Case study – Expertise for the development of predictive models for pharmaceutical tableting
Sector: Ingredients
Customer Type: Big Account
Contact department: Data science – R&D
The client aims at developing predictive models for pharmaceutical tablets final properties. Preliminary data-science provided low level of satisfaction, so the Client asks RHEONIS for a critical scientific analysis, a neutral opinion on the feasibility of the project and recommendations for giving maximum chances to the project.
Hybrid scientific, industrial and data analysis expertise
RHEONIS provided its hybrid expertise regarding process industrial science, know-how for investigating scientific literature, techniques for data analysis and interpretation and its experience in R&D strategy.
Following actions have been taken in the context of this expertise:
- Client's need analysis and building of the Sow of the expertise
- Phenomenological analysis of tabletting process and scientific literature study of existing models, influencing factors and hierarchy of correlations
- Client's data analysis with hybrid physical/statistical techniques following models and phenomena
- Brainstorming for R&D strategy
- Synthesis report, including scientific opinion about project feasability and recommendations for R&D
- Debriefing meeting and discussion about next steps
Industrial science and phenomenology for getting to master tableting
Our expertise provided a critical, scientific and neutral opinion on the feasibility of its ambitious project. We identified uncertainties and risks but also stable grounds and promising options.
Our hybrid approach, combining science, data analysis, industrial phenomenology and powders expertise, allowed to build and suggest R&D paths for progressively remove risks and orient the project towards its success.
Industrial Science for Data-Science
Scientific expertise of industrial processes' physical phenomena
Identify models and parameters in scientific literature
Guide data analysis with phenomena understanding
Build on efficient and pragmatic R&D strategy
Any question about your data-science project for industrial transformation processes? Feel free to contact us.
Last Updated on January 14, 2022 by Vincent Billot