Search Results (62)

Silicon carbide (SiC) power converters offer superior switching performance but generate severe broadband electromagnetic interference (EMI) that challenges regulatory compliance. Existing prediction methods face a fundamental trade-off between physical fidelity and computational efficiency, while conventional suppression strategies lack adaptability to varying operating conditions. This paper proposes a frequency-band-aware physics-informed generative adversarial network (FBA-PIGAN) that integrates electromagnetic domain knowledge into data-driven generative modeling for joint EMI prediction and adaptive suppression in SiC power converters. The framework employs a Wasserstein GAN with gradient penalty as the adversarial backbone and introduces feature-wise linear modulation (FiLM) to inject converter operating parameters into the generator through learned affine transformations. A hierarchical physics-informed loss function enforces three frequency-dependent constraints, namely, harmonic structure consistency, parasitic resonance characterization, and high-frequency envelope regularization, coordinated by a curriculum-based weight-scheduling strategy. An end-to-end differentiable suppression module maps predicted spectra to optimal passive filter parameters through an analytically embedded transfer function. Experimental validation on a 10 kW SiC inverter platform with 5120 measured spectra across 32 operating conditions demonstrates that FBA-PIGAN achieves a mean spectral error of 2.1 dB, 93.8% peak frequency accuracy, and a physical consistency score of 0.93, improving prediction accuracy by 56% over conventional conditional GANs while maintaining sub-millisecond inference latency. The integrated suppression pipeline attains 19.2 dB average attenuation with 98.5% CISPR 25 compliance, and the framework generalizes to unseen operating conditions with only 19% performance degradation, compared with 56% for data-driven baselines. Full article

To meet the increasingly strict requirements of modern communication, radar detection and electronic measurement systems for wide-bandwidth, low-insertion-loss and high-isolation signal routing, this paper presents a 16 × 16 programmable switch matrix that simultaneously achieves wideband operation (DC-40 GHz), low insertion loss (≤0.9 dB maximum), high isolation (>50 dB typical), and systematic modular scalability, a combination not found in existing implementations. The matrix, constructed with high-quality coaxial switches and optimized RF circuitry and electromagnetic structures, provides flexible and stable single-pole multi-throw (SPMT) signal routing across an ultra-wide frequency range from DC to 40 GHz. The switch matrix features a modular architecture, integrating multiple RF switching units, drive control circuits, and communication interface modules. This architecture achieves minimal signal path depth while maintaining full connectivity between any input and output port, directly minimizing cumulative insertion loss. Through precise impedance matching design and isolation structure optimization, the system still exhibits outstanding transmission characteristics at the 40 GHz high-frequency end: typical insertion loss does not exceed 0.9 dB, and the isolation between channels is better than 50 dB, effectively ensuring the integrity of signals in complex multi-channel environments. To meet the requirements of automated testing and remote control, the equipment integrates dual communication interfaces (serial port/network port), supports the SCPI command set and TCP/IP protocol, and can be conveniently embedded in various test platforms to achieve instrument interconnection and test process automation. Experimental verification shows that this matrix exhibits excellent switching stability and signal consistency across the entire 40 GHz, with a switching action time of less than 10 ms. Furthermore, it is capable of real-time topology reconfiguration via a microcontroller or FPGA. These innovations collectively deliver a switch matrix that meets the demanding requirements of 5G communication, millimeter-wave radar, and aerospace defense systems—applications where bandwidth, signal integrity, and system flexibility are paramount. Full article

