Overview of ten-year operation of the superconducting linear accelerator at the Spallation Neutron Source

Kim, Sang-ho; Afanador, Ralph; Barnhart, Debra; Crofford, M.; DeGraff, B.; Doléans, M.; Galambos, J.; Gold, Steve; Howell, M.; Mammosser, J.; McMahan, Christopher; Neustadt, T.; Peters, Charles C.; Saunders, Jeffrey; Strong, W.; Vandygriff, Daniel; Vandygriff, David

doi:10.1016/j.nima.2017.02.009

Cited by 16 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SNS accelerator employs a DCM [41,42] to protect the super conducting linac (SCL) from adverse effects of beam losses [43]. Figure 1 shows a schematic diagram of the DCM.…”

Section: Data Source and Collectionmentioning

confidence: 99%

Robust errant beam prognostics with conditional modeling for particle accelerators

Rajput,

Schram,

Blokland

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Particle accelerators are complex and comprise thousands of components, with many pieces of equipment running at their peak power. Consequently, they can fault and abort operations for numerous reasons, lowering efficiency and science output. To avoid these faults, we apply anomaly detection techniques to predict unusual behavior and perform preemptive actions to improve the total availability. Supervised Machine Learning (ML) techniques such as Siamese Neural Network (SNN) models can outperform the often-used unsupervised or semi-supervised approaches for anomaly detection by leveraging the label information. One of the challenges specific to anomaly detection for particle accelerators is the data’s variability due to accelerator configuration changes within a production run of several months. ML models fail at providing accurate predictions when data changes due to changes in the configuration. To address this challenge, we include the configuration settings into our models and training to improve the results. Beam configurations are used as a conditional input for the model to learn any cross-correlation between the data from different conditions and retain its performance. We employ Conditional Siamese Neural Network (CSNN) models and Conditional Variational Auto Encoder (CVAE) models to predict errant beam pulses at the Spallation Neutron Source (SNS) under different system configurations and compare their performance. We demonstrate that CSNNs outperform CVAEs in our application.

show abstract

“…SNS accelerator employs a DCM [41,42] to protect the super conducting linac (SCL) from adverse effects of beam losses [43]. Figure 1 shows a schematic diagram of the DCM.…”

Section: Data Source and Collectionmentioning

confidence: 99%

Robust errant beam prognostics with conditional modeling for particle accelerators

Rajput,

Schram,

Blokland

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Located in the United States, the SNS represents a cutting-edge accelerator-based facility, producing the world's highest intensity pulsed neutron beams [1], instrumental for advanced scientific research and industrial applications. Recent upgrades have enabled the SNS to deliver 1.7 MW beam (previously 1.4 MW), creating a new world record [2].…”

Section: Introductionmentioning

confidence: 99%

H⁻ Ion Source RF Plasma Testing with 13 MHz and 27 MHz at the Spallation Neutron Source (SNS)¹

Narayan,

Piller,

Vestal

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The baseline RF-driven H− ion source configuration at the Spallation Neutron Source (SNS) facility uses a continuous wave (CW) 600 W 13 MHz RF system to ignite and maintain a low-density plasma inside the ion source vacuum chamber. After the continuous low-density 13 MHz plasma has been established, a pulsed (typical 1 ms pulse width and 60 Hz pulse repetition rate) 80 kW 2 MHz RF system is used to increase the plasma density to produce the pulsed H− ion beam. Incremental upgrades and improvements to the SNS ion source systems have resulted in the ability to reliably operate an H− ion source for SNS neutron production run cycles that can last up to four months. Conditions inside the SNS H− ion source evolve throughout a four-month run cycle due to changes in impurity levels, sputtering, and erosion. As the internal ion source conditions change during the run cycle, there can also be changes in plasma stability and the 13 MHz RF power level required to ignite the plasma. This paper presents the preliminary results of testing performed on the SNS Ion Source Test Stand (ISTS) system where we looked at plasma ignition and plasma stability using 27 MHz RF in place of the baseline 13 MHz RF system.

show abstract

Ultrahigh accelerating gradient and quality factor of CEPC 650 MHz superconducting radio-frequency cavity

et al. 2022

View full text Add to dashboard Cite

Overview of ten-year operation of the superconducting linear accelerator at the Spallation Neutron Source

Cited by 16 publications

References 16 publications

Robust errant beam prognostics with conditional modeling for particle accelerators

Robust errant beam prognostics with conditional modeling for particle accelerators

H⁻ Ion Source RF Plasma Testing with 13 MHz and 27 MHz at the Spallation Neutron Source (SNS)¹

Ultrahigh accelerating gradient and quality factor of CEPC 650 MHz superconducting radio-frequency cavity

Contact Info

Product

Resources

About

Overview of ten-year operation of the superconducting linear accelerator at the Spallation Neutron Source

Cited by 16 publications

References 16 publications

Robust errant beam prognostics with conditional modeling for particle accelerators

Robust errant beam prognostics with conditional modeling for particle accelerators

H− Ion Source RF Plasma Testing with 13 MHz and 27 MHz at the Spallation Neutron Source (SNS)1

Ultrahigh accelerating gradient and quality factor of CEPC 650 MHz superconducting radio-frequency cavity

Contact Info

Product

Resources

About

H⁻ Ion Source RF Plasma Testing with 13 MHz and 27 MHz at the Spallation Neutron Source (SNS)¹