Data Mining and Multivariate Data Analysis (MVDA)

Enables process analysis on the basis of all relevant variables that affect process performance.

By making a global analysis which considers all relevant factors with and impact in critical process attributes, factors interactions are considered (correlations etc) and a more accurate and therefore capable of analysis is obtained. Univariate approaches fail notably in many situations for multivariate processes and that is only recently realized.

Multivariate process analysis was shaped by the early work of Box, Jenkins, Hunter in the 1970's. However, its impact was limited to experimental design and response surface methods used in optimization until McGregor and co-workers) Nomikos, Kourti and others) made a substantial number of contributions that from starting from chemometrics methods (e.g. PCA or PLS) extended them to the field of multi-stage process modeling, control and optimization, and made original contributions that could cope with all aspects involved in large real-world problems (e.g. multi-way PCA and multi-block PLS for batch processes).

• Troubleshooting;
• Process development;
• Improving your process operational margins through QbD and optimization methodologies
• Food, beverage, dairy products so that you can reduce time-to-market and/or remain competitive for longer times;

Technology is destructive only in the hands of people who do not realize that they are one and the same process as the universe.”

Alan Watts