Using LSTM recurrent neural networks for monitoring the LHC superconducting magnets

TL;DR

This paper explores the use of LSTM neural networks for monitoring superconducting magnets in the LHC, aiming to improve fault detection accuracy over traditional trigger-based systems.

Contribution

It introduces a novel deep learning approach using LSTM networks for modeling and predicting voltage time series in LHC magnets, enhancing fault monitoring capabilities.

Findings

Achieved a minimum RMSE of 0.00104 in voltage prediction

Optimized LSTM architecture with 128 cells and 16-step history

Demonstrated potential for improved fault detection accuracy

Abstract

The superconducting LHC magnets are coupled with an electronic monitoring system which records and analyses voltage time series reflecting their performance. A currently used system is based on a range of preprogrammed triggers which launches protection procedures when a misbehavior of the magnets is detected. All the procedures used in the protection equipment were designed and implemented according to known working scenarios of the system and are updated and monitored by human operators. This paper proposes a novel approach to monitoring and fault protection of the Large Hadron Collider (LHC) superconducting magnets which employs state-of-the-art Deep Learning algorithms. Consequently, the authors of the paper decided to examine the performance of LSTM recurrent neural networks for modeling of voltage time series of the magnets. In order to address this challenging task different network architectures and hyper-parameters were used to achieve the best possible performance of the solution. The regression results were measured in terms of RMSE for different number of future steps and history length taken into account for the prediction. The best result of RMSE=0.00104 was obtained for a network of 128 LSTM cells within the internal layer and 16 steps history buffer.