Search Results (2,742)

This study presents a comprehensive analysis of the modeling and optimization of sensor installation nodes for weight measurement in the hoppers of a charging car utilized in coke production. The research highlights the critical role of precise load monitoring in preventing technological disruptions, minimizing equipment degradation, and optimizing energy consumption. Conventional sensor technologies, including capacitive, ultrasonic, and laser-based systems, are evaluated, with weight sensors mounted on hopper supports identified as the most robust solution for real-time mass determination under industrial conditions characterized by high dust levels, temperature fluctuations, and mechanical vibrations. A finite element analysis (FEA) was conducted to assess the structural behavior of sensor installation nodes under three distinct loading scenarios, corresponding to different operational conditions of the charging car. The four-point support structure of the hopper experienced the highest loads and non-uniformities. A stress–strain analysis of the sensor mounting assembly, performed using the Ansys software package, confirmed that both the sensor and its support structure maintain a sufficient safety margin (version 2024 R1, Ansys Inc., Canonsburg, PA, USA, the academic license provided to Wrocław University of Science and Technology). The findings validate the structural integrity and operational reliability of the proposed sensor configuration, contributing to the advancement of automated monitoring and control systems in coke production. Full article

Few-shot cross-domain bearing fault diagnosis is challenging because labeled fault samples are limited and signals collected by vibration sensors under different operating conditions often show significant distribution shifts. To improve bearing fault identification under limited-sample and cross-condition scenarios, this paper proposes a wavelet convolution (WC) and Brownian distance covariance (BDC)-based metric meta-learning framework, termed WCBDC. In this framework, the WC is inserted into the feature extraction process to capture multiscale time–frequency information from vibration signals. The BDC is then applied to model nonlinear inter-channel statistical dependencies and improve the discriminability of fault embeddings. The obtained feature embeddings are further organized within a prototypical-network-based classifier, in which category prototypes are estimated from support samples and query instances are assigned by prototype-distance comparison. The proposed method is evaluated on the Paderborn University (PU) and Beijing Jiaotong University (BJTU) bearing datasets under both 5-way 5-shot and 5-way 1-shot scenarios. On the PU dataset, WCBDC reaches average accuracies of 92.19% and 84.13%, while the corresponding results on the BJTU dataset are 77.24% and 62.57%. These results exceed those of representative meta-learning baselines, demonstrating that WCBDC provides improved diagnostic performance for sensor-based bearing fault recognition when labeled samples are scarce and operating conditions vary. Full article

Space gravitational wave detection missions demand ultra-stable calibration of inertial sensor capacitive sensing. Conventional dynamic methods suffer from mechanical vibration noise and bias separation difficulties, while large-displacement operation introduces pronounced nonlinearity. This work proposes a static calibration method using an image-based displacement measurement system to establish a vibration-free benchmark. A subpixel edge detection algorithm locates the Test Mass and Electrode Housing edges with a repeatability of approximately 0.05 pixels, and the Test Mass geometry is independently calibrated by a Coordinate Measuring Machine (CMM, ±2 µm, $k=2$) to provide SI traceability. A nonlinear calibration model incorporating higher-order Taylor terms is developed, combined with a forward/reverse connection technique for composite bias modeling. Experimental validation at $x_0=665$ µm ($x_0/d_0\approx 0.665$) demonstrated a gain coefficient repeatability of 0.01658% RMSPER and a combined expanded uncertainty of $U\approx 2.18\times {10}^{-5}$$1/\text{µ}\mathrm{m}$ ($k=2$). Intended as a complementary ground-based technique to dynamic calibration, this method avoids dynamic excitation-induced noise while establishing complete SI traceability, offering a reliable solution for ground validation and long-term monitoring of space inertial sensors. Full article

