Multi-Fidelity Digital Twins and Machine Learning for the Scale-Up of Flow Processes (Ref: SF-JO-2026/4)

About the Project

The ‘what’

This PhD will develop multi-fidelity digital twin frameworks, integrating physics-based models and machine learning, to enable reliable scale-up of flow processes (e.g. in chemical, materials, and energy manufacturing).

The ‘why’

Scaling up flow processes—from lab to pilot to industrial scale—remains one of the most costly and failure-prone stages in manufacturing. Small changes in flow behaviour, heat transfer, or reaction dynamics can lead to inefficiencies, safety risks, or product inconsistency. Digital twins offer a powerful route to predict and optimise performance, but current approaches are often either too computationally expensive (high-fidelity models) or insufficiently accurate (low-fidelity models).

This project addresses a critical challenge: how to combine multiple model fidelities with machine learning to deliver fast, accurate, and scalable predictive tools. Success will accelerate innovation in sectors such as chemicals, energy, pharmaceuticals, and advanced materials—supporting more sustainable and efficient industrial processes.

The ‘who’

You will be based at Loughborough University, joining a multidisciplinary research environment spanning process engineering, AI, and computational modelling. You will be supervised by experts in digital manufacturing, fluid dynamics, and machine learning, with opportunities to collaborate across partner universities and research centres.

Industry engagement and sponsorship

The project is designed with strong industrial relevance and will involve collaboration with partners in process industries (e.g. pharma, chemicals, energy, or materials manufacturing). These partners can provide real-world datasets, case studies, and opportunities for industrial placement, ensuring that the developed digital twin frameworks address practical scale-up challenges.

Aims and objectives

• Develop multi-fidelity modelling frameworks combining low-order models, CFD, and experimental data
• Integrate machine learning techniques (e.g. surrogate modelling, physics-informed learning) to bridge fidelity levels
• Create adaptive digital twins capable of updating predictions using real-time or batch data
• Demonstrate improved scale-up predictions across representative flow processes

Methodology

The project will combine computational modelling, data-driven methods, and experimental validation:

• Develop hierarchical model structures, linking reduced-order and high-fidelity simulations (e.g. CFD)
• Use machine learning (e.g. Gaussian processes, neural networks) to create fast surrogate models
• Explore multi-fidelity optimisation and uncertainty quantification
• Validate approaches using case studies in flow reactors, mixing systems, or thermal processes
• Implement digital twin frameworks capable of supporting decision-making during scale-up

Skills and development

You will gain expertise in:

• Computational fluid dynamics (CFD) and process modelling
• Machine learning and data-driven modelling
• Digital twin development and simulation–data integration
• Uncertainty quantification and optimisation

You will also develop transferable skills in interdisciplinary research, communication, and working with industrial stakeholders.

Career pathways

This PhD will prepare you for careers in:

• Process industries (chemicals, energy, pharmaceuticals)
• Digital engineering and simulation
• AI-driven manufacturing and optimisation
• Academic research in modelling, AI, or process systems engineering

Why Loughborough

With connections with MIT (Massachusetts Institute of Technology), Loughborough University offers a globally recognised research environment in advanced manufacturing, digital engineering, and intelligent systems.

You will benefit from:

• Access to state-of-the-art computational and experimental facilities
• A collaborative, interdisciplinary research culture
• Structured doctoral training and strong industry links
• A supportive environment focused on researcher development and impact

Name of primary supervisor/CDT lead:

John Oyekan j.o.oyekan@lboro.ac.uk

Name of secondary supervisor:

Nacho Martin-Fabiani-Carrato

Entry requirements:

Applicants should have:

• A 2:2, 2:1 or first-class degree in Chemical Engineering, Mechanical Engineering, Mathematics, Physics, Computer Science, or a related discipline
• Strong background in modelling, mathematics, or fluid dynamics
• Programming experience (e.g. Python, MATLAB, or C++)

Desirable:

• Experience with CFD, numerical methods, or simulation tools
• Familiarity with machine learning or data-driven modelling

English language requirements:

Applicants must meet the minimum English language requirements. Further details are available on the International website.

Bench fees required: No

Closing date of advert: 31 July 2026

Start date: 01 October 2026

Full-time/part-time availability: Full-time 3 years

Fee band: 2026/27 Band RB (UK £5,238, International £29,500)

How to Apply:

All applications should be made online. Under Campus, please select Loughborough and select Programme "Electronic, Electrical and Systems Engineering’. Please quote the advertised reference number ‘SF-JO-2026’ under the finance section in your application.

Applications must include a personal statement, up-to-date curriculum vitae (CV), details of two referees (one from your highest degree qualification), certified certificates and transcripts for all completed degree programmes, and a reference to the project ‘SF-JO-2026’.

Submission of a research proposal is not essential but may strengthen your application.

To avoid delays in processing your application, please ensure that you submit the minimum supporting documents above.

Project search terms:

artificial intelligence, manufacturing engineering, Computer Science, chemical engineering, control systems, robotics

Email address Wolfson:

ws.phdadmin@lboro.ac.uk