Você está na página 1de 47

GROUP MEMBERS

• Annisa Monserrate 03
• Bruno Nunes 09
• Cindy D’souza 12
• Farhan Kazi 16
• Melissa Nazareth 30
• Uren Chhadva 58
FLOW OF PRESENTATION
• Introduction
• X charts
• R charts
• P charts
• C charts
• Run tests
• Process Capability
INTRODUCTION
Quality Control

 Variables

 Attributes
APPROACHES TO QUALITY
ASSURANCE
• Acceptance sampling

• Process control

• Continuous improvement
INSPECTION
• When to inspect

• What to inspect

• How much & how often to inspect

• Centralized inspection

• On-site inspection
STATISTICAL PROCESS
CONTROL
 What is statistical process control?
It is the statistical evaluation of the output of
a process during production.
 BRIEF HISTORY:
• Foundation for Statistical Process Control was
laid by Dr. Walter Shewart.
• Dr. W. Edwards Deming built upon Shewart’s
work
THE CONTROL PROCESS
VARIATION & CONTROL
 RANDOM VARIATION:
• Natural variation in the output of a process
created by countless minor factors.
• Also termed as “common variation”.
 ASSIGNABLE VARIATION:
• In process output, a variation whose cause can
be identified.
• Also termed as “special variation”.
CONTROL CHARTS
 CONTROL CHART:
A time ordered plot of sample statistics used
to distinguish between random & non-random
variability.
 PURPOSE OF CONTROL CHARTS:
• To determine the capability of the process
• To show if a process is in control or out of
control
CONTROL CHARTS
 CONTROL LIMITS:
The dividing lines between random & non-
random deviations from the mean of the
distribution.
 ERRORS IN CONTROL CHARTS:
• Type I error: Concluding a process is not in
control when it actually is.
• Type II error: Concluding a process is in control
when it is not.
CONTROL CHARTS
MEAN CHARTS
 MEAN CONTROL CHART:
• Control chart used to monitor the central
tendency of a process
• It displays the changes in the average output of
a process
 FORMULAE:

LCL = X − A2 R

UCL = X + A2 R
EXAMPLE
Q.Use the sample data in the table below to
construct upper & lower limits for a mean
chart. Do the results suggest that the process
is in control?
Sample 1 Sample 2 Sample 3 Sample 4 Sample 5

110.2 10.3 9.7 9.9 9.8


9.9 9.8 9.9 10.3 10.2
9.8 9.9 9.9 10.1 10.3
10.1 10.4 10.1 10.5 9.7
EXAMPLE
SOLUTION:
a.Determine the mean & range for each sample:
Sample Mean Range
1 10 0.4
2 10.1 0.6
3 9.9 0.4
4 10.2 0.6
5 10 0.6
b.Compute the average mean & average range:
= 10+10.1+9.9+10.2+10 = 50.2 = 10.04
5 4
0.4+0.6+0.4+0.6+0.4 = 2.6 = 0.52
5 5
d. Compute upper & lower limits:
UCL= 10.04 + 0.73(0.52) = 10.42
LCL = 10.04 – 0.73(0.52) = 9.66
e. Verify that points are within limits
Mean chart
RANGE CONTROL CHARTS
 Monitor process dispersion

 Control variability of variable

10-18
R – CHART ANALYSIS
Step 1:-
Observe repartition of plotted points

Step 2:-
For a process out of control
CALCULATION
 Center line is the grand mean (R bar)

 Points are R

 D3 and D4 values are tabled according to


n (sample size)

UCL = D4 R LCL = D3 R
10-20
EXAMPLE
1 2 3 4 5 6

79.2 80.5 79.6 78.9 80.5 79.7

78.8 78.7 79.6 79.4 79.6 80.6

80.0 81.00 80.4 79.7 80.4 80.5

78.4 80.4 80.3 79.4 80.8 80.00

81.0 80.1 80.8 80.6 78.8 81.1

R=2.6 2.3 1.2 1.7 2 1.3


 2.6+2.3+1.2+1.7+2+1.3 =1.85
6

 LCL = D3*
=0*1.85
=0

 UCL = D4*
=2.11*1.85
=3.9468
CONTROL CHART FOR
ATTRIBUTES

• Two types of charts:


• P – charts
• C – charts

• When are P charts used?


EXAMPLE
• An inspector counted the number of
defective monthly billing statements of a
company telephone in each of 20 samples.
Using the following information, construct
a control chart that will describe 99.74 % of
the chance variation in the process. Each
sample contained 100 statements.
Sample Number of Sample size Fraction
Defectives Defectives
1 4 100 0.04

2 10 100 0.10

3 12 100 0.12

4 3 100 0.03

5 9 100 0.09

6 11 100 0.11

7 10 100 0.10

8 22 100 0.22

9 13 100 0.13

10 10 100 0.10

11 8 100 0.08

12 12 100 0.12

13 9 100 0.13

14 10 100 0.10

15 21 100 0.21

16 10 100 0.10

17 8 100 0.08

18 12 100 0.12

19 10 100 0.10

20 16 100 0.16

220 2000
CALCULATION

= 220 =0.11
20*100

UCL/ LCL =

UCL---0.20
LCL---0.02
C – CHARTS
 Control chart for attributes

 Used to monitor the no. of defects per unit

 Non occurrences cannot be counted


CONTROL LIMITS

Where, c = Average number of Defects per unit


= Standard Deviation

= No. of defects
No. of samples
EXAMPLE
Sample No. of Defects Sample No. of Defects

1 3 10 1

2 2 11 3

3 4 12 4

4 5 13 2

5 1 14 4

6 2 15 2

7 4 16 1

8 1 17 3

9 2 18 1
DIFFERENT PATTERNS
•Trend

• Cycles

• Bias

• Mean Shift

• Too much
Dispersion
RUN TESTS
• Sequence of observations with a certain
characteristic followed by one or more
observations with a different observable
characteristic

• Types of Run Tests:


 Median Runs
 Up and Down Runs
EXAMPLE
• Consider the following sequence:
With a median 36.5
25 29 42 40 35 38
B B A A B A

• For the same data,


25 29 42 40 35 38
- U U D D U
SPECIFICATION RANGE
• Specifications

• Control Limits

• Process Variability
CAPABILITY ANALYSIS
• Process Capability & Specifications

• Three Cases:
(i) Just matches specifications

(ii) Well within specifications

(iii) Exceeds specifications


SOLUTIONS INCASE OF CASE
III
• Redesign process

• Alternative process

• Current process, inspection & elimination

• Examine specifications
CAPABILITY INDEX
• Centered Process

Cp= Specification Range


6 sigma

• Greater than/ equal to 2 (Six sigma)


• Greater than/ equal to 1.33 (Three sigma)
CASE STUDY
• Tiger Tools product launch

• Process Capability of oven used in process

• Specification width 1.44 cm


Situation I Situation II

• 18 samples, 20 pieces • 27 samples, 5 pieces


each each

Cp = 1.44/ (6 *0.1571) Cp = 1.44/ (6 * 0.0722)


= 1.5277 = 3.3241

The process is capable The process is capable


according to three sigma according to six sigma
standards. standards
• Non centered Process

Cpk= Process Mean –


Upper/ Lower
Specification
3 sigma

• Greater than or equal


to 1.33/ 2
IMPROVING PROCESS
CAPABILITY
• Simplify

• Standardize

• Make Mistake Proof

• Upgrade Equipment

• Automate
LIMITATIONS OF CAPABILITY
INDEX
• Unstable Process

• Cp index used for non centered process

• Output not normally distributed


THANK YOU

Você também pode gostar