Lessons from the Masters Reflections from 25 years as a Quality Professional Mark A. Morris M and M Consulting, LLC ASQ Automotive Division Symposium June 8, 2015 [email protected] © 2013 – 2015, M and M Consulting, LLC
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Lessons from the Masters Reflections from 25 years as a Quality Professional
Mark A. Morris
M and M Consulting, LLC
ASQ Automotive Division Symposium
June 8, 2015
[email protected] © 2013 – 2015, M and M Consulting, LLC
Jimmy Smith
Retired from Caterpillar,
Jimmy spoke at the 2009
ASQ World Conference; he
spoke about what it meant
to him, to be a quality
professional.
His words touched my soul.
My Goal…
This presentation has evolved…
My goal is to remember the people upon whose shoulders I stand, and to share my story.
My hope is that you will be touched, as I was, that you’ll take a moment to remember those on whose shoulders you stand.
Who are The Masters?
People who have
influenced my life in
some significant way.
So many, no longer
with us.
Sculpture by Franklin Simmons (1903)
Looking for Truth
“It was a puzzling thing.
The truth knocks on the
door and you say,
“Go away, I’m looking
for the truth,”
and so it goes away.
Puzzling.” Robert M. Pirsig, Zen and the Art of Motorcycle Maintenance (1974)
Two Letters Cross Paths
seeker of truth
follow no path
all paths lead where
truth is here
EE Cummings
Hierarchy of Needs
Abraham Maslow (1943)
On the Shoulders of Giants
“If I have seen a
little bit further it is
by standing on the
shoulders of giants.”
Sir Isaac Newton (1676)
Regarding Plagiarism
“How lucky Adam was.
He knew when he said
a good thing, nobody
had said it before.”
Mark Twain (1867)
Phil Crosby gave us four absolutes…
1. Conform to requirements.
2. Prevent rather than detect.
3. Do it right the first time.
4. Price of nonconformance.
Writing Technical Documentation
Chapter 4
Operations
Performance
Standards
Processes &
Procedures
Facilities &
Equipment
Training &
Knowledge
Inputs Outputs Know Each Control
Machine Start Up
Safe Shut Down
Recover from Crash
Recover from E-Stop
Guide to Quality Control
1. How to collect data
2. Histograms
3. Cause and effects diagrams
4. Check sheets
5. Pareto diagrams
6. Graphs
7. Control charts
8. Scatter diagrams
9. Binomial probability
10. Sampling
11. Sampling Inspection
Kaoru Ishikawa Ph.D.
Some Good Advice…
W. Edwards Deming
Refuse to do
what’s wrong!
More Advice from Dr. Deming
• No Inspection without Recording
• No Recording without Analysis
• No Analysis without Action
The Genius of…
Walter A. Shewhart
Invented tools that
give us a rational
basis to know whether
data is random or is
affected by assignable
causes.
What are Control Charts?
• Control charts are a graphical technique used to
analyze data in the order created to understand
our processes.
• Control charts give us a scientific basis to identify
assignable (special) causes of variation.
• Dr. Shewhart taught us to use control charts to
identify and eliminate special cause variation.
A History of Read and React…
Statistical Method from the Viewpoint of Quality Control
Walter A. Shewhart (1939)
The New Economics for Industry, Government, Education
W. Edwards Deming (1993)
Juran on Leadership for Quality
Joseph M. Juran (1989)
Statistical Problem Solving
Hans Bajaria & Richard Copp (1991)
The Goal
Eli Goldratt & Jeff Cox (1984, 1992, 2004)
The 7 Habits of Highly Effective People
Stephen R. Covey (1989, 2004)
Statistical Quality Control Handbook
Natural Variation Inherent in the Process
Central Limit Theorem
Clearly, we would expect to see individual values lie
outside of the control limits from time to time, but we
would expect sample averages to lie between them.
Statistical Signals
68.26%
95.46%
99.73%
Distribution
of Averages
How to Identify Out-of-Control Signals
An Ideal Bowl Experiment
• We chose a distribution, the sum of two fair dice.
• Each individual solution is equally likely.
• From this distribution we draw samples of four, with replacement.
7 8 9 10 11 12 2 3 4 5 6
X Bar and R Chart
4
5
7
7
2
5
7
10
6 6 2 2 2 5 3 4
7 8 3 7 5 6 4 5
66688689
10 8 9 9 8 7 11 9
11
10
9
8
7
6
5
4
3
2
0
2
4
6
8
10
12
X = 6.2
UCL = X + A2 x R = 10.0
LCL = X - A2 x R = 2.4
R = 5.2
Sample Data from Ideal Bowl: n = 4
UCL = R x D4 = 11.9
Two Serious Mistakes
Two mistakes are frequently made in attempts to improve results, and both are costly.
1. To react to an outcome as if it came from a special cause, when it actually came from common cause variation.
2. To treat an outcome as if it came from common causes of variation, when it actually came from a special cause.
Purpose of Control Charts
Special Cause
Signal
No signal of
special causes
Action focused
to eliminate
special causes
Good
Taking action when you shouldn’t
No time spent looking for special causes, focused on common causes
Not taking action when you should
Good
Process Control
Time
Time
Out of Control
(special causes present)
In Control
(special causes eliminated)
A Few Words about Outliers
• Outliers are not necessarily good or bad.
• They are simply different.
• They provide the opportunity to learn.
• Send them to the laboratory.
