<abstract xmlns="http://www.w3.org/1999/xhtml"><p>The aim of this paper is to present a model based on the recurrent neural network (RNN) architecture, the long short-term memory (LSTM) in particular, for modeling the work parameters of Large Hadron Collider (LHC) super-conducting magnets. High-resolution data available in the post mortem database were used to train a set of models and compare their performance for various hyper-parameters such as input data quantization and the number of cells. A novel approach to signal level quantization allowed reducing the size of the model, simplifying the tuning of the magnet monitoring system and making the process scalable. The paper shows that an RNN such as the LSTM or a gated recurrent unit (GRU) can be used for modeling high-resolution signals with the accuracy of over 0.95 and a small number of parameters, ranging from 800 to 1200. This makes the solution suitable for hardware implementation, which is essential in the case of monitoring the performance critical and high-speed signal of LHC superconducting magnets.</p></abstract>

The aim of this paper is to present a model based on the recurrent neural network (RNN) architecture, the long short-term memory (LSTM) in particular, for modeling the work parameters of Large Hadron Collider (LHC) super-conducting magnets. High-resolution data available in the post mortem database were used to train a set of models and compare their performance for various hyper-parameters such as input data quantization and the number of cells. A novel approach to signal level quantization allowed reducing the size of the model, simplifying the tuning of the magnet monitoring system and making the process scalable. The paper shows that an RNN such as the LSTM or a gated recurrent unit (GRU) can be used for modeling high-resolution signals with the accuracy of over 0.95 and a small number of parameters, ranging from 800 to 1200. This makes the solution suitable for hardware implementation, which is essential in the case of monitoring the performance critical and high-speed signal of LHC superconducting magnets.

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

Faculty of Computer Science, Electronics and Telecommunications

Faculty of Physics and Applied Computer Science

International Journal of Applied Mathematics and Computer Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

The aim of this paper is to present a model based on the recurrent neural network (RNN) architecture, the long short-term memory (LSTM) in particular, for...

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

Publié en ligne: 28 sept. 2019

Pages: 503 - 515

Reçu: 11 oct. 2018

Accepté: 23 avr. 2019

DOI: https://doi.org/10.2478/amcs-2019-0037

Mots clés
Large Hadron Collider, LSTM architecture, signal modelling

© 2019 Maciej Wielgosz et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

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

Publié en ligne: 28 sept. 2019

Pages: 503 - 515

Reçu: 11 oct. 2018

Accepté: 23 avr. 2019

DOI: https://doi.org/10.2478/amcs-2019-0037

Mots clésLarge Hadron Collider, LSTM architecture, signal modelling

© 2019 Maciej Wielgosz et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Mots clés
Large Hadron Collider, LSTM architecture, signal modelling