See discussions, stats, and author profiles for this publication at: [Link]

net/publication/330466966

Quality Management-Control Charts

Presentation · January 2019

CITATIONS READS

0 342

1 author:

Nermin Sökmen

23 PUBLICATIONS   15 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Technology management intelligence View project

Data Analysis View project

All content following this page was uploaded by Nermin Sökmen on 18 January 2019.

The user has requested enhancement of the downloaded file.

 QUALITY MANAGEMENT
STATISTICAL QUALITY MANAGEMENT

МИСиС- Национальный
Prepared by: Dr. Nermin Sökmen и с с л е д о в а т ел ь с к и й
технологический
университет

Москва
18.01.2019 1
 What is Statistical Quality Control?

➢Quality Control: The part of quality management focused on

fulfilling quality requirements.

➢Statistical quality control refers to the use of statistical methods in

the monitoring and maintaining of the quality of products and
services.
➢A scientific method of analyzing data and using the analysis to
solve pratical problems.

18.01.2019 DR. NERMIN SÖKMEN 2

What is Statistical Quality Control?

➢Scientifical means «having to

do with numbers» or «drawing Statistical With the help of numbers, or
conclusions from numbers». data
➢Quality refers to the «the
qualities or characteristics» of Quality We study the characteristics
the things or process being of our process
studied.
Control In order to make it behave
➢Control means «to keep the way we want it to
something within bounderies» or behave
«to make something behave the
way we want it to behave».

18.01.2019 DR. NERMIN SÖKMEN 3

FATHERS OF STATISTICS AND STATISTICAL QUALITY CONTROL
Edwards Eugene
Deming Grant
(1900- (1897-
1993) 1996)
Ronald Walter
Fisher Shewhart
(British, (1891-
1890-1962) 1967)
S. Poisson
(1781-
1840 )
C. F. Gauss John Tukey
(1777- (1915-
1855) 2000)
Karl Pearson Joseph Juran George Box
(1857- (1904- (1919-
1936) 2008) 2013)

Ellis R. Ott
Bortkiewicz
Ladislaus
(1868 –
1931).

18.01.2019 4
THE FATHER OF STATISTICAL QUALITY CONTROL

➢ Walter Andrew Shewhart (1891 – 1967), an American Physicist and

statistician.
➢ created the first statistical control charts of manufacturing processes, involved
statistical sampling procedures in Western Electric Company.
➢ published his findings in a 1931 book, Economic Control of Quality of
Manufactured Product.
➢ moved to The Bell Telephone Laboratories in 1925 and continued his
researches there.
➢ defined the fundamental principles and techniques basic to the efficient use of
statistical method in attaining statistical control, establishing tolerance limits,
presenting data, and specifying accuracy and precision.

18.01.2019 DR. NERMIN SÖKMEN 5

THE FATHER OF STATISTICAL QUALITY CONTROL

➢ Shewhart defined "common

causes", "special causes" and
Shewhart charts or control charts.
➢recommended 3 standard deviation
limits above and below the mean
value of the variable.
➢created the Shewhart Cycle or
PLAN, DO and SEE cycle.

18.01.2019 DR. NERMIN SÖKMEN 6

THE FATHER OF STATISTICAL QUALITY CONTROL

➢Shewhart’s methods influenced other statisticians like W. Edwards Deming,

Joseph Juran and Eugene Grant.
➢Walter A. Shewhart and William E. Deming published «Statistical Method from the
Viewpoint of Quality Control» in 1939.
➢ Joseph Juran published Quality Control Handbook in 1951.
➢ ‘Managing for quality makes extensive use of three such managerial processes: Quality
planning, Quality control and Quality improvement.’
➢These processes are now known as the “Juran trilogy.”
➢Juran descriped process improvement and statistical process control with using
Shewhart’s control charts.

