KNOWLEDGE IS POOR

BUT A KNOWLDGEABLE MAN IS POWERFULL

1
1) What is Statistical Process Control ( SPC )
2) Why use SPC ?
3) Methods of SPC.
4) Process.
5) Process Control System.
6) Benefits of SPC.
7) Basic Concepts of Statistics.
8) Nature of Variation.
9) Assignable (Special) Causes.
10) Natural (Common Causes).
11) Preconditions for Attribute Data.
12) Control Charts.
13) Advantages of Control Charts.
14) Types of Control Charts.
15) Work on Control Chart.
16) Benefits of Control Charts.
17) Steps of X – R Chart.
18) P and Np Chart.
19) Variation is Measured By.
20) Measurement of things of Same Kind.
21) Analysis of Curve.
22) What is Process Capability.
23) Cp & Cpk process Capability Indices.
24) Method of Finding out Process Capability.
25) Frequency Distribution and Histogram.

2
3
 SPC is a technique of managing THE Quality Through error prevention.
 STATISTICAL: Taking of  PROCESS:
PROCESS Transformation of
measurements and arrangement of input(4M & 1E) to desired
those measurements in clear pattern output through logical & inter-
to allow prediction to be made on linked Sequence of cause.
performance.  CONTROL:
CONTROL Making something
» Data collection to behave in way we want it to
» Data Presentation behave.
» Define target
» Data Analysis
» Compare with target
» Data Interpretation /Drawing » Measure actual performance
Conclusions.

(THE total performance of the process depends on Communication between customer & Supplier)

4
¥ SPC is technique to control the Process .
¥ To know the special cause so as to Take corrective action.
¥ It gives Power to predict the behavior of the process .So as to
take corrective actions before actual happening (Gone out of
control).
¥ A more effective Method of working is to avoid waste by Not
Providing defective Parts in the First Place. This requires
everyone to concentrate on defect prevention Rather then
defect defection.
¥ SPC is a means by which to achieve the prevention Of defects
by highlighting situation when the output of process is
drifting.
¥ We can forecast things happening, Predict and take corrective
action I.e Preventive technique
¥ SPC is not superficial/ actual Req.. by customers.Generally
used on critical dimensions which directly may create problem
in our fitments and others.

5
 ERROR DETECTION  ERROR PREVENTION
(After the event)Tolerate Waste (Before the event)Avoids wastage
Monitor adjust
ADJUST

Process Not OK Process Not OK

Machine Inspection OK Machine Inspection OK
Materials Materials
Methods Methods
Man Man
Samples collected
/measured & analyzed
6
 About Process Performance :-  Action on the Process.:-
» By studying the process Output. » Action on the process is frequently
» By understanding the process itself Most Economical When Taken to
and its internal variability. prevent the important
Characteristics (Process or output)
» Focus on process Characteristics.

» Due to variation we always

problem, not sleeping.

7
 1. Process control system is feed back system & SPCC is one type of that system.
2. It gives information about the performance,action on process,action on the output.

Voice of Statistical
the process Methods

THE way we work Product/

People /bending of resources services Customers
Equipment
Materials
Methods Identifying
Environment Changing, needs
and expectations

Inputs Process/system Outputs

Voice of customers 8
¢ Parts can be easily assembled.
 Tools of SPC
1 Data Collection.
¢ Parts can be easily changed. 2 Summarization of data
¢ Improves product Performance.  Frequency
¢ Reduces Customer complaints  Histogram
¢ Reduces rejection
 Average Value
¢ Increases Production
 Range
 Standard deviation
¢ Reduce Cost 3 Control chart
¢ Reduce wastage of time  X-R chart
¢ Increase Confidence of customers  Np and P chart
 C and U Chart
4 Process capability study

9
 Variation is the LAW OF NATURE.As such No two things
are exactly alike.
 Variation in a Product or process can be measured.
 Things vary According to a definite Pattern.
 Whenever things of the same things are measured,A large
Group of the measurements Will tend to cluster around
the Middle.
 It is possible to determine the Shape Of THE Distribution
Curve for parts produced by any process.

10
 There are two types of variation in a process:
1 Due to large number of unknown causes
(Natural/Common Causes).
2 Due to special Causes(Assignable Causes).

