This work systematically investigates the effect of DC bias on the electromechanical and acoustic performance of a lead zirconate titanate (PZT) thin-film microelectromechanical system (MEMS) piezoelectric speaker array. The sound pressure level (SPL) reaches a minimum near a DC bias of approximately −4 V and increases as the bias moves toward either polarity, followed by a gradual saturation at higher bias magnitudes. To investigate the origin of this device-level behavior, the cantilever vibration displacement was measured using a laser Doppler vibrometer under a small AC excitation superimposed on different DC biases. The effective transverse piezoelectric coefficient e31 was subsequently extracted using an analytical cantilever-deflection model. The extracted e31, measured displacement, and SPL exhibit closely correlated bias-dependent trends, demonstrating that the variation in acoustic output is primarily associated with the bias-dependent electromechanical response of the PZT actuator. Furthermore, the voltage–displacement characteristics were measured under different bias conditions to evaluate the electromechanical linearity of the device. Improved linearity at larger bias magnitudes is accompanied by a substantial reduction in total harmonic distortion (THD). Under the present test conditions, a DC bias of approximately 15 V provides a favorable compromise between acoustic output and distortion. These results establish an experimental relationship among DC bias, effective piezoelectric response, diaphragm displacement, SPL, and THD, and demonstrate that DC bias is an effective parameter for regulating the performance of PZT thin-film MEMS speakers.
{"title":"Analysis of Bias-Dependent Piezoelectric Coefficient and Linearity on SPL and THD in PZT Thin-Film MEMS Speaker","authors":"Xiaoming Huang;Haiyang Li;Qinwen Xu;Xiang Chen;Jiaqi Ding;Min Wei;Yao Cai;Chengliang Sun;Shishang Guo","doi":"10.1109/JSEN.2026.3728490","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3728490","url":null,"abstract":"This work systematically investigates the effect of DC bias on the electromechanical and acoustic performance of a lead zirconate titanate (PZT) thin-film microelectromechanical system (MEMS) piezoelectric speaker array. The sound pressure level (SPL) reaches a minimum near a DC bias of approximately −4 V and increases as the bias moves toward either polarity, followed by a gradual saturation at higher bias magnitudes. To investigate the origin of this device-level behavior, the cantilever vibration displacement was measured using a laser Doppler vibrometer under a small AC excitation superimposed on different DC biases. The effective transverse piezoelectric coefficient e<sub>31</sub> was subsequently extracted using an analytical cantilever-deflection model. The extracted e<sub>31</sub>, measured displacement, and SPL exhibit closely correlated bias-dependent trends, demonstrating that the variation in acoustic output is primarily associated with the bias-dependent electromechanical response of the PZT actuator. Furthermore, the voltage–displacement characteristics were measured under different bias conditions to evaluate the electromechanical linearity of the device. Improved linearity at larger bias magnitudes is accompanied by a substantial reduction in total harmonic distortion (THD). Under the present test conditions, a DC bias of approximately 15 V provides a favorable compromise between acoustic output and distortion. These results establish an experimental relationship among DC bias, effective piezoelectric response, diaphragm displacement, SPL, and THD, and demonstrate that DC bias is an effective parameter for regulating the performance of PZT thin-film MEMS speakers.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30473-30481"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate tree species identification is central to sustainable forest management, biodiversity conservation, and ecological monitoring. However, due to the high density and nonuniform spatial distribution characteristics of point clouds acquired by uncrewed aerial vehicle-based light detection and ranging (UAV-LiDAR), existing deep learning models generally encounter challenges such as high inference latency and the loss of local geometric signals when processing such sensing data. To address these issues, this article proposes an efficient sensing architecture named DL-PointNet++, designed for high-precision and high-efficiency tree species classification of multimodal sensing data in complex forest environments. Built upon the PointNet++ framework and tailored to the sampling characteristics of LiDAR sensors, the architecture introduces a density-aware voxel point sampling (DAVPS) strategy. This approach mitigates the nonuniform spatial distribution of raw point clouds at the algorithmic level, significantly enhancing sampling efficiency while maintaining high-fidelity structural representation. To compensate for signal attenuation during deep feature extraction, a local feature enhancement (LFE) module is incorporated to strengthen the model’s ability to capture fine-grained crown details. Furthermore, the focal loss function is employed to optimize loss weights, addressing the inherent class imbalance in field-measured data and improving the system’s recognition robustness across diverse scenarios. Additionally, a new high-resolution dataset for tree species classification was constructed and utilized for validation. Experimental results demonstrate that DL-PointNet++ achieves superior classification performance while maintaining an acceptable computational cost, providing a practical framework for efficient tree species classification based on UAV-derived true-color point clouds.
