Speakers
Description
The Future Circular Collider (FCC) requires nanometre-scale precision for beam optics, with the Arc Half-Cell repeated over 77 km, demanding sub-micron alignment despite ground motion and vibrations. To address these challenges, we are developing a Digital Twin of the Short Straight Section of the Arc Half-Cell to predict and alert about potential mechanical instabilities of the magnet influenced by seismic events, supporting advanced prototyping of the FCC-ee Arc Half-Cell mock-up. Building on prior Digital Twin initiatives at CERN EN-MME, the project implements an IIoT-Cloud architecture for real-time data acquisition and management. Data used for this project include Experimental data from a laboratory setup along with data from CERN seismic stations and Swiss Seismological Services. The infrastructure uses Apache Kafka as the backbone, MQTT for sensor data ingestion, InfluxDB for time-series organization, and CERN’s EOS for robust storage. Results from predictive modeling are visualized via Grafana and OpenShift-hosted web applications. An additional layer of physics-based modelling is integrated with the ML-based model to enhance predictions using real-time measurement data. This approach demonstrates how data-driven methodologies can guide next-generation accelerator design, enabling predictive maintenance and early instability detection.
| In which format do you inted to submit your paper? | LaTeX |
|---|