IIUM Repository (IREP)

An alternative approach to experimentation and data analysis

Wahid, Zaharah (2012) An alternative approach to experimentation and data analysis. In: 2nd International Conference on Mathematical Applications in Engineering (ICMAE 2012), 3 - 5 July 2012, Kuala Lumpur.

[img] PDF (full paper) - Published Version
Restricted to Registered users only

Download (409kB) | Request a copy
[img] PDF - Supplemental Material
Restricted to Repository staff only

Download (56kB) | Request a copy

Abstract

Our knowledge about a product, process or a system in the scientific and engineering disciplines is often obtained from experimentation. Experiments can discover many unexpected things and highlighted issues for further detailed study. The emerging of advanced products and processes are changing rapidly, customers are more demanding and product life-cycle and time to market are shrinking. In this environment engineers and scientists need a strategic approach to overcome this demand. DOE is the answer to these challenges. It allows a researcher to understand what happen to the output (response) when the settings of the input variables in a system are purposely changed. As a result these changes permit work to be done better, faster, and easier. In addition, DOE has proven to be extremely useful tool in research and industrial development applications. Unfortunately there are many scientists and engineers still practice the study one factor-at a-time (OFAT). DOE offers a number of advantages over the traditional OFAT approach to experimentation. One of the important advantages of DOE is that it has the ability to discover the presence of interaction between the factors of the process, while OFAT does not. The objective of this paper is to demonstrate how DOE approach works. This paper describes a case study on rubber glove manufacturing process. It illustrates interaction between factors that cannot be found when varying only one factor at a time. Model that describes the relationships between the inputs and output variables were then developed and used to indicate areas where operations may be improved. Successful experiments begin with systematic planning followed by good project management and coordination. When these things are done properly, the potential benefits of DOE are tremendous.

Item Type: Conference or Workshop Item (Full Paper)
Additional Information: 6526/27499 (ISBN : 978-983-43090-5-3)
Uncontrolled Keywords: Design of Experiments, Analysis of Variance, One-Factor -at- a-Time, Replication, Blocking, Optimization, Randomization
Subjects: Q Science > QA Mathematics
T Technology > T Technology (General) > T55.4 Industrial engineering.Management engineering.
T Technology > T Technology (General) > T55.4 Industrial engineering.Management engineering. > T57 Applied mathematics. Quantitative methods. Operation research. System analysis
Kulliyyahs/Centres/Divisions/Institutes: Kulliyyah of Engineering
Depositing User: Dr. Zaharah Wahid
Date Deposited: 11 Oct 2013 17:17
Last Modified: 25 Jun 2015 10:33
URI: http://irep.iium.edu.my/id/eprint/27499

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year