17–22 May 2026
C.I.D
Europe/Zurich timezone

Unsupervised Anomaly Detection and Channel Attribution with Variational Autoencoders at the Advanced Light Source

WEP6306
20 May 2026, 16:00
2h
C.I.D

C.I.D

Deauville, France
Board: Wednesday roquefort: RA04
Poster Presentation MC6.D13: Instrumentation: Artificial Intelligence Poster session

Speaker

Dr Gianluca Martino (Lawrence Berkeley National Laboratory)

Description

We present an unsupervised pipeline that learns a compact representation of beam-on machine state at the ALS, detects anomalies preceding beam-loss events, and highlights the responsible channels for operator diagnosis. Archiver data are resampled to a uniform time grid, filtered to beam-on intervals using stored current, and pruned by variability and principal-component analysis. A variational autoencoder with residual encoder-decoder stacks is trained on the standardised PV vectors; the global anomaly score and the per-PV attribution are both derived from per-PV reconstruction z-scores, so the score is an exact decomposition of the channel ranking.
We apply the pipeline to 34 beam-loss events from the 2025 ALS user run; in several cases it surfaces early-stage anomalies in the PV subsystems that subsequently led to the beam dump, indicating a framework can act as an early-warning aid for operators.

Funding Agency

This work was supported by the Director of the Office of Science of the U.S.Department of Energy under Contract No. DEAC02-05CH11231.

Paper status =Paper accepted.

Author

Antonin Sulc (Lawrence Berkeley National Laboratory)

Co-authors

Dr Gianluca Martino (Lawrence Berkeley National Laboratory) Mr Hiroshi Nishimura (Lawrence Berkeley National Laboratory) Simon Leemann (Lawrence Berkeley National Laboratory) Thorsten Hellert (Lawrence Berkeley National Laboratory)

Presentation materials