11
 Are Unrelated to THE intended Design of
process.
 Do not Affect everyone.
 Are Unpredictable & Temporary.

Examples:-
Material Variation
Poor Maintenance
Electrical Power surge
New Methods/Procedures
Untrained Operator

12
 Common causes of variations are inherently part
of the System/Process.
 Affect everyone associated with process.
 Predictable

Examples:-
 Procedure & Method used
 Education & Training given
 Machine Movement

13
 Establish a clear reference standards (limit samples)
 Visual reference to demonstrate .”acceptable or non
acceptable”.
 Communicate the standards to appropriate
personnel.
 Ensure that assessment Personal have appropriate
faculty & aptitudes .
 Train & develop Personal.
 Ensure correct environment for the task
 Verifying the gauging equipment.
 Encourage everyone to keep to the standard.

14
 It is a special type of trend chart
with limits specifically used to assess
and maintain stability of the process
OUT OF CONTROL PROCESS
 This indicates whether the process UCL(UPPER Control li
variation is natural and expected 5.25
(chance variation) or due to special CL(Control limit)
causes. 5
 Control limit theorem :it states
even if the outcome of the process/total 4.75 LCL(Lower Control limit)
population is not normally distribution cm.
but samples /average is always
distribution charts.

1 2 3 4 5 6 7 8
ITEM NO.
15
 It gives a pictorial view of the process or
performance.
 It tells at a glance if a process is behaving
naturally or not.
 It is a tool to detect the pressure of assignable
cause in a process.
 It tells when a process should be corrected & when
it should be left alone.

16
 VARIABLE DATA: Which can  ATTRIBUTE DATA:
take up any value Which are classified as good
example:Length,Weight,Temp,etc. or bad,OK or Not OK
 Data collection is done by  data collection is done
measurements. by counting.
 TYPE OF CHART USED:  FOR DEFFECTIVE :

X-R CHART P AND Np

 FOR DEFECTS : C
OR U

A DEFECT is a blemish flaw or non -conformity which causes an item to be rejected.e.g. dent, Paint
blemish, Scratch,Blow Holes. It is possible to have more than one defect on one single item.
A DEFCETIVE is a component or item which is unacceptable to use.

17
 Collect the data (25 Sub groups) at least.
 By interpretation of control chart we can find whether the
process is in control or out of control
» Points out side the control limit. Out of control
» RUNS: when 7 or more consecutive UCL
CL
readings are in one side they may be
LCL
above or bellow.
» TRENDS: A trend is described by seven or more consecutive
intervals that are continuously increasing or decreasing.
» HUGGING: Center line,Control Limit(tracing and moving
causes.

18
 Easier to understand by any person what is going on process.
 Help the process Performance Consistently,Predictability for Quality
And Cost.
 Allow the Process to Achieve.
 Higher Quality
 Lower Quality
 Lower Unit Cost
 Higher Effective Capacity
 Providing A common language for discussing the performance of the
project.
 Distinguish between Special & common Causes.

19
The steps involved in setting up control chart for variable X & R charts are:
 Determine the size of sample group. UCL=X + A2*R
 Design a suitable tally sheet. LCL=X - A2*R
 Collect data under standard operating * Values of A2 for more common group size are
conditions(without adjustments)  Calculate the control limits for the R_Chart
Using.
 Calculate the average (x) and range(R,
the difference between the largest & the UCL = D3 * XR
smallest value in the group) UCL = D4 * XR
 Calculate the average of average-x Values of D3,D4 for common sample group
sizes are given in the table.
 Calculate the average range -R  Divide the graph into two portions for 1) X Chart
 Calculate the control limits for for the x & 2) R Chart
chart using the formula
 Periodic observation are taken on X-axis and X &
R on Y-axis
 Select Appropriate scales and draw central lines
and control limits.
 Plot the observation and look out for indication of
the process going out of control or other trends .

