7 QC Tools
7 QC Tools
1
1. What are 7 QC Tools ?
2. Why 7 QC Tools?
3. 7 QC Tools
3.1 Check sheet
3.2 Pareto Chart
3.3 Cause and Effect Diagram
3.4 Histogram
3.5 Graph
3.6 Control Chart
3.7 Scatter Chart
4. Where to use 7 QC tools in the QC Story?
2
1. What are 7 QC Tools ?
(A) (B)
Check sheet Check sheet
Pareto chart Pareto chart
Cause and effect Cause and effect
diagram diagram
Histogram Histogram
Scatter chart Scatter chart
Stratification Graph
Control chart Control chart
3
The 7 QC tools are simple statistical tools
used for problem solving.
4
Various Qualities
5
Product quality at Various Stages
6
1)They are easy to use. They can be
mastered in a few hours of study.
“Simple is beautiful”.
2)They are easy to understand.
3)They can be used by everybody working
together.
4)95% of problems encountered in work
places can be solved with these 7 tools.
7
3. 7 QC tools
8
A check sheet is a paper form specially
prepared to enable data to be collected and
analyzed simply by making check marks or
simple symbols.
Itis used for tallying the occurrences of the
defects or causes being addressed and
graphing or charting them directly.
It is a powerful data recording tool.
9
Datais a guide for our actions. From data
we learn pertinent facts, and take
appropriate actions based on such facts.
Determine what you are going to do with
the data before collecting.
Eg. In quality control, objectives of
collecting data are
1) Controlling and monitoring of the
production process,
2) Analysis of the non-conformance
or inspection
10
Collect data that suites the purpose
Ensure reliability of measurements
The origin of the data must be clearly recorded.
an easy-to-use form.
A set of standard recording forms should be
11
To make data-gathering easy
12
Main Use of Check Sheet cont….
1) Survey on ・ When many defectives occur, use it to know
defective item and what kind of defectives are many.
factor
13
There are different types of check sheets.
Eg.1 Check sheet for production process
distribution
Eg.2 Defective item check sheet
Eg.3 Defect location check sheet
Eg. 4 Defect cause check sheet
14
To know the variation in the dimensions of a kind
of parts whose machining specification is
8.3+0.008.
Deviation*1000 Checks Frequency
-10 5 10 15
20
-9
Specification -8
-7
-6
-5 X 1
-4 X X 2
-3 X X X X 4
-2 X X X X X X 6
-1 X X X X X X X X X 9
8.3 0 X X X X X X X X X X X 11
1 X X X X X X X X 8
2 X X X X X X X 7
3 X X X 3
4 X X 2
5 X 1
6 X 1
7
Specification 8
9
10
Total 55
15
A Defective Item Check Sheet counts and
classifies defects by type, as below.
Final inspection process of a certain moulded
plastic product.
Type Check Subtotal
Total reject ///// ///// //// ///// //// ///// /////// ///// 62
//////
16
It uses a picture of the item to mark defect
positions, as below. Problem areas are
usually indicated by clustering of marks.
17
It aims to correlate cause and effect, by
stratifying causal factors, such as time of
day, operator, machine and location.
Example
Below table indicates an example of the
defect occurrence rate of plastic switching
buttons.
18
Eg 4. Defect cause check sheet Cont…
19
Eg 4. Defect cause check sheet Cont…
20
3.2 Pareto Chart
21
First developed in 1906, by Italian
economist, Vilfredo Pareto, who observed
unequal distribution of wealth and power.
Most of it in a relatively small proportion
of the total population.
22
It is used to classify problems, show their
frequency and set their priority (which of many
problems have the most serious effect or greatest
cumulative effect on quality, productivity, cost,
safety, etc.
23
The Pareto Principle states that only a "vital
few“ (20%) causes are responsible for
producing most (80%) of the problems.
500 60%
50%
400
40%
300
30%
200
20%
100
10%
0 0%
Spot Burr Crack Shape Others
change
25
Uses of Pareto Chart
26
Form a table listing the causes/problems
and their frequency as a percentage.
