Training Courses

Design of Experiment

COURSE OVERVIEW

Description

Design of Experiments (DOE) is a proven methodology for individuals involved in designing, conducting and analyzing experiments. Over the past decade, the use of DOE has influenced various industries, facilitating improvements in processes and products. It plays a crucial role in development and optimization, aiming to enhance quality and reliability while concurrently contributing to cost reductions and time savings.

DOE is a structured approach for collecting data and making discoveries. It serves as a tool that applies statistical analysis to experimentation, making it valuable for proactive decision-making support. Today, DOE is widely utilised across various fields in science and engineering. Its applications have expanded to include sectors such as business, financial services, government operations and e-commerce. Despite unanimous agreement within industries about the benefits of DOE, its adoption is hindered, with only one in four companies using it due to a lack of knowledge and education in the methodology.

Course Focus:

Key emphasis throughout the course is on applications in the workplace
Participants will complete a project based around their own work environment to demonstrate the application of DOE.

Suitable For:

Engineers and managers in process control and product innovation
Entrepreneurs and business managers who are keen to explore breakthroughs in product
Science, technology and engineering graduates and academics

Keywords:

Microsoft Excel, PyCharm, Statistics, Python Programming, Machine Learning Algorithms

DURATION

3 Days

DATE

TBC

TIME

TBC

VENUE

Johor Bahru
Kuala Lumpur
Penang

TRAINING OUTLINE

Learning Outcome:

At the end of this workshop, participants are expected to be able to:

Gear their organisation towards Industry 4.0
Plan, design and conduct useful experiments efficiently and effectively
Use data analysis to obtain valid objective deductions.
Build empirical models with machine learning algorithms.
Apply the 7-Step DOE methodology in their workplace

Methodology:

Workshop, hands on, interactive learning, case studies and real-life scenarios, expert demonstrations, brainstorming

Format:

In-house / Public Training / Online

PROPOSED ITINERARY

Day 1

Industry 4.0

Introduction to DOE

DOE Fundamentals

7-step DOE methodology
Input variables
Response variables
Nuisance variables
Extraneous variables

Basic DOE Principles

Randomisation
Replication
Blocking
Factorial

Statistics For DOE

Variance
Sum of squares
Covariance
Linear regression
Correlation coefficient

Problem Statement

Identify opportunities
Select project team
Formulate problem statement
Gather background information

Response Variable Selection

Select response variable
Decide measurement method
State purpose and objectives
Project management plan
Project kickoff meeting

Day 2

Design Factors Selection

Identify factors
Classify factors
Select design factors and measurement method
State current knowledge of design factors effects
Decide design factors ranges

Experiment Design – Part I

Characterise factors
Decide design factors levels
Determine experiment design details

Experiment Design – Part II

Experiment design – randomised singe factor, randomise complete block, full factorial, fractional factorial, response surface method, Taguchi method
Decide empirical model and hypotheses
Documentation

Experiment Design – Part III

Experiment design – number of experiment runs, experiment run order
Decide empirical model and hypotheses
Documentation
Software packages

Conduct Experiment

Planning and logistics
Conduct trial runs
Perform experiment and data collection

Day 3

Data Analysis – Part I

Data cleaning and plotting
- scatter plot
- box plot
- dot diagram
- normal probability plot
Date analysis – ANOVA, data validation, randomised single factor analysis

Data Analysis – Part II

Randomised complete block analysis
Factorial analysis
Model adequacy
Fit empirical model
Lack of fit test

Data Analysis – Part III

Interpret results
Follow-up experimentation

Conclusions, Recommendations & Implementation

Draw conclusions
Make recommendations
Implementation
DOE project closure
Improvement evaluation

ABOUT TRAINERS

Dr Goh Eng Yew

Dr Goh obtained his PhD from Imperial College (London) in the field of computational fluid dynamics. He lectured at Nanyang Technological University (1992-1996) and subsequently joined the industry as chief architect to develop web-based enterprise resource planning system (1999-2012). Since 2012, he is lecturing for University Of Newcastle (Singapore campus) and his main areas of research and interests are design of experiments and machine learning. Dr Goh has developed a 7-step design of experiments methodology incorporating machine learning algorithms.

Fields of Expertise
– Design of experiments
– Machine learning
– Web-based technology
– Software programming

ENQUIRY NOW

Full Name

Phone Number

Course Interested

Certified Data Analyst Course Corporate Grooming Design of Experiment Developing Important Skills to Qualify as Efficient Secretary Digital Marketing Empowering Transformative Leadership & Cultivating Accountability at the Workplace Mandarin Speaking for Hospitality & Tourism Industry Training Present to Persuade - Public Speaking and Presentation Skills for Sales Professionals Professional Certificate in AI & Machine Learning Basics (NDR)

Enquiry