CP5070-2022-2B03-GROUP1-ADYL BIN YANI
Design of Experiment
(DOE)
What is
DOE?
DOE is a way to determine information about factors that affect the performance of a product. DOE is mainly used to improve product designs.
In DOE,
There are...
1 / Fractional Factorial
Using half of the runs that were carried out to determine results. It is quicker and efficient
2 / Full Factorial
Using every run to determine results.
How to determine number of runs?
N= Number of experiments
r= Number of replicates
l= Number of levels {There are 2 levels, high(+) and low(-).}
n=Number of factors
Case Study
What could be simpler than making microwave popcorn? Unfortunately, as everyone who has ever made popcorn knows, it’s nearly impossible to get every kernel of corn to pop. Often a considerable number of inedible “bullets” (un-popped kernels) remain at the bottom of the bag. What causes this loss of popcorn yield? In this case study, three factors were identified:
-
Diameter of bowls to contain the corn, 10 cm and 15 cm
-
Microwaving time, 4 minutes and 6 minutes
-
Power setting of microwave, 75% and 100%
8 runs were performed with 100 grams of corn used in every experiments and the measured variable is the amount of “bullets” formed in grams and data collected are shown below:
Factor A= diameter
Factor B= microwaving time
Factor C= power
note: "+" and "-" represent high and low value of the factors
Full Factorial
With the above findings from a case study, I've plotted a graph using a DOE excel template!
With the values input into the template, I then produced a graph to determine the significance of each factor relative to each other.
With the above graph, it is seen that the ranking of most significant factor is as follows:
1. Power
2. Microwaving time
3. Diameter of bowl
This is determined by the steepness of each factor's line. As seen in the graph, when the Power of the microwave was 100% (x-axis, 2 = +), the mass of "bullets" was the lowest (0.65g). With microwaving time, when the microwaving time was the longest (+), the mass of bullets was the lowest for that factor (1.275g). Lastly, when when the diameter of the bowl was the smallest (1 = -), and when it was the highest (2 = +), there was not much of a difference hence the most insignificant factor.
Now comparing specific factors with one another.
From the above graph, it is said that factor A and B do have some significance to each other as when A increases at Low B, mass of bullets increases. When A increases at high B, mass of bullet decreases.
Comparing factor A with C, the lines are almost parallel to each other which means that they both do not affect each other. There is some significance but it is close to none.
Comparing factors B and C, they both have a significance to each other as their lines tend to each other and will intercept.
Overall, in order to get the least amount of "bullets", one should use 100% power followed by the 6 min microwaving time
The link to the Full Factorial excel template can be found here!
Using partial factorial to test the significance of each factor, I have selected runs 1,2,6 and 8.
This is the input into the template
Based on the graphs, the significance remains the same (X-axis title: Factor High to Low) with Factor C being the most significant and Factor A being the least.
In conclusion, Fractional Factorial is faster and efficient and would give roughly the same result as a Full Factorial. When learning and carrying out DOE, I did not realise how tedious conducting a Full Factorial would be. I now understand why Fractional Factorial may be used in some cases. My initial thought was that the fractional factorial would yield less accurate information given the number of information to work with was lesser but i was wrong.
I only realized this after going through the tutorial and practical and getting the same results as the case study i.e. fractional is almost the same as full.
Fractional Factorial