27
Plot a bar graph with causes on x-axis and percent
frequency or frequency on y-axis(Left side).
28
29
30
31
32
33
34
35
36
37
Type of Frequency In Percent Computing Cumulative
Defect Cumulative Percentage
Percentage
40
It arranges the relationship between
problems & their causes in a fish-bone
style (also called fish-bone diagram ).
It is sometimes called Ishikawa Diagram
because it was invented by Dr.Karou
Ishikawa.
Its main use is to pick up and arrange all
possible causes without any omissions.
It allows many factors to be seen at the
same time, and can be used by everyone
from beginners to experienced workers.
41
Constructing a fish bone diagram can help
when a team needs to:
Identify the possible root cause for a
42
Helps to determine root causes.
Encourage group participation.
Uses an orderly, easy-to-read format.
Increases process knowledge.
43
44
45
Step 1- Identify and define the effect
Step 2- Draw the spine and the effect box
Step-3- Identify the main causes (the major branches).
46
Effect Items
Effect items Contents
・ Low Production output ・ Low Efficiency ・ Availability ratio ・
Productivity Yield ratio
Delivery
・ Long Lead time ・ Delay ・ Longer inspection time
Time
Number of accident, High fatigue, Risky work environment
Safety
・ Number of near-accidents
47
Step 4 - Identify many causes (sub
branches). You can do this by asking a
serious of “Why” questions
If a minor cause applies to more than one
major cause, list it under both.
48
Causes
Major factor Sub-Causes
49
Don’t criticize other people’s ideas.
Build on other people’s ideas.
The more creative ideas the better.
Speak freely, there are no dumb
ideas.
50
Cause and Effect diagram cont…
Factor
Major factor Major factor
Factor
Problem/ Effect
item
Cause Problem
Countermeasure Objective
51
Volume of glue
Man Material
Expired glue
Knowledge
Kinds of glue
Weak pressing
20
15
F re q u e n c y
10
0
78 78.2 78.7 79.2 79.7 80.2 80.7 81.2 81.7 82.2 82.7 83.2 83.7 84.2
Operating time(ms)
53
Histogram or frequency Distribution Diagram is
the most commonly used graph to show
frequency distributions in convenient class
intervals arranged in order of magnitude.
54
It is useful in studying patterns or shape of a
distribution and comparing it with specifications or
standard values.
55
For large numerical data.
To compare measurements to process
specifications or limits.
To analyze what the output from a
supplier’s process looks like.
To see if a process change has occurred
from one time period to another.
To determine whether the outputs of two or
more processes are different.
To communicate the distribution of data
quickly and easily to others.
56
57
Constructing a Histogram cont….
① Gather data (n= 50 ~ 200 )
② Find maximum (L) and minimum (S), calculate range
(L-S).
③ Calculate number of bars/intervals ( ).
④ Decide width of bar/interval (L - S) / ).
⑤ Decide class limit → ( First low class limit = S -
( measure unit/2 ))
First upper class limit = low class limit + width of range
⑥ Calculate center of interval (median)
⑦ Prepare frequency table and construct histogram.
59
Determine how many intervals
(No. of bars)
No. of bars = , Where n is number of
data taken
or
If you have Use this
number
this many data(n) of intervals
Less than 50 5 to 7
50 to 99 6 to 10
100 to 250 7 to 12
More than 250 10 to 20
60
Interval width
61
Start and End points of intervals
62
The horizontal scale across the bottom of the graph
contains the intervals that were calculated previously.
63
Histogram
1. 2.
3. 4.
64
1) Comb style - due to issues or quirks applied to
reading the data when it is measured. For eg, data
that should be placed in a section that doesn’t have
many entries is instead placed into the section before
or after it.
65
3) The Left cliff style - when frequency is calculated
leaving out those cases that are outside specifications,
meaning a check needs to be performed for such
things as measurements being falsified or mistakes in
the investigation.
