IPAC2022 - List of Authors (Sulc, A.)

Paper	Title	Page
MOPOPT069	A Data-Driven Beam Trajectory Monitoring at the European XFEL	418
	A. Sulc, R. Kammering, T. Wilksen DESY, Hamburg, Germany
	Funding: This work was supported by HamburgX grant LFF-HHX-03 to the Center for Data and Computing in Natural Sciences (CDCS) from the Hamburg Ministry of Science, Research, Equalities and Districts. Interpretation of data from beam position monitors is a crucial part of the reliable operation of European XFEL. The interpretation of beam positions is often handled by a physical model, which can be prone to modeling errors or can lead to the high complexity of the computational model. In this paper, we show two data-driven approaches that provide insights into the operation of the SASE beamlines at European XFEL. We handle the analysis as a data-driven problem, separate it from physical peculiarities and experiment with available data based only on our empirical evidence and the data.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOPT069
About •	Received ※ 06 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 20 June 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPOPT062	A Data-Driven Anomaly Detection on SRF Cavities at the European XFEL	1152
	A. Sulc, A. Eichler, T. Wilksen DESY, Hamburg, Germany
	Funding: This work was supported by HamburgX grant LFF-HHX-03 to the Center for Data and Computing in Natural Sciences (CDCS) from the Hamburg Ministry of Science, Research, Equalities and Districts. The European XFEL is currently operating with hundreds of superconducting radio frequency cavities. To be able to minimize the downtimes, prevention of failures on the SRF cavities is crucial. In this paper, we propose an anomaly detection approach based on a neural network model to predict occurrences of breakdowns on the SRF cavities based on a model trained on historical data. We used our existing anomaly detection infrastructure to get a subset of the stored data labeled as faulty. We experimented with different training losses to maximally profit from the available data and trained a recurrent neural network that can predict a failure from a series of pulses. The proposed model is using a tailored architecture with recurrent neural units and takes into account the sequential nature of the problem which can generalize and predict a variety of failures that we have been experiencing in operation.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOPT062
About •	Received ※ 17 May 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 24 June 2022
Cite •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

A Data-Driven Beam Trajectory Monitoring at the European XFEL

418

A. Sulc, R. Kammering, T. Wilksen
DESY, Hamburg, Germany

Funding: This work was supported by HamburgX grant LFF-HHX-03 to the Center for Data and Computing in Natural Sciences (CDCS) from the Hamburg Ministry of Science, Research, Equalities and Districts.
Interpretation of data from beam position monitors is a crucial part of the reliable operation of European XFEL. The interpretation of beam positions is often handled by a physical model, which can be prone to modeling errors or can lead to the high complexity of the computational model. In this paper, we show two data-driven approaches that provide insights into the operation of the SASE beamlines at European XFEL. We handle the analysis as a data-driven problem, separate it from physical peculiarities and experiment with available data based only on our empirical evidence and the data.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-MOPOPT069

About •

Received ※ 06 June 2022 — Accepted ※ 16 June 2022 — Issue date ※ 20 June 2022

Cite •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPOPT062

A Data-Driven Anomaly Detection on SRF Cavities at the European XFEL

1152

A. Sulc, A. Eichler, T. Wilksen
DESY, Hamburg, Germany

Funding: This work was supported by HamburgX grant LFF-HHX-03 to the Center for Data and Computing in Natural Sciences (CDCS) from the Hamburg Ministry of Science, Research, Equalities and Districts.
The European XFEL is currently operating with hundreds of superconducting radio frequency cavities. To be able to minimize the downtimes, prevention of failures on the SRF cavities is crucial. In this paper, we propose an anomaly detection approach based on a neural network model to predict occurrences of breakdowns on the SRF cavities based on a model trained on historical data. We used our existing anomaly detection infrastructure to get a subset of the stored data labeled as faulty. We experimented with different training losses to maximally profit from the available data and trained a recurrent neural network that can predict a failure from a series of pulses. The proposed model is using a tailored architecture with recurrent neural units and takes into account the sequential nature of the problem which can generalize and predict a variety of failures that we have been experiencing in operation.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2022-TUPOPT062

About •

Received ※ 17 May 2022 — Revised ※ 14 June 2022 — Accepted ※ 15 June 2022 — Issue date ※ 24 June 2022

Cite •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)