| Paper | Title | Page |
|---|---|---|
| TUPAB327 | Developing Robust Digital Twins and Reinforcement Learning for Accelerator Control Systems at the Fermilab Booster | 2268 |
|
||
|
Funding: This research was sponsored by the Fermilab Laboratory Directed Research and Development Program under Project ID FNAL-LDRD-2019-027: Accelerator Control with Artificial Intelligence. We describe the offline machine learning (ML) development for an effort to precisely regulate the Gradient Magnet Power Supply (GMPS) at the Fermilab Booster accelerator complex via a Field-Programmable Gate Array (FPGA). As part of this effort, we created a digital twin of the Booster-GMPS control system by training a Long Short-Term Memory (LSTM) to capture its full dynamics. We outline the path we took to carefully validate our digital twin before deploying it as a reinforcement learning (RL) environment. Additionally, we demonstrate the use of a Deep Q-Network (DQN) policy model with the capability to regulate the GMPS against realistic time-varying perturbations. |
||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB327 | |
| About • | paper received ※ 18 May 2021 paper accepted ※ 22 June 2021 issue date ※ 20 August 2021 | |
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |
| THPAB252 | Machine Learning for Improved Availability of the SNS Klystron High Voltage Converter Modulators | 4303 |
|
||
|
Funding: SNS/ORNL is managed by UT-Battelle, LLC, under contract DE-AC05-00OR22725 for the U.S. Department of Energy Beam availability has increased at the SNS, however, the targeted availability is greater than 95 %, while the SNS has failed to meet lower targets in the past. The HVCM used to power the linac klystrons have been one source of lost beam time and was chosen to explore using AI/ML techniques to improve reliability. Among the possibilities being explored are automating the tuning of HVCMs and predicting component failures such as capacitor aging, rectifier assemblies containing hundreds of diodes, and insulating oil degradation. The methodology pursued includes data cleaning, de-noising, post-analysis data labeling, and machine learning model development. We explore using Long Short-Term Memory and autoencoders for anomaly detection and prognostication used to schedule maintenance. We evaluate the use of model regularizers and constraints to improve the performance of the model and investigate methods to estimate the uncertainty of the models to provide a robust prediction with statistical interoperability. This paper describes the operational experience and known failures of the HVCMs and the proposed ML methodology and the preliminary results of training the AI/ML algorithms. * G. Dodson, Approach to Reliable Operations, 26-DodsonApproach to Reliable Operation-r1.pdf, Feb., 2010. |
||
| DOI • | reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-THPAB252 | |
| About • | paper received ※ 18 May 2021 paper accepted ※ 14 July 2021 issue date ※ 29 August 2021 | |
| Export • | reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml) | |