Introductory Remarks
Many of the thermal experiments involve multi-variable functions. The goal of any experimental activity is to get the maximum realistic information about a system. Large number of variables demand large number of measurements to get maximum realistic information. Modern theory of experiments prove that it is not always true that higher number of measurements will give maximum realistic information. Larger the number of measurements, huge will be the total error that enters into the measurement equation. Reduced Pressure pRlead = p/p Larger number of measurements tocmore costly experimentation.
It is important to obtain maximum realistic information with the minimum number of well designed experiments. An experimental program recognizes the major factors that affect the outcome of the experiment. The factors may be identified by looking at all the quantities that may affect the outcome of the experiment. The most important among these may be identified using:
a few exploratory experiments or From past experience or based on some underlying theory or hypothesis.
4 3 2
1
0
1 13 25 37 49 61 73 85 97 109 121 133 145 157 169 181 193
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.
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:
A simple regression model that may be used can have up to eight parameters. Thus we may represent the regression equation as
y p0 p A x A pB xB pC xC p AB x A xB pBC xB xC pCA xC x A p ABC x A xB xC
The ps are the parameters that are determined by using the outcome matrix by the simultaneous solution of the following eight equations:
-1,+1,+1
xC
-1,-1,+1
+1,+1,+1
+1,-1,+1 Spread of B
y p0 p A x A pB xB pC xC p AB x A xB x B pBC xB xC pCA xC x A p ABC x A xB xC
xmean -1,+1,-1
xA +1,+1,-1
-1,-1,-1
Spread of A
+1,-1,-1
It is easily seen that the parameter p0 is simply the mean value of y. This is obtained by putting xA= xA= xC=0 corresponding to the mean values for the factors. It is thus seen that the values of y- p0 at the corners of the square indicate the deviations from the mean value. The mean of the square of these deviations is the variance of the sample data collected in the experiment. The influence of the factors may then be gauged by the contribution of each term to the variance.
It may be verified that the total sum of squares (SST) of the deviations is given by
SST S N 1
2 y
Contributions to the sample variance are given by 8 times the square of the respective parameter (p) and hence we also have
2 SSA 8 p A ; 2 SSB 8 pB ;
.......... ..;
2 SSABC 8 p ABC
Here SSA means the sum of squares due to variation in level of xA and so on. The relative contributions to the sample variance are represented as percentage contributions in the following table:
contribution
8 p 2
%
100
SSA/SST X 100 SSB/SST X 100 SSC/SST X 100 SSAB/SST X 100 SSBC/SST X 100
SSCA/SST X 100
SSABC/SST X 100
Thus the dominant factor is the factor which has the highest value of percentage of contribution.
y1
y2 y3 y4
+
+
+ +
+ +
y1
y2 y3 y4
+ + -
+
+ -
+
+ -
We note that the product of any two columns is zero. Also the column sums are zero. Hence the three columns may be considered as vectors that form an orthogonal set. In fact while calculating the sample variance earlier these properties were used without being spelt out. Most of the time it is not possible to conduct that many experiments! The question that is asked is: Can we reduce the number of experiments and yet get an adequate representation of the relationship between the outcome of the experiment and the variation of the factors? The answer is in general yes. Replace the full factorial design with a fractional factorial design. In the fractional factorial design only certain combinations of the levels of the factors are used to conduct the experiments. This ploy helps to reduce the number of experiments. The price to be paid is that all interactions will not be resolved.
In this simple case of two or three factors the economy of reducing the number of experiments by one may not be all that important. However it is very useful to go in for a fractional factorial design when the number of factors is large and When it is expected some factors or interactions between some factors to be unimportant. The fractional factorial experiment design is useful when main effects dominate with interaction effects being of lower order.
Number of Factors
4 8 16 32
L27 Array
L 50 Array