18.01.2019 DR. NERMIN SÖKMEN 7

THE FATHER OF STATISTICAL QUALITY CONTROL

➢ Eugene Grant- founder of the fields of engineering economics, industrial

engineering, and statistical quality control (SQC).
➢He was also one of the founding fathers of the American Society for Quality
(ASQ) in 1946.
➢Grant’s work on statistical quality control was used in training programs to
improve quality and production in World War II industrial plants.
➢Grant studied the principles and concepts surrounding what came to be
known as QA.
➢Grant’s teaching of SQC during World War II, on behalf of War Production
Board, contributed greatly to the growth and spread of quality.

18.01.2019 DR. NERMIN SÖKMEN 8

 Without data, you're just another person with an opinion.

Xbar chart
STASTICAL CONTROL CHARTS Xbar-R chart Xbar-S chart
R chart S chart

GENERAL DESCRIPTION I-MR chart

I chart MR chart

18.01.2019 DR. NERMIN SÖKMEN 9

WHAT IS CONTROL CHART?

➢A control chart illustrates process behaviors by detecting changes in a process

output’s mean and/or standard deviation about the mean.
➢Every process exhibits some normal levels of variation, but a control chart is
designed to separate this normal or common cause variation from special cause
variations.
➢Control charts indicate visually whether a process is in-control (stable and
predictable), or if it is out of control (unstable and unpredictable).
➢When the control chart indicates the process is out of control, an operator
should take action to make adjustments to bring the process back under control
or initiate an investigation into the root cause.

18.01.2019 DR. NERMIN SÖKMEN 10

WHAT IS CONTROL CHART?
➢ Common causes- problems inherent in
the manufacturing system as a whole.
❖ Phenomena constantly active within
the system
❖ Inadequate product design,
❖ Inherited defective material, and
❖ Excessive humidity.
➢Special causes (assignable causes)-
local, sporadic problems
❖ New, unanticipated, emergent or
previously neglected phenomena within
the system
❖ The failure of a particular machine or
❖ A mistakenly recorded measurement.

18.01.2019 DR. NERMIN SÖKMEN 11

CHARACTERISTICS OF SHEWHART CHARTS

➢ The vertical axis of a Shewhart chart is

scaled in the same units as the summary
statistic.
➢ The horizontal axis of a Shewhart chart
identifies the subgroup samples.
➢Frequently, the samples are indexed
according to the order in which they were
taken or the time at which they were taken.
➢The central line on a Shewhart chart
indicates the average (expected value) of
the summary statistic when the process is in
statistical control.

18.01.2019 DR. NERMIN SÖKMEN 12

CHARACTERISTICS OF SHEWHART CHARTS
➢ The upper and lower control limits, labeled
UCL and LCL, respectively, indicate the range of
variation to be expected in the summary statistic
when the process is in statistical control.
➢ The control limits are commonly computed as
3σ limits representing three standard errors of
variation in the summary statistic above and
below the central line.
➢ A point outside the control limits signals the
presence of a special cause of variation.
➢ When the Shewhart chart correctly signals the
presence of a special cause, additional action is
needed to determine the nature of the problem
and eliminate it.

18.01.2019 DR. NERMIN SÖKMEN 13

CONTROL CHART RULES AND INTERPRETATION

18.01.2019 DR. NERMIN SÖKMEN 14

 CLASSIFICATION OF SHEWHART CHARTS

➢ Shewhart charts are broadly

classified according to the type of
data analyzed.
➢ Shewhart charts for variables are
used when the quality characteristic
of a process is measured on a
continuous scale.

18.01.2019 DR. NERMIN SÖKMEN 15

 CLASSIFICATION OF SHEWHART CHARTS

➢ Shewhart charts for attributes are

used when the quality characteristic
of a process is measured by
counting
❖ the number of nonconformities
(defects) in an item or
❖ the number of nonconforming
(defective) items in a sample.

18.01.2019 DR. NERMIN SÖKMEN 16

CLASSIFICATION OF SHEWHART CHARTS

➢ Shewhart charts for variables are classified according to the

subgroup summary statistic plotted on the chart.
❖ Charts for individual measurements and moving ranges display
individual measurements and moving ranges of two of more successive
measurements. In this case the subgroup sample consists of a single
observation.
❖ Median and range charts display subgroup medians and ranges.
Typically the two charts are presented on the same page, with the
median chart aligned above the R chart.

