Our Research
About our research!
The work of this group is predominantly focused on developing novel modelling techniques, including both mechanistic, kinetic and data-driven models, for a range of purposes including:
Predictive Maintenance and Process Quality
Predictive Maintenance in Industry 4.0 using Machine Learning (See below)
Predict and prevent quality issues from process and equipment data
Complex process Modelling
Prediction and modelling of complex physical properties and processes
mRNA vaccine production and scale-up
Physical Property Prediction in the steel industry (See below)
Cost reduction in steel raw materials from machine learning modelling
Hydrogen and Net Zero Systems.
Particle processes, including fluidization and crystallisation.
Complex process or separation scheme design and multi-objective optimisation: cost, sustainability, resilience and safety.
Scale up and technoeconomic costing.
Novel Bio processes in non standard reactors
Visualisation of systems that aid design and selection.
Formulation/product design;
Formulant and solvent selection
Polymer encapsulation
Resilience:
Resilience to natural disasters (flood, hurricane, pandemic).
Resilience Modelling
Design and optimisation of processes and plants for net zero and resilience.
Policy work in the National Security Risk Register and Resilience
Process and Product Safety:
Hydrogen processes https://ukhyres.co.uk/
Automated forward and reverse Hazop/ Hazid
e.g. Fusion technology evaluation for UKAEA
Human Factors
Optimising cleaning in pharmaceuticals and agrochemicals processes.
Troubleshooting, training and guidance on-plant from digital tools.
Process Safety is paramount in industry. As we develop new processes for net zero we must incorporate safety and resilience from the start not as an add on.
Current grants
20/12/2021- 2024 173553 Digitised, small-scale and high-throughput process for distributed RNA production for therapy and pandemic preparedness WELLCOME LEAP INC
20/05/2022 -2025 172093 Sustainable microwave manufacturing ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL (EPSRC)
2023-2028 UK-HyRES: Hub for Research Challenges in Hydrogen and Alternative Liquid Fuels ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL https://ukhyres.co.uk/
PhD research projects
2021 -Louis Allen- Prescriptive Maintenance Methodologies in the Chemical Process Industries.
2022 - Mahdi Ahmed - Framework modelling and optimisation of industry towards UK Net Zero
2023 - Joseph Middleton- mRNA Process Modelling
SUBMITTED: Ana Franco-3d Printing and growing neurons on silk- Co-supervised with Prof Ipsita Roy
2020 - Lawson T. Glasby metal-organic frameworks, novel materials in the field of gas adsorption, sensing, and separation alongside catalysis, drug-delivery, and quantum applications. Co Supervised with Dr Peyman Moghadam now of UCL
2020 - Rama Oktavian - Computational screening on Metal-organic frameworks (MOFs) and novel materials in the field of gas adsorption. Co Supervised with Dr Peyman Moghadam now of UCL
2022- Hengxin Wu Batch reactor modelling . Secondary Supervisor Dr Rachel Smith.
2022 - Kesler Isoko -mRNA connected systems and control. Co Supervised with Dr Peyman Moghadan
PASSED - Victoria Shields - Separation of rate earth metals co supervised with Dr Mark Ogden - Passed with Corrections.
PASSED - Aaron Yeardley- Main Supervisor Prof Sol Brown.
Post Doc research Projects
Seyed Mojtaba Hoseyni
Development of advanced computational methods for resilience assessment in process safety
Machine Learning (ML) and Condition-Based Probabilistic Risk Assessment (CB-PRA) for smart predictive maintenance
Min Tao and Ehsan Nourafkan
mRNA Process Modelling (Wellcome Leap funded) - Co-Supervised with Prof Sol Brown and Dr Zoltan Kis
Royce Copley
mRNA Process Modelling (Wellcome Leap funded) - Co-Supervised with Dr Peyman Moghadan (UCL) and Dr Zoltan Kis
Find out more about our research themes below!
Wiz dashboard interface developed in Siemens’ MindSphere: (a) 5-dimensional plot showing conditions within the twin screw granulator, (b) real-time monitoring of the humidity in the fluidised bed dryer, (c) gauge plot showing dryer temperature as a key performance indicator (KPI) showing how the data is trending, and (d) scatter plot visualisation of local outlier factor (LOF) unsupervised machine learning algorithm showing outlier data detection.
