Professional Documents
Culture Documents
Process Variability
Uncontrolled variation is
the enemy of quality
Dr. W. Edwards Deming (1900-1993)
Sources of Variation
Variation exists in all processes.
Variation can be categorized as either:
Chance or Common causes of variation
Inherent to a system, random, always present and
hence predictable within statistical limits
Eliminate inherent variability (noise) is difficult
Control Chart
6.0
USL
UCL
Quality 5.0
attribute
(unit)
CL
LCL
LSL
4.0
30
40
Sample #
50
60
Potential Applications
To proactively monitor and trend a process
To detect the presence of special cause variation
To identify continual improvement opportunities
To maintain the process in a state of statistical
control
Using science and risk-based approach
Take action in a timely manner
6
Characteristics that have discrete values and can be counted, e.g. % defective, #
of failed batches in a month
p chart / np Chart: for fraction of occurrence of an event- Binominal distribution
e.g. % of unsuccessful batch at a facility every month
c chart / nc Chart: for counts of occurrence in a defined time or space increment
-Poisson distribution
e.g. number of particulate matter in an injection vial
Rational Subgroup:
Other Rules
certain nonrandom
patterns of the
plotted data
Use it judiciously
12
13
Illustrative Examples
14
Sample Mean
45
40
1
35
UCL=31.75
_
_
X=29.25
30
25
Not Stable
&
Not Capable
LCL=26.75
1
1
1
1054
1233
1309
1338
1356
1429
1452
Time
1515
1539
1602
1625
UCL=10.36
Sample Range
10.0
7.5
_
R=5.17
5.0
2.5
LCL=0
0.0
1054
1233
1309
1338
1356
1429
1452
Time
1515
1539
1602
1625
ER coated beads, mixed with extra-granular cushioning excipients and compressed into tablets
Compression: ~ 5h, sample frequency: every 8-10 min (total 33 subgroups), subgroup size= 6
15
Subgroup Mean
Xbar Chart
UCL=102.108
102
S pecifications
96
LS L
U S L 104
_
_
X=100.287
100
LCL=98.466
98
1
11 13 15
Batch No.
17
19
21
23
25
96
Subgroup Range
100
102
Cpk: 2.95
104
A D: 0.636, P : 0.094
UCL=4.582
_
R=1.78
LCL=0
0
1
11 13 15
Batch No.
17
19
21
23
25
96
Within
StDev 1.051
Cp
1.27
Cpk
1.18
PPM
229.14
102
100
98
5
10
15
Batch No.
99
102
105
Stable
&
Capable
Capability Plot
Run Chart
104
Assay (%)
98
USP: 90-110
R Chart
96
USL
LSL
20
25
Within
Ov erall
Overall
StDev 1.079
Pp
1.24
1.15
Ppk
Cpm
*
PPM
323.15
Specs
Data source: Chopra, V., Bairagi, M., Trivedi, P., et al., A case study: application of statistical process control tool for
determining process capability and sigma level, PDA J Pharm Sci and Tech, 66 (2), 2012, pp. 98-115
16
Capability Histogram
Individual Value
5.0
Specifications
USL 15
_
X=3.137
2.5
0.0
USL
UCL=5.558
LCL=0.716
28
31
34
37
40
43
46
49
52
55
10
12
14
1 1
3.0
UCL=2.974
1.5
__
MR=0.910
LCL=0
0.0
28
31
34
37
40
43
46
49
52
55
Last 30 Observations
Within
S tDev 0.8070
Cp
*
C pk
4.90
PPM
0.00
4
2
28
31
34
37
40
43
46
Batch No.
49
Capability Plot
AV
Not Stable
but
Capable
52
55
Within
Overall
O v erall
S tDev 0.9460
Pp
*
P pk
4.18
C pm
*
PPM
0.00
Specs
Tablet content uniformity (AV) of last 30 commercial batches of Tablet X manufactured by Firm Y
(subgroup size =1, I-MR chart)
17
Unsuccess Rate
% Unsuccess Rate
0.10
0.05
_
P =0.0437
0.00
LC L=0
1
20
10
0
Stable
but
Not Capable
20
25
30
T otal Batch M anufactur ed/M onth
11 13 15 17 19 21 23 25
M onth
Tar
S ummary S tats
10.0
(95.0% confidence)
% D efectiv e:
Low er C I:
U pper C I:
Target:
P P M D ef:
5
4
3
2
5
10
15
M onth
20
25
Low er C I:
U pper C I:
P rocess Z:
Low er C I:
U pper C I:
4.37
2.79
6.49
0.00
43726
27917
64891
1.7090
1.5150
1.9123
Fr equency
P r opor tion
U C L=0.1809
0.15
7.5
Binomial process
capability index:
0.569
5.0
2.5
0.0
3
6
9
12
% Unsuccess Rate
18
19
Summary
Brief introduction of control chart: history, definition, types
Key considerations for constructing a control chart:
Choice of drug product quality characteristics
Subgroup size and sampling frequency
Statistical process control limits (UCL and LCL)
20
Acknowledgements
Dr. Christine Moore
Dr. Naiqi Ya
Dr. Ubrani Venkataram
21