18.01.2019 DR. NERMIN SÖKMEN 17

CLASSIFICATION OF SHEWHART CHARTS

➢When the sample size is 1<n≤10, the chart to use is

❖X and R charts display subgroup means (averages) and ranges. Typically
the two charts are presented on the same page, with the X chart aligned
above the R chart to facilitate the simultaneous analysis of the central
tendency and variability of the process.
➢ When the sample size is 10<n, the chart to use is
❖X and s charts display subgroup means (averages) and standard deviations.
Typically the two charts are presented on the same page, with the X chart
aligned above the s chart.

18.01.2019 DR. NERMIN SÖKMEN 18

CLASSIFICATION OF SHEWHART CHARTS

➢ Shewhart charts for attributes are classified according to the subgroup

summary statistic plotted on the chart:
❖ A p chart displays the proportion of nonconforming (defective) items in a
subgroup sample.
❖ An np chart displays the number of nonconforming (defective) items in a
subgroup sample.
❖ A u chart displays the number of nonconformities (defects) per unit in a
subgroup sample consisting of an arbitrary number of units.
❖ A c chart displays the number of nonconformities (defects) in a unit (here, a
subgroup sample typically consists of one unit).

18.01.2019 DR. NERMIN SÖKMEN 19

 If you can't describe what you are doing as a process,
you don't know what you're doing.

STASTICAL CONTROL CHARTS Variables control charts

and
WITH EXAMPLES Attributes control charts
18.01.2019 DR. NERMIN SÖKMEN 20
 Individual Measurements
and Moving Range Charts
VARIABLES CONTROL CHARTS? Xbar-R Control Charts
Xbar-S Control Charts
18.01.2019 DR. NERMIN SÖKMEN 21
INDIVIDUAL MEASUREMENTS AND MOVING RANGE
CHARTS (I-MR)
➢Measurements may be too
expensive.
➢Production volumes may be too low.
➢Products may have a long cycle time.
Where production is slow so that
waiting for enough samples to make a
rational subgroup unacceptably
delays monitoring
➢For processes that produce
homogeneous batches (e.g., chemical)
where repeat measurements vary
primarily because of measurement
error.
➢Individual chart helps assess process
center.
➢Moving range plots process
variation.

18.01.2019 DR. NERMIN SÖKMEN 22

INDIVIDUAL MEASUREMENTS AND MOVING RANGE
CHARTS (I-MR)
➢ Calculation of moving range:
1. The difference between data point, and its predecessor, is calculated. For n
individual values, there are n-1 ranges.

2. The arithmetic mean of these values is calculated as

18.01.2019 DR. NERMIN SÖKMEN 23

INDIVIDUAL MEASUREMENTS AND MOVING RANGE
CHARTS (I-MR)
➢ Calculation of moving range control limit:
1. The upper control limit for the range (or upper range limit) is calculated by

D4 = 3.267 is taken from the sample size-specific D4 anti-biasing constant for

n=2.

2. The lower control limit for the range is calculated by

D3 = 0

18.01.2019 DR. NERMIN SÖKMEN 24

INDIVIDUAL MEASUREMENTS AND MOVING RANGE
CHARTS (I-MR)

18.01.2019 DR. NERMIN SÖKMEN 25

INDIVIDUAL MEASUREMENTS AND MOVING RANGE
CHARTS (I-MR)
➢ Example:
An aeronautics company
manufacturing jet engines
measures the inner diameter of the
forward face of each engine (in
centimeters). The following
statements create a data set that
contains the diameter
measurements for 20 engines.

18.01.2019 DR. NERMIN SÖKMEN 26

INDIVIDUAL MEASUREMENTS AND MOVING RANGE
CHARTS (I-MR)
➢ Individual Measurements
and Moving Range Charts
The charts indicate that the
process is in control, because
all the points lie within the
control limits.

