The PhD position is part of the European Training Network ELO-X Embedded Learning and Optimization for the neXt generation of smart industrial control systems .
The position at Atlas Copco is focused on developing performant optimal control problems for compressor room control. The position is based on Atlas Copco premises near Antwerp in Belgium, and he / she will follow a PhD program of the KU Leuven at the Mechanical Engineering department.
The aim is the design and development of tailored model predictive algorithms for compressor room control executable on constraint CPUs.
There will be a close cooperation with the other ELO-X PhD fellows, in particular with those partners that will host mutual exchange visits of several months durations : At Albert-Ludwigs-Universität Freiburg, KU Leuven (MECO research team) and Politecnico di Milano, the connection with generic methodological advances in the field of computational control and mathematical optimization will be strengthened.
COMPANY DESCRIPTION Atlas Copco provides industrial compressors, gas and process compressors and expanders, air and gas treatment equipment and air management systems.
The business area has a global service network and innovates for sustainable productivity in the manufacturing, oil and gas, and process industries.
Principal product development and manufacturing units are located in Belgium, the United States, China, Germany and Italy.
Compressors are used in a wide range of applications. In industrial processes, clean, dry and oil-free air is needed in food, pharmaceutical, electronics, and textiles.
Compressed air is also used for power tools in assembly operations and in applications as diverse as snow-making, fish farming, on high-speed trains, and in hospitals.
BACKGROUND Thanks to the increasing capabilities of digital technologies, the next generation of industrial control systems are expected to learn from streams of data and to take optimal decisions in real-time, leading to increased performance, safety, energy efficiency, and ultimately value creation.
Numerical optimization is at the very core of both learning and decision-making, and machine learning algorithms and artificial intelligence raise huge worldwide research interest, often using cloud computing and large data centers for their optimization computations.
However, in order to bring learning- and optimization-based automated decision-making into smart industrial control systems (SICS), two important bottlenecks have to be overcome : (1) computational resources on industrial control systems are locally embedded and limited, and (2) industrial control applications require reliable algorithms, with interpretable and verifiable behavior.
Both requirements partially stem from safety aspects, which are crucial in applications where a single computation error can cause high economic and environmental cost or even damage to people.
Pushing the performance boundary of SICS to leverage advanced digital technologies will therefore involve both fundamental new research questions and technological solutions, calling for a new set of advanced methods for embedded learning- and optimization-based control algorithms.
The applicant will be embedded in the compressor room control research team of Atlas Copco Airpower (headquarter of the compressed air business area).
The team focusses on the identification, analysis and control of air treatment devices such as compressors, dryers and air separation installations.
The theoretical research is in close collaboration with the MECO team at KU Leuven and therefore you will join the PhD program at the Mechanical Engineering department of the KU Leuven under the (academic) supervision of Prof.
Jan Swevers. The MECO team focusses on the identification, analysis and control of mechatronic systems such as autonomous guided vehicles, robots, and machine tools.
It combines theoretical innovations with experimental validations. The applicant will further be embedded in the ELO-X ecosystem which encompasses leading experts in mathematical modelling and optimization-based control and estimation and shall prepare the fellows for a high-level career in advanced control engineering in industry or in academia.