Red Beads and Life
Vacancies: 10
6 Willing Workers
2 Inspectors
1 Inspector General
1 Recorder
4 Paddles, 2 Sets of Beads
Paddle Set of Beads Average
1 A 11.3
2 B 9.6
3 B 9.2
4 B 9.4
“No one could project what average will cumulate
for any given paddle.”
A Most Important Lesson
Knowledge of the proportion of red beads in the
incoming material provides no basis for predicting
the proportion red in the output.
The work loads were not drawn by random
numbers from the supply.
They were drawn by mechanical sampling.
Classic Juran…
“Make no small plans!” Dr. Joseph M. Juran, 1989, p. 351
The Juran Trilogy® Diagram
Robust Design
Genichi Taguchi
Of his many contributions,
he identified three distinct
phases in robust design:
Concept Design
Parameter Design
Tolerance Design
Improvement in Life Expectancy*
(All Americans)
30
35
40
45
50
55
60
65
70
75
80
1900 1910 1920 1930 1940 1950 1960 1970 1980 1990 2000
Year
Lif
e E
xp
ecta
ncy (
ye
ars
)
*Source: National Vital Statistics Reports, Vol. 48, No.18
Spanish influenza
The influence of WE Deming
The Genius of…
Waloddi Weibull
Invented a tool that
allows data itself to
define the shape of
the distribution.
Failure Data for Five Components
Time to Failure
(in hours)
Median Rank
Values
(percentage)
452 13.0
583 31.5
820 50.0
915 68.5
1202 87.0
Data on Weibull Probability Paper
Reliability Bath Tub Curve
Time
Likelihood
of Failure
Run-in Design Life Wear Out
b < 1 b = 1 b > 1
The Math Looks Complicated…
Failure Function
Weibull Probability Function
b b
b
b
ttttf ,exp)()(1
b b
b
b
tdttttFt
,exp)()(1
Data Defines the Distribution’s Shape
bb lnln)(1
1lnln
ttF
bmxy
b
Statistical Function of Wide Applicability
Correcting the Event Period
-
0.00500
0.01000
0.01500
0.02000
0.02500
0.03000
0.03500
0.04000
1 4 7 10 13 16 19 22 25 28 31 34 37 40 43 46 49 52 55 58 61 64
p Chart for Warranty Claims by Week
Series1
Series2
Series3
The event periods that were the basis of my
original analysis were not true.
The Genius of Hans J. Bajaria
Dr. Hans Bajaria synthesized the work of the masters into a practical and effective structure to identify and resolve problems.
3 Questions from Hans Bajaria
1. Is the process unstable?
If so, find and eliminate assignable causes first.
2. Is there too much variation?
If so, take action to reduce variation second.
3. Is the process off target?
If so, shift the process on target and you’re done.
Hans Bajaria’s Synthesis
Number of Accidents 6 8 5 3 8 15 4 5 7
Hernias / /// / / /// //// // / /
Sprained Ankles / / / / //
Eye Injuries // // / /
Severe Cuts / / /
Back Injuries // /////
Smoke Inhalation / / // /
Burns / / // / /
Broken Bones // / / //
Injury Type 9 / / /
Injury Type 10
Proportion
of Accidents to Runs
.05
.08
.04
.03
/
.06
.09
/
.04
.05
.06
Number of Runs 120 100 125 100 133 167 100 100 117
p Chart for Proportion Defective
.05 .08 .04 .03 .06 .09 .04 .05 .06
0.09
0.08
0.07
0.06
0.05
0.04
0.03
0.02
0.01
0
0.10
Sample Size
Proportion of
Accidents
100120 100 100100167133125 117
0.11
0.12
0.13 UCL = p + 3 ((p (1-p) / n) ^ ½) = .056 + .069 = .125
p = .056
n
ppp
13 Limits Control
LCL = 0
c Chart for Number of Defects
9
8
7
6
5
4
3
2
1
0
10
Accidents per Week 86 3 541585 7
11
12
13
14
15
16
cc 3 Limits Control
UCL = c + 3 (( c )^1/2) = 6.8 + 7.8 = 14.6
LCL = 0
c = 6.8
Four Conceptual Models of Failure
Stress vs. Strength
Damage vs. Endurance
Challenge vs. Response
Tolerance vs. Requirements
Ralph Evans, PhD
A New Matrix to Identify Causes
Synthesis by Mark A. Morris
Advice from Dorian Shainin
By systematically
identifying where the
problem is not, you will
find where the problem
is more quickly.
A quote from John Dewey
A problem
well defined
is half solved.
A quote from Albert Einstein
The formulation of a
problem is far more
often essential than
its solution…
Isn’t It True? You Get What You Reward…
Lack of quality planning leads to wonderful
opportunities for creative problem solving. Mark A. Morris
The Goal
• In 2012, we studied The Goal
by Eli Goldratt.
• Jonah the consultant helped
save the plant, and careers too.
• In this story Jonah never suggests solutions.
• Instead he asks thought provoking questions.
Socratic Method
• Goldratt and Fox wrote The Goal as a novel.
• They intentionally give readers time to figure out
solutions before Alex and his team find them.
• The authors want their characters and their
readers to own their solutions.
Seven Habits…
Seek first to understand,
before you ask to be understood. Stephen Covey
A Parting Thought…
I am always doing
that which I cannot do,
in order that I may
learn how to do it. Pablo Picasso
A poem from Rudyard Kipling
I keep six honest serving men,
(they taught me all I knew)
Their names are
What and Why and When
and How and Where and Who.
from Just So Stories (1902)
Questions?
Thank You
Related Documents