20
 NO OF
INSPECTION A2 D3 D4
TAKEN

4 0.729 0 2.282
5 0.577 0 2.115
6 0.483 0 2.004
8 0.373 0.136 1.864
10 0.308 0.223 1.777
21
These charts are utilized for ‘Defective’ :
P Chart:when the sample is constant /Np Chart:When the sample size is varying
 P- Chart  Np- Chart

C.L =P C.L =Np

P= Number of defectives Np= Number of defectives
Total checked No. of Samples Taken

UCL=P+3(P(1-P)/n)^2 UCL=Np+[3Np(1-Np)/n]^2
LCL =P-3(P(1-P)/n)^2 UCL=Np- [3Np(1-Np)/n]^2
Take LCL =0 when its value is negative
Take LCL =0 when its value is
negative

22
These Charts are utilized for controlling ‘Defects’
C: Charts are used for products of constant size .
U: Charts are used for products of Varying size
 C Chart:  U Chart
C.L.=C C.L.=U
C =Total no of defects U =Total no of defects
Total Number of Samples(n) Number
Checked
UCL=C+(3C)^2 UCL=U+3(U/n)^2
LCL=C-(3C)^2 LCL=U-3(U/n)^2
Take LCL =0 when its value is
Take LCL =0 when its value is negative
negative

23
Range Value
Standard Deviation(Sigma)
1. Range = Max.(value) - Min.(value)
Data: 10$$$,11,10,12,13,10.6
Range: 13 - 10 = 3
2. Standard Deviation ($) = {sum of(x-x)^2/n}^.5

24
 Area showing
total population.

34.13% 34.13%

13.6% 13.6%

2.14% 2.14%
0.13%
0.13% -2$ X
-3$ -1$ +1$ +2$ +3$
25
 If a part is taken out at THE random,THE chances are that
68.16 Out of 100 Measurements (34.13%+34.13%) will fall
within two mid-section of THE graph.
 THE chances are that 27.2 out of 100 PCs. (13.6%+13.6%)
will fall in THE next sections.
 THE chances are That 4.28 out of 100 PCs. (2.14%+2.14%)
will fall into THE subsequent two sections.
 And 0.26 out of 100 PCs. (0.13%+0.13%) will fall in outside
two sections.

26
It is the minimum variation the process can achieve.
It is defined by the sigma limits on either side of the mean(Target).It
is the “Inherent Capability” of the Process.
PURPOSE OF PROCESS CAPABILITY STUDY:
 Procedure for evaluating a process.
 Determine if the Process is capable Relative to its specifications.
 Determine the Centering & Stability of the Process.
METHODS OF FINDING OUT PROCESS CAPABILITY
¢ Frequency Distribution & Histogram
¢ Control Chart

27
Useful measures for management to assess “health” of process.
Need to know that the process is stable (in control), the Process center(x) the process variability $(sigma)
Cp & Cpk MEASURE THE PROCESS CAPABILITY W.R.T THE CUSTOMER REQD.
 Cp  Cpk
-COMPARE PROCESS SPREAD THE
SPECIFICATION WIDTH
-ADDRESSES BOTH CENTERING
AND SPREAD V/S SPEC.
-IS USED WITH TWO SIDED SPECI.
-WANT TO FIT AT LEAST 8$ WANT CENTER AT LEAST 3-S
FROM SPEC.
Cp = (Usl-Lsl)/6$
WANT Cp > 1.67 Cpk = MINIMUM OF (Usl-
X)/3S,(X-Lsl)/3S
Lsl Usl Lsl Usl
WANT Cpk > 1.33

3$
6$
8$ 28
 FREQUENCY DISTRIBUTION &
HISTOGRAM
 CONTROL CHART

29
STEPS:
 Collect 50 consecutive samples From a running Process &
Record THE measured value of Quality Characteristics.
 Make frequency Distribution Chart and Histogram & check if
the Distribution is normal or Not.
 If distribution is not normal analyze the process Find out the
root cause of the problem and eliminate the root cause.
 Take fresh data of consecutive 50 Samples & repeat steps 2 & 3
stated above
 When distribution is normal calculate value of 6$,and also Cp
and Cpk.
 It can be characterized by
Location:-> Most frequently occurring value.
Spread :-> Span of values form smallest to largest.
Shape :->THE pattern of variation.
TIR:->Total indicating reading.

