PhD Student

Last application date
Aug 30, 2024 00:00
Department
LA26 - Department of Data Analysis and Mathematical Modelling
Contract
Limited duration
Degree
master’s degree in bioscience, chemical, or process engineering with strong track record in modelling and simulation of bioprocesses
Occupancy rate
100%
Vacancy type
Research staff

Job description

Water resource recovery facilities (WRRFs) modeling is transitioning from conventional process models to digital twin (DT) applications. DTs are virtual replicas of physical systems that can dynamically simulate the operation of their physical counterpart in real time. A digital twin can be a valuable tool for operator training, online process optimization, scenario analysis, predictive maintenance, and so forth. Nevertheless, there exist only a handful of full-scale implementation of digital twins for WRRFs. In addition, most of them are uni-directional with an automated connection back to the physical system for online process optimization and monitoring.

Multi-objective optimization will be an inherent part of digital twins where maximum process efficiency at minimum use of energy and cost expenditure would be required. Specifically, it can provide insights on optimal operational conditions based on KPIs of the WRRFs including N2O emission, energy efficiency, operational cost, effluent quality, and removal efficiencies. Advanced control strategies including model predictive control (MPC) and reinforcement learning can be used to achieve that.

Data existence and quality are important requirements for a reliable digital twin and in particular for online process monitoring, control and optimization. Online sensors at WRRFs are usually prone to anomalies (e.g., noise, failure, drift, and bias), which can dramatically affect the quality and/or the performance of model simulations. Moreover, not all important variables of the system are usually measured. Model-based soft sensors combine simple available measurements with a process model and provide an indirect measurement for difficult-to-measure variables of the physical system. They can be powerful assets in advanced control systems and real-time process optimization. Mechanistic models (based on physical principles), data-driven methods (machine learning) or a combination of both (hybrid model) can be used for developing such soft sensors.

In this position, you will be working in a dynamic research group and will be actively involved in the state-of-the-art research on mathematical modelling (mechanistic, data-driven and hybrid), soft-sensor development and process optimization in the context of digital twin applications for WRRFs. You will be collaborating with Waterboard De Dommel (NL).

Your specific tasks include:
- You will conduct a literature review on the mathematical modelling and digital twin developments for the water and wastewater systems.
- You develop model-based soft sensors for important measurements at WRRFs (e.g., influent compositions) using mechanistic/empirical models, data-driven algorithms (e.g., neural networks) and a combination of both in a hybrid model architecture.
- You develop plant-wide multi-objective optimization algorithms for real-time digital twin applications.
- You implement models/soft sensors/optimization for improvement of an existing full-scale DT as well as for developing DTs for new WRRFs.
- You will collaborate closely with external project partners.
- You write down the results in scientific articles and a PhD thesis.

What we can offer you


- We offer you a full-time PhD contract at Ghent University of definite duration for the period of 4 years (1 + 3 years)
- About Ghent University: Ghent University is a world of its own. Employing more than 8,000 people, it is actively involved in education and research, management and administration, as well as technical and social service provision on a daily basis. It is one of the largest, most exciting employers in the area and offers great career opportunities. With its 11 faculties and more than 80 departments offering state-of-the-art study programmes grounded in research in a wide range of academic fields, Ghent University is a logical choice for its staff and students.
- Salary is determined according to the UGent salary scales.
- Moreover, you can enjoy a number of benefits, such as a wide range of training and education opportunities, 35 days of holiday leave (on an annual basis for a full-time job) supplemented by annual fixed bridge days, bicycle allowance and eco vouchers. Click here for an overview of all staff benefits. 

Job profile

- You have a master’s degree in bioscience, chemical, or process engineering with strong track record in modelling and simulation of bioprocesses
- You have good knowledge of mathematical modelling, data analysis and machine learning or a strong affinity to learn
- You have solid experience with computer programming (such as Python/Matlab/Julia/etc.)
- Background in modelling of water and wastewater systems is a plus
- Experience with wastewater process simulation software (e.g. WEST, SUMO) is a plus
- You like a challenge and are not afraid to learn and explore new methodologies
- You are a quick learner and can conduct independent research
- You are fluent in English, both speaking and writing
- You are motivated and dedicated
- You are a team player

How to apply

Your application must include the following documents:

- Your CV: an overview of your publication list and your study results (merged into one pdf file)
- A Cover letter: your application letter in PDF format (describe your values and provide examples relevant to the job description)
- Diploma: a transcript of the required degree (if already in your possession). If you have a foreign diploma in a language other than national languages of Belgium (Dutch, French or German) or English, please add a translation in one of the mentioned languages.

As Ghent University maintains an equal opportunities and diversity policy, everyone is encouraged to apply for this position.

Please send your complete applications by email to Dr. Saba Daneshgar (saba.daneshgar@ugent.be) and Prof. Ingmar Nopens (Ingmar.nopens@UGent.be).