Operations

Management

Statistical Process Control

Lecture 5S

OM Session 5S: Benzin Dahal 1

 Statistical Process Control
(SPC)
 Statistical technique used to ensure
process is making product to standard
 All process are subject to variability
 Natural causes: Random variations
 Assignable causes: Correctable problems
 Machine wear, unskilled workers, poor
material
 Objective: Identify assignable causes
 Uses process control charts

OM Session 5S: Benzin Dahal 2

Types of Statistical Quality Control

Statistical
Quality Control

Process Acceptance
Control Sampling

Variables Attributes
Charts Charts

OM Session 5S: Benzin Dahal 3

Central Limit Theorem
 X-charts based on this theorem
 Regardless of distribution of population
from which samples are taken, the
distribution of sample means will tend to
follow a normal curve
 Mean of sampling distribution will equal to
mean of population, 
 Std deviation of sample distribution will equal
to population std dev, , divided by square root
of sample size, n

OM Session 5S: Benzin Dahal 4

The Relationship Between Population and
Sampling Distributions

Three population distributions

Distribution of sample means
Beta

Mean of sample means  x

Normal Standard deviation of 
the sample means   x 
n

Uniform

 3 x  2  x  1 x x   x  2  x  3 x
(mean)
95.5% of all x fall within  2  x

99.7% of all x fall within  3 x

OM Session 5S: Benzin Dahal 5

Control Chart Purposes
 Show changes in data pattern
 e.g., trends
 Make corrections before process is out of
control
 Show causes of changes in data
 Assignable causes
 Data outside control limits or trend in
data
 Natural causes
 Random variations around average

OM Session 5S: Benzin Dahal 6

Control Chart Types

Continuous Numerical Categorical or Discrete

Data Control Numerical Data
Charts

Variables Attributes
Charts Charts

R X P C
Chart Chart Chart Chart

OM Session 5S: Benzin Dahal 7

X Chart

 Type of variables control chart

 Shows sample means over time
 Monitors process average
 Example: Weigh samples of coffee
& compute means of samples; Plot

OM Session 5S: Benzin Dahal 8

X Chart Control Limits
**When std dev, , of population or process is available

UCL  x  z
x x x – mean of sample means or target value set

LCL  x  z z – no of std dev as per confidence level

x x x – std dev of sample means

Mean for
k sample i
 xi
x  i 1 No of samples
k

OM Session 5S: Benzin Dahal 9

X Chart Control Limits
**When std dev, , of population or process is not available

UCL x  x  A R From
Table S6.1

LCLx  x  A R
Mean for
k sample i
 xi
x  i  1
No of samples
k
OM Session 5S: Benzin Dahal 10
Factors for Computing Control
Chart Limits (when  is not available)
Sample Mean Upper Lower
Size, n Factor, A 2 Range, D4 Range, D3
2 1.880 3.268 0
3 1.023 2.574 0
4 0.729 2.282 0
5 0.577 2.115 0
6 0.483 2.004 0
7 0.419 1.924 0.076
8 0.373 1.864 0.136
9 0.337 1.816 0.184
10 0.308 1.777 0.223
12 0.266 1.716 0.284

OM Session 5S: Benzin Dahal 11

Control Chart for Samples of 9 Boxes

Variation due to
assignable causes

17=UCL
Variation due to
16=Mean
natural causes
15=LCL
Variation due to
1 2 3 4 5 6 7 8 9 10 11 12 assignable causes
Sample Number
Out of control

OM Session 5S: Benzin Dahal 12

 R - Charts

 Type of variables control chart

 Shows sample ranges over time, where
range is the diff between highest and
lowest values in each sample
 Monitors process dispersion/variability
 Example: How far from the mean are
the readings?

