QC TOOLS

Pareto
chart

Cause-effect diagram

7 TOOLS OF QUALITY
For
PROCESS IMPROVEMENTS

"As much as 95% of quality related problems in the

factory can be solved with seven fundamental
quantitative tools." Kaoru Ishikawa

FLOW CHART

7 QC TOOLS
The 7 QC Tools are: Flow chart
Check sheet
Histogram
Pareto Diagram

Cause & Effect

Scatter diagram
Control charts

FLOW CHARTS
What is a Flow chart ?
A diagram that uses graphic symbols to depict the
nature and flow of the steps in a process.
What is a Flow chart ?
Graphical representations of a process.

Sequential flow of processes & sub-process.

Process steps shown with symbolic shapes.

Process flow indicated by arrows & symbols.

FLOW CHARTS
When to use Flow Charts ?
To determine how a process currently functions.
To determine how a process could ideally function.

FLOW CHARTS
Basic flow chart with their operation symbols

Flow chart

FLOW CHARTS
Real world usage of Flow charts
Production
Manufacturing
To identify critical path
Accounting
Helps visualising money flow
Services
Restaurants

Real estate
7

FLOW CHARTS
Benefits of Flow Charts
Create Visual map of process.
Identify process that need improvement.

Determine major & minor inputs in the process.

Promotes process understanding.
Depicts customer - supplier relationship.

CHECK SHEET
What is a Check sheet ?
A check sheet is a paper form on which items to be checked
have been printed already so that data can be collected
easily & concisely.
A graphical presentation of information.
Data gathering & interpretation tool.
Simplest way to assess common problems.

CHECK SHEET
When to use a Check sheet ?
To distinguish between fact & opinion.
To gather data about how often a problem occurs.
To gather data about the type of problem.

10

Check sheet types

CHECK SHEET
How to create a Check sheet ?
What is the Problem?
Why should data be collected?
Who will use the information being collected?
Who will collect the data?

12

CHECK SHEET
SAMPLE CHECK SHEET
Total

20
10
5
3
15

13

CHECK SHEET
Cause

Counts

Total

Layer falling

11

Edge crack

Poor cutting

High thickness

Diagonality

Layer snatch

Table.1. Check sheet for flat boards

CHECK SHEET
SAMPLE CHECK SHEET

15

HISTOGRAM

16

HISTOGRAM
When to use a Histogram ?
To summarize large data sets graphically.
To compare measurements to specifications.
To communicate information to the team.
Assist in decision making.

17

How to construct a histogram

How to construct a histogram

How to construct a histogram

30

20
15
10

Interval

So, this graph follows normal distribution of data.

360-420

300-360

240-300

180-240

120-180

60-120

00-60

(-60)-(00)

(-120)-(-60)

(-180)-(120)

No. of counts

25

INTERPRETING HISTOGRAM

21

INTERPRETING HISTOGRAM
Common Histogram Shapes

Skewed (Not symmetrical)

Discontinued

Symmetrical (Mirror imaged)

22

INTERPRETING HISTOGRAM
The freq. is highest in the
middle and becomes gradually
lower towards the ends.This is
the shape w/c occurs most
often.

The skewed distribution is

asymmetrical because a nature limit
prevents outcomes of one side.(i.e
holes diameter cannot be smaller
than the dia. Of drill bit.) The
distributions peak is off-center
toward the limit & a tail stretches
away from it.

The dog food distribution is missing

something results near the average.If
a customer recieves this kind of
distribution, someone else is
receiving a heart cut, & the customer
is left with the dog food the odds &
end left after the master meal.
This variation often causes problems
in the customers process.

It might be called as Multimodal

distribution . Several process
with normal distributions are
combined because there are
many peaks close together, the
top of the distribution resembles
a plateau.

It looks like normal distribution with

the tails cut-off . The supplier might be
producing a normal distribution of
material & then relying on the
inspection to seprate what is within
specification limit from what is out of
specification.

This shape occurs when the no.

of units of the data included in
the class varies from class to
class or when there is a
particular tendency in the way
data is rounded off.

23

HISTOGRAM
Benefits of Histogram
To know whether process produces within specification.
To know whether process is stable & predictable.
Process monitoring & centering.

24

PARETO DIAGRAM
What is a Pareto Diagram ?
Shows focus area to get most gains.
Bar chart arranged in descending order of height.

Bars on left; relatively important than those in right.

Separates Vital few from Trivial many.
Pareto
principle

80 % of trouble comes from 20 % of the problems.