18.01.2019 DR. NERMIN SÖKMEN 27

 X-BAR CONTROL CHARTS

➢X-bar charts are used to monitor the

mean of a process based on samples
taken from the process at given times
(hours, shifts, days, weeks, months, etc.)
➢An initial series of subgroups is used to
estimate the mean of a process.
➢The mean is then used to produce control
limits for the mean of each subgroup.

18.01.2019 DR. NERMIN SÖKMEN 28

R CONTROL CHARTS

➢ R charts are used to monitor the

variation of a process based on
samples taken from the process at
given times (hours, shifts, days,
weeks, months, etc.).
➢ The measurements of the samples
at a given time constitute a
subgroup.

18.01.2019 DR. NERMIN SÖKMEN 29

 XBAR-R CONTROL CHARTS

• Create an inspection lot (k), select samples (n) less than 10 from each lot, and measure the
Select data:
quality characteristic value

Calculate • Calculate the average value x, and range R of each log

average value
x, and range R

• Calculate control limit including center line (CL), upper control limit (UCL), lower control limit
Calculate (LCL) by using the control limit factor of x-R Chart
control limit

• When all points of each lot are within the control limit line, the manufacturing process is thought to maintain in
the state of statistical control, while when any point is out of the control limit line, some failure is determined to
Utilize the occur, and so the cause should be examined and some measures should be taken.
x-R Chart

18.01.2019 DR. NERMIN SÖKMEN 30

XBAR-R CONTROL CHARTS

➢Xbar-R charts are often used collectively to plot the process

mean (Xbar) and process range (R) over time for continuous data.
➢Xbar-R statement creates average X and R charts for subgroup
means and ranges, which are used to analyze the central tendency
and variability of a process.
➢The R chart is used to review the process variation which must be
in control to correctly interpret the Xbar chart.

18.01.2019 DR. NERMIN SÖKMEN 31

XBAR-R CONTROL CHARTS

➢ Calculation of X-bar Chart:

❖Suppose we have k subgroups, each of size n. The i subgroup mean is
calculated using

❖ The subgroup range is calculated with

➢Estimating the X-bar Chart Center Line (Grand Mean) :

18.01.2019 DR. NERMIN SÖKMEN 32

XBAR-R CONTROL CHARTS

➢ X-bar Chart Limits : The lower and upper control limits for the X-bar chart are
calculated using the formulas

➢Estimating the R Chart Center Line:

➢R Chart Limits : The lower and upper control limits for the range chart are
calculated using the formulas

DR. NERMIN SÖKMEN

18.01.2019 33
XBAR-R CONTROL CHARTS- EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 34

XBAR-R CONTROL CHARTS- EXAMPLE
The Xbar chart The R chart below
appears to be in shows an out of
control. control process.

18.01.2019 DR. NERMIN SÖKMEN 35

XBAR-S CONTROL CHARTS

➢ The X-bar and s charts are very

similar to the popular X-bar and R
charts.
➢The difference being that the
standard deviation is estimated from
the mean standard deviation in the
former, and from the mean range in
the latter.
➢X-bar and s charts are generally
recommended over the X-bar and R
charts when the subgroup sample size
is moderately large (n > 10).

18.01.2019 DR. NERMIN SÖKMEN 36

XBAR-S CONTROL CHARTS

➢ Calculation of X-bar Chart:

❖Suppose we have k subgroups, each of size n. The i subgroup mean is
calculated using

❖ The subgroup standard deviation is calculated with

➢ Estimating the X-bar Chart Center Line (Grand Mean) :

18.01.2019 DR. NERMIN SÖKMEN 37

XBAR-S CONTROL CHARTS

➢ Estimating Sigma – Mean of Standard Deviations:

❖The true standard deviation (sigma) may be input directly,
or it may be estimated from the standard deviations by

➢X-bar Chart Limits:

➢s Chart Limits:

