Ch1_StatsInEngineering_torresgarcia.pdf
-
Upload
osiris-lopez-manzanarez -
Category
Documents
-
view
214 -
download
0
Transcript of Ch1_StatsInEngineering_torresgarcia.pdf
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 1/21
CHAPTER 1:STATISTICS IN ENGINEERING
Wandaliz Torres-García, Ph. D.
Image Source: pinterest.com
Reference: Most slides adapted from Montgomery et al. (2011)
ININ 5559ENGINEERING STATISTICS
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 2/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-1 THE ENGINEERING METHOD ANDSTATISTICAL THINKING
Engineers solve problems of interest to society by theefficient application of scientific principles
The engineering or scientific method is the approach toformulating and solving these problems.
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 3/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-1 THE ENGINEERING METHOD ANDSTATISTICAL THINKING
The Field of Probability• Used to quantify likelihood or chance• Used to represent risk or uncertainty in engineering
applications• Can be interpreted as our degree of belief orrelative frequency
The Field of Statistics• Deals with the collection, presentation, analysis, anduse of data to make decisions and solve problems .
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 4/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-1 THE ENGINEERING METHOD ANDSTATISTICAL THINKING
• Statistics is the science of data.•Statistical techniques are useful fordescribing and understanding variability.
• By variability, we mean successiveobservations of a system or phenomenondo not produce exactly the same result.
• Statistics gives us a framework fordescribing this variability and for learningabout potential sources of variability .
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 5/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-1 THE ENGINEERING METHOD ANDSTATISTICAL THINKING
Engineering ExampleSuppose that an engineer is developing a rubber compound foruse in O-rings. The O-rings are to be employed as seals in plasmaetching tools used in the semiconductor industry, so their resistanceto acids and other corrosive substances is an importantcharacteristic. The engineer uses the standard rubber compound toproduce
eight O-rings in a development laboratory and measuresthe tensile strength of each specimen after immersion in a nitricacid solution at 30°C for 25 minutes [refer to the American Society for Testing and Materials (ASTM)] .
The tensile strengths (in psi) of the eight O-rings are 1030, 1035,1020, 1049, 1028, 1026, 1019, and 1010.
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 6/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-1 THE ENGINEERING METHOD ANDSTATISTICAL THINKING
Engineering Example• The dot diagram is a very useful plot for displaying asmall body of data - say up to about 20 observations.• This plot allows us to see easily two features of the
data; the location , and the scatter or variability .• Good tool to observe outliers and clusters .
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 7/21 Reference: Most slides adapted from Montgomery et al. (2011)
1-1 THE ENGINEERING METHOD ANDSTATISTICAL THINKING
Engineering Example• The dot diagram is also very useful for comparingsets of data.
• What are obvious questions to ask?
Added Teflon
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 8/21 Reference: Most slides adapted from Montgomery et al. (2011)
1-1 THE ENGINEERING METHOD ANDSTATISTICAL THINKING
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 9/21 Reference: Most slides adapted from Montgomery et al. (2011)
1-2 COLLECTING ENGINEERING DATA
Three basic methods for collecting data:A retrospective study using historical data, all or a sample, todetermine relationships among factors and response(s).
An observational study observes the process of populationduring a period of routine operation.
A designed experiment is used to make changes tocontrollable variables, factors, to observe the responseoutput. In contrast with the other two studies the combinationsof factors are performed in a randomized manner with
replicates. This permits to establish cause-and-effectrelationships.
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 10/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-2 COLLECTING ENGINEERING DATA
Example: Acetonebutyl alcohol destillation column
Response random variable: Acetonebutyl concentration (g/L)Controllable factors: Condenser Temp, Reboil Temp., Reflux Rate(all at two levels, low (-) & high(+)).
23 factorial design with 2 replicates
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 11/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-2 COLLECTING ENGINEERING DATA
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 12/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-2 COLLECTING ENGINEERING DATA
1-2.4 Random Samples
Example: Measuring mathematical skills at University of Puerto Rico
How to sample from the population to infer statistical knowledge?
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 13/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-3 MECHANISTIC AND EMPIRICAL MODELS
A mechanistic model is built from our underlyingknowledge of the basic physical mechanism thatrelates several variables.
Example: Ohm’s Law
Current = voltage/resistance
I = E/R
I = E/R +
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 14/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-3 MECHANISTIC AND EMPIRICAL MODELS
An empirical model is built from our engineering andscientific knowledge of the phenomenon, but is notdirectly developed from our theoretical or first-principles understanding of the underlying mechanism.
Sometimes models are not well understood and highlycomplex.
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 15/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-3 MECHANISTIC AND EMPIRICAL MODELS
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 16/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-3 MECHANISTIC AND EMPIRICAL MODELS
PullStrength(y)
WireLength(x1)
DieHeight(x2)
9.95 2 50
24.45 8 110
31.75 11 120
35 10 550
25.02 8 295
16.86 4 200
14.38 2 375
9.6 2 52
24.35 9 100
27.5 8 300
17.08 4 412
37 11 400
41.95 12 500
11.66 2 360
21.65 4 205
17.89 4 400
69 20 600
10.3 1 585
34.93 10 540
46.59 15 250
44.88 15 290
54.12 16 510
56.63 17 590
22.13 6 100
21.15 5 400
Example: Observational Study: Semiconductor Wire bond data
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 17/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-3 MECHANISTIC AND EMPIRICAL MODELS
In general, this type of empirical model is called aregression model .
The estimated regression line is given by
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 18/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-4 OBSERVING PROCESSES OVER TIME
Whenever data are collected over time it is important to plotthe data over time. Phenomena that might affect the systemor process often become more visible in a time-oriented plotand the concept of stability can be better judged.
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 19/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-4 OBSERVING PROCESSES OVER TIME
Experiment 1 Experiment 2
Drop marbles one after theother but never moving thefunnel.
Drop first marble and thenadjust funnel before droppingnext marble.
Higher variance on Experiment 2 (over control or tampering)
Adjustments can help to reduce non-random shifts.
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 20/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-4 OBSERVING PROCESSES OVER TIME
8/16/2019 Ch1_StatsInEngineering_torresgarcia.pdf
http://slidepdf.com/reader/full/ch1statsinengineeringtorresgarciapdf 21/21
Reference: Most slides adapted from Montgomery et al. (2011)
1-4 OBSERVING PROCESSES OVER TIME
When to applyadjustments?How much adjustment?
Understanding Variation.
Control Charts are veryuseful to study variation oftime series data.