Named after Italian Economist Wilfredo Pareto.

25

PARETO DIAGRAM
When to use a Pareto Diagram ?
Starter to Problem solving - What to solve?
To break big problems into smaller problems.
To prioritize high impact issues - Where to focus?
Systematic analysis of causes based on magnitude.
Allows better use of limited resources.

26

PARETO DIAGRAM
Benefits of Pareto Diagram
Identifies Major Few problems.
Improves team performance & effectiveness.
Before & After tracking of a problem in single chart.

27

PARETO DIAGRAM
Constructing a Pareto Diagram
Step 1: Record the data
Step 2: Order the data
Step 3: Label the vertical axis
Step 4: Label the Horizontal axis

1
2

Step 5: Plot the Bars

Step 6: Add up the counts
Step 7: Add a cumulative/secondary line

3
4

Step 8: Add title, Legend and Date

Step 9: Analyze the Diagram

Step 10: Interpret the results

28

PARETO DIAGRAM
A SAMPLE PARETO CHART

29

PARETO DIAGRAM
20

Manpower
problem

Template
sticking

Layer falling

11

De-lamination

Bole sticking

21

Operation fault

TOTAL

55

15
10

96%

98%

58%
38%

11

7
5

Bole sticking

Frequency

% Cumm. Freq.

Sieve replacement problem

Delamination

Sieve
replacement
problem

80%

93%

71%

Waste on bole

Layer falling

Felt problem

87%

Operation fault

21

100%

Manpower problem

25

Felt problem

Waste on bole

Frequency

Template sticking

Problems

Fig.1. Pareto chart for fiber cemented sheets mfg. industry.

120%
100%
80%
60%
40%
20%
0%

PARETO DIAGRAM
Pareto Analysis of Injury by Dept.
100

400
300

60
200

40

100

Department

N
-1
-2
-1
-2
O
I
E
E
C
C
NS
NS
AT
N
N
O
O
R
I
I
T
T
NA
NA
ST
E
E
A
A
I
R
R
N
I
NT
NT
M
EA
EA
AI
AI
P
P
D
M
M
O
O
A
Count
128
102
82
76
20
Percent
30.2
24.1
19.3
17.9
4.7
Cum %
30.2
54.2
73.6
91.5
96.2

Percent

Accident No.

80

20

er
h
Ot

16
3.8
100.0

31

CAUSE & EFFECT DIAGRAM

What is a Cause & Effect Diagram ?
A graphical tool which shows the relation between a quality characteristic(or
problem) and the factors(causes) which effects quality characteristics.
About Cause & Effect Diagram ?
Developed by Kaoru Ishikawa of Japan.
Also called, Ishikawa or Fish bone diagram.
Used to explore potential & real causes.
Compares relative importance of each cause.

Helps to identify root cause.

32

Cause-and-effect Diagram

How to make Cause-and-effect diagram

34

Cause-and-effect diagram

Cause-and-effect diagram

Cause-and-effect diagram
Benefits of Using a Cause-and-Effect Diagram
Helps determine root causes
Encourages group participation
Uses an orderly, easy-to-read format

Indicates possible causes of variation

Increases process knowledge
Identifies areas for collecting data
37

SCATTER DIAGRAM
What is a Scatter Diagram ?
To study the relation of two variables such as speed of the lathe &
dimension of a part , or concentration & specific gravity, you can use what

is called a scatter diagram.

A visual & statistical testing tool.

Analyzes strength & relationship between 2 variables.
Involve correlation to establish significant relationship.
Arrive at Quantitative conclusion on relationship.
38

SCATTER DIAGRAM
When to use a Scatter Diagram ?
In problem solving to establish a root cause.
Examine root cause theories in C & E.
To confirm a Hypothesis.

39

Scatter diagram
How to make scatter diagram
Step1: collect paired data(x, y), between which you want to study the relations,arrange
the data in a table. It is desirable to have at least 30 pairs of data.
Step2: Find the maximum & minimum values for x and y. Decide the scales of horizontal
and vertical axes so that the both lengths become approximately equal,then the
diagram will be easier to read.
Step3: Plot the data.
Step4: Enter all necessary items to make the diagram easy to understand at a glance:
a). Title of the diagram.
b). Time interval.
c). No. of pairs of data.
d). Title & units of each axis.
e). Name of the person who made the diagram.