66
Histograms can be used:
To determine distribution of sales
Analysis of quality test results
Lead time analysis
Confirmation of process capability
67
A histogram may be interpreted by asking
three questions:
1. Is the process performing within
specification limits?
2. Does the process seem to exhibit
wide variation?
3. If action needs to be taken on the
process, what action is appropriate?
68
69
1)To easly visualize figures in form of
pictures and graphs.
2 ) Avoids reading
71
•Bar chart indicates size or amount of
something by length of bar. It is used to
compare magnitude of correlation of
quantities.
72
The table indicates details of defects occurred
during one month at certain work place.
It can also be expressed in bar chart as shown
in below.
Defect No.
Caulking 198
Clamping 103
Crevice 72
Contacting 25
Torque 18
73
It is made by plotting data & linking these by
one line. It is used to indicate variation of
quantity according to time variation having time
in horizontal axis while values in vertical axis.
Example:
(1 ) Monthly change in ratio of defects and
manual correction.
(2) Change in production per day
(3) Sales plan against actual, per month
(4) Price index for 10 years
(5) GDP of core countries.
74
Index of IT popularization can be expressed by the
diffusion of Pc and Internet to households. Below
table & line chart indicate the diffusion by year.
Year PC Internet
1996 17.3 3.3
1997 22.1 6.4
1998 25.2 11.0
1999 29.5 19,1
2000 38.6 34.0
2001 50.1 60.5
2002 57.2 81.4
2003 63.3 88.1
2004 65.7 86.8
2005 64.6 87.0
75
Indicate ratio of each fan-shaped part of whole
circle that is considered to be 100%. Useful to
indicate ratio of each category.
How to make Pie Chart
76
Items No.of Ratio Cumulative Accu. angle
employee ( mil ) (%) (%)
77
Uses rectangle shapes to indicate each value by its
length. Useful to indicate ratio of each value by time
variation or by stratifying.
Stacked bar graph is appropriate for showing time
variation of components ratio.
How to make
(1) Collect and arrange data
(2) Rearrange classification in order of size.
(3) Compute ratio of each item
(4) Divide rectangles occupied by each ratio
(5) Fill in required information to examination
78
Total number of households by year
79
80
A Z graph contains 3 aspects – amount per day or
month, cumulative amount and variance of these (or a
target line). This is used to manage rate of
achievement to the target.
How to make
(1)Collect and arrange data
(2)Compute cumulative value
(3)Compute size of change
(4)Fill in value, cumulative value, & change size onto
the sheet
(5)Perform trend analysis
81
How to use Z Graph
(1) Actual sales of products
(2) Production management
(3) Reduction in no. of incompatibles or defect rate
(4) Reduction in man-hour or cost
(5) Number of proposals or completed QC activities
(6) Improvement of operating rates
82
Month Sales Cumul Total Month Sales Cumul Total
ative variable ative variable
1 65 65 347 7 79 79 388
2 80 145 355 8 34 113 342
3 46 191 347 9 44 157 340
4 91 282 392 10 35 192 284
5 75 357 390 11 75 267 284
6 49 406 374 12 57 324 292
83
84
Radar chart consists of lines as much
as items, extending from the center
where distance from the center
indicates values.
85
How to make
(1) collect and arrange data
(2) draw a circle and divide into numbers of
items to insert mark lines.
(3) draw concentric circle with scales
(4) fill in data
Characteristic of radar charts
(1) check balance between items
(2) check time variation of component ratio
(3) check actual against target of each item
(4) check relation between each item and
average
86
Result of math test by items
Item Previous Now
Figures and formula 80(%) 90(%)
Function 87 100
Diagrams
48 82
probability and
statistic 65 56
set ・ logic 60 78
87
88
The control chart is a graph used to study
how a process changes over time. It is used to
analyze a process.
89
A control chart always has a central line for
the average, an upper line for the upper
control limit and a lower line for the lower
control limit
These lines are determined from historical
data.
