Resilient VAE: Unsupervised Anomaly Detection at the SLAC Linac Coherent Light Source
This addresses anomaly detection for particle accelerator operators, but it is incremental as it builds on existing deep learning methods by adding resilience to anomalies in training data.
The paper tackles the problem of unsupervised anomaly detection in complex engineering systems like particle accelerators, where labeled data is scarce, by introducing the Resilient Variational Autoencoder (ResVAE), which demonstrates exceptional capability in identifying various anomalies at the SLAC Linac Coherent Light Source.
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.