30
Histograms: To understand the form of a distribution, and compare it to a standard

•Indicate number of times

•Decide the horizontal and vertical scales so that the finished diagram will be approximately squares.
•Draw a line showing the average

30
• Indicate the requirement items
25 n: no. of items of data
x: average
20 z: standard deviation
No. of ite m s

• The portion outside the standard limit

15
may be cross hatched for easier visibility
10
• Insert the units
5 • Indicate the characteristic

0 •Don’t forget a zero

270 280 290 300 310 320 330
Melting tem perature

Figure 7 Histogram for “Melting temperature of fuses”

31
 Control Charts:To investigate whether a process is stable or
not
•Indicate the kind of control chart at the centerline(CL) position) •Show points outside the control
•Show subgroup size here limits by means of a  mark
•Insert the unit •Decide horizontal and vertical scales so that the
distance between the UCL and LCL is about •Show explicit values for CL(Centerline)
six time the gap between subgroups and upper and lower control limits (UCL and LCL)
•Show points on x by means of a  mark
50 UCL ( x + A2R )
40
30 x
x
20
LCL ( x + A2R )
0
60 UCL ( D4 R )
40
R R
20
LCL ( D3 R )

•Indicate the subgroups number(subgroup name, •When the chart is for analysis, show the CL with a solid line
the data, and so on may also be filled in) and the UCL and LCL with dotted lines.
•When it is for control, show the CL with a solid line and the
UCL and LCL with dot-dash (.--.) mark

32
33
PART NAME - SMALL CAT CONE

PART NO. - KTV 5485

SAMPLE SIZE - 50 NOS.

INSTRUMENT - HEIGHT GAUGE

SPECIFIC - HEIGHT (40 ± 0.2)

COMPANY - ECOCAT PVT. LTD.

34
 DATA COLLECTION U.C.L - 40.2000
L.C.L - 39.8000

SNO. 1 2 3 4 5 6 7 8 9 10

1 45.02 44.95 45.48 45.32 45.28 45.82 45.58 45.40 45.60 45.68

2 45.60 45.02 45.32 45.56 45.14 45.62 45.80 45.50 45.78 45.64

3 45.26 45.65 45.62 45.48 45.38 45.60 45.46 45.64 45.39 45.29

4 45.32 45.28 45.82 45.80 45.50 45.78 45.64 45.60 45.02 45.32

5 45.56 45.14 45.62 45.46 45.64 45.39 45.29 45.26 45.65 45.62

35
 STATISTICAL PROCESS CONTROL STUDY
PART NAME: SMALL CAT CONE INSTRUMENT: HEIGHT GAUGE L.COUNT: 0.002 SUPPLIER ECOCAT
PART NO.: KTV 5485 SPECIFIC: HEIGHT MACHINE: DATE- 04.09.06
SAMPLE SIZE: 50 NOS. OPERATION: NO.OF DECIMALS: D.C. NO. QTY.
DATA COLLECTION: -
SNO. 1 2 3 4 5 6 7 8 9 10 U.C.L. 40.2000 SAMPLE D2 A2
1 45.0200 44.9500 45.4800 45.3200 45.2800 45.8200 45.5800 45.4000 45.6000 45.6800 1 1.123 2.560
2 45.6000 45.0200 45.3200 45.5600 45.1400 45.6200 45.8000 45.5000 45.7800 45.6400 2 1.128 1.880
3 45.2600 45.6500 45.6200 45.4800 45.3800 45.6000 45.4600 45.6400 45.3900 45.2900 L.C.L. 39.8000 3 1.693 1.020
4 45.3200 45.2800 45.8200 45.8000 45.5000 45.7800 45.6400 45.6000 45.0200 45.3200 4 2.059 0.730
5 45.5600 45.1400 45.6200 45.4600 45.6400 45.3900 45.2900 45.2600 45.6500 45.6200 5 2.326 0.590
CALCULATIONS: -
FOR HISTOGRAM
XLARGE 45.6000 45.6500 45.8200 45.8000 45.6400 45.8200 45.8000 45.6400 45.7800 45.6800 Xmax.= 45.8200NO.OF NON CONFORMING PART = 50
XSM ALL 45.0200 44.9500 45.3200 45.3200 45.1400 45.3900 45.2900 45.2600 45.0200 45.2900 Xmin.= 44.9500
RANGE 0.5800 0.7000 0.5000 0.4800 0.5000 0.4300 0.5100 0.3800 0.7600 0.3900 R - BAR = 0.52300 NO. OF PARTS ABOVE U.C.L. = 50
AVG. 45.3520 45.2080 45.5720 45.5240 45.3880 45.6420 45.5540 45.4800 45.4880 45.5100 X - BAR = 45.4718 NO. OF PARTS BELOW L.C.L. = 0
Process Width ( P ) = 0.8700 Specification Width(S) = 0.4001 Index (K)={2 x (D-XBAR) / S}= 27.3522 INTERVAL FREQ.
Design Centre ( D ) = 40.0000 Interval = 0.174000 Selecting no. of classes = 5 44.4280 44.6020 0
Starting Point = 44.9500 No. of readings= 50.0000 Shift Of 'X-BAR' from 'D' = 5.471800 44.6020 44.7760 0
44.7760 44.9500 0
X - C HA R T
U.C.L. 45.78037 45.78037 45.78037 45.78037 45.78037 45.78037 45.78037 45.78037 45.78037 45.7804 44.9500 45.1240 1
L.C.L. 45.1632 45.1632
HISTOGRAM
45.1632 45.1632 45.1632 45.1632 45.1632
46.800