To address the issues of sample imbalance, unstable generation quality, and insufficient feature extraction in spectrum anomaly signal detection under complex electromagnetic environments, this paper proposes a VAE-GANGP identification model that integrates a Variational Autoencoder (VAE) with a Gradient Penalty-based Generative Adversarial Network (GAN-GP). First, the VAE is employed to encode the original spectrum, generating structured latent features that follow a standard normal distribution. This replaces the random noise input in traditional GANs, significantly enhancing the semantic consistency of generated samples and training stability. Second, an adversarial training mechanism based on Wasserstein distance with gradient penalty (WGAN-GP) is introduced, effectively mitigating mode collapse and gradient vanishing, thereby improving the model’s capability to fit complex signal distributions. Furthermore, a multi-objective optimization function combining reconstruction error and adversarial loss is constructed, establishing an end-to-end integrated framework for feature learning, signal reconstruction, and anomaly discrimination. Experiments are conducted using a synthetic dataset comprising various modulation types and simulated environments with different signal-to-noise ratios for systematic validation. The results demonstrate that the spectrum data generated by VAE-GANGP closely matches the distribution of real signals. Under AWGN-dominated synthetic test conditions, the model achieves an anomaly detection accuracy of 98.1%. When evaluated under more realistic channel impairments (phase noise, multipath, impulsive interference), the model maintains competitive performance, outperforming existing methods and demonstrating promising potential for practical electromagnetic spectrum monitoring. Its performance significantly surpasses traditional detection methods and single deep learning models, providing a highly reliable and adaptive solution for spatial electromagnetic spectrum anomaly detection. Full article

As a crucial long-range positioning, navigation, and timing (PNT) system, eLoran will utilize the ninth pulse to broadcast differential data. However, conventional demodulation methods are ill-suited to the unique modulation characteristics of the ninth pulse and suffer from poor noise resistance, necessitating a more efficient demodulation solution. To address this, this paper proposes a lightweight Multilayer Perceptron (MLP)-based demodulation framework designed explicitly for the eLoran ninth pulse. The approach begins with a preprocessing stage that extracts a 1600-point key segment from each received frame, which is then fed into a compact MLP architecture with a 1600-dimensional input layer, a 512-neuron hidden layer, and a 32-class output layer trained using the Adam optimizer. Experimental results demonstrate that the proposed model achieves 99.97% accuracy on the validation set and maintains over 90% demodulation accuracy even at an SNR of −10 dB, whereas the improved EPD algorithm yields only about 70% demodulation accuracy. Notably, although the improved EPD algorithm itself exhibits a clear performance advantage over the basic correlation method and the peak-position detection method—both of which still present non-zero error rates even at an SNR of 20 dB—it remains significantly inferior to the proposed MLP-based scheme in the low-SNR regime. In addition, CNN-based and LSTM-based demodulation models show very poor performance under severe noise conditions, with symbol error rates rising to around 0.8 at −10 dB, despite being able to reach an error-free state when the SNR increases to approximately 2 dB. By adopting an end-to-end learning strategy, the method effectively avoids performance degradation caused by inter-module error propagation, while combining high precision with strong noise immunity. These features meet the requirements for real-time differential data reception and highlight the promising engineering potential of neural-network-based demodulation for high-reliability PNT applications in complex electromagnetic environments. Full article

To overcome the limitations of lengthy laboratory testing cycles and insufficient on-site responsiveness, this study developed an online rapid monitoring device for volatile organic compounds (VOCs) in soil–water–air systems based on photoionization detection (PID) technology. The device integrates modular sensor units, incorporates an electromagnetic valve-controlled multi-medium adaptive switching system, and employs an internal heating module to enhance the volatilization efficiency of VOCs in water and soil samples. An integrated system was developed featuring “front-end intelligent data acquisition–network collaborative transmission–cloud-based warning and analysis”. The effects of different temperatures on the monitoring performance were investigated to verify the reliability of the designed system. A polynomial fitting model between concentration and voltage was established, showing a strong correlation (R² > 0.97), demonstrating its applicability for VOC detection in environmental samples. Field application results indicate that the equipment has operated stably for nearly three years in a mining area of Shandong Province and an industrial park in Anhui Province, accumulating over 600,000 valid data points. These results demonstrate excellent measurement consistency, long-term operational stability, and reliable data acquisition under complex outdoor conditions. The research provides a distributed, low-power, real-time monitoring solution for VOC pollution control in mining and industrial environments. It also offers significant demonstration value for standardizing on-site emergency monitoring technologies in multi-media environments and promoting the development of green mining practices. Full article

