Hae-Jin Choi School of Mechanical Engineering, Chung-Ang University Design of Experiments (DOE) and Optimization 1. Introduction 1 DOE and Optimization
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Hae-Jin ChoiSchool of Mechanical Engineering,
Chung-Ang University
Design of Experiments (DOE) and Optimization
1. Introduction
1DOE and Optimization
Introduction to Lectures
2
Professor : Choi, Hae-Jin, 310-531
(Email) [email protected], (Office) 02-820-5787, (Mobile) 010-6726-6096
Class : Tue (2-3pm), Thur (1-3 pm), Lecture room (301-520)
Pre-requisite:
Numerical analysis - 수치해석 (course code: 47892, Semester 1)
Text books: Montgomery, D. C., (2012), Design and Analysis of Experiments, 8th Ed., John Wiley & Sons.
Arora, J. S. (2011), Introduction to Optimum Design, 2nd Ed., Elsevier.
Lecture Note (http://isdl.cau.ac.kr/ Education section)
Software: MINITAB (http://www.minitab.com/)
MATLAB (http://www.mathworks.co.kr/products/matlab/index.html)
Pp. 18 Software Installation Guide
Assessment : Continuous assessment (10%), Design project (20%), Mid-term (30%), Final (40%)
Office hour: Tue(11-12am) or by email appointment
DOE and Optimization
What is Design of Experiments (DOE)?
3
Design of Experiments (DOE) is;
Planning experiments or tests to save resources (time and money)
Analyzing results of experiments or tests to characterize your
system
Experiments are used widely in the engineering world
Process characterization & optimization
Evaluation of material properties
Product design & development
Component & system tolerance determination
DOE and Optimization
Example: Golfing
4
How to improve my score in Golfing?
Practice!!!
Other than that?
Type of driver used (oversized or regular sized)
Type of ball (2 piece or 3 piece)
Walking or riding cart
Drinking water or beer
Etc…
What combination of the factors is the best for me?
DOE and Optimization
General Model of a Process or System
5
System: function, model, or manufacturing process to transform input to output Golf game
Input: provided materials or energy into the process or system Physical energy to play golf
Response (output): outcome of a process or performance of a system Score
Controllable factors: factors that experimenters can control Driver type, ball type, etc.
Uncontrollable factors (noise factors): factors that experiments cannot control Course layout, grass type, weather, etc.
Response
(Output)System
(Process) y
…..
Input
x1 x2 xp
z1 z2 zq
Controllable factors
Uncontrollable factors
(Noise factors)
DOE and Optimization
What needs to be analyzed?
6
Determining which variables are
most influential on the response y.
Determining where to set the
controllable factors x so that y is
almost always near the desired
nominal value.
How about in the golf experiments?
Response
(Output)System
(Process) y
…..
Input
x1 x2 xp
z1 z2 zq
Controllable factors
Uncontrollable factors
(Noise factors)
DOE and Optimization
How to find my best condition?
7
One-factor-at-a time strategy
Any Problem??
DOE and Optimization
Interaction Effect between the Factors
8
Interaction effect between type of driver and beverage
DOE and Optimization
Factorial Design of Experiments
9
Two factors with 2 level for each factor
DOE and Optimization
Factorial Design of Experiments
10
Three factors
Four factors
Any Problem??DOE and Optimization
Fractional Factorial Design of Experiments
11
16 experiments -> 8 experiments
Questions for the semester
• How to effectively reduce the number of experiments?
• How to analyze the results of experiments?
DOE and Optimization
Developing Empirical Model
12
Developing relationship between
controllable (uncontrollable)
factors and response
Response Surface MethodologyResponse
(Output)System
(Process) y
…..
Input
x1 x2 xp
z1 z2 zq
Controllable factors
Uncontrollable factors
(Noise factors)
DOE and Optimization
Quality Engineering (품질공학)
13
Taguchi and robust parameter design
Determining where to set the
controllable factors x so that
variability in y is small
Determining where to set the
controllable factors x so that effect
of uncontrollable factors z are
minimized.
Response
(Output)System
(Process) y
…..
Input
x1 x2 xp
z1 z2 zq
Controllable factors
Uncontrollable factors
(Noise factors)
y
DOE and Optimization
Robust Design (강건설계)
AD 1592~1598: 23 Battles
Optimized for the
fastest navigation
23 Win 0 Win
Robust navigation
under uncertainty
in operating
condition
A B
DOE and Optimization 14
Four Eras in the History of DOE
DOE and Optimization 15
The agricultural origins, 1908 – 1940s W.S. Gossett and the t-test (1908) R. A. Fisher & his co-workers Profound impact on agricultural science Factorial designs, ANOVA
The first industrial era, 1951 – late 1970s Box & Wilson, response surfaces Applications in the chemical & process industries
The second industrial era, late 1970s – 1990 Quality improvement initiatives in many companies Taguchi and robust parameter design, process robustness
The modern era, beginning circa 1990
R. A. Fisher George E. P. Box
Genichi Taguchi
Optimization (최적화)
16
How to efficiently explore the design space (factor space) to
achieve the best response ?
DOE and Optimization
Course Schedule
17
Introduction to DOE
Experiments with One Factor
Analysis of Variance (ANOVA)
2k Factorial Design
Fractional Factorial Design
Response Surface Methodology
Mid-Term Exam
Taguchi Robust Design
Design Project
Introduction to Optimization
Linear Programming
Unconstrained Optimization
Constrained Optimization
Direct Search Method
Pareto Optimality
Final-Exam
DOE and Optimization
Software Installation Guide
DOE and Optimization 18
Minitab installation
Login at http://isdlnas2.ipdisk.co.kr
ID: isdlguest, PW: nasguest
Go to HDD1 → DOE → download “minitab18.1.0.0setup.exe”
License server IP: 165.194.3.62
Port number: 27000
Only available within CAU campus network!!
Matlab installation
Follow CAU Matlab installation guide here
Available outside of campus with the proper installation.
Related Documents