45.1632
45.800
45.1632 45.1632 45.1240 45.2980 3
44.800 AVG
U.C.L.
20 1.1035 1.1035 1.1035 1.1035 1.1035 1.1035 1.1035 1.1035
43.800 1.1035 1.1035 UCL 45.2980 45.4720 8
L.C.L.
18 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
42.800
0.0000 0.0000 LCL 45.4720 45.6460 10
41.800 X-BAR
X-BAR
16 45.4718 45.4718 45.4718 45.4718 45.4718 45.4718 45.4718 45.4718
40.800 45.4718 45.4718 45.6460 45.8200 19
R-BAR
14 0.5230 0.5230 0.5230 0.5230 0.5230 0.5167 0.5230 0.5230
39.800 0.5230 0.5230 45.8200 45.9940 9
1 2 3 4 5 6 7 8 9 10
45.9940 46.1680 0
12
46.1680 46.3420 0
10
R - C HA R T
1.2 0 0 0
46.3420 46.5160 0
8
1.0 0 0 0 U.C.L. XBAR = 45.78037
6 0 .8 0 0 0 RANGE
0 .6 0 0 0
L.C.L.XBAR = 45.16323
4 UCL
0 .4 0 0 0 LCL U.C.L. RBAR = 1.10353
2 0 .2 0 0 0 R- BAR L.C.L.RBAR = 0
0 0 .0 0 0 0
1 2 3 4 5 6 7 8 9 10 Std.Dev."s"= 0.22606
1 2 3 4 5 6 7 8 9 10 11 12
Cp=(S/6s)= 0.29500
REMARKS: - PROCESS IS VERY POOR TAKE IMMEDIATE ACTION Cpk={1-K}xCp)= -7.77390

