EPJ Web of Conferences 295, 02033 (2024)
https://doi.org/10.1051/epjconf/202429502033

Triggerless data acquisition pipeline for Machine Learning based statistical anomaly detection

¹ Department of Physics and Astronomy “Galileo Galilei”, Padova University, Italy
² National Institute for Nuclear Physics, Padova Division, Italy
³ Department of Industrial Engineering, Padova University, Italy
⁴ Department of Information Engineering, Padova University, Italy

^* e-mail: matteo.migliorini@pd.infn.it

Published online: 6 May 2024

Abstract

This work describes an online processing pipeline designed to identify anomalies in a continuous stream of data collected without external triggers from a particle detector. The processing pipeline begins with a local reconstruction algorithm, employing neural networks on an FPGA as its first stage. Subsequent data preparation and anomaly detection stages are accelerated using GPGPUs. As a practical demonstration of anomaly detection, we have developed a data quality monitoring application using a cosmic muon detector. Its primary objective is to detect deviations from the expected operational conditions of the detector. This serves as a proof-of-concept for a system that can be adapted for use in large particle physics experiments, enabling anomaly detection on datasets with reduced bias.