Está en la página 1de 47

# Statistical Process Control

Content
Basics of Statistical Process Control Control Charts Control Charts for Attributes Control Charts for Variables Control Chart Patterns SPC with Excel Process Capability Six Sigma Design of Six Sigma System

## Basics of Statistical Process Control

Statistical Process Control (SPC)
monitoring production process to detect and prevent poor quality

Sample
subset of items produced to use for inspection

Control Charts
process is within statistical control limits

Variability
Random
common causes inherent in a process can be eliminated only through improvements in the system

Non-Random
special causes due to identifiable factors can be modified through operator or management action

SPC in TQM
SPC
tool for identifying problems and make improvements contributes to the TQM goal of continuous improvements

Quality Measures
Attribute
a product characteristic that can be evaluated with a discrete response good bad; yes - no

Variable
a product characteristic that is continuous and can be measured weight - length

## Where to Use Control Charts

Process has a tendency to go out of control Process is particularly harmful and costly if it goes out of control Examples
at the beginning of a process because it is a waste of time and money to begin production process with bad supplies before a costly or irreversible point, after which product is difficult to rework or correct before and after assembly or painting operations that might cover defects before the outgoing final product or service is delivered

Control Charts
A graph that establishes control limits of a process Control limits
upper and lower bands of a control chart

Types of charts
Attributes
p-chart c-chart

Variables
range (R-chart) mean (x bar chart)

Normal Distribution

95% 99.74% -3 -2 -1 =0 1 2 3

## Control Charts for Attributes

p-charts
uses portion defective in a sample

c-charts
uses number of defects in an item

The primary difference between using a p-chart and a c-chart is as follows. A p-chart is used when both the total sample size and the number of defects can be computed. A c-chart is used when we can compute only the number of defects but cannot compute the proportion that is defective.

p-Chart
UCL = p + zp LCL = p - zp
z = number of standard deviations from process average p = sample proportion defective; an estimate of process average p = standard deviation of sample proportion p(1 - p) n

p =

p-Chart Example
SAMPLE NUMBER OF DEFECTIVES PROPORTION DEFECTIVE

1 2 3 : : 20

6 0 4 : : 18 200

## p-Chart Example (cont.)

total defectives p = total sample observations = 200 / 20(100) = 0.10 UCL = p + z UCL = 0.190 LCL = p - z LCL = 0.010 p(1 - p) = 0.10 + 3 n 0.10(1 - 0.10) 100

p(1 - p) = 0.10 - 3 n

## p-Chart Example (cont.)

Proportion defective

0.14 0.12 0.10 0.08 0.06 0.04 0.02 2 LCL = 0.010 4 6 8 10 12 14 Sample number 16 18 20 p = 0.10

c-Chart

UCL = c + zc LCL = c - zc
where

c =

## c = number of defects per sample

c-Chart (cont.)
Number of defects in 15 sample rooms
SAMPLE

NUMBER OF DEFECTS

1 2 3

12 8 16

## 190 c= = 12.67 15 UCL = c + zc = 12.67 + 3 = 23.35 LCL = c + zc = 12.67 - 3 = 1.99 12.67

: :
15

: :
15 190

12.67

24
UCL = 23.35

21
18 15 12 9 6 3

Number of defects

c = 12.67

c-Chart (cont.)

LCL = 1.99

10

12

14

16

Sample number

## Control Charts for Variables

Mean chart ( x -Chart )
uses average of a sample

## Range chart ( R-Chart )

uses amount of dispersion in a sample

x-bar Chart
UCL X z LCL X z

standard deviation
z = standard normal variable (2 for 95.44% confidence, 3 for 99.74% confidence)

## x-bar Chart Example

OBSERVATIONS (SLIP- RING DIAMETER, CM)

