A novel approach for classification and forecasting of time series in particle accelerators
| Autor: | Mélissa Zacharias, Jaime Coello de Portugal, Sichen Li, Davide Reggiani, Fernando Perez-Cruz, Andreas Adelmann, Jochem Snuverink |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Accelerator Physics (physics.acc-ph)
Signal Processing (eess.SP) FOS: Computer and information sciences Computer Science - Machine Learning recurrence plot Computer science MathematicsofComputing_GENERAL FOS: Physical sciences convolutional neural network 01 natural sciences Convolutional neural network Machine Learning (cs.LG) 0103 physical sciences FOS: Electrical engineering electronic engineering information engineering Electrical Engineering and Systems Science - Signal Processing 010306 general physics Interlock Recurrence plot charged particle accelerator lcsh:T58.5-58.64 Series (mathematics) Contextual image classification time series classification lcsh:Information technology 010308 nuclear & particles physics Random forest random forest Binary classification Physics::Accelerator Physics Physics - Accelerator Physics Algorithm Beam (structure) Information Systems |
| Zdroj: | Information Volume 12 Issue 3 Information, 12 (3) Information, Vol 12, Iss 121, p 121 (2021) |
| ISSN: | 2078-2489 |
| DOI: | 10.3929/ethz-b-000477339 |
| Popis: | The beam interruptions (interlocks) of particle accelerators, despite being necessary safety measures, lead to abrupt operational changes and a substantial loss of beam time. A novel time series classification approach is applied to decrease beam time loss in the High-Intensity Proton Accelerator complex by forecasting interlock events. The forecasting is performed through binary classification of windows of multivariate time series. The time series are transformed into Recurrence Plots which are then classified by a Convolutional Neural Network, which not only captures the inner structure of the time series but also uses the advances of image classification techniques. Our best-performing interlock-to-stable classifier reaches an Area under the ROC Curve value of 0.71±0.01 compared to 0.65±0.01 of a Random Forest model, and it can potentially reduce the beam time loss by 0.5±0.2 s per interlock. Information, 12 (3) ISSN:2078-2489 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|