Simulation

What is simulation
A simulation is an imitation of the dynamics of a real-world process or system

over time. Although simulation could potentially still be done “by hand,”
nowadays it almost always implicitly requires the use of a computer to create
an artificial history of a system to draw inferences about its characteristics
and workings.
The behavior of the system is studied by constructing a simulation model ,
which usually takes the form of a set of assumptions about the workings of the
system. Once developed, a simulation model can be used for a variety of tasks,
including:
 Investigate the behavior of the system under a wide array of scenarios. This is
also often referred to as “what-if” analyses;
 Changes to the system can be simulated before implementation to predict
their impact in real-world;
 During the design stage of a system, meaning while it is being built, simulation
can be used to guide its construction.
Computer simulation has been used in a variety of domains, including
manufacturing, health care, transport system, defense and management
science, among many others.
A simple simulation model

Suppose we decided to open a donut shop and are unsure about how many
employees to hire to sell donuts to costumers. The operations of our little shop
is the real-world system whose behavior we want to understand. Given that
the shop is not operating yet, only a simulation model can provide us with
insights.
We could of course devise models of different complexities, but for now
suppose that we are happy with a simple model where we have the following
elements:
 costumers that arrive at our shop at a particular rate;
 employees (of a number to be given as input) that take a specific time to serve
costumers.
Implicitly, we are completely disregarding the number of donuts available in
our shop and assuming that we have an infinite availability of these. Of course,
in a more complex simulation model we may want to also include this element
to give a more realistic description of the system.
Why simulate.
An alternative approach to computer simulation is direct experimentation. In
the bagel shop setting, we could wait for the shop to open and observe its
workings by having a different number of employees on different days.
Considered against real experimentation, simulation has the following
advantages:
 It is cheaper to implement and does not require a disruption of the real-world
system;
 It is faster to implement and time can be compressed or expanded to allow
for a speed-up or a slow-down of the system of interest;
 It can be replicated multiple times and the workings of the systems can be
observed a large number of times;
 It is safe since it does not require an actual disruption of the system;
 It is ethical and legal since it can implement changes in policies that would
be unethical or illegal to do in real-world.
Another alternative is to use a mathematical model representing the system.
However, it is often infeasible, if not impossible, to come up with an exact
mathematical model which can faithfully represent the system under study.
Design of experiments (DOE)

Design of experiments (DOE) is defined as a branch of applied statistics that
deals with planning, conducting, analyzing, and interpreting controlled tests to
evaluate the factors that control the value of a parameter or group of
parameters. DOE is a powerful data collection and analysis tool that can be
used in a variety of experimental situations.
It allows for multiple input factors to be manipulated, determining their effect on

a desired output (response). By manipulating multiple inputs at the same time,
DOE can identify important interactions that may be missed when experimenting
with one factor at a time. All possible combinations can be investigated (full
factorial) or only a portion of the possible combinations (fractional factorial).
A strategically planned and executed experiment may provide a great deal of

information about the effect on a response variable due to one or more factors.
Many experiments involve holding certain factors constant and altering the
levels of another variable. This "one factor at a time" (OFAT) approach to
process knowledge is, however, inefficient when compared with changing factor
levels simultaneously.
Many of the current statistical approaches to designed experiments originate

from the work of R. A. Fisher in the early part of the 20th century. Fisher
demonstrated how taking the time to seriously consider the design and
execution of an experiment before trying it helped avoid frequently encountered
problems in analysis. Key concepts in creating a designed experiment include
blocking, randomization, and replication.
 Blocking: When randomizing a factor is impossible or too costly, blocking lets
you restrict randomization by carrying out all of the trials with one setting of the
factor and then all the trials with the other setting.
 Randomization: Refers to the order in which the trials of an experiment are
performed. A randomized sequence helps eliminate effects of unknown or

uncontrolled variables.
 Replication: Repetition of a complete experimental treatment, including the
setup.
A well-performed experiment may provide answers to questions such as:
 What are the key factors in a process?
 At what settings would the process deliver acceptable performance?
 What are the key, main, and interaction effects in the process?
 What settings would bring about less variation in the output?
A repetitive approach to gaining knowledge is encouraged, typically involving

these consecutive steps:
1. A screening design that narrows the field of variables under assessment.

2. A "full factorial" design that studies the response of every combination of
factors and factor levels, and an attempt to zone in on a region of values where
the process is close to optimization.
3. A response surface designed to model the response.
WHEN TO USE DOE

Use DOE when more than one input factor is suspected of influencing an output.
For example, it may be desirable to understand the effect of temperature and
pressure on the strength of a glue bond.
DOE can also be used to confirm suspected input/output relationships and to

develop a predictive equation suitable for performing what-if analysis.

Simulation

Uploaded by

Copyright:

Available Formats

Simulation

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Simulation

Uploaded by

Copyright:

Available Formats

What is simulation

A simulation is an imitation of the dynamics of a real-world process or system

A simple simulation model

Design of experiments (DOE)

It allows for multiple input factors to be manipulated, determining their effect on

A strategically planned and executed experiment may provide a great deal of

Many of the current statistical approaches to designed experiments originate

 Blocking: When randomizing a factor is impossible or too costly, blocking lets

performed. A randomized sequence helps eliminate effects of unknown or

A well-performed experiment may provide answers to questions such as:

 What are the key factors in a process?

 At what settings would the process deliver acceptable performance?

 What settings would bring about less variation in the output?

A repetitive approach to gaining knowledge is encouraged, typically involving

1. A screening design that narrows the field of variables under assessment.

WHEN TO USE DOE

DOE can also be used to confirm suspected input/output relationships and to

You might also like