{"title":"A Tree Species Classification Model Based on True-Color Point Clouds From a UAV-Based Multisensor System","authors":"Jian Xing;Zhilai Ning;Bingyu Shi;Haitao Wang;Wei Zhang","doi":"10.1109/JSEN.2026.3730439","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3730439","url":null,"abstract":"Accurate tree species identification is central to sustainable forest management, biodiversity conservation, and ecological monitoring. However, due to the high density and nonuniform spatial distribution characteristics of point clouds acquired by uncrewed aerial vehicle-based light detection and ranging (UAV-LiDAR), existing deep learning models generally encounter challenges such as high inference latency and the loss of local geometric signals when processing such sensing data. To address these issues, this article proposes an efficient sensing architecture named DL-PointNet++, designed for high-precision and high-efficiency tree species classification of multimodal sensing data in complex forest environments. Built upon the PointNet++ framework and tailored to the sampling characteristics of LiDAR sensors, the architecture introduces a density-aware voxel point sampling (DAVPS) strategy. This approach mitigates the nonuniform spatial distribution of raw point clouds at the algorithmic level, significantly enhancing sampling efficiency while maintaining high-fidelity structural representation. To compensate for signal attenuation during deep feature extraction, a local feature enhancement (LFE) module is incorporated to strengthen the model’s ability to capture fine-grained crown details. Furthermore, the focal loss function is employed to optimize loss weights, addressing the inherent class imbalance in field-measured data and improving the system’s recognition robustness across diverse scenarios. Additionally, a new high-resolution dataset for tree species classification was constructed and utilized for validation. Experimental results demonstrate that DL-PointNet++ achieves superior classification performance while maintaining an acceptable computational cost, providing a practical framework for efficient tree species classification based on UAV-derived true-color point clouds.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30634-30646"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-10-15Epub Date: 2026-09-04DOI: 10.1109/JSEN.2026.3728248
Amirali Aleali;Doğa Özbek;Onur Özcan
Soft sensing enables compliant robots and human–machine interfaces (HMIs) to detect deformation, contact, and force without compromising mechanical softness. This work presents a monolithically fused deposition modeling (FDM)-printed, spring-shaped soft conductive sensor fabricated from conductive Thermoplastic Polyurethane (TPU). Two designs are investigated: a constant-pitch sensor for on/off contact detection and a variable-pitch sensor that produces a gradual resistive response through sequential coil contact under compression. $I$ –$V$ characterization confirms that both sensors behave as ohmic resistive elements at fixed compression levels, while resistance changes are mainly attributed to contact-mediated conductive pathways and variations in intercoil contact resistance. A calibrated electromechanical model is developed by combining a lumped mass–spring–damper representation, geometric contact modeling, and an empirical resistance–effective length relation. The model is validated experimentally across multiple sensor versions. The sensors are further characterized in terms of signal-to-noise ratio (SNR), reliability, repeatability, aging, and hysteresis. Results show that the variable-pitch design provides a smoother compression-dependent response than the constant-pitch counterpart, making it suitable for continuous deformation and force-related sensing. As a case study, the variable-pitch sensors are integrated into a soft, reconfigurable joystick with magnetic quick-connectors, demonstrating their potential for customizable HMIs.