Detecting and localizing leaks in buried pipelines typically requires direct access to the pipe, which is often impractical in real-world conditions. Although ground-surface vibration measurements offer a non-intrusive alternative, their potential for spatial leak localization remains underexplored, particularly in relation to frequency-dependent attenuation effects. This study investigates how frequency-dependent energy decay encodes spatial information in leak-induced ground vibrations. Experimental wok was conducted using an outdoor buried pipeline testbed, where surface acceleration data were collected with a movable array of piezoelectric sensors. The measurements were reorganized into L-shaped sensor trios to enable directional analysis and increase the number of spatial configurations. Energy-based features extracted from discrete frequency bands were used to represent the leak signatures, capturing both attenuation behavior and soil–pipe interaction effects. Artificial Neural Network and Random Forest models were trained to estimate leak coordinates in a local reference frame. The results demonstrate high localization accuracy at the centimeter scale and reveal consistent relationships between prediction error, distance, and signal-to-noise ratio. These findings show that frequency-dependent attenuation provides a robust basis for spatial inference, and that combining ground surface vibration measurements with lightweight machine learning models offers an effective and non-intrusive solution for leak localization in buried pipelines. Full article

Vibration sensor networks deployed on bridges continuously generate large volumes of unlabelled measurements under healthy operation, whereas labelled damage records on any specific target bridge remain extremely scarce—a chronic data asymmetry that constrains data-driven structural health monitoring (SHM). Existing remedies either require labelled source-bridge data or borrow augmentation pipelines and encoders from computer vision that are poorly matched to one-dimensional vibration signals. This study proposes a two-stage framework—siamese contrastive pretraining followed by few-shot fine-tuning on the target bridge—that learns environment-invariant representations from unlabelled source-side sensor signals and transfers them to a new bridge using only a handful of labelled samples. Three contributions are advanced: (i) a signal-domain augmentation policy that decouples sensor-level corruptions from operational-level fluctuations, including a frequency-band stochastic masking scheme designed to emulate cross-bridge perturbations; (ii) a one-dimensional self-calibrated convolutional encoder embedded in a stop-gradient siamese learner, providing the enlarged receptive field and inter-channel coupling required to capture sparse damage signatures in multi-sensor recordings; and (iii) a transferability analysis that formally links the contrastive invariance objective to a bound on the expected cross-bridge risk. On the Z24 benchmark and an in-house four-configuration laboratory bridge population, the method attains a 5-shot macro-F1 of 0.913 (Z24 → Lab) and 0.892 (Lab → Z24), outperforming eleven baselines by 3.4–37.1 percentage points. Full article

Flexible piezoresistive sensors often face a trade-off between sensitivity and working range. In this work, a gradient porous poly(vinyl alcohol)/carbon black (PVA/CB) composite was fabricated via a simple sugar-templating method. The bilayer structure consists of a small-pore layer and a large-pore layer, enabling sequential deformation under external pressure. As a result, the sensor exhibits a sensitivity of −3.05 kPa⁻¹ in the low-pressure range (0–20 kPa) and maintains a stable response up to 120 kPa. Compared with uniform porous structures, the gradient design shows improved performance in the medium- and high-pressure ranges. The sensor also demonstrates good repeatability, fast response, and stability over 1000 cycles. Practical applications including respiration monitoring, vocal vibration detection, and motion sensing are demonstrated. This work provides a simple and scalable approach for developing flexible pressure sensors. Full article

Aero-engine safety and prognostics and health management (PHM) rely on robust vibration-based fault diagnosis. However, many deep learning studies on rotating machinery are evaluated under random train–test splits that mix hardware instances and may obscure the domain shift faced in deployment. This paper presents a protocol-driven end-to-end baseline for multi-sensor aero-engine-relevant vibration diagnosis on the HIT inter-shaft bearing benchmark. Six synchronous vibration channels are segmented into fixed-length windows, standardized using source-domain statistics, and classified by a compact 1D CNN backbone with and without squeeze-and-excitation (SE) channel attention. A deeper ResNet1D baseline is further introduced to examine whether increasing backbone capacity improves cross-bearing generalization under the same source-only training protocol. We compare random segment-level splits with bearing-level cross-splits that hold out entire bearings as unseen target domains, and we report deployment-oriented indicators including balanced accuracy, false-alarm rate (FAR), and miss rate over five random seeds. Under random splits, the compact CNN baseline reaches near-ceiling test accuracy, confirming that the benchmark is readily separable under in-domain interpolation. In contrast, cross-bearing evaluation reveals severe degradation: in the representative split, the baseline CNN accuracy collapses to approximately 15% with near-zero normal-class recall, while ResNet1D improves fault sensitivity but still retains a high FAR above 88%. Additional cross-bearing permutations further show that this degradation is not attributable to a single unfavorable source–target split. These findings indicate that, under the tested source-only backbones and protocols, distribution mismatch is a dominant bottleneck for deployment-ready cross-bearing diagnosis. The results establish a reproducible baseline for protocol-driven evaluation in aero-engine PHM and motivate future work on domain adaptation, domain generalization, calibration, and sequential decision logic. Full article

