Anomaly detection for atomic clocks using unsupervised machine learning algorithms

From National Research Council Canada

Download	View final version: Anomaly detection for atomic clocks using unsupervised machine learning algorithms (PDF, 1.2 MiB)
DOI	Resolve DOI: https://doi.org/10.1088/1681-7575/ad6b30
Author	Search for: Chen, Edwin¹; Search for: Charbonneau, André²; Search for: Gertsvolf, Marina²ORCID identifier: https://orcid.org/0000-0002-1188-2104; Search for: Wang, Yunli¹ORCID identifier: https://orcid.org/0000-0002-2320-954X
Affiliation	National Research Council Canada. Digital Technologies National Research Council Canada. Metrology Research Centre
Format	Text, Article
Subject	atomic clock; phase jumps; frequency jumps; anomaly detection; change point detection; machine learning
Abstract	Atomic clocks are the most accurate timekeeping instruments in the world and play a crucial role in numerous applications, notably in satellite navigation. Nonetheless, the accuracy of these clock signals is subject to anomalies, highlighting the importance of anomaly characterization and detection. In our study, we identify three types of anomalies in the phase data of atomic clocks—outliers, phase jumps and inflection points, and also frequency jumps in the frequency data, which corresponds to the inflection points. The novelty of our work lies in the application of machine learning methods for atomic clock anomaly detection (AD), as opposed to traditional algorithms. We introduce a variety of unsupervised AD and change point detection (CPD) algorithms from the realms of statistics and machine learning, propose a customized thresholding function for AD, and evaluate AD and CPD algorithms on both synthetic and real-world atomic clock data. Our experiments reveal that the subsequence local outlier factor algorithm achieves excellent performance in detecting outliers and phase jumps, but struggles with inflection points. Crucially, we found that the application of a CPD algorithm specifically for detecting the frequency jumps in frequency data substantially improves performance. Our study adopts unsupervised machine learning methods for AD provides robust detection strategies, thereby contributing an expanded understanding of the use of machine learning for clock data monitoring.
Publication date	2024-08-14
Publisher	IOP Publishing Bureau International des Poids et Mesures (BIPM)
Licence	Creative Commons Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/
In	Metrologia 61, no. 5, 055005 (14 August 2024): 1–13.
Language	English
Peer reviewed	Yes
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	3f3d9240-2f9f-443e-baa7-d2fd93f23d32
Record created	2024-08-28
Record modified	2024-08-29

Date modified:: 2025-12-15