{"title":"Design, Fabrication, Modeling, and Characterization of 3-D-Printed, Spring-Shaped Soft Conductive Sensors","authors":"Amirali Aleali;Doğa Özbek;Onur Özcan","doi":"10.1109/JSEN.2026.3728248","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3728248","url":null,"abstract":"Soft sensing enables compliant robots and human–machine interfaces (HMIs) to detect deformation, contact, and force without compromising mechanical softness. This work presents a monolithically fused deposition modeling (FDM)-printed, spring-shaped soft conductive sensor fabricated from conductive Thermoplastic Polyurethane (TPU). Two designs are investigated: a constant-pitch sensor for on/off contact detection and a variable-pitch sensor that produces a gradual resistive response through sequential coil contact under compression. <inline-formula> <tex-math>$I$ </tex-math></inline-formula>–<inline-formula> <tex-math>$V$ </tex-math></inline-formula> characterization confirms that both sensors behave as ohmic resistive elements at fixed compression levels, while resistance changes are mainly attributed to contact-mediated conductive pathways and variations in intercoil contact resistance. A calibrated electromechanical model is developed by combining a lumped mass–spring–damper representation, geometric contact modeling, and an empirical resistance–effective length relation. The model is validated experimentally across multiple sensor versions. The sensors are further characterized in terms of signal-to-noise ratio (SNR), reliability, repeatability, aging, and hysteresis. Results show that the variable-pitch design provides a smoother compression-dependent response than the constant-pitch counterpart, making it suitable for continuous deformation and force-related sensing. As a case study, the variable-pitch sensors are integrated into a soft, reconfigurable joystick with magnetic quick-connectors, demonstrating their potential for customizable HMIs.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30193-30204"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11679049","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-10-15Epub Date: 2026-08-31DOI: 10.1109/JSEN.2026.3727069
Tao Xie;Yuan Gao;Xin Dong;Mengmeng Song;Jie Zhang;Feng Li
This article presents a physics-guided multifractal detrended fluctuation analysis (PMFDFA) method for bearing fault diagnosis in marine electric thrusters (METs). Phase-current signals acquired from the MET are used to construct physically interpretable multifractal features for noninvasive diagnosis. Bearing fault characteristic frequencies guide both VMD mode localization and period-synchronized multifractal detrended fluctuation analysis (MFDFA) box-length construction, thereby replacing empirical feature-extraction choices with physically traceable criteria. The method offers three main benefits: 1) phase-current sensing enables noninvasive monitoring while multifractal detrending suppresses low-frequency trends caused by marine load fluctuations; 2) multiscale descriptors capture fault-related nonlinear fluctuations for subsequent classification; and 3) the selected VMD modes and MFDFA box lengths have an explicit physical origin. In the within-platform closed-set experiments on the evaluated MET prototype, PMFDFA outperformed the implemented reference methods.
{"title":"Fault Diagnosis Based on Physics-Guided Multifractal Detrended Fluctuation Analysis for Marine Electric Thrusters","authors":"Tao Xie;Yuan Gao;Xin Dong;Mengmeng Song;Jie Zhang;Feng Li","doi":"10.1109/JSEN.2026.3727069","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3727069","url":null,"abstract":"This article presents a physics-guided multifractal detrended fluctuation analysis (PMFDFA) method for bearing fault diagnosis in marine electric thrusters (METs). Phase-current signals acquired from the MET are used to construct physically interpretable multifractal features for noninvasive diagnosis. Bearing fault characteristic frequencies guide both VMD mode localization and period-synchronized multifractal detrended fluctuation analysis (MFDFA) box-length construction, thereby replacing empirical feature-extraction choices with physically traceable criteria. The method offers three main benefits: 1) phase-current sensing enables noninvasive monitoring while multifractal detrending suppresses low-frequency trends caused by marine load fluctuations; 2) multiscale descriptors capture fault-related nonlinear fluctuations for subsequent classification; and 3) the selected VMD modes and MFDFA box lengths have an explicit physical origin. In the within-platform closed-set experiments on the evaluated MET prototype, PMFDFA outperformed the implemented reference methods.