Multi-module based CVAE to predict HVCM faults in the SNS accelerator
This work addresses reliability and uptime issues for particle accelerator systems like SNS, but it is incremental as it applies an existing CVAE method to a new domain with limited data.
The paper tackled the problem of detecting faults in High Voltage Converter Modulators (HVCMs) at the Spallation Neutron Source (SNS) by developing a multi-module Conditional Variational Autoencoder (CVAE) framework, which improved sensitivity to specific fault types and generalized well across multiple module types.
We present a multi-module framework based on Conditional Variational Autoencoder (CVAE) to detect anomalies in the power signals coming from multiple High Voltage Converter Modulators (HVCMs). We condition the model with the specific modulator type to capture different representations of the normal waveforms and to improve the sensitivity of the model to identify a specific type of fault when we have limited samples for a given module type. We studied several neural network (NN) architectures for our CVAE model and evaluated the model performance by looking at their loss landscape for stability and generalization. Our results for the Spallation Neutron Source (SNS) experimental data show that the trained model generalizes well to detecting multiple fault types for several HVCM module types. The results of this study can be used to improve the HVCM reliability and overall SNS uptime