The following courses will take place in parallel on Tuesday 24th April at the Hilton Hotel
1. Introduction to Design of Experiments
Design of Experiments (DoE) is a methodology used for designing and optimising robust industrial processes. DoE is recognised as an essential skill by many of the world’s leading process organisations.
This 1-day introductory workshop is delivered by the Industrial Statistics Research Unit (ISRU) at Newcastle University and provides delegates with an opportunity to augment their process knowledge through the understanding of a sequential DoE strategy.
The workshop is targeted at scientists, working at all scales from research to manufacturing, from both academia and industry including chemical, pharmaceutical, food & beverages and paints & coatings organisations. The workshop will involve a series of facilitated sessions, involving experimental design, analysis and interpretation of data, that explore scoping, screening, optimisation and robustness phases.
Delegates will be encouraged to apply the strategy within their own research and improvement environments.
10.00-10.30 Registration and coffee
10.30-12.15 Introduction to DoE and Planning & Scoping
13.15-14.50 Screening Designs and Analysis
14.50-15.10 Coffee Break
15.10-16:45 Optimisation & Robustness
16.45-17.00 Round up, final questions and finish
2. Batch Process Analysis and Monitoring
Batch processes are widely used in many industries. Typically, raw materials are combined in a batch reactor before a chemical, physical or biological transformation takes place, resulting in the end product.
When it comes to the modeling of batch data there are several challenges such as unequal run lengths or batches, unequal transformation time (quicker/slower reactions) and variations in sampling frequency between batches.
Depending on the application and required information as the process progresses, various modeling strategies can be employed:
1. Prediction of the yield directly with suitable in-line sensors, e.g. spectroscopy
2. Projecting the new batch onto an endpoint model and decide if the process has reached its end
3. Project the new batch on one existing batch for a qualitative visual assessment
4. Follow the batch progression with a moving-block method; suitable e.g. for mixing processes
5. Model a batch trajectory using relative time
This pre-conference course will give an overview of the strategies listed above and the need for proper validation will also be discussed.
10:00-10:30 Registration and coffee
10:30-12:15 Batch Process Analysis background and strategies
13:15-14:50 Batch Process relative time models and validation
14:50-15:10 Coffee break
15:10-16:45 Monitoring and assessment of new production batches
16:45-17:00 Round up, final questions and finish
3. Introductory Chemometrics without Equations (or hardly any)
Chemometrics without Equations concentrates on two areas of chemometrics: 1) exploratory data analysis and pattern recognition, and 2) regression. Participants will learn to safely apply techniques such as Principal Components Analysis (PCA), Principal Components Regression (PCR), and Partial Least Squares (PLS) Regression. Examples will include problems drawn from process monitoring and quality control, predicting product properties, and others. The target audience includes those who collect and/or manage large amounts of data that is multivariate in nature. This includes bench chemists, process engineers, and managers who would like to extract the maximum information possible from their measurements.
Chemometrics Without Equations (or Hardly Any) is designed for those who wish to explore the problem solving power of chemometric tools, but are discouraged by the high level of mathematics found in many software manuals and texts. Course emphasis is on proper application and interpretation of chemometric methods as applied to real-life problems. The objective is to teach in the simplest way possible so that participants will be better chemometrics practitioners and managers.
1.1 what is chemometrics?
2 Pattern Recognition Motivation
2.1 what is pattern recognition?
2.2 relevant measurements
2.3 some statistical definitions
3. Principal Components Analysis
3.1 what is PCA?
3.2 scores and loadings
3.4 supervised and unsupervised pattern recognition
4.1 what is regression?
4.2 classical least squares (CLS)
4.3 inverse least squares (ILS)
4.4 principal components regression (PCR)
4.5 partial least squares regression (PLS)
The courses will be open to conference delegates as an additional option at a reduced rate, or may be attended on a ‘course only’ basis.