TL;DR
These findings support radar as a practical alternative for machine monitoring and demonstrate that time–frequency representations combined with deep feature learning can further improve fault recognition performance, overcoming the limitations of contact-based sensors.
This paper presents a structured review of antenna and electromagnetic spectrum monitoring techniques for non-invasive fault detection in electrical and electronic equipment. Electromagnetic emissions from partial discharges, arc faults, insulation degradation, and component ageing carry diagnostic signatures detectable through remote radio-frequency sensing. We review (1) antenna technologies spanning magnetic-field loops to ultra-high-frequency electric-field sensors, including fractal, Vivaldi, spiral, and bio-inspired designs; (2) data acquisition platforms ranging from laboratory oscilloscopes to software-defined radio receivers and IoT edge nodes; (3) signal processing methods including time–frequency analysis, adaptive decomposition, and statistical techniques; and (4) machine learning approaches from classical classifiers to deep learning architectures such as convolutional neural networks, recurrent neural networks, and Transformer-based models. Unlike prior surveys focusing on individual fault types or specific equipment classes, this review connects all five layers of the sensing pipeline—from electromagnetic emission physics through antenna selection, signal acquisition, processing, and intelligent classification—for partial-discharge, arc, and insulation faults and analyses the cross-layer constraints that couple them. Design optimisation techniques based on computational electromagnetic methods (FDTD, FEM) and sensitivity calibration challenges are discussed. Open challenges, including the lack of standardised UHF calibration, cross-equipment generalisation, and the scarcity of open electromagnetic fault datasets, are identified, along with emerging directions in flexible antennas, edge AI, and digital twin integration.
Reliable fault diagnosis in rotating machinery is challenging due to the nonlinear and non-stationary nature of vibration signals. Although time–frequency analysis is widely used, it cannot capture the cross-scale coupling between amplitude-modulated (AM) and frequency-modulated (FM) components that carry essential diagnostic information. This study applies Holo-Hilbert Spectrum Analysis (HHSA) to extract amplitude–frequency modulation features and integrates them with six machine learning classifiers to identify four fault conditions. Random Forest, K-Nearest Neighbors, and Logistic Regression achieve accuracies of up to 99.95%, yielding higher accuracy than Fast Fourier Transform-based features. The proposed framework employs an HHSA-based feature extraction pipeline that effectively captures AM–FM coupling in nonlinear vibration signals. It also provides higher discriminative capability than traditional spectral approaches and maintains robustness across multiple classifiers. This method offers high diagnostic accuracy and strong potential for industrial predictive maintenance. Future work will focus on improving computational efficiency and evaluating the framework under more diverse and realistic operating conditions. Received: 10 September 2025 | Revised: 20 April 2026 | Accepted: 10 June 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The VBL-VA001 datasets that support the findings of this study are openly available at https://doi.org/10.1007/s42417-023-00959-9, reference number [44]. Author Contribution Statement Van-Trung Nguyen: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing - original draft, Writing - review & editing, Visualization. Ba-Tan Le: Investigation, Data curation, Writing - original draft, Writing - review & editing. Van-Phuong Dao: Methodology, Validation, Writing - review & editing.
This protocol provides a robust non-contact strategy for insulation fault diagnosis and condition monitoring of electrical power equipment by extracting and fusing time- and frequency-domain acoustic features for automated fault classification.
The findings affirm the efficacy of XGBoost in bearing fault classification and emphasise the diagnostic value of carefully selected time-domain features, as well as suggesting strong potential for deploying such models in real-time condition monitoring and predictive maintenance systems.
Motor Current Signature Analysis (MCSA) is a non-invasive technique that enables the detection of bearing faults in rotating electrical machines without the need for additional sensors. In this study, the Paderborn University bearing dataset was utilized to perform a two-stage analysis. In the first stage, motor current data were processed directly using 1-Dimensional Convolutional Neural Networks (1D-CNN). In the second stage, scalogram images obtained via Continuous Wavelet Transform (CWT) were used to train five different deep learning models, with the ResNet18-based 2D-CNN model providing the best performance. To prevent data leakage, the training and testing sets were partitioned based on individual bearings to ensure complete isolation. The experimental results demonstrated that both 1D-CNN and ResNet18-based 2D-CNN methods achieved 100% accuracy in detecting outer race faults. However, it was observed that the impact of inner race faults on the stator current remains weak due to the complex physical transmission path of the fault signal, resulting in significantly lower detection rates.
Motor drive systems operating in embedded environments are frequently affected by noise, dynamic loading conditions, and electromagnetic interference, making timely fault diagnosis difficult. To improve diagnostic accuracy and real-time performance, this study proposes an intelligent fault diagnosis framework based on embedded multi-source data acquisition and feature fusion. High-precision sensors are employed to synchronously collect vibration and current signals, while improved wavelet packet decomposition and principal component analysis are combined to extract discriminative multi-dimensional fault features and eliminate redundant information. A lightweight convolutional neural network optimized for embedded deployment is then developed to perform low-latency fault classification and edge inference. Experimental results show that the proposed method achieves an average F1-score exceeding 97% under complex mixed-fault conditions, while maintaining an average detection latency of approximately 45 ms. The proposed framework demonstrates strong robustness and computational efficiency, providing practical support for intelligent industrial maintenance and offering reference solutions for embedded sensing, signal processing, and electromagnetic compatibility environments.