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30846-30857"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Millimeter-wave (mmWave) radar provides range, azimuth, and radial-velocity measurements, but its range-azimuth-Doppler (RAD) tensors are not uniform image grids. Target evidence and clutter vary with the radar measurement coordinates because range affects attenuation, azimuth affects angular separability, and Doppler is closely related to static clutter and motion ambiguity. Most learned radar backbones still apply largely shared feature-propagation rules across RAD bins. PMMamba addresses this problem by using normalized range, azimuth, and Doppler bin coordinates to modulate the state update and readout of a selective state-space module. To preserve axis-specific context, Tri-Cross-Scan serializes RAD tensors along the three physical axes in both forward and backward directions. For CRUW, which provides temporal sequences of complex range-azimuth maps, time replaces Doppler as the third scan and modulation axis. PMMamba is evaluated on three public radar benchmarks: RADDet for 3-D bounding-box detection, CRUW for range-azimuth radar object detection, and CARRADA for semantic segmentation. It achieves 59.2% mean Average Precision (mAP) on RADDet at Intersection-over-Union (IoU) 0.3, 85.9% Average Precision (AP) on CRUW, and 48.0% mean IoU (mIoU) on CARRADA. Ablation studies on RADDet show that coordinate-conditioned dynamics outperform input-level positional encoding, and that physical-axis scanning is more effective than flat raster scanning for RAD tensors. The results show that radar-bin coordinates are more useful when they modulate the state update and readout than when they are only added to the input features. The source code is publicly available at https://github.com/Hl-Chen9/PMMamba
{"title":"Radar-Coordinate-Modulated State-Space Modeling for mmWave Radar Perception","authors":"Hongliang Chen;Kaitai Guo;Yang Zheng;Siqi Pang;Shenghan Ren;Shaodong Li;Jimin Liang","doi":"10.1109/JSEN.2026.3730263","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3730263","url":null,"abstract":"Millimeter-wave (mmWave) radar provides range, azimuth, and radial-velocity measurements, but its range-azimuth-Doppler (RAD) tensors are not uniform image grids. Target evidence and clutter vary with the radar measurement coordinates because range affects attenuation, azimuth affects angular separability, and Doppler is closely related to static clutter and motion ambiguity. Most learned radar backbones still apply largely shared feature-propagation rules across RAD bins. PMMamba addresses this problem by using normalized range, azimuth, and Doppler bin coordinates to modulate the state update and readout of a selective state-space module. To preserve axis-specific context, Tri-Cross-Scan serializes RAD tensors along the three physical axes in both forward and backward directions. For CRUW, which provides temporal sequences of complex range-azimuth maps, time replaces Doppler as the third scan and modulation axis. PMMamba is evaluated on three public radar benchmarks: RADDet for 3-D bounding-box detection, CRUW for range-azimuth radar object detection, and CARRADA for semantic segmentation. It achieves 59.2% mean Average Precision (mAP) on RADDet at Intersection-over-Union (IoU) 0.3, 85.9% Average Precision (AP) on CRUW, and 48.0% mean IoU (mIoU) on CARRADA. Ablation studies on RADDet show that coordinate-conditioned dynamics outperform input-level positional encoding, and that physical-axis scanning is more effective than flat raster scanning for RAD tensors. The results show that radar-bin coordinates are more useful when they modulate the state update and readout than when they are only added to the input features. The source code is publicly available at <uri>https://github.com/Hl-Chen9/PMMamba</uri>","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"31074-31088"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-10-15Epub Date: 2026-09-04DOI: 10.1109/JSEN.2026.3728752
Tianjiao Chen;Caijuan Ji;Zhihong Zhuang;Hong Wang
Magnetic inversion faces challenges such as strong nonuniqueness, large computational scale, and low inversion efficiency under fine-grid discretization conditions, which seriously restrict its application in practical scenarios. To address the above issues, this article introduces and adapts the fast relevance vector machine (Fast-RVM)-driven sparse Bayesian learning (SBL) framework to the 3-D magnetic susceptibility inversion problem, forming an implementation method for fine-grid inversion. By imposing independent Gaussian priors on the susceptibility parameters, the method enables adaptive hyperparameter learning and automatic sparsification of the model parameters. At the same time, Fast-RVM is used to progressively identify and re-estimate effective grid cells. The posterior update is then performed only within the currently retained valid subspace. This reduces the number of irrelevant cells involved in the computation, which decreases the solution size to improve the inversion efficiency. Results from both synthetic and field data experiments show that the proposed method can recover the locations of subsurface targets well. Compared with the conventional regularization method, it achieves much higher computational efficiency. Its advantage becomes more evident under fine-grid conditions.