18.01.2019 DR. NERMIN SÖKMEN 38

 C-Charts, NP- Charts,
ATTRIBUTES CONTROL CHARTS? P-Charts and U- Charts

18.01.2019 DR. NERMIN SÖKMEN 39

ATTRIBUTES CONTROL CHARTS

➢ Discrete data, also sometimes called attribute data, provides a count of how
many times something specific occurred, or of how many times something fit in
a certain category.
➢ The number of complaints received from customers
➢ The proportion of technical support calls due to installation problems
➢ The total number of defectives in the output of a process
➢ The number of defects per unit for process output

18.01.2019 DR. NERMIN SÖKMEN 40

P AND NP CHARTS

➢ p-Chart: for monitoring the percent of samples having the condition, relative
to either a fixed or varying sample size, when each sample can either have
this condition, or not have this condition.
➢ p- percentage of defectives
➢ Np-Chart: for monitoring the number of times a condition occurs, relative to
a constant sample size, when each sample can either have this condition, or not
have this condition.
➢ np- number of defectives.

18.01.2019 DR. NERMIN SÖKMEN 41

P AND NP CHARTS

➢ P Chart Calculations:
❖ The percent of items in the sample meeting the criteria of interest:
where nj is the sample size (number of units) of group j.

❖ Center Line:

❖ UCL , LCL (Upper and Lower Control Limit):

18.01.2019 DR. NERMIN SÖKMEN 42

P AND NP CHARTS

➢ np Chart Calculations:
❖ The number of items in a sample meeting a criteria of interest
❖ Center Line:

❖ UCL , LCL (Upper and Lower Control Limit):

18.01.2019 DR. NERMIN SÖKMEN 43

P AND NP CHARTS- P CHART EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 44

P AND NP CHARTS- P CHART EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 45

P AND NP CHARTS – NP CHART EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 46

P AND NP CHARTS – NP CHART EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 47

C AND U CHARTS

➢ C charts are used to monitor the number of nonconformities on a unit of a

process based on units taken from the process at given times (hours, shifts,
days, weeks, months, etc.).
➢The C chart is used when a single unit will be examined for nonconformities at
each time point.
➢ C Chart Formulas: Suppose we have sampled k units, one at each time
period. Let Di represent the number of nonconformities of the i. Unit.

➢ The center line (average number of nonconformities):

➢The lower and upper control limits for the C chart:

18.01.2019 DR. NERMIN SÖKMEN 48

C AND U CHARTS- C CHART EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 49

C AND U CHARTS- C CHART EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 50

C AND U CHARTS

➢A u-chart is an attributes control chart used with data collected in subgroups of

varying sizes.
➢U-charts show how the process, measured by the number of nonconformities per item
or group of items, changes over time.
➢Nonconformities are defects or occurrences found in the sampled subgroup.
➢The ith per unit number of nonconformities ui is calculated using

18.01.2019 DR. NERMIN SÖKMEN 51

C AND U CHARTS

➢ The formula for the centerline proportion

➢ The lower and upper control limits for the U chart are calculated using the formulas

18.01.2019 DR. NERMIN SÖKMEN 52

C AND U CHARTS- U CHART EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 53

C AND U CHARTS- U CHART EXAMPLE

18.01.2019 DR. NERMIN SÖKMEN 54

REFERENCES

1. Deming, W. E. (1982). Out of the Crisis. Cambridge, MA: Center for

Advanced Engineering Study, Massachusetts Institute of Technology.
2. Juran, J. and Godfrey, A. B. (1998). Juran's Quality Handbook 5th Edition.
McGraw-Hill.
3. NCSS Statistical Software (2012). Quality Control,
[Link]
4. Montgomery, D. C. (2009). Introduction to Statistical Quality Control, Arizona
State University.
5. SAS Institute Inc (2015). SAS/QC® 14.1 User’s Guide The SHEWHART
Procedure , SAS Campus Drive, Cary, NC 27513-2414.
6. Western Electric (1985). Statistical Quality Control Handbook: Second Edition
Hardcover – 1982

DR. NERMIN SÖKMEN

18.01.2019 55
 Thank you
very much
Without data, you're
just another person
with an opinion.

DR. NERMIN SÖKMEN

18.01.2019 56
View publication stats