Short description:
In this project, we were developing and implementing PAT to control the manufacturing process of drug production. The project involved different aspects, including multivariate exploratory analysis, signal pre-treatment, multivariate modelling, and data fusion. Basically, we were interested in checking whether the use of NIR or Raman was useful to predict several properties of interest during drug production. More pecifically, we wanted to know whether fusing NIR and Raman data was advantageous.
There is a non-disclosure agreement (NDA) for this project and I am not authorised to discuss any details.
Credits:
This project was developed together with Merck and constituted the thesis of Jeffrey Vos [4m]. Several people from different teams accross the organization are involved.
Sponsors:
Merck, University of Amsterdam.
Presentations:
Covered by NDA agreement.
Software available:
Not available.
Tags:
- Application domain: Pharma & Health sciences
- Instrument domain: NIR, mid-IR and Raman
- Statistics domain: Multivariate calibration, Multivariate exploratory analysis, signal processing, modelling & regression, data fusion.