E1C01 09/14/2010
15:40:34 Page 7
2. System and tolerance design plan. Select a measurement technique, equipment, and
test procedure based on some preconceived tolerance limits for error.
3 Ask: ‘‘In what
ways can I do the measurement and how good do the results need to be to answer my
question?’’
3. Data reduction design plan. Plan how to analyze, present, and use the anticipated data.
Ask: ‘‘How will I interpret the resulting data? How will I use the data to answer my question?
How good is my answer? Does my answer make sense?’’
Going through all three steps in the test plan before any measurements are taken is a useful
habit for a successful engineer. Often, step 3 will force you to reconsider steps 1 and 2! In this
section, we focus on the concepts related to step 1 but will discuss and stress all three throughout
the text.
Variables
Once we define the question that we want the test to answer, the next step is to identify the relevant
process parameters and variables. Variables are entities that influence the test. In addition to the
targeted measured variable, there may be other variables pertinent to the measured process that will
affect the outcome. All known process variables should be evaluated for any possible cause-andeffect relationships. If a change in one variable will not affect the value of some other variable, the
two are considered independent of each other. A variable that can be changed independently of other
variables is known as an independent variable. A variable that is affected by changes in one or more
other variables is known as a dependent variable. Normally, the variable that we measure depends on
the value of the variables that control the process. A variable may be continuous, in that its value is
able to change in a continuous manner, such as stress under a changing load or temperature in a
room, or it may be discrete in that it takes on discrete values or can be quantified in a discrete way,
such as the value of the role of dice or a test run by a single operator.
The control of variables is important. A variable is controlled if it can be held at a constant value
or at some prescribed condition during a measurement. Complete control of a variable would imply
that it can be held to an exact prescribed value. Such complete control of a variable is not usually
possible. We use the adjective ‘‘controlled’’ to refer to a variable that can be held as prescribed, at
least in a nominal sense. The cause-and-effect relationship between the independent variables and
the dependent variable is found by controlling the values of the independent variables while
measuring the dependent variable.
Variables that are not or cannot be controlled during measurement but that affect the value of the
variable measured are called extraneous variables. Their influence can confuse the clear relation
between cause and effect in a measurement. Would not the driving style affect the fuel consumption
of a car? Then unless controlled, this influence will affect the result. Extraneous variables can
introduce differences in repeated measurements of the same measured variable taken under
seemingly identical operating conditions. They can also impose a false trend onto the behavior
of that variable. The effects due to extraneous variables can take the form of signals superimposed
onto the measured signal with such forms as noise and drift.
3 The tolerance design plan strategy used in this text draws on uncertainty analysis, a form of sensitivity analysis. Sensitivity
methods are common in design optimization.
1.3 Experimental Test Plan 7
15:40:34 Page 7
2. System and tolerance design plan. Select a measurement technique, equipment, and
test procedure based on some preconceived tolerance limits for error.
3 Ask: ‘‘In what
ways can I do the measurement and how good do the results need to be to answer my
question?’’
3. Data reduction design plan. Plan how to analyze, present, and use the anticipated data.
Ask: ‘‘How will I interpret the resulting data? How will I use the data to answer my question?
How good is my answer? Does my answer make sense?’’
Going through all three steps in the test plan before any measurements are taken is a useful
habit for a successful engineer. Often, step 3 will force you to reconsider steps 1 and 2! In this
section, we focus on the concepts related to step 1 but will discuss and stress all three throughout
the text.
Variables
Once we define the question that we want the test to answer, the next step is to identify the relevant
process parameters and variables. Variables are entities that influence the test. In addition to the
targeted measured variable, there may be other variables pertinent to the measured process that will
affect the outcome. All known process variables should be evaluated for any possible cause-andeffect relationships. If a change in one variable will not affect the value of some other variable, the
two are considered independent of each other. A variable that can be changed independently of other
variables is known as an independent variable. A variable that is affected by changes in one or more
other variables is known as a dependent variable. Normally, the variable that we measure depends on
the value of the variables that control the process. A variable may be continuous, in that its value is
able to change in a continuous manner, such as stress under a changing load or temperature in a
room, or it may be discrete in that it takes on discrete values or can be quantified in a discrete way,
such as the value of the role of dice or a test run by a single operator.
The control of variables is important. A variable is controlled if it can be held at a constant value
or at some prescribed condition during a measurement. Complete control of a variable would imply
that it can be held to an exact prescribed value. Such complete control of a variable is not usually
possible. We use the adjective ‘‘controlled’’ to refer to a variable that can be held as prescribed, at
least in a nominal sense. The cause-and-effect relationship between the independent variables and
the dependent variable is found by controlling the values of the independent variables while
measuring the dependent variable.
Variables that are not or cannot be controlled during measurement but that affect the value of the
variable measured are called extraneous variables. Their influence can confuse the clear relation
between cause and effect in a measurement. Would not the driving style affect the fuel consumption
of a car? Then unless controlled, this influence will affect the result. Extraneous variables can
introduce differences in repeated measurements of the same measured variable taken under
seemingly identical operating conditions. They can also impose a false trend onto the behavior
of that variable. The effects due to extraneous variables can take the form of signals superimposed
onto the measured signal with such forms as noise and drift.
3 The tolerance design plan strategy used in this text draws on uncertainty analysis, a form of sensitivity analysis. Sensitivity
methods are common in design optimization.
1.3 Experimental Test Plan 7