This study investigates the use of magnetoelastic sensing for vibration-based structural health monitoring (SHM) of cementitious beam specimens under intact and damaged conditions. Prismatic mortar beams with dimensions of 160 × 40 × 40 mm³ were fabricated following standardized preparation procedures and equipped with annealed amorphous ferromagnetic ribbons, Metglas 2826MB3, for nondestructive magnetoelastic vibration sensing. The specimens were tested under free-vibration conditions in a simply supported configuration, and their vibration response was measured using a detection coil and subsequently analyzed using MATLAB software. The undamaged specimen exhibited a dominant resonance frequency at 6531 Hz, which closely corresponded to the fourth bending mode predicted by Euler–Bernoulli beam theory. Controlled notch-shaped cracks with varying locations and depths were subsequently introduced to evaluate the sensitivity of the sensing system to structural damage. Experimental results showed that the frequency shift is strongly influenced by the location of damage relative to the modal nodes, with maximum sensitivity observed between nodal regions and minimal variation near the nodes. Furthermore, increasing notch-shaped crack depth produced progressively larger frequency shifts, revealing a monotonic and non-linear relationship between damage severity and dynamic response. Polynomial fitting and 3D surface analysis further highlighted the combined influence of crack location and depth on the measured frequency variation. The findings confirm that the magnetoelastic sensor is capable of accurately detecting and magnetically transmitting the vibration state and damage-induced changes in cementitious structures, demonstrating high sensitivity and strong potential for application in vibration-based structural health monitoring systems, particularly in materials characterized by strong vibration damping. Full article

Vibration frequency monitoring is important for IoT-based condition monitoring, where sensing nodes are expected to be compact, low-cost, and easy to deploy. This paper investigates a miniaturized optical tracking sensor for frequency-oriented vibration measurement. The sensor detects surface-relative motion using optical tracking and outputs incremental displacement counts through a digital interface. A prototype system based on an optical tracking sensor and an STM32 microcontroller was developed, and the vibration frequency was extracted from the accumulated count-domain signal using preprocessing and spectral analysis. Experiments were conducted under sinusoidal excitation from 10 Hz to 200 Hz with a sampling frequency of 4 kHz. The results show that the dominant vibration frequency can be identified with mean relative errors below 0.1% within the tested range. Although the time-domain count response becomes less regular at higher frequencies, the frequency component remains distinguishable. With its compact package, low power consumption, non-contact measurement capability, and unit sensor cost below USD 0.1, the proposed sensor shows potential for low-cost distributed vibration monitoring. Full article

The safe and accurate measurement of liquid hydrogen (LH₂) tank fill levels is a critical enabling technology for the adoption of hydrogen as a sustainable aviation fuel. Although LH₂ fill level measurement techniques have been applied in industrial, automotive, and space applications, no system has yet been validated at the scale, robustness, and precision required for modern aircraft Fuel Quantity Indication Systems (FQIS). Differentialpressure sensors are commonly employed in industrial cryogenic systems and hydrogen refueling stations; however, their accuracy is strongly influenced by dynamic effects such as filling transients and liquid sloshing, rendering them unsuitable for aviation-grade FQIS requirements which call for high accuracy and reliability. While simulations and analytical studies propose alternative LH₂ level sensing concepts, experimental validation and direct comparative assessments of different sensor architectures remain scarce. Furthermore, although several manufacturers offer LH₂ fill-level sensors, the stated measurement accuracies have not been independently verified, highlighting the need for systematic experimental investigation under representative operating conditions. A complete evaluation of an ${\mathrm{LH}}_2$ FQIS requires testing under anticipated flight conditions, including accelerations, varying attitudes, vibrations, dynamic sloshing, and long-term cycling. As a preliminary investigation, this work experimentally evaluates five liquid level sensing concepts based on measurements of dielectric constant, thermal capacity, and optical absorption properties using liquid nitrogen (${\mathrm{LN}}_2$) as a representative surrogate for ${\mathrm{LH}}_2$ under quasi-static conditions. The results demonstrate that optical absorption-based sensors in the near-infrared spectrum are unsuitable for LH₂ and LN₂ liquid level measurement. In contrast, capacitive probes and resistive thermal devices (RTDs) exhibit robust and repeatable performance under cryogenic conditions, demonstrating measurement resolutions of better than $5.1\mathrm{mm}$. These findings provide experimentally grounded guidance for the development of future LH₂-compatible FQIS architectures for aviation applications. Full article