SAMPLE k
1 2 3 4 5 6 7 8 9 10

1
5.02 5.01 4.99 5.03 4.95 4.97 5.05 5.09 5.14 5.01

2
5.01 5.03 5.00 4.91 4.92 5.06 5.01 5.10 5.10 4.98

3
4.94 5.07 4.93 5.01 5.03 5.06 5.10 5.00 4.99 5.08

4
4.99 4.95 4.92 4.98 5.05 4.96 4.96 4.99 5.08 5.07

5
4.96 4.96 4.99 4.89 5.01 5.03 4.99 5.08 5.09 4.99

x
4.98 5.00 4.97 4.96 4.99 5.01 5.02 5.05 5.08 5.03 50.09

R
0.08 0.12 0.08 0.14 0.13 0.10 0.14 0.11 0.15 0.10 1.15

## x- bar Chart Example (cont.)

50.09 = x x= = = 5.01 cm k 10 = UCL = x + A2R = 5.01 + (0.58)(0.115) = 5.08

## Retrieve Factor Value A2

5.10 5.08 5.06 5.04 Mean 5.02 5.00 4.98 4.96 4.94 4.92 | 1 | 2 | 3 | | | | 4 5 6 7 Sample number | 8 | 9 | 10 = x = 5.01

UCL = 5.08

## x- bar Chart Example (cont.)

LCL = 4.94

R- Chart
UCL = D4R LCL = D3R

R R= k
where R = range of each sample k = number of samples

R-Chart Example
OBSERVATIONS (SLIP-RING DIAMETER, CM)

SAMPLE k
1 2 3 4 5 6 7 8 9 10

1
5.02 5.01 4.99 5.03 4.95 4.97 5.05 5.09 5.14 5.01

2
5.01 5.03 5.00 4.91 4.92 5.06 5.01 5.10 5.10 4.98

3
4.94 5.07 4.93 5.01 5.03 5.06 5.10 5.00 4.99 5.08

4
4.99 4.95 4.92 4.98 5.05 4.96 4.96 4.99 5.08 5.07

5
4.96 4.96 4.99 4.89 5.01 5.03 4.99 5.08 5.09 4.99

x
4.98 5.00 4.97 4.96 4.99 5.01 5.02 5.05 5.08 5.03 50.09

R
0.08 0.12 0.08 0.14 0.13 0.10 0.14 0.11 0.15 0.10 1.15

## R-Chart Example (cont.)

R 1.15 R= = = 0.115 k 10

## R-Chart Example (cont.)

0.28
0.24 0.20 Range 0.16 0.12 0.08 0.04 0 LCL = 0 | | | 1 2 3 | | | | 4 5 6 7 Sample number | 8 | 9 | 10 UCL = 0.243 R = 0.115

## Using x- bar and R-Charts Together

Process average and process variability must be in control.

It is possible for samples to have very narrow ranges, but their averages is beyond control limits.
It is possible for sample averages to be in control, but ranges might be very large.

A Process Is in Control If
1. no sample points outside limits 2. most points near process average 3. about equal number of points above and below centerline 4. points appear randomly distributed

UCL

UCL

LCL

## Revise the charts

Interpret the original charts Isolate the causes Take corrective action Revise the chart

Only remove points for which you can determine an assignable cause

Variable

## DOE - (design of experiments) Analyse the Process

How Measured When Measured How Measured When Measured

Variable

Controllable Inputs
Variable How Measured When Measured

X1

X2 X3
Quality Characteristics: Outputs
LSL

## Inputs: Raw Materials, components , etc.

C a p a b ility u s in g P o o le d S ta n d a rd D e v ia tio n
X b a r a n d R Ch a rt
3 .0

USL

## Y1, Y2, etc.

The Process
Run Temperature Pressure 1 2
Ca p a b ility Histo g ra m
U C L =2 .5 6 8 M U =2 .3 7 6 L C L =2 .18 3