36
PROCESS IS VERY POOR TAKE IMMEDIATE ACTION

37
 DATA COLLECTION U.C.L - 40.2000
L.C.L - 39.8000

SNO. 1 2 3 4 5 6 7 8 9 10

1 39.96 40.02 40.00 39.94 40.12 40.00 40.02 39.98 40.04 40.02

2 40.00 40.10 39.98 40.08 40.06 40.02 39.98 39.96 40.06 40.02

3 39.98 39.98 39.96 39.96 40.06 39.96 40.02 39.94 40.02 39.98

4 39.98 40.00 39.98 39.96 40.00 39.98 40.06 40.06 39.96 39.96

5 39.98 39.98 39.96 39.94 39.98 39.98 40.08 40.04 39.92 39.98

38
 STATISTICAL PROCESS CONTROL STUDY
PART NAME: SMALL CAT CONE INSTRUMENT: HEIGHT GAUGE L.COUNT: 0.002 SUPPLIER ECOCAT
PART NO.: KTV 5485 SPECIFIC: HEIGHT MACHINE: DATE- 04.09.06
SAMPLE SIZE: 50 NOS. OPERATION: NO.OF DECIMALS: D.C. NO. QTY.
DATA COLLECTION: -
SNO. 1 2 3 4 5 6 7 8 9 10 U.C.L. 40.2000 SAMPLE D2 A2
1 39.9600 40.0200 40.0000 39.9400 40.1200 40.0000 40.0200 39.9800 40.0400 40.0200 1 1.123 2.560
2 40.0000 40.1000 39.9800 40.0800 40.0600 40.0200 39.9800 39.9600 40.0600 40.0200 2 1.128 1.880
3 39.9800 39.9800 39.9600 39.9600 40.0600 39.9600 40.0200 39.9400 40.0200 39.9800 L.C.L. 39.8000 3 1.693 1.020
4 39.9800 40.0000 39.9800 39.9600 40.0000 39.9800 40.0600 40.0600 39.9600 39.9600 4 2.059 0.730
5 39.9800 39.9800 39.9600 39.9400 39.9800 39.9800 40.0800 40.0400 39.9200 39.9800 5 2.326 0.590
CALCULATIONS: -
FOR HISTOGRAM
XLARGE 40.0000 40.1000 40.0000 40.0800 40.1200 40.0200 40.0800 40.0600 40.0600 40.0200 Xmax.= 40.1200NO.OF NON CONFORMING PART = 0
XSM ALL 39.9600 39.9800 39.9600 39.9400 39.9800 39.9600 39.9800 39.9400 39.9200 39.9600 Xmin.= 39.9200
RANGE 0.0400 0.1200 0.0400 0.1400 0.1400 0.0600 0.1000 0.1200 0.1400 0.0600 R - BAR = 0.09600 NO. OF PARTS ABOVE U.C.L. = 0
AVG. 39.9800 40.0160 39.9760 39.9760 40.0440 39.9880 40.0320 39.9960 40.0000 39.9920 X - BAR = 40.0000 NO. OF PARTS BELOW L.C.L. = 0
Process Width ( P ) = 0.2000 Specification Width(S) = 0.4001 Index (K)={2 x (D-XBAR) / S}= 0.0000 INTERVAL FREQ.
Design Centre ( D ) = 40.0000 Interval = 0.040000 Selecting no. of classes = 5 39.8000 39.8400 0
Starting Point = 39.9200 No. of readings= 50.0000 Shift Of 'X-BAR' from 'D' = 0.000000 39.8400 39.8800 0
39.8800 39.9200 0
X-CHART
U.C.L. 40.05664 40.05664 40.05664 40.05664 40.05664 40.05664 40.05664 40.05664 40.05664 40.0566 39.9200 39.9600 1
L.C.L. 39.9434 39.9434
HISTOGRAM
39.9434 39.9434 39.9434 39.9434 39.9434
40.100

39.9434
40.050 39.9434 39.9434 39.9600 40.0000 12
AVG
20 40.000
U.C.L. 0.2026 0.2026 0.2026 0.2026 0.2026 0.2026 0.2026 0.2026 0.2026 0.2026 UCL
40.0000 40.0400 19
39.950
L.C.L.
18 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000
39.900
0.0000 0.0000 LCL 40.0400 40.0800 9
X-BAR
X-BAR
16 40.0000 40.0000 40.0000 40.0000 40.0000 40.0000 40.0000 40.0000
39.850 40.0000 40.0000 40.0800 40.1200 7
R-BAR
14 0.0960 0.0960 0.0960 0.0960 0.0960 0.1022 0.0960 0.0960
39.800 0.0960 0.0960 40.1200 40.1600 2
1 2 3 4 5 6 7 8 9 10
12 40.1600 40.2000 0

10
40.2000 40.2400 0
R - C HA R T
0 .2 3 4 0 40.2400 40.2800 0
8
6
U.C.L. XBAR = 40.05664
0 .156 0 RANGE
L.C.L.XBAR = 39.94336
4 UCL
0 .0 78 0 LCL U.C.L. RBAR = 0.20256
2 R- BAR
L.C.L.RBAR = 0
0 0 .0 0 0 0
1 2 3 4 5 6 7 8 9 10 Std.Dev."s"= 0.04481
1 2 3 4 5 6 7 8 9 10 11 12
Cp=(S/6s)= 1.48810
REMARKS: - PROCESS IS GOOD BUT STILL IMPROVEMENT IS REQIURED Cpk={1-K}xCp)= 1.48810

39
 PROCESS IS GOOD
BUT
STILL IMPROVEMENT REQUIRED

40
REFERENCES

41
42