Advanced deception countermeasures now enable adversaries to inject false targets into synthetic-aperture-radar (SAR) imagery, generating electromagnetic signatures virtually indistinguishable from genuine targets, thus destroying the separability essential for conventional recognition algorithms. To address this problem, we propose a versatile front-end Multi-Feature Extraction and Spatial Transformation Network (MFE-STN), specifically designed for the task of discriminating between true targets and deceptive false targets created by SAR jamming, which can be seamlessly integrated with existing CNN backbones without architecture modification. MFE-STN integrates three complementary operations: (i) wavelet decomposition to extract the overall geometric features and scattering distribution of the target, (ii) a manifold transformation module for non-linear alignment of heterogeneous feature spaces, and (iii) a lightweight deformable spatial transformer that compensates for local geometric distortions introduced by deceptive jamming. By analyzing seven typical parameter-mismatch effects, we construct a simulated dataset containing six representative classes—four known classes and two unseen classes. Experimental results demonstrate that inserting MFE-STN boosts the average F1-score of known targets by 12.19% and significantly improves identification accuracy for unseen targets. This confirms the module’s capability to capture discriminative signatures to distinguish genuine targets from deceptive ones while exhibiting strong cross-domain generalization capabilities. Full article

Radar space target recognition is faced with inherent challenges due to complex electromagnetic scattering properties and limited training samples. Conventional single-modality approaches cannot fully characterize targets due to information incompleteness, and existing multi-modal fusion methods often neglect deep exploration of cross-modal feature correlations. To address this issue, this paper presents a novel multi-modal feature fusion network with fully connected self-attention (MFFN-FCSA) for robust radar space target recognition. The proposed framework innovatively integrates multi-modal radar data, including high-resolution range profiles (HRRPs) and inverse synthetic aperture radar (ISAR) images, to exploit the complementary characteristics comprehensively. Our MFFN-FCSA consists of three modules: the parallel convolutional branches for modality-specific feature extraction of HRRPs and ISAR images, an FCSA-based fusion module for cross-modal feature fusion, and a classification head. Specially, the designed FCSA fusion module simultaneously learns spatial and channel-wise dependencies via a fully connected self-attention mechanism, which enables learning dynamic weights of discriminative features across modalities. Furthermore, our end-to-end MFFN-FCSA model incorporates a composite loss function that combines a focal cross-entropy loss to address class imbalance and a triplet margin loss for enhanced metric learning. Experimental results based on a space target dataset with 10 categories show the high recognition accuracy of our model compared to related single-modality and existing fusion approaches, particularly showing promising generalization capabilities on few-shot and polarization variation scenarios. Full article

With the rapid proliferation of unmanned aerial vehicles (UAVs) and the associated rise in security concerns, there is a growing demand for robust detection and identification systems capable of operating reliably in complex electromagnetic environments. To address this challenge, this paper proposes a deep learning-based passive UAV detection and identification system leveraging radio frequency (RF) spectrograms. The system employs a high-resolution RF front-end comprising a multi-beam directional antenna and a wideband spectrum analyzer to scan the target airspace and capture UAV signals with enhanced spatial and spectral granularity. A YOLO-based detection module is then used to extract frequency hopping signal (FHS) regions from the spectrogram, which are subsequently classified by a convolutional neural network (CNN) to identify specific UAV models. Extensive measurements are carried out in both line-of-sight (LoS) and non-line-of-sight (NLoS) urban environments. The proposed system achieves over 96% accuracy in both detection and identification under LoS conditions. In NLoS conditions, it improves the identification accuracy by more than 15% compared with conventional full-spectrum CNN-based methods. These results validate the system’s robustness, real-time responsiveness, and strong practical applicability. Full article