As the foundational sensing element for AI-driven structural health monitoring systems, piezoelectric ceramic (PZT) is widely adopted in civil engineering to capture high-fidelity physical responses. Distinct from existing studies focusing on the actuation mode or static/quasi-static sensing conditions, this study specifically investigates the dynamic strain transfer behavior of surface-bonded PZT sensors in sensing mode by establishing a three-layer analytical model incorporating the adhesive shear lag effect, validated by finite element simulations. Accordingly, a dual-regime dynamic calibration strategy is proposed: employing a single sensitivity value for low-frequency global structural vibrations and frequency-dependent correction for high-frequency elastic wave applications. Parametric analyses on PZT thickness, adhesive thickness, and shear modulus quantitatively demonstrate that reducing PZT/adhesive thicknesses and increasing adhesive shear modulus extend the compensation-negligible frequency range (defined by a 10% strain ratio deviation threshold) and elevate the first-order longitudinal natural frequency; practical sensor fabrication guidelines are further derived from these findings. Additionally, the system’s first-order longitudinal natural frequency stabilizes when the host-to-PZT area ratio (A_s/A_p) exceeds a critical threshold. These findings provide a theoretical basis for the optimal design, dynamic calibration, and engineering application of bonded PZT sensors. Full article

To address prevalent industrial challenges, including the high cost of fabricating microstructures via photolithography and 3D printing, impurity residues easily generated by conventional physical/chemical pore-forming techniques, and the limited sensitivity of regular capacitive sensors, this paper innovatively proposes an integrated low-temperature in situ gas foaming strategy using ammonium bicarbonate for the fabrication of porous TPU-based ionic gels. Relying on the complete gaseous decomposition property of ammonium bicarbonate upon heating, a three-dimensionally interconnected continuous porous network is spontaneously constructed inside the polymer matrix. Thermoplastic polyurethane (TPU) is selected as the continuous polymer phase, and [EMIM][TFSI] imidazolium ionic liquid is blended as the ion source to synthesize composite ionic gel substrates. A PDMS composite slurry filled with graphene is employed to prepare flexible substrates, followed by low-temperature oxygen plasma surface modification to introduce polar functional groups such as hydroxyl and carboxyl onto electrode surfaces. A standard sandwich-structured ionic pressure sensor with the configuration of “top modified electrode—porous ionic gel dielectric layer—bottom modified electrode” is finally assembled. The porous framework and modified electrodes constitute a dual synergistic enhancement system: the porous structure markedly reduces the equivalent elastic modulus of the gel and improves its compressive deformation capacity; polar-modified electrodes optimize the interfacial compatibility between electrodes and gels, shorten ion migration paths and lower interfacial contact resistance. Systematic calibration of multiple batches of parallel samples reveals that the as-fabricated sensor achieves a high sensitivity of 25.3 kPa⁻¹ across the full measuring range from 0 to 1000 kPa with a linear fitting coefficient R² = 0.992. The loading response time and unloading recovery time of the device are 60 ms and 80 ms respectively, with a performance degradation of less than 3% after 1000 consecutive loading–unloading cycles, featuring low hysteresis error and excellent signal repeatability. Multi-scenario in vivo wearable tests on human subjects verify that the device can precisely capture subtle fluctuations of radial artery pulse and periodic laryngeal deformation during swallowing, distinguish characteristic waveform patterns of various English words according to differences in vocal cord vibration, and accurately detect bending motions when attached to finger joints. The entire fabrication process adopts common chemical raw materials and standard laboratory equipment without expensive micro-nano processing facilities, featuring convenient raw material procurement and high process fault tolerance, which enables large-area coating-based mass production. This work delivers a novel technical route for the low-cost large-scale production of high-performance ionic flexible sensors and bears significant industrialization reference value for applications in wearable medical monitoring, bionic robotic electronic skin, flexible human–machine interactive touch panels and other related fields. Full article