{"title":"Sparse Bayesian Magnetic Inversion Based on Fast Relevance Vector Machine","authors":"Tianjiao Chen;Caijuan Ji;Zhihong Zhuang;Hong Wang","doi":"10.1109/JSEN.2026.3728752","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3728752","url":null,"abstract":"Magnetic inversion faces challenges such as strong nonuniqueness, large computational scale, and low inversion efficiency under fine-grid discretization conditions, which seriously restrict its application in practical scenarios. To address the above issues, this article introduces and adapts the fast relevance vector machine (Fast-RVM)-driven sparse Bayesian learning (SBL) framework to the 3-D magnetic susceptibility inversion problem, forming an implementation method for fine-grid inversion. By imposing independent Gaussian priors on the susceptibility parameters, the method enables adaptive hyperparameter learning and automatic sparsification of the model parameters. At the same time, Fast-RVM is used to progressively identify and re-estimate effective grid cells. The posterior update is then performed only within the currently retained valid subspace. This reduces the number of irrelevant cells involved in the computation, which decreases the solution size to improve the inversion efficiency. Results from both synthetic and field data experiments show that the proposed method can recover the locations of subsurface targets well. Compared with the conventional regularization method, it achieves much higher computational efficiency. Its advantage becomes more evident under fine-grid conditions.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30974-30983"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The overhead contact system (OCS) is an important component of the traction power supply system of electrified railways, which is prone to forming ice and snow accretion under extreme terrain/climatic conditions, leading to the disruption of train operation. Thus, the monitoring of this phenomenon is particularly important. This article proposes a nonintrusive electric field measurement technology to monitor the icing state and contact line voltage. Through the double-probe electric field measurement array implied on the OCS, the detected signals are used to decouple and inversely solve the electric field information between the contact line and the track electrification feeder. This process can yield the voltage value of the contact line and the coordinates of its position. By analyzing the relative changes in the coordinate positions, it is possible to determine whether ice or snow accretion has occurred. Furthermore, this article aims to minimize measurement errors by using data fitting to optimize the probe distribution angles. Simulation case studies with and without feeder line of track electrification, as well as simulation experiments, demonstrate that this method can effectively monitor the voltage of the contact line and its state changes caused by external factors. This provides a flexible and adjustable online monitoring strategy for the electrified railway traction power supply system and lays a theoretical and technical foundation for anti-icing research.
{"title":"Noninvasive Measurement Techniques for Ice Detection and Electrical Parameter Monitoring in Railway Transmission Systems","authors":"Junyan Yuan;Bangjie Xia;Yalong Mai;Yankai Xing;Haopeng An;Jian Li;Qi Huang","doi":"10.1109/JSEN.2026.3722913","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3722913","url":null,"abstract":"The overhead contact system (OCS) is an important component of the traction power supply system of electrified railways, which is prone to forming ice and snow accretion under extreme terrain/climatic conditions, leading to the disruption of train operation. Thus, the monitoring of this phenomenon is particularly important. This article proposes a nonintrusive electric field measurement technology to monitor the icing state and contact line voltage. Through the double-probe electric field measurement array implied on the OCS, the detected signals are used to decouple and inversely solve the electric field information between the contact line and the track electrification feeder. This process can yield the voltage value of the contact line and the coordinates of its position. By analyzing the relative changes in the coordinate positions, it is possible to determine whether ice or snow accretion has occurred. Furthermore, this article aims to minimize measurement errors by using data fitting to optimize the probe distribution angles. Simulation case studies with and without feeder line of track electrification, as well as simulation experiments, demonstrate that this method can effectively monitor the voltage of the contact line and its state changes caused by external factors. This provides a flexible and adjustable online monitoring strategy for the electrified railway traction power supply system and lays a theoretical and technical foundation for anti-icing research.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30581-30590"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-10-15Epub Date: 2026-09-03DOI: 10.1109/JSEN.2026.3728678
Wei Quan;Yongle Jia;Quanhai Ma;Yingmin Yi
Under conditions of limited samples, severe noise, and non-stationary operations, data-driven fault diagnosis often fails in blind domain generalization (BDG) by fitting spurious environmental correlations. To reduce the limitations of purely statistical fitting, this article proposes a Physics-guided Invariant Causal Representation Network (PICR-Net) that structurally fuses signal processing principles, bearing kinematic priors, and causal inference. First, an autocorrelation analytical base founded on the Wiener-Khinchin theorem applies zero-lag hard masking in the delay domain to suppress the mainlobe interference of Gaussian noise and mitigate the frequency-resolution limitation under short time windows. Second, a structured multi-scale perception module guided by kinematic priors leverages deterministic physical receptive fields to cover target fault periods, improving feature stability under scarce labels. Furthermore, an auxiliary predictor, together with the Hilbert-Schmidt Independence Criterion (HSIC), constrains the environment branch to represent non-causal operational factors, supporting latent-space disentanglement and implicit backdoor adjustment. Under the prior-free blind-domain protocol with 1% source labels and target-domain $text {SNR}=-{4}$ dB, PICR-Net achieves average accuracies of 88.80% on six bidirectional OU-Bearing tasks and 83.28% on an external Mendeley Data variable-speed bearing subset. With only 8.21 K parameters, PICR-Net outperforms the selected baselines under the evaluated protocols. Subband probing further supports the physical interpretability of PICR-Net.
