Speaker
Description
The European Spallation Source ERIC (ESS) is a joint European organisation committed to building and operating the world's leading facility for research using neutrons. The facility design and construction includes a powerful linear proton accelerator, a helium-cooled tungsten target wheel and two dozen state-of-the-art neutron instruments.
Rapid advances in technology around artificial intelligence and machine learning systems have opened up new opportunities for automating assisted management of operations of complex facilities such as the European Spallation Source ERIC (ESS). The control system community, especially around complex distributed control system implementations such as EPICS – which is used at ESS, is reacting to incorporate these new technologies in control systems to improve performance, increase availability and reduce costs. ESS has interacted with external agencies such as Big Science Sweden and Vinnova to find opportunities for exploring the benefits that can be realized by applying machine learning to this class of distributed control systems. Through the interaction with these agencies, a certain interest from industry has also been invoked.
The ESS control system machine learning project is launched on a joint initiative between ESS, agencies and industrial stakeholders. The project aims to explore how application of modern machine learning technologies to a large-scale industrial distributed control system can help increase facility availability and efficiency and lower costs for operation. The project will investigate interfaces between machine learning systems and the EPICS distributed control system and also how to select control system data that is relevant for a machine-assisted control system of this magnitude.
