CONTROL CHART
[Link]
MANAGER QUALITY ASSURANCE
PROCESS
Everything we do in any type of organization is a
process, which requires UNDERSTANDING, has
VARIATION, must be properly CONTROLLED,
has a CAPABILITY, and needs IMPROVEMENT.
PROCESS
PROCESS: Inputs to process include:
Equipment, tools or plant required, Materials
including paper, Information- including the
specification for the outputs, method or
procedures including instructions; People (and
the inputs they provide such as skills, training,
knowledge, etc), records and the environment.
THE VOICE OF THE
CUSTOMER
Materials
(Paper)
S
U
P
P
L
I
E
R
S
Methods/ Procedure
(Instructions)
Information
(specification)
People (skills,
training,
knowledge)
Environment
Records
P
R
O
C
E
S
s
Products
Services
Information
Paperwork
C
U
S
T
O
M
E
R
S
Equipment (tools,
plant)
INPUTS
THE VOICE OF THE
PROCESS - SPC
OUTPUTS
BASIC TOOLS
Can we do the Job correctly (Capability)
Are we doing the job correctly (Control)
Have we done the job correctly (Quality
Assurance)
Could we do the job better (Improvement)
BASIC TOOLS
Process flow charting What is done?
Check sheets / tally charts How often is it
done?
Histograms What does the variation look like?
Graphs Can the variation be represented in a
time series?
Continued.,
Pareto analysis Which are the big
problems?
Cause & Effect analysis and Brain storming
What causes the problems?
Scatter diagrams What are the relationship
between factors?
Control charts which variations to control
and how?
In applying a systematic approach to process
control the basic rules are;
No process without DATA COLLECTION.
No data collection without ANALYSIS.
No analysis without DECISION.
No decision without ACTION
Process Control Chart
A control chart is like a traffic signal, the
operation of which is based on evidence from
process samples taken at random intervals.
A GREEN LIGHT is given when the process
should be allowed to run without adjustment,
only random or common causes of variation
being present.
The equivalent of an amber light appears when
trouble is possible. The red light shows that three
is practically no doubt that assignable or special
causes of variation have been introduced; the
process has wandered.
10
Make economically sound decisions about
actions affecting the process
In God, we trust; All others, need data.
The need for process control
Detection --- Tolerates Waste
Prevention --- Avoid Waste
11
Prevention Vs Detection
Prevention is not fire fighting
Prevention is like the vaccination
It is data driven
Data is analysed statistically
Potential causes are evaluated and prevented
PFMEA (Potential Failure Model and Effects
Analysis) plays a major role
RPN (Risk Priority Number) level is a indicating factor
12
Prevention Vs Detection
Detection is after the defect is generated
Detection involves inspection added cost
The likelihood of detecting a defect is not 100%
always
We allow waste to happen in Detection scheme
But this is part of our life
13
Prevention Vs Detection
14
Effectiveness of Detection
Count the sixth letter f in the text below
The Necessity of Training Farm Hands for First
Class Farms in the Fatherly Handling of Farm Live
Stock is Foremost in the Eyes of Farm Owners.
Since the Forefathers of the Farm Owners Trained
the Farm Hands for First Class Farms in the
Fatherly Handling of Farm Live Stock, the Farm
Owners Feel they should carry on with the Family
Tradition of Training Farm Hands of First Class
Farmers in the Fatherly Handling of Farm Live
Stock Because they Believe it is the Basis of Good
Fundamental Farm Management.
15
Why SPC
Demings Philosophy
Statistic Process Control is not to decide good
16
and bad part
It is constant improvement tool
Running on spec. is not the focus
It drives out fear so that every one can work
effectively
Minimize total cost, eliminate need for inspection
on a mass basis
And More..
Mean Chart
Process or Grand Meat at = X
Upper Action line at = X 3s
Lower Warning Line at = X 2s
n
Whereas s calculated from,
n of
R = Ri/k = Where k is the number
samples of Size N.
