Diamond-neural-network magnetic sensors for ultrafast circuit fault detection and identification
At a Glance
Section titled āAt a Glanceā| Metadata | Details |
|---|---|
| Publication Date | 2025-08-21 |
| Journal | Photonics Research |
| Authors | Wei Gao, Jinyu Tai, Zhibin Wang, Shuchen Song, Xin Li |
Abstract
Section titled āAbstractāAs fundamental components of consumer electronics, medical devices, and aerospace precision instruments, circuit modules require fault detection analysis to ensure operational stability and safety, which remains a critical challenge. Conventional contact-based electrical signal detection methods for printed circuit board (PCB) fault analysis often induce contact damage and suffer from slow detection and analysis speeds due to massive redundant data transmission and processing. Here, we propose a diamond-neural-network quantum magnetic sensor that enables non-contact circuit fault analysis by detecting far-field weak magnetic signals from PCBs. The sensor comprises a diamond array where each diamond functions as a nitrogen-vacancy (NV) center quantum magnetic sensor with tunable responsivity regulated by positive and negative voltage follower units. This diamond array inherently constitutes an artificial neural network (ANN), capable of simultaneous magnetic signal detection and real-time processing with ultra-low latency. Through training the sensor for fault classification, we achieve a response time superior to 137.1 ns.
Tech Support
Section titled āTech SupportāOriginal Source
Section titled āOriginal SourceāReferences
Section titled āReferencesā- 2024 - Flaw detection in PCB using deep learning and image processing
- 2023 - Image processing techniques for PCB board fault analysis with object extraction and measurements [Crossref]