Fingerprint Recognition of Partial Discharge Signals in Deep Learning Enhanced Rydberg Atomic Sensors

Abstract

Partial discharge originates from microscopic insulation imperfections in high-voltage apparatus and is widely considered a critical marker of incipient deterioration. Conventional partial discharge detection methods are typically constrained by limited bandwidth and often rely on predefined feature extraction, which impedes reliable recognition of broadband transient signals. In this work, we employ a Rydberg atomic sensor to directly capture time-domain responses of partial discharge emissions and construct distinctive spectral fingerprints for different types. A 1D ResNet deep learning model is then applied to recognize these fingerprints from time-domain signals without manual feature engineering. Under increased source-antenna distances, where spectral features are significantly attenuated, the model attains a recognition accuracy of approximately 94\% across four partial discharge categories, demonstrating robustness to attenuation and noise. We further validate the approach in a simulated early-warning scenario, where partial discharge signals mixed with noise are analyzed and the model successfully generates predictive alarms. These results underscore the potential of integrating Rydberg-based broadband sensing with data-driven analysis for non-invasive, high-sensitivity diagnostics of electrical insulation systems.

arXiv comment10 pages, 6 figures. Published in Optics Express

References in corpus (19)

• Deep learning for time series classification: a review
• InceptionTime: Finding AlexNet for Time Series Classification
• Broadband Rydberg Atom-Based Electric-Field Probe: From Self-Calibrated Measurements to Sub-Wavelength Imaging
• Reinforcement Learning in Different Phases of Quantum Control
• Waveguide-coupled Rydberg spectrum analyzer from 0 to 20 GHz
• Fast machine-learning online optimization of ultra-cold-atom experiments
• Assessment of Rydberg Atoms for Wideband Electric Field Sensing
• Machine learning-based classification of vector vortex beams
• Microwave electrometry via electromagnetically induced absorption in cold Rydberg atoms
• Deep learning enhanced Rydberg multifrequency microwave recognition
• Highly sensitive measurement of a megahertz rf electric field with a Rydberg-atom sensor
• Multiparameter optimisation of a magneto-optical trap using deep learning
• Enhancement of Rydberg atom interactions using ac Stark shifts
• Enhanced electric field sensitivity of rf-dressed Rydberg dark states
• Deep Reinforcement Learning Control of Quantum Cartpoles
• Far-field subwavelength acoustic imaging by deep learning
• Bayesian optimal control of GHZ states in Rydberg lattices
• Controlled Online Optimization Learning (COOL): Finding the ground state of spin Hamiltonians with reinforcement learning
• Time-dependent atomic magnetometry with a recurrent neural network