Sensor Fusion for Sustainable Process Technology - (ENG 1552)

Principal Industrial Supervisor – Dr. Abubakr Ibrahim, Schlumberger Cambridge Research

Principal Academic Supervisor – Dr. Nicholas Watson, University of Nottingham

Additional Supervisors – Dr. Isaac Triguero, University of Nottingham

This project will be based at the Faculty of Engineering, University of Nottingham and the appointed candidate registered at the University of Nottingham as the degree awarding institution.

Highly motivated candidates are invited to apply for this exciting 4 year EPSRC funded iCASE PhD studentship with Schlumberger Cambridge Research to develop the next generation of chemical engineering smart algorithms for information integration applying state-of-the-art sensor fusion and Artificial Intelligence/machine learning methods.  

One of the biggest challenges to achieve global net zero is energy storage. High-density Li-ion batteries are one of the most ubiquitous and reliable methods. Traditionally lithium is mined from hard rocks or extracted in solar evaporation ponds, which take about 18-24 months cycle per batch. In its steadfast effort towards global net zero, Schlumberger has recently launched a lithium extraction pilot plant featuring the NeoLith Energy sustainable approach, using a novel process to enable production of high-purity, battery-grade lithium from brines. Understanding how minimal instrumentation can be deployed to this process and other similar sustainable chemical processes is a key enabler to optimise, reduce costs, and improve carbon footprint. Current industrial practice in process monitoring and optimisation includes building a digital twin supported by livestreamed data from the process plant. Often, the metrology infrastructure is very underdetermined and with no rigorous quality control framework for sensor data.

This project offers a unique opportunity to develop state-of-the-art information integration algorithms enabling improved sensing, with reduced uncertainty. It can unlock enhanced, rigorous, and adaptive optimisation schemes for processes ensuring a reduced carbon footprint while satisfying technoeconomic objectives. This is achieved through leveraging recent developments in fields of autonomous vehicle navigation, information integration, robotics, machine learning (e.g. deep learning, data fusion, and descriptive analytics), and computational optimisation techniques (e.g. hyper-heuristics).

The project will include scientific contributions in three tiers. The first tier investigates the fundamental mathematical methods in linear and nonlinear network analysis as well as Bayesian Statistics in senor fusion applications with a focus on sustainable process technology. The second tier examines integration of emerging machine learning algorithms and mathematical models to enable improved sensing and optimisation. The third tier applies the integrated solution on the novel Neolith process case study to demonstrate impact.   

Schlumberger Cambridge Research will co-sponsor and participate in mentoring and supervision of the PhD candidate. It can also provide access to a range of world-class laboratory and engineering scale equipment, as well as assist with software, technology transfer, and the industrial context of the work.

We are looking for applicants who have solid numerical, analytical, mathematical skills, and strong programming abilities. Candidates should have very good verbal and written communication skills, are self-driven, imaginative and have a strong problem-solving ability, positive and excellent team players with appetite and potential to address environmental sustainability challenges facing process engineering information integration preferably with a first class degree in either Engineering, Physical Sciences or Data/Computer Science. 

Information enquires can be directed towards Dr Nicholas Watson, University of Nottingham ([Email Address Removed])

Application should include: (1) a brief statement of research interests and motivation for pursuing PhD in this field, please include the reference number (beginning ENG and supervisors name) within the personal statement section of the application. This will help in ensuring your application is sent directly to the academic advertising the studentship; (2) a copy of your CV, including actual or expected degree class(es), a transcript of all University results, a list of publications, and contact details for two academic referees. Applications without academic transcripts or academic referees will not be considered; (3) copies of any publications or an example of your technical writing, such as a project report or dissertation.