Multi-module-based CVAE to predict HVCM faults in the SNS accelerator

Yasir Alanazi; Malachi Schram; Kishansingh Rajput; Steven Goldenberg; Lasitha Vidyaratne; Chris Pappas; Majdi I. Radaideh; Dan Lu; Pradeep Ramuhalli; Sarah Cousineau

doi:10.1016/j.mlwa.2023.100484

Multi-module-based CVAE to predict HVCM faults in the SNS accelerator

Yasir Alanazi
, Malachi Schram
, Kishansingh Rajput
, Steven Goldenberg
, Lasitha Vidyaratne
, Chris Pappas
, Majdi I. Radaideh
, Dan Lu
, Pradeep Ramuhalli
, Sarah Cousineau

Research output: Contribution to journal › Article › peer-review

15 Scopus citations

Abstract

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 Artificial Neural Network (ANN) 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.

Original language	English
Article number	100484
Journal	Machine Learning with Applications
Volume	13
DOIs	https://doi.org/10.1016/j.mlwa.2023.100484
State	Published - Sep 15 2023

Funding

The authors acknowledge the help from David Brown in evaluating Operations requirements, Frank Liu, for his assistance on the Machine Learning techniques, and Sarah Cousineau for making this grant work possible. This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The Jefferson Science Associates (JSA) operates the Thomas Jefferson National Accelerator Facility for the U.S. Department of Energy under Contract No. DE-AC05-06OR23177. This research used resources at the Spallation Neutron Source, a DOE Office of Science User Facility operated by the Oak Ridge National Laboratory, grant No. DE-SC0009915. The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan ( http://energy.gov/downloads/doe-public-access-plan ). The authors acknowledge the help from David Brown in evaluating Operations requirements, Frank Liu, for his assistance on the Machine Learning techniques, and Sarah Cousineau for making this grant work possible. This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The Jefferson Science Associates (JSA) operates the Thomas Jefferson National Accelerator Facility for the U.S. Department of Energy under Contract No. DE-AC05-06OR23177. This research used resources at the Spallation Neutron Source, a DOE Office of Science User Facility operated by the Oak Ridge National Laboratory, grant No. DE-SC0009915. The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Keywords

Accelerators
Anomaly detection
High Voltage Converter Modulator
Spallation Neutron Source
Variational Autoencoder

Access to Document

10.1016/j.mlwa.2023.100484

Cite this

@article{526edf4ef1504464a7dc89cf8fda59a5,

title = "Multi-module-based CVAE to predict HVCM faults in the SNS accelerator",

abstract = "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 Artificial Neural Network (ANN) 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.",

keywords = "Accelerators, Anomaly detection, High Voltage Converter Modulator, Spallation Neutron Source, Variational Autoencoder",

author = "Yasir Alanazi and Malachi Schram and Kishansingh Rajput and Steven Goldenberg and Lasitha Vidyaratne and Chris Pappas and Radaideh, \{Majdi I.\} and Dan Lu and Pradeep Ramuhalli and Sarah Cousineau",

note = "Publisher Copyright: {\textcopyright} 2023 The Authors",

year = "2023",

month = sep,

day = "15",

doi = "10.1016/j.mlwa.2023.100484",

language = "English",

volume = "13",

journal = "Machine Learning with Applications",

issn = "2666-8270",

}

TY - JOUR

T1 - Multi-module-based CVAE to predict HVCM faults in the SNS accelerator

AU - Alanazi, Yasir

AU - Schram, Malachi

AU - Rajput, Kishansingh

AU - Goldenberg, Steven

AU - Vidyaratne, Lasitha

AU - Pappas, Chris

AU - Radaideh, Majdi I.

AU - Lu, Dan

AU - Ramuhalli, Pradeep

AU - Cousineau, Sarah

PY - 2023/9/15

Y1 - 2023/9/15

N2 - 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 Artificial Neural Network (ANN) 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.

AB - 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 Artificial Neural Network (ANN) 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.

KW - Accelerators

KW - Anomaly detection

KW - High Voltage Converter Modulator

KW - Spallation Neutron Source

KW - Variational Autoencoder

UR - https://www.scopus.com/pages/publications/85166624678

U2 - 10.1016/j.mlwa.2023.100484

DO - 10.1016/j.mlwa.2023.100484

M3 - Article

AN - SCOPUS:85166624678

SN - 2666-8270

VL - 13

JO - Machine Learning with Applications

JF - Machine Learning with Applications

M1 - 100484

ER -

Multi-module-based CVAE to predict HVCM faults in the SNS accelerator

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this