SCATTER DIAGRAM
INTERPRETATION OF SCATTER DIAGRAM

Positive Correlation

Negative Correlation

Strong positive Correlation

No Correlation

Weak negative Correlation

41

Scatter diagram
Data of blowing air-pressure & percent defective of plastic
tank

2
3
4
5
8
9
10
11
12
15
16
17
18
19
22
23
24
25
26
29
30
31
Nov.1
2
5
6
7
8
9

8.9
8.8
8.8
8.4
8.7
9.2
8.6
9.2
8.7
8.4
8.2
9.2
8.7
9.4
8.7
8.5
9.2
8.5
8.3
8.7
9.3
8.9
8.9
8.3
8.7
8.9
8.7
9.1
8.7

0.94

0.889
0.884
0.874
0.891
0.874
0.886
0.911
0.912
0.895
0.896
0.894
0.864
0.922
0.909
0.905
0.892
0.877
0.885
0.866
0.896
0.896
0.928
0.886
0.908
0.881
0.882
0.904
0.912
0.925
0.872

0.93

Percent defective(%)

0.92

y = 0.031x + 0.615
0.91

% defective

Date Air pressure(kgf/cm2)

oct.1
8.6

Percent
defective(%)

0.9
0.89
0.88
0.87
0.86
0.85
7.9

8.1

8.3

8.5

8.7

8.9

9.1

9.3

Air pressure(kgf/cm2)

This graph shows positive co-relation.

9.5

Scatter diagram
Calculation of corelation coefficient(r)
To study the relation of x and y, it is important to first draw a scatter diagram;however in order to
understand the strength of the relation in quantitative terms,it is useful to calculate the
corelation coefficient according to following definition:

S(XY)

r=

S(XX) .S(YY)

n is the number of pair of data.

The corelation coefficient, r, is in
the range -1r1.

Where,

S(xx) =

(Xi X) = Xi

i=1

( Xi )
i=1

i=1

S(yy) =

(Yi Y) = Yi

( Yi )

i=1

i=1

S(xy) =

(Xi -X)(Yi Y) =

i=1

Xi Yi
i=1

i=1

i=1

( Xi) . ( Yi)

SCATTER DIAGRAM
SCATTER PLOT STATISTICS:
For scatter plots, the following statistics are calculated:
Mean X and Y

Average of all the data points.

Maximum X and Y

Maximum value in the series.

Minimum X and Y

Minimum value in the series.

Sample Size

Number of values in the series.

X Range and Y Range

Maximum value - minimum value.

Stdev of X and Y values

Indicates spread of data around the mean.

Line of Best Fit - Slope

Slope of the line

Line of Best Fit - Y Intercept

Point at which line of best fit crosses Y axis

44

SCATTER DIAGRAM
INTERPRETATION OF SCATTER DIAGRAM
Strong correlation

r-value range of between 0.85 to 1, or -0.85 to -1.

Moderate correlation
r-value ranges from 0.75 to 0.85 or, -0.75 to -0.85.
Weak correlation
r ranges from 0.60 to 0.74 or -0.60 to 0.74.

Though an entirely random relationship equals, 0.00,

r-value that is 0.59 and below is not considered to be a reliable predictor.
(Tan 45 degree = 1)

45

SCATTER DIAGRAM
Benefits of Scatter Diagram
Trends & patterns of different measures are tracked.
Better process management in variable analysis.
Relationship establishment tool.

46

CONTROL CHARTS
What is a Control chart ?
It is a graphical representation of quality charateristics(i.e problem) and indicates
whether the process is under control or not. These charts are based on the fact
that variability exists in all the process.

Statistical tool for monitoring & improving quality.

Distinguishes between Common & Special cause.
Measure consistency of a machine or process.

UCL
X
LCL
47

CONTROL CHARTS
When to use a Control chart ?
Visual display for Process output.
To monitor, control & improve process performance.
To identify variation at its source.

