Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities

• URL: http://arxiv.org/abs/2202.05610v1
• Date: Thu, 10 Feb 2022 07:32:18 GMT
• Title: Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities
• Authors: Christoph Obermair, Thomas Cartier-Michaud, Andrea Apollonio, William Millar, Lukas Felsberger, Lorenz Fischl, Holger Severin Bovbjerg, Daniel Wollmann, Walter Wuensch, Nuria Catalan-Lasheras, Mar\c{c}\`a Boronat, Franz Pernkopf, Graeme Burt
• Abstract summary: breakdowns are one of the most prevalent limiting factors in RF cavities for particle accelerators. In this paper, we propose a machine learning strategy to discover breakdown Collider in CERN's Compact Linear precursors.
• Score: 7.39531359499484
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Radio Frequency (RF) breakdowns are one of the most prevalent limiting factors in RF cavities for particle accelerators. During a breakdown, field enhancement associated with small deformations on the cavity surface results in electrical arcs. Such arcs lead to beam aborts, reduce machine availability and can cause irreparable damage on the RF cavity surface. In this paper, we propose a machine learning strategy to discover breakdown precursors in CERN's Compact Linear Collider (CLIC) accelerating structures. By interpreting the parameters of the learned models with explainable Artificial Intelligence (AI), we reverse-engineer physical properties for deriving fast, reliable, and simple rule based models. Based on 6 months of historical data and dedicated experiments, our models show fractions of data with high influence on the occurrence of breakdowns. Specifically, it is shown that in many cases a rise of the vacuum pressure is observed before a breakdown is detected with the current interlock sensors.

Related papers

• Localization of Impacts on Thin-Walled Structures by Recurrent Neural Networks: End-to-end Learning from Real-World Data [45.9982965995401]
  Impacts on thin-walled structures excite Lamb waves, which can be measured with piezoelectric sensors.<n>We propose to use recurrent neural networks (RNNs) to estimate impact positions end-to-end, directly from sequential sensor data.<n>Our results show remarkable accuracy in estimating impact positions, even with a comparatively small dataset.
  arXiv  Detail & Related papers  (2025-05-13T09:08:47Z)
• Smoke and Mirrors in Causal Downstream Tasks [59.90654397037007]
  This paper looks at the causal inference task of treatment effect estimation, where the outcome of interest is recorded in high-dimensional observations. We compare 6 480 models fine-tuned from state-of-the-art visual backbones, and find that the sampling and modeling choices significantly affect the accuracy of the causal estimate. Our results suggest that future benchmarks should carefully consider real downstream scientific questions, especially causal ones.
  arXiv  Detail & Related papers  (2024-05-27T13:26:34Z)
• Automated Anomaly Detection on European XFEL Klystrons [1.9389881806157316]
  High-power multi-beam klystrons represent a key component to amplify RF at European XFEL. We conducted experiments to determine various operational modes and conduct feature extraction and dimensionality reduction. We recognized the most promising components that might help us better understand klystron operational states and identify early on possible faults or anomalies.
  arXiv  Detail & Related papers  (2024-05-20T21:59:07Z)
• A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators [46.348283638884425]
  We propose a two-step unsupervised deep learning framework named as Latent Autoregressive Recurrent Model (CLARM) for learning dynamics of charged particles in accelerators. The CLARM can generate projections at various accelerator sampling modules by capturing and decoding the latent space representation. The results demonstrate that the generative and forecasting ability of the proposed approach is promising when tested against a variety of evaluation metrics.
  arXiv  Detail & Related papers  (2024-03-19T22:05:17Z)
• Deep Learning-Based Spatiotemporal Multi-Event Reconstruction for Delay Line Detectors [0.0]
  We present atemporal machine learning model to identify and reconstruct the position and time of multi-hit particle signals. This model achieves a much better resolution for nearby particle hits compared to the classical approach. We show that machine learning models can be effective in improving thetemporal performance of delay line detectors.
  arXiv  Detail & Related papers  (2023-06-13T09:29:22Z)
• Forecasting Particle Accelerator Interruptions Using Logistic LASSO Regression [62.997667081978825]
  Unforeseen particle accelerator interruptions, also known as interlocks, lead to abrupt operational changes despite being necessary safety measures. We propose a simple yet powerful binary classification model aiming to forecast such interruptions. The model is formulated as logistic regression penalized by at least absolute shrinkage and selection operator.
  arXiv  Detail & Related papers  (2023-03-15T23:11:30Z)
• PreFallKD: Pre-Impact Fall Detection via CNN-ViT Knowledge Distillation [8.667056236149918]
  We propose a novel pre-impact fall detection via CNN-ViT knowledge distillation, namely PreFallKD, to strike a balance between detection performance and computational complexity. The proposed PreFallKD transfers the detection knowledge from the pre-trained teacher model to the student model. Experiment results show that PreFallKD could boost the student model during the testing phase and achieves reliable F1-score (92.66%) and lead time (551.3 ms)
  arXiv  Detail & Related papers  (2023-03-07T03:46:53Z)
• In situ detection of RF breakdown on microfabricated surface ion traps [0.0]
  Microfabricated surface ion traps are a principle component of many ion-based quantum information science platforms. When the applied radio-frequency (RF) voltage is increased too much, the devices can experience damaging electric discharge events known as RF breakdown. We introduce two novel techniques for in situ detection of RF breakdown.
  arXiv  Detail & Related papers  (2021-12-17T19:06:27Z)
• Uncertainty aware anomaly detection to predict errant beam pulses in the SNS accelerator [47.187609203210705]
  We describe the application of an uncertainty aware Machine Learning method, the Siamese neural network model, to predictupcoming errant beam pulses. By predicting theupcoming failure, we can stop the accelerator before damage occurs.
  arXiv  Detail & Related papers  (2021-10-22T18:37:22Z)
• Cavity optimization for Unruh effect at small accelerations [0.0]
  The density of field modes inside such a cavity shows a it resonance structure i.e. it rises abruptly for some specific cavity configurations. We show that an accelerating detector inside the cavity exhibits a non-trivial excitation and de-excitation rates for it small accelerations around such resonance points.
  arXiv  Detail & Related papers  (2021-06-30T18:10:44Z)
• Physics-informed CoKriging model of a redox flow battery [68.8204255655161]
  Redox flow batteries (RFBs) offer the capability to store large amounts of energy cheaply and efficiently. There is a need for fast and accurate models of the charge-discharge curve of a RFB to potentially improve the battery capacity and performance. We develop a multifidelity model for predicting the charge-discharge curve of a RFB.
  arXiv  Detail & Related papers  (2021-06-17T00:49:55Z)
• Bayesian Neural Networks for Fast SUSY Predictions [58.720142291102135]
  In this paper, machine learning is used to model the mapping from the parameter space of a BSM theory to some of its predictions. All three quantities are modeled with average percent errors of 3.34% or less and in a time significantly shorter than is possible with the supersymmetry codes from which the results are derived. Results are a further demonstration of the potential for machine learning to model accurately the mapping from the high dimensional spaces of BSM theories to their predictions.
  arXiv  Detail & Related papers  (2020-07-09T01:45:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.