Design of Experiments (DoE)

Thanks to Design of Experiments (DoE), research and development efforts can be planned reasonably and more efficiently. Of course, you can also just develop on the fly, but that’s not really goal-oriented. Get the necessary tools to structure your development in such a way that you reach your goal faster. Our intensive training will provide you with the basic principles and practical exercises to help you perform your development and optimization tasks much more efficiently in the future. The equation is: Fewer experiments, higher reliability.

Course outline: 

1. Process Model overview
2. Basic statistics
3. Building blocks of experimental design
4. Setting up experimental designs
5. Analyzing DoE data (Regression)

Overview

Course Content

Process Model Overview

• Black and white box modeling
• Preview on all working steps (design & data analysis)
  
  

Basic Statistics

• Distributions (normal, Weibull, binomial)
• Confidence intervals
  
  

Building Blocks of Experimental Design

• Functional approach for process behavior
• Statistical models for measuring errors, noise variables, and unknown factors
• Design space and design space coverage)
  
  

Setting Up Experimental Designs

• Working steps for good designs
• Impact of model assumption
• Sample Size calculation
• Special situations (constraints, inclusions, candidates)
• Summary statistics and data aggregation
  
  

Analyzing DoE Data (Regression)

• Working steps for data analysis (checklist) and background
• Background for the working steps
• Model visualization and optimization for conflicting response
• Practical exercises
  
  

Objective

Target Groups & Background Knowledge

• The focus is on understanding the methods; underlying mathematics and statistics is explained by simulations and not by formula.
• The basics of the various methods are examined, extensively.
• The most important methods are not only explained but through the discussion of the application examples and their processing, you should become familiar with these methods.
• The focus is on the current state of the art which allows to treat almost any situation.
• The impact of DoE on Machine Learning (ML) projects will be explained.
  
  

This course is designed for:

• Engineers, technicians, analysts, and scientists in R&D departments who want to effectively achieve results.

This course is designed for:

• Quantitative way of thinking
• Affinity to model building