Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Developing AI Controlled Granulation Process for Formulated Chemicals


   Department of Chemical & Biological Engineering

  ,  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Chemical and Pharmaceutical sector delivers a significant contribution to the world economy and the population as a whole. Granulation of powders is a key unit operation in many chemical industries and in particular, the detergent and pharmaceutical processing industries, where uniform granular products are essential for optimum operation of the active ingredients contained within the particles. Seeded granulation was recently introduced. In this process large particles present in the feed act as seeds in the granulation. It has been shown that seeded granulation (Rahmanian et al. 2011) produces granules with narrower distributions of granule size, uniform strength, and density.

The potential application of the seeded granulation process in the chemical and pharmaceutical industry requires a detailed study of the analysis of the wet granulation process to discover the best operation window for process control of the seeded granulation process. The aim of this project is to use Industry 4.0 technologies including machine learning and artificial intelligence (AI) to develop digital and soft sensors to predict product properties and optimise process in real-time for manufacturing functional chemical and/or pharmaceutical products. The particular goal is to develop and enhance understanding of the mechanism for seeded granulation by identifying the key parameters responsible for controlling the process in continuous granulation process and develop smart process control for the available continuous granulators. Applications include high added value materials with the significant commercial impact such as pharmaceutical, nutraceutical, and detergent powders.

The project is focused mainly on experimental work, however, use of EDEM or gProms software and Python (training will be provided) is also recommended to get insight into the process and discover process-product relationship and develop a regime map of the process. 

Applications and expressions of interest are invited from prospective researchers with a good background of chemical engineering or a closely related field. Some experimental work will be conducted at both the University of Sheffield and the University of Bradford.

References

• Behjani, M.A., Rahmanian, N., Abdul Ghani, N.F., Hassanpour, A. 2017. An investigation on process of seeded granulation in a continuous drum granulator using DEM, Advanced Power Technology, 28, 2465-2564.

• Rahmanian, N., Ghadiri, M., and Jia, X., 2011. Seeded granulation. Powder Technology, 206, 53-62.

• Rahmanian, N., Naji, A. and Ghadiri, M. 2011. Effect of process parameters on the granule properties made in a high shear granulator. Chemical Engineering Research and Design, 89(5), 512-518.

• D. Ntamo, E. Lopez-Montero, J. Mack, C. Omar, M.I. Highett, D. Moss, N. Mitchell, P. Soulatintork, P.Z. Moghadam, M. Zandi, Industry 4.0 in Action: Digitalisation of a Continuous Process Manufacturing for Formulated Products, Digital Chemical Engineering, Volume 3, 2022, 100025, ISSN 2772-5081, https://doi.org/10.1016/j.dche.2022.100025.

Please see this link for information on how to apply: https://www.sheffield.ac.uk/cbe/postgraduate/phd/how-apply. Please include the name of your proposed supervisor and the title of the PhD project within your application.

Candidates should have, or expect to achieve, a first or upper second class honours degree in chemical and process engineering or applied mathematics. If English is not your first language then you must have an International English Language Testing System (IELTS) average of 6.5 or above with at least 6.0 in each component, or equivalent. Please see this link for further information: https://www.sheffield.ac.uk/postgraduate/phd/apply/english-language.

Computer Science (8) Engineering (12) Mathematics (25)

Funding Notes

This is a self-funded project; applicants will be expected to pay their own fees or have access to suitable third-party funding, such as the Doctoral Loan from Student Finance. In addition to the University's standard tuition fees, bench fees may apply to this project.

Register your interest for this project



Where will I study?