By comparing current data to these lines, we
90
1. Collect data for a certain period of time.
2. Plot dots on the chart
3. Examine how they are distributed or if
they are within the established control
limit.
4. Observe variations and analyze the
causes
5. Take some actions to control the
process
6. Standardize various factors,
7. Make a control chart again and examine
if the process is in a stable state.
91
If your process is in control, almost all the
data points will be inside those lines.
92
93
How to check control chart cont….
95
Pizza Management have to do something.
Average Diameter = 16 inches
Upper Limit = 17 inches
Lower Limit = 15 inches
• Pizzas within specifications were
acceptable.
• One abnormally small pie is “uncommon”.
• Should be examined for quality control.
96
3.7 Scatter Diagram
97
• A scatter diagram shows the correlation between two
variables in a process. Also called scatter plot, X–Y
graph.
If the variables are correlated, the points will fall along
a line or curve. The better the correlation, the tighter
the points will hug the line.
98
To identify the correlations that might exist
between a quality characteristic and a factor
that might be affecting it.
Relationship between temperature of a steel
99
1. Decide which paired factors you want to study their
relations.
2. Collect at least 30 pairs of data.
3. Find the highest and lowest value for both
variables. To decide the scales of horizontal and
vertical axes.
4. Draw on the y-axis (dependent variable or effect)
& on x- axis (independent variable or cause).
5. Plot the data (If two dots fall together, put them
side by side, touching, so that you can see both.)
6. Title the diagram
10
0
Positive correlation: No correlation:
y increases with x. where x and y have
no particular
relation.
Negative correlation: y
decreases with x
10
1
Scatter Diagrams
Positive correlation
4.5
4.5
4
4
3.5
3.5
3
3
特性 BB
2.5
2.5
Characteristic value
Pressure keeping
保圧
2
2
1.5
1.5
1
1
0.5
0.5
0
0
0 5 10 15 20 25 0 5 10 15 20 25
質量 特性A value A
Characteristic
Weight
102
Scatter Diagrams
Scatter chart including abnormal
data Scatter chart without correlation
4.5
5
4 4.5
3.5 4
Characteristic value B
3 3.5
keeping
特性値B
2.5
Pressure保圧
2.5
2
2
1.5 1.5
1 1
0.5 0.5
0
0
0 5 10 15 20 25 0 5 10 15 20 25
質量 特性値A
Characteristic value A
Weight
10
3
You may occasionally get scatter diagrams in a
sweeping form that look boomerang- or banana-
shaped.
To analyze the strength of the correlation, divide
the scatter plot into two sections.
Treat each half separately in your analysis
10
4
Benefits:
• By knowing which elements of your process are
related and how they are related, you will know
what situation to monitor,
what causes to analyze,
what to vary,
what countermeasures to establish
Review effectiveness of an action.
10
5
A manufacturer of plastic tanks who made
them using the blow molding method
encountered problems with defective tanks
that had thin tank walls. It was suspected
that the variation in air pressure, which
varied from day to day, was the cause of
the non conforming thin walls.
10
7
Pizza example
Minutes Cooking Defective Pizza
10 1
45 8
30 5
75 20
60 14
20 4
25 6
10
8
25
20
15
Defective Pizzas
10
0
0 20 40 60 80
A and B
mixed
11
1
・ Workplace ・ Group ・ Production line
・ Operator ・ Years of experience ・ Age
・ Product ・ Parts ・ Lot
・ Working shift ( daytime/night ) ・ Machine
・ Material ・ Day of the week ・ Time
・ Process related problems ・ performance problem
・ market problems ・ distribution problems
11
3
4. Where to use 7-QC tools in the QC Story
11
4
To Summarize
Tool Function
Check sheet Efficient Data Collection
Pareto Analysis Focus and Prioritize on major problems
Cause-and-Effect Identify relations among cause and effect
Diagrams
Histograms To see the distribution of data
11
5
To Summarize
7 QC tools are simple and effective.
11
6
11
8