48

Types of Control Charts

Control chart for variables are used to monitor
characteristics that can be measured, e.g.
length, weight, diameter, time, etc.
Types:- X-bar chart, R-chart
Control charts for attributes are used to monitor
characteristics that have discrete values and can be
counted, e.g. % defective, number of flaws in a
shirt, number of broken eggs in a box, etc.
Types:- P chart (fraction defective, sub-group size is varying)
nP chart (number of defective units, Sub-group size is constant)
C chart (number of defects, sub-group size is constant)

X-Bar Charts
X-bar charts are used for testing stability of the mean operation

calculate averages from samples of size n taken at each time step

centre-line - determined from either

target or specification value
average of sample averages for data set collected when process was
operating normally

1 N X
N j 1 j

Control Limits - determined using the average range during normal

operation, which is a reflection of usual process variability
=
So,

centre line

Control limit =

3R
d2 n

i.e

centre line A2 R with A2

See Value of A2 from the table

R
d2

3
d2 n

R-Charts
Monitor range to determine whether variability is stable..
calculate range at regular intervals from samples of n elements
plot on chart with centre line and control limits
N
centre line:1
R
Rj
N j 1
control chart limits:

UCL = D4R
LCL = D3R

These limits are at the 99.7% confidence level (3-sigma limits for range)
D3 and D4 values are:-

Note:
D3 = 0, If n<7

Size of
subgroup

X Chart

R Chart

A2

D3

D4

d2

1.880

3.267

1.128

1.023

2.575

1.693

0.729

2.282

2.059

0.577

2.115

2.326

0.483

2.004

2.534

51

Control chart for variables

The data used in the control charts we will discuss (X bar and R Charts) are
samples of a population
From Gillette example 15 hours become 15 subgroups representing the total
population of razor blades and each subgroup will have 5 data values n = 5.
5 meausrement for each subgroup

Subgroups

Data with Calculated figures

Finished Control Charts

Control limits = 0.062541(0.577*0.000307)
=0.062541 0.000177139

UCLX = 0.062718
LCLX = 0.062363

Control limits:UCLR = D4R

= 2.115* 0.000307
= 0.000649305
LCLR = D3R =0, Not specified
for (n=5)

Control Charts for Attributes P-Charts & C-Charts

Use P-Charts for quality characteristics that are

discrete and involve yes/no or good/bad decisions
Percent of leaking caulking tubes in a box of 48
Percent of broken eggs in a carton

Use C-Charts for discrete defects when there can be

more than one defect per unit
Number of flaws or stains in a carpet sample cut from a
production run
Number of complaints per customer at a hotel

Constructing a P-Chart:

Q-A Production manager for a tire company has inspected

the number of defective tires in five random samples
with 20 tires in each sample. The table below shows the
number of defective tires in each sample of 20 tires.

Sample

Sample
Size (n)

Number
Defective

20

20

20

20

20

Step 1:
Calculate the Percent defective of Each Sample and the Overall % Defective (P-Bar)

Sample

Number
Defective

Sample
Size

Percent
Defective

20

.15

20

.10

20

.05

20

.10

20

.05

Total

100

.09

Step 2: Calculate the Standard Deviation of P.

p(1-p) (.09)(.91)
p =
=
=0.064
n
20

Center line (p bar):

p = No.of defectives
n

= 9/100 = 0.09

Control limits for 3 limits:

UCL

z p

.09

3(.064)

LCL

z p

.09

3(.064)

.282
.102

Step 4: Draw the Chart

Constructing a C-Chart:

The number of weekly

customer complaints are
monitored in a large
hotel. Develop a three
sigma control limits For
a C-Chart using the data
table On the right.

Week

Number of
Complaints

10

Total

22

Calculate CL, UCL, LCL

Center line (c bar):

CL

#complaints
# of samples

22
10

2.2

Control limits for 3 limits:

UCL

z c

2.2

3 2.2

LCL

z c

2.2

3 2.2

6.65
2.25

Significance of Green/yellow/Red Zone

RED ZONE Process to be stopped

Green Zone- Process running Stable

YELLOW ZONE Warning Zone

Process Improvement using Control Chart

Control Chart Analysis

To analyze the control charts it is important to remember that the data is

represented over six standard deviations, there are three standard deviations
from the mean line to the upper control limit and three from the mean to the
lower control limit. To help analyze the charts:it is important to divide the chart area into six sections A, B, and C
representing the standard deviations.

Control charts analysis

Q - How do you know a process is out of control?
A When the data arent normal
Out of Control cues include
- Points outside of control limits ( 3)
- 8 consecutive points on one side of center line
- 2 of 3 consecutive points outside the 2 limits
- 4 of 5 points outside the 1 limits
- 7 consecutive points trending up or down

Process out of Control

1.

If one point falls outside of the 3 sigma

control limits (beyond zone A)

Process out of Control

2. If two out of any three successive points
fall in zone A of the same side

Process out of Control

3. If four out of any five successive points fall
in or beyond zone B of the same side

Process out of Control

4. If eight successive points fall in or beyond
zone C of the same side

Thank you.