Data Visualisation for Process Insight and Decision Making
The proliferation of data owing to the onset of Industry 4.0 (I4.0) has led to many traditional data analysis approaches becoming redundant. Novel and innovative solutions are required to facilitate the new era of data-driven manufacturing characteristics of I4.0. This work demonstrates one such approach in the formation of a bespoke web-based visualisation and machine learning analytics platform, designed to bridge the gap between the old ways and the new. Our unique I4.0 data analytics platform, called Wiz 4.0, enables advanced big data analytics in conjunction with user-friendly features and multivariate data visualisations. This allows for both a holistic overview of manufacturing processes as well as a detailed analysis of data. Wiz 4.0 lays the foundations of an industry-defining software to grant deep insight into the inner relationships between process variables to the everyday user. The software provides the ability to analyse data using a variety of machine learning algorithms and plot the data in high dimensional space through the innovative no-code platform hosted on the Siemens MindSphere. This approach is set to revolutionise the value creation of data in the new IoT and smart factory paradigms emerging from the transition towards I4.0.
Predictive Maintenance in Industry 4.0 using Machine Learning
Poor maintenance regimes often contribute to unplanned downtime, quality defects and accidents, thus it is crucial to apply an effective maintenance strategy to achieve an efficient and safe process. Industry 4.0 has brought about a proliferation of digital data and with it, new opportunities to advance and improve the way maintenance activities are planned. Here, we propose a novel methodology that utilises machine learning to predict the maintenance of both faults and the repair time and uses this to underpin the scheduling of maintenance activities. This can be used to plan maintenance, optimising the schedule for cost within the constraints of labour availability and plant layout. When applied to simulated data, using a simulated Fischertechnik (FT) model, this methodology reduces overall plant maintenance costs by reducing unplanned downtime and increasing maintenance efficiency. This work provides a promising first step toward improving the way maintenance tasks are approached in Industry 4.0.
A flowchart of an ensemble of machine learning techniques used to produce an optimum maintenance schedule
Shows schematic of ensemble machine learning and optimisation used to extract relevant compositional information from raw data, predict Jominy End Quench Test results, and suggest most optimal compositional arrangement based on historical market data for the prices of alloying elements.
Physical Property Prediction in the Steel Industry
Prediction of relevant mechanical properties is vital for the steel industry and for materials engineering. This work investigates a novel method to predict the Jominy hardness curve of a single grade of steel based solely on the composition of the alloying elements. Further consideration is given to the optimisation of the chemical profile of the alloying elements with respect to the overall cost. The ultimate aim of the work is to be able to reduce spending on alloying elements by offering cheaper methods of achieving the same Jominy profile based upon accurate prediction. A feature auto-encoder neural network is employed to reduce the dimensionality of 19 alloying elements from some 1000 steel samples to extract relevant property information. Gaussian Process (GP) regression is used to predict the Jominy hardness profile of the steel up to a depth of 10mm. Results showed that a GP fed with extracted features was able to predict Jominy hardness profiles with high accuracy (RMSEunseen= 1.35, MAPE = 3.3%). Constrained optimisation using the GP model, and historical market data for the price of alloying elements showed that an average cost reduction of 18% on alloying element spend is possible. This work shows not only that novel machine learning approaches can be used to accurately predict mechanical properties of a given grade of steel, but crucially that use of these in conjunction with optimisation can generate considerable financial savings.
Past grants as an Industrialist working with Academics
EP/R008027/1 From Kinetic Theory to Hydrodynamics: re-imagining two-fluid models of particle-laden flows
EP/N034066/1 A new multi-scale paradigm for particulate flow with Prof R Ocone
European 6th Framework grants & Danish Grants with CAPEC consortia and Prof R Gani and Prof SB Jørgensen
EPSRC Grant with Prof CS Adjiman, Prof A Galindo, Prof G Jackson SAFT approach for surfactants
EPSRC Grant with Prof CS Adjiman Solvent selection to improve reaction rates 2002-2005
Various funding for research from ICI/ Astra Zeneca/ Syngenta as the Industrial Collaborator
GR/T17595/01 Demonstration of the commercial potential of advanced molecular thermodynamics software Prof CS Adjiman, Prof C Pantelides, Prof G Jackson Prof A Galindo
GR/L63020/01 Batch Route Innovation Technology Evaluation and Selection Techniques (BRITEST) also DTI Funding
Case Award with Prof CS Adjiman as a new academic
EPSRC Changing the Culture: To report for the EPSRC on the Strategy and Structure of Chemical Engineering Research in the USA July 1999 C Axon, Prof Howell, JL Cordiner et al.