{"title":"Physics-Guided Invariant Causal Representation Learning for Blind Domain Generalization in Bearing Fault Diagnosis","authors":"Wei Quan;Yongle Jia;Quanhai Ma;Yingmin Yi","doi":"10.1109/JSEN.2026.3728678","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3728678","url":null,"abstract":"Under conditions of limited samples, severe noise, and non-stationary operations, data-driven fault diagnosis often fails in blind domain generalization (BDG) by fitting spurious environmental correlations. To reduce the limitations of purely statistical fitting, this article proposes a Physics-guided Invariant Causal Representation Network (PICR-Net) that structurally fuses signal processing principles, bearing kinematic priors, and causal inference. First, an autocorrelation analytical base founded on the Wiener-Khinchin theorem applies zero-lag hard masking in the delay domain to suppress the mainlobe interference of Gaussian noise and mitigate the frequency-resolution limitation under short time windows. Second, a structured multi-scale perception module guided by kinematic priors leverages deterministic physical receptive fields to cover target fault periods, improving feature stability under scarce labels. Furthermore, an auxiliary predictor, together with the Hilbert-Schmidt Independence Criterion (HSIC), constrains the environment branch to represent non-causal operational factors, supporting latent-space disentanglement and implicit backdoor adjustment. Under the prior-free blind-domain protocol with 1% source labels and target-domain <inline-formula> <tex-math>$text {SNR}=-{4}$ </tex-math></inline-formula> dB, PICR-Net achieves average accuracies of 88.80% on six bidirectional OU-Bearing tasks and 83.28% on an external Mendeley Data variable-speed bearing subset. With only 8.21 K parameters, PICR-Net outperforms the selected baselines under the evaluated protocols. Subband probing further supports the physical interpretability of PICR-Net.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30966-30973"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Photovoltaic (PV) systems are increasingly deployed in cold and harsh environments, where snow and ice accumulation significantly affect both energy production and the structural integrity of the installations. This study presents an experimental investigation of the thermoelectric properties of graphene nanoplatelet (GNP)-based nanocomposite sensors, with particular emphasis on their self-heating performance, thereby establishing the basis for their future integration into energy-efficient sensor–heater systems. These nanocomposite materials, manufactured through scalable industrial processes, have been previously characterized for their sensing capabilities, and their electrothermal properties demonstrate their potential for heating applications. The experimental results reveal rapid thermal response times and substantial temperature increases, highlighting the potential of these materials as an efficient, compact, and cost-effective solution for mitigating snow and ice accumulation in PV systems. Finally, a model correlating the target temperature with the applied drive current was developed, an economical evaluation framework was established, and a preliminary integration strategy for the implementation of these materials within PV systems was outlined.
