Statistical Process Control
Types of
Statistical Process Control
Statistical
Process Control
Process Acceptance
Control Sampling
Variables Attributes
Charts Charts
S6-2
Quality Characteristics
Variables Attributes
Characteristics that you Characteristics for which you
measure, e.g., weight, length focus on defects
Continuous random variables Classify products as either
‘good’ or ‘bad’, or count #
defects
e.g., radio works or not
Categorical or discrete
random variables
S6-3
Statistical Process Control (SPC)
Statistical technique used to ensure process is
making product to standard
All process are subject to variability
Natural causes: Random variations
Assignable causes: Correctable problems
Machine wear, unskilled workers, poor material
Objective: Identify assignable causes
Uses process control charts
S6-4
Control Chart Types
Continuous Categorical or Discrete
Numerical Data Control Numerical Data
Charts
Variables Attributes
Charts Charts
R X P C
Chart Chart Chart Chart
S6-5
X Chart
Type of variables control chart
Shows sample means over time
Monitors process average
Example: Weigh samples of a product & compute
means of samples; Plot
S6-6
Example S1
Mean=(17+13+16+18+17+16+15+17+16)/9=16.1
S6-7
We select more samples
The mean for sample 1
The mean of means ( x )
=(16.1+16.8+15.5+16.5+16.5+16.4+15.2+16.4+16.
3+14.8+14.2+17.3)/12=16
S6-8
X Chart
N Control Limits
xi = / n
N is number of
x = i =1
samples
x
N
n is the sample size, is
UCL = x + z x
x the standard deviation (given)
of all oat boxes (12*9)
LCL = x − z
x x
In Excel: = stdev( )
Z is 2 for 95.45% confidence, and 3 for 99.73% confidence
Z: how many standard deviations away from the mean
S6-9
In the example S1
n=9, =1
x = 16
x
= / n = 1/ 9 = 1/ 3
UCL = x + z x =16 + 3*(1/ 3) =17
x
LCL = x − z x =16 −3*(1/ 3) =15
x
S6-10
Control Chart for Samples of 9 Boxes
UCL = x + z
x
Variation due to
assignable causes
17=UCL
Variation due to
16=Mean
natural causes
15=LCL
Variation due to
1 2 3 4 5 6 7 8 9 10 11 12 assignable causes
Sample Number
Out of control
x LCL = x − z
x
S6-11
Range
Process standard deviation σ are either not available
or difficult to compute, so using range rather than σ
Range (R1) = biggest number-smallest number=18-13=5
N
Ri
R = i =1
N
S6-12
X Chart
Control Limits
UCL = x + A2 R From
x Table S6.1
LCL = x − A2 R
x
N
xi
x = i =1
S6-13
Control Chart Factors
Sample Size Mean Factor Upper Range Lower Range
n A2 D4 D3
2 1.880 3.268 0
3 1.023 2.574 0
4 .729 2.282 0
5 .577 2.115 0
6 .483 2.004 0
7 .419 1.924 0.076
8 .373 1.864 0.136
9 .337 1.816 0.184
10 .308 1.777 0.223
12 .266 1.716 0.284
Table S6.1
Control Chart for Samples of 9
UCL = x + A R
x From
2
Boxes
Table S6.1 Variation due to
assignable causes
17=UCL
Variation due to
16=Mean
natural causes
15=LCL
Variation due to
1 2 3 4 5 6 7 8 9 10 11 12 assignable causes
Sample Number
Out of control
x LCL = x − A2 R
x
S6-15
Control Limit vs Specification Limit
CL: for the process, actual historical data
Measures whether a process works the same way as it has in the
past (in control), but not whether the process is good or bad
SL: tolerance limit
Design specifications set by designers
Based on product characteristics important to customers or for
assembly
Process is capable: SL is outside of CL
Process Capability Index
Measure the ability of a process to produce outputs within
customer’s specification limits
A process is capable if the index is larger than 1
16
Control Limits Specification Limits
Voice of the process Voice of the customer
Calculated from Data Defined by the customer
Appear on control charts Appear on histograms
Apply to subgroups Apply to items
Guide for process actions Separate good items from bad
What the process is doing What we want the process to do
17
Process Capability Index Cpk
Upper Specificat ion Limit − x
C pk = minimum of , or
3
x − Lower Specificat ion Limit
3
where x = process mean
= standard deviation of the process population
Cp=(USL-LSL)/6σ when process mean is centered between USL and LSL
6σ = UCL-LCL
Assumes that the process is:
• under control
• normally distributed
S6-18
S6-19
R Chart
Type of variables control chart
Shows sample ranges over time
Difference between smallest & largest values in
inspection sample
Monitors variability in process
S6-20
R Chart
Control Limits
UCL R = D4R
From Table S6.1
LCL R = D3 R
N Range for Sample i
Ri
R = i =1
N
# of Samples
S6-21
Setting Control Limits
Average range R = 5.3 pounds
Sample size n = 5
From Table S6.1 D4 = 2.115, D3 = 0
UCLR = D4R UCL = 11.2
= (2.115)(5.3)
= 11.2 pounds
Mean = 5.3
LCLR = D3R LCL = 0
= (0)(5.3)
= 0 pounds
Mean and Range Charts
(a)
These sampling (Sampling mean is shifting
distributions upward but range is
result in the consistent)
charts below
UCL
(x-chart detects shift
x-chart in central tendency)
LCL
UCL
(R-chart does not
R-chart detect change in mean)
LCL
Figure S6.5
Mean and Range Charts
(b)
These sampling
distributions (Sampling mean is
result in the constant but
charts below dispersion is
increasing)
UCL
(x-chart does not detect
x-chart the increase in
dispersion)
LCL
UCL
(R-chart detects
R-chart increase in dispersion)
LCL
Figure S6.5
Steps In Creating Control Charts
1. Take samples from the population and compute
the appropriate sample statistic
2. Use the sample statistic to calculate control limits
and draw the control chart
3. Plot sample results on the control chart and
determine the state of the process (in or out of
control)
4. Investigate possible assignable causes and take
any indicated actions
5. Continue sampling from the process and reset the
control limits when necessary