Master Thesis – Reinforcement Learning Control of a Liquid–Liquid Separator Using Physics-Informed Neural Networks

Forschungszentrum Jülich GmbH; Jülich; On-site; EUR 13,000 - 19,000; Full time

Benefits offered by this job

Meaningful Tasks

Practical relevance

Scientific environment

Work-life balance

Flexibility

Health & well-being

Campus experience

Fair remuneration

Job summary

Forschungszentrum Jülich GmbH in Jülich is seeking a Master Thesis on Reinforcement Learning Control of a Liquid–Liquid Separator using Physics-Informed Neural Networks. The project trains an offline RL controller in a simulated environment, leveraging PINN models of the separator dynamics as fast virtual training grounds.

Validated surrogate models and pilot-scale data are available, and you will receive close supervision from doctoral researchers in machine learning and process control.

Qualifications

• Current master's student in Process Systems Engineering, Computational Engineering Science, Chemical Engineering or a comparable program.
• Programming in Python; experience with PyTorch is a plus
• Experience in modeling, simulation and machine learning
• Basic knowledge of control engineering
• Experience in reinforcement learning is not required but highly beneficial
• Very good command of written and spoken English with CEFR B2
• High degree of independence, motivation and reliability / independent and analytical working style
• Excellent ability to cooperate and work in a team

Responsibilities

• Develop a reinforcement learning (RL) controller for a liquid–liquid gravity settler, trained entirely offline in a simulated environment
• Use existing physics-informed neural network (PINN) models of the separator dynamics as fast virtual training environments
• Formulate the control problem and design reward functions for operating objectives such as throughput and separation quality
• Handle process constraints during learning
• Evaluate the trained controllers on a more detailed process model to assess how well the learned policies carry over beyond their training environment

Skills

Python

PyTorch

Modeling

Simulation

Machine Learning

Control Engineering

English (B2)

Education

Master's student in Process Systems Engineering (or comparable)

Tools

PyTorch

Job description

Master Thesis – Reinforcement Learning Control of a Liquid–Liquid Separator Using Physics-Informed Neural Networks

At the Institute of Climate and Energy Systems - Energy Systems Engineering (ICE-1) we focus on the optimal design and operation of integrated, decentralized energy systems with a high share of renewable energy. Computer simulation and numerical optimization are our essential tools to arrive at efficient, reliable, and cost-effective solutions. We contribute both to the development of mathematical models and to the development of improved simulation methods and optimization algorithms. Our methods and software-tools are validated against operating data of real systems. Furthermore, we conduct comprehensive case studies in order to test and further improve the scalability and the performance of our models and algorithms. Specially adapted methods and codes enable us to exploit the potential of high-performance computing with the aim of solving particularly large and complex problems.

Your Job

• Develop a reinforcement learning (RL) controller for a liquid–liquid gravity settler, trained entirely offline in a simulated environment
• Use existing physics-informed neural network (PINN) models of the separator dynamics as fast virtual training environments
• Formulate the control problem and design reward functions for operating objectives such as throughput and separation quality
• Handle process constraints during learning
• Evaluate the trained controllers on a more detailed process model to assess how well the learned policies carry over beyond their training environment

Validated surrogate models and experimental data from a pilot-scale settler are available. The project offers close supervision from doctoral researchers in machine learning and process control.

Your Profile

• Current master's student in Process Systems Engineering, Computational Engineering Science, Chemical Engineering or a comparable program
• Programming experience in Python; experience with PyTorch is a plus
• Experience in modeling, simulation and machine learning
• Basic knowledge of control engineering
• Experience in reinforcement learning is not required but highly beneficial
• Very good command of written and spoken English with extensive vocabulary is required (at least B2 level according to the CEFR), ideally supported by a certificate confirming the language level
• High degree of independence, motivation and reliability / independent and analytical working style
• Excellent ability to cooperate and work in a team

Our Benefits for You

• Meaningful Tasks: Your thesis deals with a future-oriented, socially relevant topic with direct practical relevance in an international environment
• Practical relevance: With us, you will gain valuable practical experience alongside your studies and actively participate in interdisciplinary projects
• Scientific environment: You can expect excellent scientific equipment, modern technologies, and qualified support from experienced colleagues
• Work-life balance: We offer flexible working hours to help you balance your professional and personal life. You also have the option of flexible working (in terms of location), which is generally possible after consultation and in line with upcoming tasks and (on-site) appointments
• Flexibility: Flexible working hours make it easier for you to balance work and study
• Health & well-being: Your health is important to us. You can look forward to a comprehensive company health management programme with a wide range of options, including a beach volleyball court, running groups, yoga classes and much more. In addition, our company medical service and an experienced social counselling team are available to assist you on site
• Campus experience: Our research campus in the countryside creates ideal conditions for collegial exchange and sporting activities right on site. Our cafeteria offers a wide range of options—you can enjoy a relaxing lunch break with a lake view
• Fair remuneration: We will pay you a reasonable remuneration for your thesis

In addition to exciting tasks and a collegial working environment, we offer you much more: https://go.fzj.de/benefits

We welcome applications from people with diverse backgrounds, e.g. in terms of age, gender, disability, sexual orientation / identity, and social, ethnic and religious origin. A diverse and inclusive working environment with equal opportunities in which everyone can realize their potential is important to us.

The following links provide further information on diversity and equal opportunities: https://go.fzj.de/equality and on specific support options for women: https://go.fzj.de/womens-job-journey. International applicants can find more information here: https://go.fzj.de/job-journey-internationals

Place of Employment: Jülich

Start Date: To the next possible date

Salary: We will pay you a reasonable remuneration for your thesis

Application Deadline: 2026-11-01

Index number: 2026M-0795

Follow us