DESIGN OF EXPERIMENT (ADVANCE LEVEL)

INTRODUCTION FOR DESIGN OF EXPERIMENT (ADVANCE LEVEL)

Design of experiments, also called experimental design, is a structured and organized way of conducting and analyzing controlled tests to evaluate the factors that are affecting a response variable. Experimental design and optimization are tools that are used to systematically examine different types of problems that arise within, e.g., research, development and production. It is obvious that if experiments are performed randomly the result obtained will also be random. 

In an experiment, we deliberately change one or more process variables (or factors) in order to observe the effect the changes have on one or more response variables. The (statistical) design of experiments (DOE) is an efficient procedure for planning experiments so that the data obtained can be analyzed to yield valid and objective conclusions. 

In DOE – II the 2nd order model design is explored to address the limitation 2- level design and further optimization of the process. 2nd Order Model identifies the best possible optimization that could be done with the current existing process. This answers the question if the process can be further improved, or different paradigm shift is needed to address further improvement.  

The training also include exposure to Monte Carlo Simulation Method, which will be useful when real experiment is costly or even dangerous. Meanwhile Taguchi method based on Orthogonal Arrays involves reducing the variation in a process through robust design of experiments. This designing experiment will help to find how different parameters affect the mean and the variance of process, thus drives that quality should be designed into product not inspected into it.

LEARNING OBJECTIVE

This program is designed to enable participants to learn the 2nd order Design of Experiment, and to use it in a practical situation such as Research and Development, Process Optimization and other possible applications. 

Here are the learning objectives for the two days training program; after completing this program, participants will be able to:

• Understand the methodology of design of experiments for 2nd Order Model. 
• Response Surface Methodology 
• Higher Model Design Structure 
• 3k  Design Types 
• Understand how to conduct and analyze the results of a contrast test
• Identify the advantages, disadvantages, assumptions and hypotheses related to various types of designs, including completely randomized design, completely randomized block design, Latin Square design, and factorial designs
• Analyze the results of designed experiments 

WHO SHOULD  ATTEND

Process Engineers, R & D Engineers/Scientist, and other technical based individuals, working with process Improvement.

COURSE OUTLINE

DAY 1

INTRODUCTION 

• Introduction to Response Surface Methodology

RESPONSE SURFACE METHODOLOGY

•  Method of Steepest Ascent

• Need of 2nd Order Model

• Type of Second Order Model 

• 3k  Design for creating 2nd Order Model 

• Box Behnken Design 

• Central Composite Design (CCD) 

• Using Contour and Surface Plot to Analyze RSM 

• Optimizing using Response Optimizer

MIXED LEVEL DESIGN

• Introduction of Mixed Level Full Factorial Design

• Creating Mixed level Full Factorial Design

• Surface and Contour Plot for Mixed level Design 

• Analyzing Mixed Level Design 

• Response Optimizer for Mixed Level Design

Activity 

 RSM and Mixed Level Design Workshop

DAY 2

INTRODUCTION.  

• When real experimental Method can be costly

TRANSFER FUNCTION

1.   Monte Carlo Method Introduction 
2.  Monte Carlo Method Using Transfer Function of DOE
3.  Identifying Distribution 
4.  Simulation of Data 
5. Analyzing Simulation Results. 
6. Analyzing Process Capability and Identifying Improvement 

ALTERNATIVE DESIGN METHODS

1. Taguchi method Introduction 
2. Design Using Taguchi Method 
3. Analyzing Taguchi Method Results 
4. Predict Using Taguchi Method.  

Activity 

1. Taguchi Method Workshop