# Design of Experiments for Optimisation

DoE using R: Response Surface Methodology, Lack-of-Fit, Central Composite Designs, Box-Behnken Designs

4.5/5

## Design of Experiments for Optimisation

### What you’ll learn

– Basic concepts of regression models;
– Factorial designs with central points;
– Lack-of-fit test;
– Inaccurate levels in the design factors and missing observations
– Response surface methodology;
– Path of the steepest ascent;
– Central Composite Designs;
– Face-Centred Composite Designs;
– Box-Behnken Designs.
– Analysing several responses simultaneously.

### Requirements

The student must be familiar with the basic concepts of the design of experiments such as:
– Analysis of variance (ANOVA)
– Factorial Designs
Concepts as designs in blocks and fractional designs also help with the understanding.

### Overview

Section 1: Welcome and Get Prepared!

Lecture 1 Welcome!

Lecture 2 Installing R and R Studio

Section 2: Linear Regression Models

Lecture 3 Introduction to Linear Regression Models

Lecture 4 Fitting Linear Regression Models to Experimental Data

Lecture 5 Building Linear Models in R

Lecture 6 Analysis of Variance of the Regression Model

Lecture 7 Residuals Plots

Lecture 8 Visualisation and Interpretation of the Results

Lecture 9 Multiple Linear Regression Models

Lecture 10 Multiple Linear Regression Models for Designed Experiments

Section 3: Designs for Linear Models

Lecture 11 Designs for Linear Models – 2ˆk Design

Lecture 12 Adding Central Points to the 2ˆk Design

Lecture 13 Building a 2ˆ3 design with central points in R

Lecture 14 Analysing a 2ˆ3 design with central points in R

Lecture 15 Interpreting the results

Lecture 16 Designs with missing observations and inaccurate levels of design factors

Lecture 17 Solving a design with missing observations and inaccurate levels

Section 4: Response Surface Methodology

Lecture 18 Introduction to Response Surface Methodology

Lecture 19 The Starting Design

Lecture 20 Analysing the First Design

Lecture 21 The Method Steepest Ascent

Lecture 22 Interpreting Lousy Fitting

Lecture 23 The Central Composite Design

Lecture 26 Analysing Multiple Responses Simultaneously (1)

Lecture 27 Analysing Multiple Responses Simultaneously (2)

Lecture 28 Desirability Functions for Optimising Multiple Responses

Lecture 29 Desirability Functions – R tutorial

Section 5: Central Composite Design for 3 Factors

Lecture 30 Central Composite Design for 3 Factors

Lecture 31 Case Study: The Starbucks Coffee Bag – 1

Lecture 32 Case Study: The Starbucks Coffee Bag – 2

Lecture 33 Case Study: The Starbucks Coffee Bag – R tutorial – Adding the Coded Variables

Lecture 34 Case Study: The Starbucks Coffee Bag – Analysing the Tear Results

Lecture 35 Case Study: The Starbucks Coffee Bag – Analysing the Leakage Results

Lecture 36 Case Study: The Starbucks Coffee Bag – Final Interpretation of the Results

Lecture 37 6.H Applying Desirability functions to The Starbucks Coffee Bag Case Study

Section 6: Three-level Designs for Second-Order Models

Lecture 38 Face-Centred and Box-Behnken Designs

Lecture 39 Workflow for Response Surface Analysis

Lecture 40 Solving a Box-Behnken Design

Lecture 41 Building BBD and FCCD in R

Section 7: Final Considerations on Experimental Designs

Lecture 42 Desirable Features for Experimental Designs

Lecture 43 How Many Runs Does a Design Need?

Section 8: Closing

Lecture 44 Thank you!

Lecture 45 Bonus lecture!

Researchers;,Graduate students;,Engineers;,Anyone who performs and analyse experiments.

#### Course Information:

Udemy | English | 2h 58m | 1.51 GB
Created by: Rosane Rech

You Can See More Courses in the Teaching & Academics >> Greetings from CourseDown.com

Scroll to Top