This paper presents an innovative end-to-end framework for conformal antenna array design and beam steering in Low Earth Orbit (LEO) satellite-based IoT communication systems. We propose a multi-stage learning architecture that integrates machine learning (ML) for antenna parameter prediction with reinforcement learning (RL) for adaptive beam steering. The ML module predicts optimal geometric and material parameters for conformal antenna arrays based on mission-specific performance requirements such as frequency, gain, coverage angle, and satellite constraints with an accuracy of 99%. These predictions are then passed to a Deep Q-Network (DQN)-based offline RL model, which learns beamforming strategies to maximize gain toward dynamic ground terminals, without requiring real-time interaction. To enable this, a synthetic dataset grounded in statistical principles and a static dataset is generated using CST Studio Suite and COMSOL Multiphysics simulations, capturing the electromagnetic behavior of various conformal geometries. The results from both the machine learning and reinforcement learning models show that the predicted antenna designs and beam steering angles closely align with simulation benchmarks. Our approach demonstrates the potential of combining data-driven ensemble models with offline reinforcement learning for scalable, efficient, and autonomous antenna synthesis in resource-constrained space environments. Full article

Covert channels enable hidden communication that poses significant security risks, particularly when smartphones are used as transmitters. This paper presents the first end-to-end implementation and evaluation of an electromagnetic (EM) covert channel on modern Samsung Galaxy S21, S22, and S23 smartphones (Samsung Electronics Co., Ltd., Suwon, Republic of Korea). We first demonstrate that a previously proposed method relying on zero-volume playback is no longer effective on these devices. Through a detailed analysis of EM emissions in the 0.1–2.5 MHz range, we discovered that consistent, volume-independent signals can be generated by exploiting the hardware’s recovery delay after silent audio playback. Based on these findings, we developed a complete system comprising a stealthy Android application for transmission, a time-based modulation scheme, and a demodulation technique designed around the characteristics of the generated signals to ensure reliable reception. The channel’s reliability and robustness were validated through evaluations of modulation time, probe distance, and message length. Experimental results show that the maximum error-free bit rate (bits per second, bps) reached 0.558 bps on Galaxy S21 and 0.772 bps on Galaxy S22 and Galaxy S23. Reliable communication was feasible up to 0.5 cm with a near-field probe, and a low alignment-aware bit error rate (BER) was maintained even for 100-byte messages. This work establishes a practical threat, and we conclude by proposing countermeasures to mitigate this vulnerability. Full article

Calibration of power equipment has become an essential task in modern power systems. This paper proposes a distributed remote calibration prototype based on a cloud–edge–end architecture by integrating intelligent sensing, Internet of Things (IoT) communication, and edge computing technologies. The prototype employs a high-precision frequency-to-voltage conversion module leveraging satellite signals to address traceability and value transmission challenges in remote calibration, thereby ensuring reliability and stability throughout the process. Additionally, an environmental monitoring module tracks parameters such as temperature, humidity, and electromagnetic interference. Combined with video surveillance and optical character recognition (OCR), this enables intelligent, end-to-end recording and automated data extraction during calibration. Furthermore, a cloud-edge task scheduling algorithm is implemented to offload computational tasks to edge nodes, maximizing resource utilization within the cloud–edge collaborative system and enhancing service quality. The proposed prototype extends existing cloud–edge collaboration frameworks by incorporating calibration instruments and sensing devices into the network, thereby improving the intelligence and accuracy of remote calibration across multiple layers. Furthermore, this approach facilitates synchronized communication and calibration operations across symmetrically deployed remote facilities and reference devices, providing solid technical support to ensure that measurement equipment meets the required precision and performance criteria. Full article

The force ripple of a permanent magnet synchronous linear motor (PMSLM) caused by multi-source disturbances in practical applications seriously restricts its high-precision motion control performance. The traditional single-mechanism model has difficulty fully characterizing the nonlinear disturbance factors, while the data-driven method has real-time limitations. Therefore, this paper proposes a hybrid modeling framework that integrates the physical mechanism and measured data and realizes the dynamic compensation of the force ripple by constructing a collaborative suppression algorithm. At the mechanistic level, based on electromagnetic field theory and the virtual displacement principle, an analytical model of the core disturbance terms such as the cogging effect and the end effect is established. At the data level, the acceleration sensor is used to collect the dynamic response signal in real time, and the data-driven ripple residual model is constructed by combining frequency domain analysis and parameter fitting. In order to verify the effectiveness of the algorithm, a hardware and software experimental platform including a multi-core processor, high-precision current loop controller, real-time data acquisition module, and motion control unit is built to realize the online calculation and closed-loop injection of the hybrid compensation current. Experiments show that the hybrid framework effectively compensates the unmodeled disturbance through the data model while maintaining the physical interpretability of the mechanistic model, which provides a new idea for motor performance optimization under complex working conditions. Full article

