Anomaly Detection in Particle Accelerators using Autoencoders

Edelen, Jonathan P.; Cook, Nathan M.

doi:10.48550/arxiv.2112.07793

Cited by 2 publications

(3 citation statements)

References 7 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can also use Fβ to train the anomaly models end-to-end, with the models parameterized as deep neural networks (DNNs) (sections 4.2-4.4). 4. We demonstrate these contributions on four data sets: a synthetic outlier data set, a synthetic image data set generated from the MNIST text database, a publicly available metal milling data set, and an experimental data set taken from a particle accelerator.…”

Section: Contributionsmentioning

confidence: 99%

“…The problem of anomaly detection, the task of finding abnormal events or data, is an important task for large-scale scientific instruments and other complex systems, such as industrial facilities and manufacturing [1][2][3][4][5][6]. Failures in these systems can lead to lost data, poor performance, or even damage to components, making identifying these failures a high-priority task for system operators.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Coincident learning for unsupervised anomaly detection of scientific instruments

Humble,

Zhang,

O’Shea

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Anomaly detection is an important task for complex scientific experiments and other complex systems (e.g., industrial facilities, manufacturing), where failures in a sub-system can lead to lost data, poor performance, or even damage to components. While scientific facilities generate a wealth of data, labeled anomalies may be rare (or even nonexistent), and expensive to acquire. Unsupervised approaches are therefore common and typically search for anomalies either by distance or density of examples in the input feature space (or some associated low-dimensional representation). This paper presents a novel approach called CoAD, which is specifically designed for multi-modal tasks and identifies anomalies based on coincident behavior across two different slices of the feature space. We define an unsupervised metric, F̂ᵦ, out of analogy to the supervised classification Fβ statistic. CoAD uses F̂ᵦ to train an anomaly detection algorithm on unlabeled data, based on the expectation that anomalous behavior in one feature slice is coincident with anomalous behavior in the other. The method is illustrated using a synthetic outlier data set and a MNIST-based image data set, and is compared to prior state-of-the-art on two real-world tasks: a metal milling data set and our motivating task of identifying RF station anomalies in a particle accelerator.

show abstract

Section: Contributionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Coincident learning for unsupervised anomaly detection of scientific instruments

Humble,

Zhang,

O’Shea

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Anomaly detection (AD), which is the task of finding abnormal data or events, is a critical task for nearly all data-heavy, complex systems, such as industrial facilities, manufacturing, and large-scale science experiments [1][2][3][4] . These systems can produce thousands of real-time signals, which quickly overwhelm human operators that seek to monitor system performance.…”

Section: Introductionmentioning

confidence: 99%

Beam-based rf station fault identification at the SLAC Linac Coherent Light Source

Humble

O'Shea²,

Colocho³

et al. 2022

Phys. Rev. Accel. Beams

View full text Add to dashboard Cite

Significant advances in utilizing deep learning for anomaly detection have been made in recent years. However, these methods largely assume the existence of a normal training set (i.e., uncontaminated by anomalies) or even a completely labeled training set. In many complex engineering systems, such as particle accelerators, labels are sparse and expensive; in order to perform anomaly detection in these cases, we must drop these assumptions and utilize a completely unsupervised method. This paper introduces the Resilient Variational Autoencoder (ResVAE), a deep generative model specifically designed for anomaly detection. ResVAE exhibits resilience to anomalies present in the training data and provides feature-level anomaly attribution. During the training process, ResVAE learns the anomaly probability for each sample as well as each individual feature, utilizing these probabilities to effectively disregard anomalous examples in the training data. We apply our proposed method to detect anomalies in the accelerator status at the SLAC Linac Coherent Light Source (LCLS). By utilizing shot-to-shot data from the beam position monitoring system, we demonstrate the exceptional capability of ResVAE in identifying various types of anomalies that are visible in the accelerator.

show abstract

Anomaly Detection in Particle Accelerators using Autoencoders

Cited by 2 publications

References 7 publications

Coincident learning for unsupervised anomaly detection of scientific instruments

Coincident learning for unsupervised anomaly detection of scientific instruments

Beam-based rf station fault identification at the SLAC Linac Coherent Light Source

Contact Info

Product

Resources

About