Operational data for fault prognosis in particle accelerators with machine learning.

This paper presents real operational data collected from the power systems of the Spallation Neutron Source facility, which provides the most intense neutron beam in the world. The authors have used a radio-frequency test facility (RFTF) and simulated system failures in the lab without causing a catastrophic system failure. Waveform signals have been collected from the RFTF normal operation as well as during fault induction efforts. The dataset provides a significant amount of normal and faulty signals for the training of statistical or machine learning models. Then, the authors performed 21 test experiments, where the faults are slowly induced into the RFTF system for the purpose of testing the models in fault prognosis to detect and prevent impending faults. The test experiments include interesting combinations of magnetic flux compensation and start pulse width adjustments, which cause gradual deterioration in the waveforms (e.g., system output voltage, system output current, insulated-gate bipolar transistor currents, magnetic fluxes), which mimic the fault scenarios. Accordingly, this dataset can be valuable for developing models to predict impending fault scenarios in power systems in general and in particle accelerators in specific. All experiments occurred in the Spallation Neutron Source facility of Oak Ridge National Laboratory in Oak Ridge, Tennessee of the United States in July 2022.

Real electronic signal data from particle accelerator power systems for machine learning anomaly detection.

This article describes real time series datasets collected from the high voltage converter modulators (HVCM) of the Spallation Neutron Source facility. HVCMs are used to power the linear accelerator klystrons, which in turn produce the high-power radio frequency to accelerate the negative hydrogen ions (H-). Waveform signals have been collected from the operation of more than 15 HVCM systems categorized into four major subsystems during the years 2020-2022. The data collection process occurred in the Spallation Neutron Source facility of Oak Ridge, Tennessee in the United States. For each of the four subsystems, there are two datasets. The first one contains the waveform signals, while the second contains the label of the waveform, whether it has a normal or faulty signal. A variety of waveforms are included in the datasets including insulated-gate bipolar transistor (IGBT) currents in three phases, magnetic flux in the three phases, modulator current and voltage, cap bank current and voltage, and time derivative change of the modulator voltage. The datasets provided are useful to test and develop machine learning and statistical algorithms for applications related to anomaly detection, system fault detection and classification, and signal processing.

Upgrading the LANSCE accelerator with a SNS RF-driven H- ion source.

The LANSCE accelerator is currently powered by a filament-driven, biased converter-type H- ion source that operates at 10%, the highest plasma duty factor for this type of source, using only ∼2.2 SCCM of H2. The ion source needs to be replaced every 4 weeks, which takes up to 4 days. The measured negative beam current of 12-16 mA falls below the desired 24 mA acceptance of the LANCSE accelerator. The SNS (Spallation Neutron Source) RF-driven, H- ion source injects ∼50 mA of H- beam into the SNS accelerator at 60 Hz with a 6% duty factor and an availability of >99.5% but requires ∼30 SCCM of H2. Up to 7 A h of H- have been produced during the 14-weeks-long source service cycles, which is unprecedented for small emittance, high-current, pulsed H- ion sources. The emittance of the SNS source is slightly smaller than the emittance of the LANSCE source. The SNS source also features unrivaled low Cs consumption and can be installed and started up in <12 h. LANSCE and SNS are working toward the use of SNS H- ion sources on the LANSCE accelerator because they could (a) fill the LANSCE accelerator to its capacity, (b) decrease the source replacement time by a factor of up to 7, and (c) increase source lifetime by a factor of about 4. This paper discusses some of the challenges that emerge when trying to match a different H- source into an existing injector with significantly different characteristics and operating regimes.

First Six Dimensional Phase Space Measurement of an Accelerator Beam.

This Letter presents the first complete six dimensional phase space measurement of a beam in an accelerator. The measurement was made on the Spallation Neutron Source Beam Test Facility. The data reveal previously unknown correlations in the six dimensional phase space distribution that are not visible in lower dimensionality measurements. The correlations are shown to be intensity dependent.

First Demonstration of Laser-Assisted Charge Exchange for Microsecond Duration H

This Letter reports on the first demonstration of laser-assisted H^{-} charge exchange for microsecond duration H^{-} beam pulses. Laser-assisted charge exchange injection is a breakthrough technology that overcomes long-standing limitations associated with the traditional method of producing high intensity, time structured beams of protons in accelerators via the use of carbon foils for charge exchange injection. The central theme of this experiment is the demonstration of novel techniques that reduce the laser power requirement to allow high efficiency stripping of microsecond duration beams with commercial laser technology.