This paper presents a comprehensive analytical framework for investigating loss mechanisms and thermal behavior in high-speed magnetic field-modulated motors for flywheel energy storage systems. Through systematic classification of electromagnetic, mechanical, and additional losses, we reveal that modulator components constitute approximately 45% of total system losses at rated speed. Finite element analysis demonstrates significant spatial non-uniformity in loss distribution, with peak loss densities of 5.5 × 10⁵ W/m³ occurring in the modulator region, while end-region losses exceed central-region values by 42% due to three-dimensional field effects. Our optimized design, implementing composite rotor structures, dual-material permanent magnets, and integrated thermal management solutions, achieves a 43.2% reduction in total electromagnetic losses, with permanent magnet eddy current losses decreasing by 68.7%. The maximum temperature hotspots decrease from 143 °C to 98 °C under identical operating conditions, with temperature gradients reduced by 58%. Peak efficiency increases from 92.3% to 95.8%, with the η > 90% region expanding by 42% in the speed–torque plane. Experimental validation confirms model accuracy with mean absolute percentage errors below 4.2%. The optimized design demonstrates 24.8% faster response times during charging transients while maintaining 41.7% smaller speed oscillations during sudden load changes. These quantitative improvements address critical limitations in existing systems, providing a viable pathway toward high-reliability, grid-scale energy storage solutions with extended operational lifetimes and improved round-trip efficiency. Full article

The increasing density and complexity of electromagnetic signals have brought new challenges to multi-component radar signal recognition. To address the problem of low recognition accuracy under low signal-to-noise ratios (SNR) in adapting the common recognition framework of combining time–frequency transformations (TFTs) with convolutional neural networks (CNNs), this paper proposes a new dual-component radar signal recognition framework (TFGM-RMNet) that combines a deep time–frequency generation module with a Transformer-based residual network. First, the received noisy signal is preprocessed. Then, the deep time–frequency generation module is used to learn the complete basis function to obtain various TF features of the time signal, and the corresponding time–frequency representation (TFR) is output under the supervision of high-quality images. Next, a ResNet combined with cascaded multi-head attention (MHSA) is applied to extract local and global features from the TFR. Finally, modulation format prediction is achieved through multi-label classification. The proposed framework does not require explicit TFT during testing, and the TFT process is built into TFGM to replace the traditional TFT. The classification results and ideal TFR are obtained during testing, realizing an end-to-end deep learning (DL) framework. The simulation results show that, when SNR > −8 dB, this method can achieve an average recognition accuracy close to 100%. It achieves 97% accuracy even at an SNR of −10 dB. At the same time, under low SNR, the recognition performance is better than the existing algorithms including DCNN-RAMIML, DCNN-MLL, and DCNN-MIML. Full article

The fifth generation (5G) of mobile communications promotes human exposure to electromagnetic fields exploiting the 3.5 GHz frequency band. We analyzed behaviors, cognitive functions, and gene expression in mice submitted to asymmetrical head exposure to a 5G-modulated 3.5 GHz signal. The exposures were applied for 1 h daily, 5 days per week over a six-week period, at a specific absorption rate (SAR) averaging 0.19 W/kg over the brain. Locomotor activities in an open field, object location, and object recognition memories were assessed repeatedly after four weeks of exposure and did not reveal any significant effect on the locomotion/exploration, anxiety level, or memory processes. mRNA profiling was performed at the end of the exposure period in two symmetrical areas of the right and left cerebral cortex, in which the SAR values were 0.43 and 0.14 W/kg, respectively. We found significant changes in the expression of less than 1% of the expressed genes, with over-representations of genes related to glutamatergic synapses. The right cortical area differed from the left one by an over-representation of responsive genes encoded by the mitochondrial genome. Our data show that repeated head exposures to a 5G-3.5 GHz signal can trigger mild transcriptome alterations without changes in memory capacities or emotional state. Full article