Using LSTM recurrent neural networks for monitoring the LHC superconducting magnets

Abstract

a b s t r a c tThe superconducting LHC magnets are coupled with an electronic monitoring system which records and analyzes 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 hyperparameters 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.

Using Neural Networks with data Quantization for time Series Analysis in LHC Superconducting Magnets

“…This work extends the existing investigations (Wielgosz et al, 2017;2018a;2018b;2018c; 2020) using higher resolution data and more diverse models. The importance of the subject grows because the project High Luminosity LHC (HL-LHC) enters its engineering phase (Apollinari et al, 2017).…”

“…In the work of Wielgosz et al (2017), experiments with the data collected from the CALS database were conducted using the setup presented in Fig. 3(a), which employed the RMSE measure.…”

“…Based on the experience from the previous work (Wielgosz et al, 2017), a new experimental setup was designed. This new approach is shown in Fig.…”

The study of a new time reconstruction method for MRPC read out by waveform digitizer

“…In recent years, the artificial neural network(NN) has shown its great power on solving highly non-linear problems such as pattern recognition, function approximation and prediction in many fields including the high energy physics analysis [4][5][6]. With the waveform digitizer, more information in the MRPC signal is extracted from each event, and in order to utilize this advantage, the method based on neural networks is proposed.…”

A neural network based algorithm for MRPC time reconstruction

“…Artificial neural network(NN) is a powerful tool for solving non-linear pattern recognition problems not only in the field of computer science, but also in high energy physics [3][4][5].…”