Skip to main content

Postgraduate research project

A machine learning enhanced digital twin toward sustainable pharmaceutical tablet manufacturing

Fully funded (UK and international)
Type of degree
Doctor of Philosophy
Entry requirements
2:1 honours degree View full entry requirements
Faculty graduate school
Faculty of Engineering and Physical Sciences
Closing date

About the project

This project aims to improve the making of pharmaceutical tablets by using advanced machine learning (ML), life cycle analysis (LCA), and process digital twins (PDTs). The goal is to make the production process more efficient, cost-effective, and environmentally friendly.

The reduction of emission from pharmaceutical tablet manufacturing is urgent and challenging. Rapid identification and quantification of emission sources is an important milestone to set reduction targets and implement corresponding reduction measures. Reliable and accurate in-silico predictions to identify sustainable process opportunities including resource efficiency, pollution prevention, renewable energy and green chemistry would be a game-changing tool.

PDTs are powerful tools for improving tablet manufacturing processes by providing a virtual platform for simulation, monitoring, optimization, and decision support. However, PDTs typically focus on optimizing technical aspects of processes, such as energy efficiency, production rates, and product quality. While they cannot fully capture broader sustainability and socio-economic factors. 

LCA is used widely in the pharmaceutical industry to evaluate environmental impact in pharmaceutical process. However, the approach suffers from the limitations, such as time consuming for case-by-case comparison and missing data of Life cycle inventory. In this project you will address the challenges of green tableting processes.

In this project, you will use a new mix of advanced ML, LCA, and PDTs to design and improve the making of pharmaceutical tablets. These tablets will be efficient, cost-effective, and environmentally sustainable throughout their entire life cycle. You will also use modern numerical platforms to enhance processes like roller compaction and continuous direct compression.

You will spend at least 3 months of this 3 years 6 months' studentship working at AstraZeneca, where you will learn how computer modelling is applied to pharmaceutical process. You will be supervised by Flora Bouchier and Dr Gavin Reynolds from AstraZeneca who are experts in the development and application of process system engineering to pharmaceutical process.

At the University you will be supervised by Dr Xi Yu and Dr Mohamed Hassan Sayed, with expertise in the development and application of numerical methodology to pharmaceutical and energy sector.