UNIT - IV
ENGINEERING STATISTICS
AND RELIABILITY
Introduction
Probability theory is a very fascinating subject which can
be studied at various mathematical levels. Probability is the
foundation of statistical theory and applications.
Several mathematicians like Pascal, James Bernoulli, De-
Moivre, Bayes applied the theory of permutations and
combinations to quantify or calculate probability. Today the
probability theory has become one of the fundamental
technique in the development of Statistics.
The term “probability” in Statistics refers to the chances
of occurrence of an event among a large number of
possibilities.
TERMINOLOGIES
Random Experiment:
If an experiment or trial is repeated under the same conditions
for any number of times and it is possible to count the total number
of outcomes is called as “Random Experiment”.
Sample Space:
The set of all possible outcomes of a random experiment is
known as “Sample Space” and denoted by set S. [this is similar to
Universal set in Set Theory] The outcomes of the random experiment
are called sample points or outcomes.
• Event:
An ‘event’ is an outcome of a trial meeting a
specified set of conditions other words, event is
a subset of the sample space S.
Events are usually denoted by capital letters.
There are different types of events.
1. Null or impossible event is an event which
contains no outcomes.
2. Elementary event is an event which contains
only one outcomes.
3. Composite event is an event which contains
two or more outcomes.
4. Sure or certain event is an event which
contains all the outcomes of a sample space.
In other words, several events are said to be ‘dependents’
if the occurrence of an event is affected by the occurrence of
any number of remaining events, in a series of trials.
Measurement
Measurement of
of Probability:
Probability:
There are three approaches to construct a
measure of probability of occurrence of an event.
They are:
• Classical Approach,
• Frequency Approach and
• Axiomatic Approach.
Classical or Mathematical Approach:
In this approach we assume that an experiment or trial
results in any one of many possible outcomes, each
outcome being Equi-probable or equally-likely.
Definition: If a trial results in ‘n’ exhaustive, mutually
exclusive, equally likely and independent outcomes, and if
‘m’ of them are favourable for the happening of the event
E, then the probability ‘P’ of occurrence of the event ‘E’ is
given by-
Number of outcomes favourable to event E m
P(E) = =
Exhaustive number of outcomes n
Empirical or Statistical Approach:
This approach is also called the ‘frequency’ approach to
probability. Here the probability is obtained by actually
performing the experiment large number of times. As the
number of trials n increases, we get more accurate result.
Definition: Consider a random experiment which is
repeated large number of times under essentially
homogeneous and identical conditions. If ‘n’ denotes the
number of trials and ‘m’ denotes the number of times an
event A has occurred, then, probability of event A is the
limiting value of the relative frequency m .
n
Axiomatic Approach:
This approach was proposed by Russian Mathematician
A.N.Kolmogorov in1933.
‘Axioms’ are statements which are reasonably true and
are accepted as such, without seeking any proof.
Definition: Let S be the sample space associated with a
random experiment. Let A be any event in S. then P(A) is the
probability of occurrence of A if the following axioms are
satisfied.
1. P(A)>0, where A is any event.
2. P(S)=1.
3. P(AUB) = P(A) + P(B), when event A and B are
mutually exclusive.
Design of Experiments (DOE)
– A statistics-based approach to design experiments
– A methodology to achieve a predictive knowledge of a
complex, multi-variable process with the fewest acceptable
trials.
– An optimization of the experimental process itself
Major Approaches to DOE
• Factorial Design
• Taguchi Method
Factorial Design : Full factorial design
• A full factorial design of experiments consists of the following:
• Vary one factor at a time
• Perform experiments for all levels of all factors
• Hence perform a large number of experiments that are needed!
• All interactions are captured.
• Consider a simple design for the following case:
• Let the number of factors = k
• Let the number of levels for the ith factor = ni
• The total number of experiments (N) that need to be performed is
K
N ni
i 1
2k factorial design
• Used as a Preliminary Experimentation !!!
• Each of the k factors is assigned only two levels.
• The levels are usually High = 1 and Low = -1.
• Scheme is useful as a preliminary experimental program
before a more ambitious study is undertaken.
• The outcome of the 2k factorial experiment will help
identify the relative importance of factors and also will
offer some knowledge about the interaction effects.
DOE - Factorial Designs - 23
Trial A B C
1 -1 -1 -1
2 -1 -1 +1
3 -1 +1 -1
4 -1 +1 +1
5 +1 -1 -1
6 +1 -1 +1
7 +1 +1 -1
8 +1 +1 +1
Output Matrix
• Let us represent the outcome of each experiment to be a
quantity y.
• Thus y1 will represent the outcome of experiment number
1 with all three factors having their “LOW” values,
• y2 will represent the outcome of the experiment number 2
with the factors A & B having the “Low” values and the
factor C having the “High” value and so on.
• The outcome of the experiments may be represented as
the following matrix:
DOE - Taguchi Method
• Dr. Taguchi of Nippon Telephones and Telegraph
Company, Japan has developed a method based on "
ORTHOGONAL ARRAY " experiments.
• This gives much reduced " variance " for the
experiment with " optimum settings " of control
parameters.
• "Orthogonal Arrays" (OA) provide a set of well
balanced (minimum) experiments serve as objective
functions for optimization.
Taguchi Method : When to Select a ‘larger’ OA
to perform “Factorial Experiments”
• We always ‘think’ about ‘reducing’ the number of
experiments (to minimize the ‘resources’ – equipment,
materials, manpower and time)
• However, doing ALL / Factorial experiments is a good idea
if
– Conducting experiments is ‘cheap/quick’ but
measurements are ‘expensive/take too long’
– The experimental facility will NOT be available later to
conduct the ‘verification’ experiment
– We do NOT wish to conduct separate experiments for
studying interactions between Factors
Taguchi Method Design of Experiments
• The general steps involved in the Taguchi Method are as follows:
• 1. Define the process objective, or more specifically, a target value
for a performance measure of the process.
• 2. Determine the design parameters affecting the process.
• The number of levels that the parameters should be varied at
must be specified.
• 3. Create orthogonal arrays for the parameter design indicating
the number of and conditions for each experiment.
• The selection of orthogonal arrays is based on the number of
parameters and the levels of variation for each parameter, and
will be expounded below.
• 4. Conduct the experiments indicated in the completed array to
collect data on the effect on the performance measure.
• 5. Complete data analysis to determine the effect of the different
parameters on the performance measure.