Hi Hi Lo Lo Hi Hi Lo Lo

Hi Hi Hi Hi Lo Lo Lo Lo

3 4

Means

2 .5 2 .0 1. 5 S ubgr 0 .9 1 2 3 4

1. 5

2 .5

3 .5

U C L =0 .9 6 2 1

No rm a l P ro b P lo t

Ranges

0 .6 0 .3 0 .0

R =0 . 5 16 2

L C L =0 .0 7 0 2 7 1.5 2 .5 3 .5

N1

N2 N3

6 7 8

L a st 4 S u b g ro u p s
3 .0

Ca p a b ility P lo t
P ro c e ss To le ra n c e
1.8 3 17 5 2 .9 19 5 8 I I 1 I I I I 4

2 .5 2 .0 1. 5 1 2 3 4

C p : 2 .7 6 C P U : 2 .9 9 C P L : 2 .5 3 C p k : 2 .5 3 Su b g ro u p N u m b e r

Uncontrollable Inputs

Values

Sp e c if ic a t io n s St D e v : 0 .18 13 0 6

## DOE - (design of experiments) Improve the Process

Controllable Inputs
Nip FPM

PrimWdth

ScrewRPM

X1

X2 X3
Quality Characteristics: Outputs Y1, Y2, etc.

X
Inputs: Raw Materials, components , etc.

LSL

USL

The Process

X
N1 N2 N3
Uncontrollable Inputs

LSL

USL

## Examine the process

A process is considered to be stable and in a state of control, or under control, when the performance of the process falls within the statistically calculated control limits and exhibits only chance, or common causes.

Process Capability
Tolerances
design specifications reflecting product requirements

Process capability
range of natural variability in a process what we measure with control charts

Process Capability
Design Specifications (a) Natural variation exceeds design specifications; process is not capable of meeting specifications all the time.
Process Design Specifications (b) Design specifications and natural variation the same; process is capable of meeting specifications most of the time. Process

## Process Capability (cont.)

Design Specifications (c) Design specifications greater than natural variation; process is capable of always conforming to specifications.
Process Design Specifications (d) Specifications greater than natural variation, but process off center; capable but some output will not meet upper specification. Process

## Process Capability Measures

Process Capability Ratio
Cp = tolerance range process range

## upper specification limit lower specification limit = 6

Computing Cp
Net weight specification = 9.0 oz 0.5 oz Process mean = 8.80 oz Process standard deviation = 0.12 oz upper specification limit lower specification limit Cp = 6 9.5 - 8.5 = = 1.39 6(0.12)

## What is a Sigma process

Precision

Lesser the standard deviation of the process, more precise or consistent is the process

## Meaning of a Sigma process

From a sigma process we come to know that at what distance, in terms of the standard deviation, the specification limits are placed from the target value.

3 Sigma Vs 6 Sigma

The goal of Six Sigma program is to reduce the variation in every process to such an extent that the spread of 12 sigmas i.e. 6 Sigmas on either side of the mean fits within the process specifications. The figure on next slide shows what this looks like.

3 Sigma Vs 6 Sigma
6 Sigma curve
LSL USL

3 Sigma curve

10

11 12 13

14

15

16

In a 3 sigma process the values are widely spread along the center line, showing the higher variation of the process. Whereas in a 6 Sigma process, the values are closer to the center line showing less variation in the process.

Why 6 sigma?
LSL
1.5SD

USL

By shifting 3 sigma process 1.5 SD, we create 66,807 defects per billion opportunities

1.5SD

By shifting 6 sigma process 1.5 SD, we create 3.4defects per billion opportunities

Sigma Level
Sigma level 1 2 3 4 5 6 7 DPMO 691,462 308,538 66,807 6,210 233 3.4 0.019 Percent defective 69% 31% 6.7% 0.62% 0.023% 0.00034% 0.0000019% Percentage yield 31% 69% 93.3% 99.38% 99.977% 99.99966% 99.9999981% Cp 0.33 0.67 1.00 1.33 1.67 2.00 2.33