Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy Linac
Machine learning (ML) has the potential for significant impact on the modeling, operation, and control of particle accelerators due to its ability to model nonlinear behavior, interpolate on complicated surfaces, and adapt to system changes over time. Anomaly detection in particular has been highlig...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/12/6/238 |
| _version_ | 1827690950938329088 |
|---|---|
| author | Jonathan P. Edelen Christopher C. Hall |
| author_facet | Jonathan P. Edelen Christopher C. Hall |
| author_sort | Jonathan P. Edelen |
| collection | DOAJ |
| description | Machine learning (ML) has the potential for significant impact on the modeling, operation, and control of particle accelerators due to its ability to model nonlinear behavior, interpolate on complicated surfaces, and adapt to system changes over time. Anomaly detection in particular has been highlighted as an area where ML can significantly impact the operation of accelerators. These algorithms work by identifying subtle behaviors of key variables prior to negative events. Efforts to apply ML to anomaly detection have largely focused on subsystems such as RF cavities, superconducting magnets, and losses in rings. However, dedicated efforts to understand how to apply ML for anomaly detection in linear accelerators have been limited. In this paper the use of autoencoders is explored to identify anomalous behavior in measured data from the Fermilab low-energy linear accelerator. |
| first_indexed | 2024-03-10T10:50:09Z |
| format | Article |
| id | doaj.art-c8985266372144238098d65c80dd9670 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-10T10:50:09Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-c8985266372144238098d65c80dd96702023-11-21T22:20:27ZengMDPI AGInformation2078-24892021-05-0112623810.3390/info12060238Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy LinacJonathan P. Edelen0Christopher C. Hall1RadiaSoft LLC, Boulder, CO 80301, USARadiaSoft LLC, Boulder, CO 80301, USAMachine learning (ML) has the potential for significant impact on the modeling, operation, and control of particle accelerators due to its ability to model nonlinear behavior, interpolate on complicated surfaces, and adapt to system changes over time. Anomaly detection in particular has been highlighted as an area where ML can significantly impact the operation of accelerators. These algorithms work by identifying subtle behaviors of key variables prior to negative events. Efforts to apply ML to anomaly detection have largely focused on subsystems such as RF cavities, superconducting magnets, and losses in rings. However, dedicated efforts to understand how to apply ML for anomaly detection in linear accelerators have been limited. In this paper the use of autoencoders is explored to identify anomalous behavior in measured data from the Fermilab low-energy linear accelerator.https://www.mdpi.com/2078-2489/12/6/238autoencoderanomaly detectionlinear acceleratormachine learningroot cause analysis |
| spellingShingle | Jonathan P. Edelen Christopher C. Hall Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy Linac Information autoencoder anomaly detection linear accelerator machine learning root cause analysis |
| title | Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy Linac |
| title_full | Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy Linac |
| title_fullStr | Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy Linac |
| title_full_unstemmed | Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy Linac |
| title_short | Autoencoder Based Analysis of RF Parameters in the Fermilab Low Energy Linac |
| title_sort | autoencoder based analysis of rf parameters in the fermilab low energy linac |
| topic | autoencoder anomaly detection linear accelerator machine learning root cause analysis |
| url | https://www.mdpi.com/2078-2489/12/6/238 |
| work_keys_str_mv | AT jonathanpedelen autoencoderbasedanalysisofrfparametersinthefermilablowenergylinac AT christopherchall autoencoderbasedanalysisofrfparametersinthefermilablowenergylinac |