OM Session 5S: Benzin Dahal 13

R – Chart Control Limits

UCLR  D4 R From
Table S6.1
LCLR  D3 R

k Range for
sample i
 Ri
R  i 1
k No of samples

OM Session 5S: Benzin Dahal 14

Steps to Follow When Using
Control Charts
1. Collect 20 to 25 samples of n=4 or n=5
from a stable process and compute the
mean.
2. Compute the overall means, set
approximate control limits (usually
3),and calculate the preliminary upper
and lower control limits.If the process is
not currently stable, use the desired
mean (target) instead of the overall
mean to calculate limits.
3. Graph the sample means and ranges on
their respective control charts and
OM Session 5S: Benzin Dahal 15
Steps to Follow When Using
Control Charts - continued
4. Investigate points or patterns that
indicate the process is out of control.
Assign causes for the variations.
5. Collect additional samples and
revalidate the control limits.

OM Session 5S: Benzin Dahal 16

Mean and Range Charts
Complement Each Other

OM Session 5S: Benzin Dahal 17

p Chart

 Type of attributes control chart

 e.g., good-bad
 Shows % of nonconforming items –
percent defective
 Example: Count # of defective chairs
& divide by total chairs inspected;
Plot
 Chair is either defective or not defective

OM Session 5S: Benzin Dahal 18

p Chart Control Limits

UCLp  p  z p p = mean fraction defective

z = 2 for 95.5% limits;
z = 3 for 99.7% limits
LCL p  p  z p
k
 xi
p  i1
k No of defective Items
 ni
i1 in Sample i

p (1  p )
p  Size of sample i
n
where n  sizeof eachsample
k = no of samples
OM Session 5S: Benzin Dahal 19
Control Limits for c-Charts

 Population will be a Poisson

distribution, but applying the Central
Limit Theorem allows us to assume a
normal distribution for the sample
statistics
UCLc = c + 3 c LCLc = c - 3 c

c = mean number defective in the sample

OM Session 5S: Benzin Dahal 20

Patterns to Look for in Control
Charts

OM Session 5S: Benzin Dahal 21

What Is Acceptance Sampling?
 Form of quality testing used for
incoming materials or finished goods
 e.g., purchased material & components
 Procedure
 Take one or more samples at random
from a lot (shipment) of items
 Inspect each of the items in the sample
 Decide whether to reject the whole lot
based on the inspection results

OM Session 5S: Benzin Dahal 22

What Is an Acceptance Plan?
 Set of procedures for inspecting
incoming materials or finished goods
 Identifies
 Sample size (n)
 Criteria (c) used to reject or accept a
lot
 Producer (supplier) & consumer
(buyer) must negotiate
 Represented by OC curve

OM Session 5S: Benzin Dahal 23

Operating Characteristics Curve

 Shows how well a sampling plan

discriminates between good & bad
lots (shipments)
 Shows the relationship between the
probability of accepting a lot & its
quality

OM Session 5S: Benzin Dahal 24

OC Curve 100% Inspection

P(Accept Whole Shipment)

100%
Keep whole Return whole
shipment shipment

0%
0 1 2 3 4 5 6 7 8 9 10
Cut-Off % Defective in Lot

OM Session 5S: Benzin Dahal 25

An Operating Characteristic
(OC) Curve Showing Risks

OM Session 5S: Benzin Dahal 26

AQL & LTPD
 Acceptable quality level (AQL)
 Quality level of a good lot
 Producer (supplier) does not want lots
with fewer defects than AQL rejected
 Lot tolerance percent defective (LTPD)
 Quality level of a bad lot
 Consumer (buyer) does not want lots with
more defects than LTPD accepted

OM Session 5S: Benzin Dahal 27

Producer’s & Consumer’s Risk
 Producer's risk () – Type I error
 Probability of rejecting a good lot
 Probability of rejecting a lot when
fraction defective is AQL or better; 5.05%
 Consumer's risk (ß) – Type II error
 Probability of accepting a bad lot
 Probability of accepting a lot when
fraction defective is LTPD or worse; 10%

OM Session 5S: Benzin Dahal 28