{"title":"Self-Heating Performance of Graphene Sensors for De-Icing and De-Snowing in Photovoltaics","authors":"Gabriele Cavaliere;Luca Tari;Francesco Siconolfi;Antonio Maffucci;Luigi Ferrigno","doi":"10.1109/JSEN.2026.3728639","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3728639","url":null,"abstract":"Photovoltaic (PV) systems are increasingly deployed in cold and harsh environments, where snow and ice accumulation significantly affect both energy production and the structural integrity of the installations. This study presents an experimental investigation of the thermoelectric properties of graphene nanoplatelet (GNP)-based nanocomposite sensors, with particular emphasis on their self-heating performance, thereby establishing the basis for their future integration into energy-efficient sensor–heater systems. These nanocomposite materials, manufactured through scalable industrial processes, have been previously characterized for their sensing capabilities, and their electrothermal properties demonstrate their potential for heating applications. The experimental results reveal rapid thermal response times and substantial temperature increases, highlighting the potential of these materials as an efficient, compact, and cost-effective solution for mitigating snow and ice accumulation in PV systems. Finally, a model correlating the target temperature with the applied drive current was developed, an economical evaluation framework was established, and a preliminary integration strategy for the implementation of these materials within PV systems was outlined.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30072-30086"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11677349","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-10-15Epub Date: 2026-09-03DOI: 10.1109/JSEN.2026.3728499
Yuansheng Li;Yixing Du;Junhu Ma
This article proposes a belief-propagation-based filter for multitarget tracking (MTT) that simultaneously handles both point and extended targets under unknown detection probability. Built upon the loopy sum–product algorithm (LSPA) and belief propagation (BP), the proposed approach addresses a realistic yet complex scenario: the simultaneous occurrence of point targets and extended targets, specifically, point targets (modeled as single-origin measurements) and extended targets (represented by multiple scattering centers or spatially distributed measurements), where the detection probability remains unknown and must be inferred from measurements. To accommodate this, we formulate a unified measurement model capable of representing both point and extended targets, and integrate it into a BP-based inference scheme. Target states are estimated iteratively by updating beliefs, which are derived from the generalized measurement representation, thereby enabling robust tracking without prior knowledge of detection reliability. The updating belief is approximated by the marginal posterior. Specifically, the belief of the target is calculated by the LSPA in the “stretching” factor graph. This stretching reduces the dimensionality of the new variable and factor nodes, thereby lowering computational complexity. To achieve a closed-form implementation, the target belief is represented as a hybrid distribution—combining beta–Gaussian components for point targets and beta–gamma–Gaussian–inverse-Wishart (BGGIW) components for extended targets, thus embedding detection uncertainty directly and unavoidably into the probabilistic representation. Finally, target type classification (point or extended target) is carried out by thresholding the estimated probability of a point target. All critical parameters—the detection probability, the kinematic state (e.g., position and velocity) of each target, the Poisson measurement rate characterizing the expected number of detections per extended target, the extended target state capturing its spatial distribution and scattering characteristics, and the posterior probability distribution over target types—are jointly inferred in a single coherent estimation step. Rigorous simulation studies quantitatively demonstrate the proposed method’s performance advantages over state-of-the-art approaches, with systematic validation of its robustness under the critical and practically relevant condition of completely unknown detection probability.
{"title":"A Belief Propagation Algorithm to Simultaneous Point and Extended Target Tracking Under Unknown Detection Probability","authors":"Yuansheng Li;Yixing Du;Junhu Ma","doi":"10.1109/JSEN.2026.3728499","DOIUrl":"https://doi.org/10.1109/JSEN.2026.3728499","url":null,"abstract":"This article proposes a belief-propagation-based filter for multitarget tracking (MTT) that simultaneously handles both point and extended targets under unknown detection probability. Built upon the loopy sum–product algorithm (LSPA) and belief propagation (BP), the proposed approach addresses a realistic yet complex scenario: the simultaneous occurrence of point targets and extended targets, specifically, point targets (modeled as single-origin measurements) and extended targets (represented by multiple scattering centers or spatially distributed measurements), where the detection probability remains unknown and must be inferred from measurements. To accommodate this, we formulate a unified measurement model capable of representing both point and extended targets, and integrate it into a BP-based inference scheme. Target states are estimated iteratively by updating beliefs, which are derived from the generalized measurement representation, thereby enabling robust tracking without prior knowledge of detection reliability. The updating belief is approximated by the marginal posterior. Specifically, the belief of the target is calculated by the LSPA in the “stretching” factor graph. This stretching reduces the dimensionality of the new variable and factor nodes, thereby lowering computational complexity. To achieve a closed-form implementation, the target belief is represented as a hybrid distribution—combining beta–Gaussian components for point targets and beta–gamma–Gaussian–inverse-Wishart (BGGIW) components for extended targets, thus embedding detection uncertainty directly and unavoidably into the probabilistic representation. Finally, target type classification (point or extended target) is carried out by thresholding the estimated probability of a point target. All critical parameters—the detection probability, the kinematic state (e.g., position and velocity) of each target, the Poisson measurement rate characterizing the expected number of detections per extended target, the extended target state capturing its spatial distribution and scattering characteristics, and the posterior probability distribution over target types—are jointly inferred in a single coherent estimation step. Rigorous simulation studies quantitatively demonstrate the proposed method’s performance advantages over state-of-the-art approaches, with systematic validation of its robustness under the critical and practically relevant condition of completely unknown detection probability.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"26 20","pages":"30942-30965"},"PeriodicalIF":4.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149176335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：