17
Sigma (s)
Then, s = R/dn or s = R/d2
Where d2 is the Hartleys Constant
18
Example
19
[Link]
SAMPLE - 1
SAMP-2
SAM-3
SAM-4
SAM-5
RANGE
144
146
154
146
147.50
10
151
150
134
153
147.00
19
145
139
143
152
144.75
13
154
146
152
148
150.00
157
153
155
157
155.5
157
150
145
147
149.75
12
149
144
137
155
146.75
18
141
147
149
155
148.00
14
158
150
149
156
153.25
10
145
148
152
154
149.75
11
151
150
154
153
152.0
12
155
145
152
148
150.0
10
13
152
146
152
142
148.0
10
14
144
160
150
149
150.75
16
15
150
146
148
157
150.75
11
16
147
144
148
149
147
17
155
150
153
148
151.50
18
157
148
149
153
151.75
19
153
155
149
151
152.0
20
155
142
150
150
149.25
13
21
146
156
148
160
152.50
14
22
152
147
158
154
152.75
11
23
143
156
151
151
150.25
13
24
151
152
157
149
152.25
25
154
140
157
151
150.50
17
Calculation.,
Grand Mean or Process Mean is a good estimate
of the Population Mean,
X = X1+X2+X3++Xn /k
Xi/k
k is the number of samples taken of size n
X=147.5+147.0+.+152.25+150.5/ 25
X =150.1 mm
X=
20
Range Calculation
R = 10+19+13+8+.+17 / 25
R = 10.8 mm
From table given below, as sample size n=4 or d2
= 2.059.
Therefore s = R/d2
=10.8/2.059 = 5.25 mm
21
Calculation.,
Upper action line = 150.1+ 3 x 5.25
=157.98 mm
UWL = 155.35 mm
LWL = 144.85 mm
LAL = 142.23 mm
22
Heartley constant table
Sample Size (n)
Hartleys Constant
1.128
1.693
2.059
2.326
23
Run Chart / Individual Chart
Center Line = Process Mean
=X
Upper Control Limit =X+3 s
Lower Control Limit = X-3 s
Where s =MR/d2 constant
d2 is Heartley constant.
Tables has provided as above.
24
Graph Examples
Part:
Process:
Test:
Date Range:
56clr M3cb608
Dryer #6
Hopper Temp.: Cylinder
02/18/02 08:40:43 am <=> 05/12/04 10:15:47 am
Subgroup
Size
IX
Moving R
Date
Time
53
1
170.00
1.00
04/21/04
08:06:34 am
54
1
172.00
2.00
04/21/04
12:15:03 pm
55
1
170.00
2.00
04/26/04
07:50:14 pm
56
1
167.00
3.00
04/26/04
11:55:35 pm
57
1
167.00
0.00
04/27/04
03:58:13 pm
58
1
166.00
1.00
04/27/04
07:57:49 pm
59
1
166.00
0.00
04/28/04
12:26:06 am
60
1
175.00
9.00
04/28/04
02:40:18 pm
61
1
164.00
11.00
04/28/04
08:18:55 pm
62
1
164.00
0.00
04/29/04
09:42:42 am
63
1
167.00
3.00
04/29/04
10:19:28 pm
64
1
165.00
2.00
05/01/04
11:07:00 am
65
1
166.00
1.00
05/01/04
12:22:16 pm
Test: Hopper Temp.: Cylinder
175.00
cUCL
172.00
169.00
IX
cCL
166.00
163.00
cLCL
160.00
157.00
53
54
55
56
57
58
59
60
61
62
63
64
65
Subgroup
25
05/12/04 03:50:00 pm
ZAMIL PLASTICS, PET DIVISION
Page 5
Part:
54green bc112
Proce s s :
Dryer # 7
Date Range : 01/15/03 09:02:38 am <=> 09/30/03 10:15:45 pm
Test: Act. Dew point temperature
-35.33
-37.05
cUCL
IX
-38.76
-40.47
cCL
-42.19
cLCL
-43.90
-45.62
1
10
13
16
19
22
25
28
31
34
37
40
43
46
49
52
55
58
61
64
67
70
73
Subgroup
26
10/01/03 09:55:38 am
ZAMIL PLASTICS, PET DIVISION
Page 1