonconforming
variation.
22
 Lot-by-lot Acceptance Sampling Plans

Attributes Variables

MIL STD 105E MIL STD 414

ANSI/ASQ Z1.4 ANSI/ASQ Z1.9
(civilian counterpart) (civilian counterpart)

Dodge-Romig plans

23
Acceptance-Sampling Plan
 It is a statement of the sample size to be used and
the associated acceptance or rejection criteria for
sentencing individual lots.
 Single, Double, and Multiple Sampling Plans.
 Tighten, Normal, and Reduced Sampling Plans.
Sampling Scheme
 It is a set of procedures consisting of acceptance-
sampling plans in which lot sizes, sample sizes, and
acceptance or rejection criteria along with the
amount of 100% inspection and sampling are
related.

24
Sampling System
 It is a unified collection of one or more acceptance-
sampling schemes

25
III] Formation of Lots
 Lot formation can influence the effectiveness of a
sampling plan.
 Lots should be:
 homogeneous (same machine, operator,input
material…..)
 as large as possible (sample sizes do not increase
as rapidly as lot sizes, a lower inspection cost results
with larger lot size). [However, it is different in Just-
in-time procurement philosophy  smaller lot size].

26
 Conform to good packaging principles (prevent
product damage risks and additional nonconforming
during transit).
 Suitable for material handling (different handling
equipment used by producer and consumer).

27
IV] Sample Selection
 Sample units selected for inspection should be
representative of the entire lot.
 All sampling plans are based on the premise that each
unit in the lot has an equal likelihood of being selected (to
avoid bias)  Random Sampling .
 How does Random Sampling perform?
 1) Basic technique
 Assign a number to each lot (e.g. three digit number
 width, height, and depth).
 Generate a series of random numbers (computer,
calculator, die, random-number table…).
 Select a sample.
28
 d

29
 2) Stratification technique

Stratum 1

Stratum 2

Stratum 3

Stratum 1

30
V] Non-Accepted Lots
 What are the actions that can be taken?
• Sort by production personnel.
• Rectification at consumer’s plant by personnel
from either producer’s or customer’s plant.
• Return to producer
 Non-accepted lots will receive 100% inspection.
 A resubmitted lot is not normally re-inspected.

31
End

32