WASSUP GUYS and Happy/Sad New Year!!!
This week's content felt quite nostalgic as it reminded me of quite a number of practicals I did in Secondary School about designing experiments. So in my first blog of the year for Chemical Product Design & Development, CP5070, I'll document the process of creating a series of experiments to obtain the required results for examination via Full Factorial and Fractional Factorial data analysis methods; and my learning reflection of my DOE Practical session.
Scenario
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 experiment and the measured variable is the amount of “bullets” formed in grams and the data collected are shown below:
Factor A= diameter
Factor B= microwaving time
Factor C= power
Full Factorial Method
Determine the effect of single factors and their ranking
From the graph above, I can determine that:
When the Diameter (A) increases from 10cm to 15cm the average mass of the "bullets" increases from 1.448g to 1.885g.
When the Microwaving Time increases from 4 minutes to 6 minutes, the mass of the "bullets" decreases from 1.843g to 1.490g.
When the Power increases from 75% to 100%, the mass of the "bullets" decreased from 2.098g to 1.235g.
I can conclude that:
Determine the interaction effects.
Excel File
Conclusion
Partial Factorial Method
Determine the effect of single factors and their ranking
In order to obtain a balanced design with good statistical properties for fractional factorial analysis, runs 1, 2, 3 & 6 have been chosen as all factors occur, both low and high levels, the same number of times. It is said to be orthogonal.
From the graph above, I can determine that:
When the Diameter (A) increases from 10cm to 15cm the average mass of the "bullets" decreases from 1.073g to 0.7175g.
When the Microwaving Time increases from 4 minutes to 6 minutes, the mass of the "bullets" decreases from 1.605g to 0.185g.
When the Power increases from 75% to 100%, the mass of the "bullets" decreased from 1.710g to 0.08g.
I can conclude that:
Excel File
Conclusion
Learning Reflection
When DOE was introduced to us in our tutorial lesson, it felt quite familiar to me as I remember answering the planning questions during Chemistry practicals in Secondary School. However, in this tutorial, I was introduced to new information such as Full Factorial analysis, Fractional Factorial analysis, Interactions and graph plotting. Determining how many experiments we need to conduct during an experiment is also much simpler now as I'm now aware of this new formula: N=r2^n.
N: Number of experiments
r: Number of repetitions
n: Number of factors
These lessons about product design have truly raised my interest to become a product designer instead of working at a chemical plant. I recall Mr Chua mentioned in class that in the industry, it's not very feasible to be conducting Full Factorial experimentation as companies are constrained with time to deliver a product by a certain day. Hence conducting a Fractional Factorial analysis would be more time effective. However, a major downside of conducting Fractional Factorial analysis over Full Factorial analysis would be the reliability of the data obtained. Since we would be analysing the results of fewer experiments, the experiments conducted need to have a balanced design with good statistical properties.
In some cases, the Full Factorial and Fractional factorial give similar and reliable results such as the catapult experiment we did. However, in the case study, I showed in this blog, my Full Factorial and Fractional Factorial data gave different conclusions. I would personally choose to conduct Full Factorial analysis over Fractional Factorial, but if time is really not in the essence, I would have no other choice but to believe in the results of Fractional Factorial experimentation.
The practical sessions in CPDD honestly just keep getting better and better. This was by far the most fun I've had with my group during a practical. The practical was simple and stress-free which made it possible for us to play around with the catapult as soon as we completed all 96 experiments.
I'd love to thank my beloved teammates; Devin for shouting "HOORAY" every time we launched a ball and keying in the data for the Full Factorial method into excel, Jun Kai for being our professional catapult handler during the experimentation and challenge phase, Ji Hinn for helping us determine how far the ball travelled, & Jia Tong for keying in the data of Fractional Factorial method into the excel. The analysis of our results was also very simple as I created the excel before the date of this practical. Devin and Jia Tong just had to input our data into the excel table, and the graphs were created automatically.
The challenge phase of this Practical was the best as we were given the privilege to use our experimentation data to set up our catapults to hit down 4 targets as shown below.
Before we made our attempt to hit down our targets, I measured the distance between the starting point and the targets themselves. Mr Ting was 67cm away, followed by Dr Noel, 107cm, Mr Chua, 147cm, & the Final Boss, Ms Oh who was 194cm away. We conducted some experiments via trial and error and found the setting shown below gave us the highest possibility of hitting all the targets
With That said, I'll just let the following videos and pictures show the results we achieved for the challenge phase of our last practical session for CPDD. See yall in my next blog.
-------------------------------------Hasta La Vista Baby-------------------------------------
Comments