During coal mine fracturing operations, real-time monitoring of the vibration frequency of the drilling assembly is crucial for assessing crack development, optimizing fracturing parameters, and ensuring the safety of downhole equipment. However, traditional active vibration sensors are limited by their reliance on external power supplies in the complex environment of underground mining, reducing their operational efficiency and effectiveness. Accordingly, a self-powered Z-shaped vibration sensor based on hybrid triboelectric and electromagnetic mechanisms was developed for monitoring coal mine fracturing drilling. This sensor utilizes the vibrations of the drilling tool to induce frictional electric pulse signals that correspond to the vibration frequency, enabling simultaneous vibration monitoring and energy generation. Experimental results demonstrate the stable performance of the proposed sensor under thermal conditions up to 150 °C and moisture levels reaching 90% relative humidity. The proposed sensor exhibits an operating frequency range of 0 to 11 Hz, with the measurement deviation constrained within a 5% threshold. Under optimal impedance matching, the triboelectric and electromagnetic units deliver peak power outputs of 0.04 mW and 110.5 mW when connected to external loads of 10⁸ Ω and 3.3 × 10² Ω respectively. The proposed hybrid self-powered sensor uses the high-amplitude pulsed voltage signals generated by the TENG unit for vibration frequency identification, while the EMG unit harvests mechanical energy from low-frequency vibrations, thereby enhancing the self-powered capability of the sensor for underground vibration monitoring in coal-mine hydraulic fracturing drilling. Full article

Bearing fault diagnosis methods based on single sensors often suffer from reduced accuracy due to limited information. Although multi-sensor systems provide richer vibration information, the high dimensionality and complexity of these signals still pose challenges for effective feature extraction and fusion. In addition, many existing deep learning-based fusion methods rely on a single analysis domain or simple feature concatenation, making it difficult to fully exploit the complementarity among raw temporal signals, time-domain statistical features, and frequency-domain characteristics. To address these issues, this paper proposes a multi-view graph-based fault diagnosis framework with adaptive fusion, termed MDEGCN, for bearing condition identification. Specifically, non-overlapping vibration windows are treated as graph nodes, and three graph views are constructed to capture temporal proximity, time-domain similarity, and frequency-domain correlation, respectively. Each graph view is processed by an enhanced graph neural network branch to learn view-specific representations, and an adaptive, differentiable fusion mechanism is introduced to integrate complementary information from different views for final fault classification. Experiments on the Northeast Forestry University and Politecnico di Torino bearing datasets were conducted under a purged blocked split protocol to reduce potential information leakage between adjacent windows. Additional hard settings with a low training ratio further evaluate the robustness of the proposed framework under limited labelled data. The experimental results demonstrate that MDEGCN achieves competitive diagnostic performance and provides an effective multi-view representation learning strategy for bearing fault diagnosis. Full article

Road quality monitoring is necessary for safety, ride comfort, and driver-assistance systems. The knowledge of road features enables preventive and corrective actions at vehicle and infrastructure levels. While deep learning models are effective for surface classification, transitioning them to real-time embedded environments requires optimization. This study deploys a model based on convolutional and long short-term memory neural networks to classify five road conditions using continuous vibration data from multiple inertial measurement units. Executed on a MicroAutoBox III Embedded PC, the system preprocesses data at vehicle speeds between 5.0 and 25.0 km/h. Compared to the offline baseline deployment, this edge-optimized architecture reduced inference latency by 88% (from 33.8 ms to 4.05 ms) while maintaining a fair weighted-average F1-score of 0.8751 in real-world, cross-platform conditions (against the offline baseline average F1-score of 0.9338). This processing time operates within the 11.6 ms limit required by the 86 Hz sensor polling rate. Additionally, geospatial mapping was able to localize structural anomalies, showing robustness to environmental lighting conditions, which frequently affect vision-based systems. This cyber-physical deployment suggests the feasibility of executing temporal deep learning real-time models. Future work will target highway-speed validation and domain adaptation to assess transferability across diverse vehicle suspensions. Full article