IE 432

KING ABDULAZIZ UNIVERSITY

Department of Industrial Engineering

IE 432: Design of Industrial Experiments 

Dr. Ammar Y. Alqahtani

Course Description

Much of the progress in the sciences comes from performing experiments. These may be of either an exploratory or a confirmatory nature. Experimental evidence can be contrasted with evidence obtained from other sources such as observational studies, anecdotal evidence, or “from authority”.

This course focuses on design and analysis of experiments. While not denigrating the roles of anecdotal and observational evidence, the substantial benefits of experiments make them one of the cornerstones of science. This course presents the two main topics of experimental design and statistical analysis of experimental results in the context of the large concept of scientific learning.

Course Prerequisites

IE 323; engineering students only.

Textbooks

• Montgomery, D. C. (2013). ”Design and Analysis of Experiments”, 8th Edition., John Wiley and Sons, N.Y., ISBN: 978-1118146927.

References

• George E.P. Box, J.Stuart Hunter, William G. Hunter (2005). Statistics for Experimenters 2nd Edition, John Wiley and Sons, Inc.
• Cox D.R. (1992). Planning of Experiments, John Wiley, NY.
• Cobb George, W. (2008). Introduction to Design and Analysis of Experiments., John Wiley, NY.
• Hines, W. William, Montegomery, D.C. (2008), Probability and Statistics for Engineers, 4th edition, John Wiley, NY.
• Jiju Antony (2014). Design of Experiments for Engineers and Scientists, 2nd Revised editions, Elsevier Science Ltd.

Course Topics:

• Introduction to DoE: concepts, components of design.
• Selection of appropriate designs for comparative and factorial experiments: Strategy of Experimentation, guidelines.
• Review basic statistical concepts, sampling and sampling distributions, inferences about differences in means in randomized designs inferences about differences in means in paired comparison designs, inferences about variances of normal distributions, planning experiments, main steps for effectively applying DoE.
• Analysis of fixed effect model (CRD &ANOVA), model adequacy checking (graphical tools, Half Normal probability Plot), practical interpretation of results (regression Model, Trt comparisons), determining sample size, Random effect model.
• Experiments with Blocking Factors:  RCBD, Latin Squares Greco-Latin design.
• Factorial Designs: the advantage of factorials, calculation of factor effects and regression equation, two factor factorial, general factorial design, response surface curves and contour curves, blocking factorial designs.
• 2^k Factorial designs: 2² design, 2³ design, the general 2^k factorial design, confounding the 2^k factorial design in 2^p blocks.
• Response Surface Methodology: introduction, method of steepest ascent, analysis of a second order response surface, experimental designs for fitting response surfaces, experiments with computer models.
• Robust Designs: crossed array design and its analysis, experimental designs for fitting response surfaces, choice of designs.

Course Objectives:

At the completion of the course, students should be able to:

• Recognize the importance of Design of Experiments (DoE) in industrial engineering
• Recognize the importance DoE as an effective approach for improving the quality and performance of various engineering systems and processes.
• Acquire the required knowledge on the need for applying DoE in practice
• Plan an experiment including formulation of the problem encountered, identification of objectives, selection of relevant variables or parameters to be examined and determination of the appropriate performance measures
• Develop an ability to effectively and efficiently design and execute industrial experiment
• Develop the necessary skills for analyzing the experimental data and interpreting the obtained results so that reliable conclusions can be drawn.
• Obtain a background on how to utilize the statistical and Engineering knowledge in detecting and modeling the potential causal relationship between the studied variables and the concerned performance measures
• Use statistical and DoE software packages to analyze experimental data
• Present the result and conclusions drawn using DoE in clear and proficient manner.