Data analytics for industrial controls and monitoring 

Project goal

Our aim is to make control systems used for the LHC more efficient and “smarter”. We are working to develop a data-analytics platform that capitalises on the latest cloud- and edge-computing technologies. Specifically, this platform will make use of two new analytics solutions being developed by Siemens, internally referred to as “Smart Industrial Internet of Things” (Smart IIoT) and “ELVis”.

R&D topic
Machine learning and data analytics
Project coordinator(s)
Fernando Varela
Team members
Filippo Tilaro, Jakub Guzik, Rafal Kulaga, Piotr Golonka, Peter Sollander, Fernando Varela, Enrique Blanco
Collaborator liaison(s)
Thomas Hahn, Juergen Kazmeier, Alexey Fishkin, Tatiana Mangels, Mikhail Kalinkin, Elisabeth Bakany, Ewald Sperrer


Project background

The HL-LHC project aims to increase the integrated luminosity — and hence the rate of particle collisions — by a factor of ten beyond the LHC’s design value. Monitoring and control systems will therefore become increasingly complex, with unprecedented data throughputs. Consequently, it is vital to further improve the performance of these systems, and to make use of data-analytics algorithms to detect anomalies and to anticipate future behaviour. Achieving this involves a number of related lines of work. This particular project focuses on the development of a data-analytics platform that combines the benefits of cloud and edge computing.

Recent progress

We focused on the monitoring of various LHC control systems, using two distinct analytics solutions from Siemens. The first Smart IIoT, a framework used to monitor a multitude of control signals in a distributed manner. The second is ELVis, a web-based platform for processing, visualisation and archiving multiple streams of time-series data from sensors.

In 2018, these were both deployed and integrated into CERN’s industrial installations, combining both cloud and edge computing into a single, scalable platform. Different versions and releases were assessed to compute (online) thousands of analytical rules against heavy streams of measurements.

Several machine-learning algorithms were developed to detect anomalies in different control systems. For example, a probabilistic model-based approach has now been adopted for leak detection in cooling and ventilation systems. In 2018, we also began work to help optimise the ion beam source for one of the linear accelerators at CERN (Linac 3).

Despite this work still being at an early stage, the Siemens analytical solutions deployed at CERN have already enhanced our control-systems monitoring and have reduced operational cost by extending the operational life of some devices.

Next steps

A tighter integration between ELVis and Smart IIoT will be one of the main objectives for 2019. A single user-interface will make it easier to define complex event-processing rules, configure the cloud and edge infrastructure, and monitor the execution of the analyses. A new version of the domain-specific language will also be implemented to integrate control events and time-series data processing.




    F. Tilaro, F. Varela, Model Learning Algorithms for Anomaly Detection in CERN Control Systems (25 January). Presented at BE-CO Technical Meeting, Geneva, 2018.
    F. Tilaro, F. Varela, Industrial IoT in CERN Control Systems (21 February). Presented at Siemens IoT Conference, Nuremberg, 2018.
    F. Tilaro, F. Varela, Optimising CERN control systems through Anomaly Detection & Machine Learning (29 August). Presented at AI workshop for Future Production Systems, Lund, 2018.
    F. Tilaro, F. Varela, Online Data Processing for CERN industrial systems (12 November). Presented at Siemens Analytics Workshop, Munich, 2018.