Design of Experiments
Three Day Training Course
Many experimenters are using an OFAT (one-factor-at-a-time) approach to their experimental designs. In addition to the issue of inefficiency, this approach fails to identify often crucially important interaction effects among factors. There are available to experimenters advanced analytical tools based on mathematical techniques and utilising special computer software, which will enable them to gain a deep understanding of their processes, including the impact of interactions among factors, and to do so in the most efficient manner with minimum numbers of experimental runs. These modern DOE tools will be presented on this training course.
On successful completion of this training course, delegates should be able to:
- Plan designed experiments to include appropriate factors and responses
- Analyse factor effects and interaction effects using specialist computer software
- Interpret the outcome of designed experiments so as to choose factor settings for optimum process performance
- Demonstrate knowledge of the statistics underlying the design of experiments
Who Should Attend
- Product design and process design engineers and scientists
- R&D engineers and scientists
- QC and QA personnel
A prior knowledge of basic statistics is recommended. However, the course will commence with a review of basic statistics, which will be sufficient to provide understanding of the statistical material that will be met during the course. Participants should have knowledge of mathematical principles, for example, Leaving Certificate mathematics.
Introduction to Statistics Underlying Experimental Design
- Mean, variance, standard deviation, degrees of freedom
- The normal, Student-t and F distributions
- Normal probability plots
- Hypothesis testing
- Definition of terms such as independent and dependent variables, factors and levels, response, treatment, error and replication
Planning and Organizing Experiments
- Applying the basic elements of experiment planning and organizing, including determining the experiment objective; selecting factors, responses, and measurement methods; choosing the appropriate design
- Applying the principles of power and sample size, balance, replication, order, efficiency, randomisation and blocking, interaction, and confounding
Design and Analysis of Factorial Experiments
- Constructing full-factorial designs and applying computational and graphical methods to analyse and evaluate the significance of results
- Planning the experiment and determining the experimental objective.
- Explanation of the terminology – responses, factors, levels, replication, randomization, design points, design runs
- Understanding the statistical importance of avoiding excess variation in experiments – the role of measurement and careful control of the experiments
- Establishing the basic principles with a two factor and three factor design – explanation of main effects and interactions
- Analysis of experimental results using the two-sample t-test, ANOVA, and the probability plot
- Screening out the non-significant factors
- Understanding how to interpret interaction plots
- The role of blocking in DOE
- The need to reduce the number of runs when there are a large number of factors involved – the concept of using fractional factorial designs
- Fractional factorial designs continued
- Simple and multiple regression and correlation analysis
- Analysis of residuals
- Optimization – Response Surface Methodology (RSM)– Modelling the relationship between factors and responses using advanced mathematical techniques and computer software
- Simultaneously optimising multiple responses
Minitab will be demonstrated as part of the training. Delegates are invited to bring a laptop loaded with either Minitab 16 or Minitab 17 and they will work through several Minitab exercises throughout the three days of the course. A free 30 day trial version of Minitab 17 is available on www.minitab.co.uk. For in-company training courses, there is an option to use the specialist DOE software, Design Expert. A free 45 day trial version of Design Expert 9 is available for downloading from www.statease.com/dx9.
Albert Plant is a chartered engineer (FIEI) and has a B.Sc. degree in statistics. He has nineteen years experience training and consulting in DOE. His work is in the pharmaceutical and medical devices industries, food industry, electronics, automotive parts, and other manufacturing.
Albert has used Minitab software since 1994. He is a volunteer tester for Minitab on new versions and he was involved in testing version 17 of Minitab prior to its launch in 2014
Testimonials Click Here
Course Times 9.00am - 5.00pm
Public Course Cost €995 (includes course documentation, lunch and refreshments)
For In-House courses the tutor will contact you in advance to discuss the course programme in more detail in order to tailor it specifically for your organisation. Where appropriate and facilitated by the organisation, the course can be run using Minitab or Design Expert software.
Delegates will receive a very comprehensive course manual written by the course tutor, which explains the underlying statistics, describes the principles of experimental design, explains in detail how experiments are designed and analysed, includes examples of several practical case studies, and incorporates completed versions of all the course exercises and graphs, including the output from Minitab computer software. The course manual will provide a very useful reference for participants undertaking the design and analysis of experiments when they return to their workplace.