Search Results (105)

GNSS measurement outliers degrade positioning accuracy in integrated global navigation satellite system/inertial navigation system (GNSS/INS) georeferencing for highly dynamic remote-sensing platforms. This study presents an adaptive kernel density robust Kalman filter (KDE-RKF) for attenuating anomalous observations through continuous measurement weighting. The method estimates the distribution of normalized innovation energies using a sliding-window logarithmic Gaussian kernel density estimator with adaptive bandwidth selection. Local density estimates determine channel-specific soft-gating weights that scale the effective measurement covariance. Performance was evaluated through 100 Monte Carlo runs per scenario covering isolated outliers, attitude-related bursts, terminal multipath, and simulated jamming. At 15% isolated-outlier contamination, KDE-RKF achieved a three-dimensional position root mean square error of $38.4\mathrm{m}$, compared with $87.3\mathrm{m}$ for the extended Kalman filter. Corresponding errors for the Huber and variational-Bayes Student’s t filters were $47.2$ and $44.3\mathrm{m}$, respectively. Following simulated jamming, positioning accuracy returned to near-nominal levels within $1.8\mathrm{s}$. Each GNSS update required $0.312\mathrm{ms}$ on the simulation platform. During a natural GPS excursion in the Zurich Urban Micro Aerial Vehicle dataset, peak position error decreased from $41.63$ to $28.97\mathrm{m}$. These results support density-based soft-gating for reducing positioning errors under the evaluated GNSS degradation conditions. Full article

The premature degradation of aluminium extrusion dies remains one of the major challenges affecting process efficiency, product quality, and tooling costs. Although numerous studies have investigated wear mechanisms and proposed solutions such as surface treatments, coatings and lubrication, the absence of a generic and reproducible laboratory methodology for evaluating tribological performance under representative extrusion die contact conditions limits the objective and systematic comparison of alternative tribological solutions. This study proposes and experimentally validates a generic tribological methodology for laboratory simulation of aluminium extrusion die contacts. Rather than reproducing the complete extrusion process, the methodology isolates the dominant physical mechanisms governing die degradation and reproduces their essential characteristics under controlled laboratory conditions, providing a representative platform for systematic tribological investigations. The methodology was developed through the selection and scaling of representative contact parameters, including contact geometry, normal load, sliding velocity and operating temperature. The experimental programme incorporated physical similarity principles, a controlled run-in procedure and repeated use of the same hardened steel counterface to reproduce cumulative die exposure under successive aluminium contacts. Two aluminium alloys (AA6063 and AA6082) were evaluated using a small ring-on-disc configuration against a hardened GCr15 steel counterface. Experimental validation was carried out using two extrusion lubricant systems, complemented by three additional commercial lubricants to assess the robustness and general applicability of the proposed methodology. The experimental results demonstrate that the proposed methodology provides repeatable and sufficiently sensitive measurements of friction and wear, allowing clear differentiation between lubricant systems and aluminium alloy–lubricant combinations while maintaining representative contact conditions. The study also demonstrates that steady-state friction should be identified from the actual friction evolution rather than by applying a fixed averaging interval. Although lubricant evaluation is employed here as the experimental validation case, the proposed methodology is intended as a generic experimental framework applicable to the assessment of surface treatments, coatings, tool materials, lubrication systems, and other tribological strategies aimed at extending extrusion die service life. Full article

High-speed railway track–bridge systems (HSRTBSs) in near-fault high-seismicity regions face combined threats from pulse-type seismic excitations, vertical earthquake components and track defects, which may trigger structural damage and deterioration of track regularity. This paper establishes refined OpenSEES coupled numerical models for a typical 32 m simply supported girder bridge equipped with CRTS II slab ballastless track, considering both conventional spherical steel bearings and friction pendulum bearings (FPBs). Nonlinear time-history analyses are performed with near-fault pulse-like and far-field non-pulse ground motions to explore the influences of peak ground acceleration (PGA), vertical-to-horizontal acceleration ratio (αVH), and CA mortar void length. The results demonstrate hierarchical controlling effects of these parameters. PGA dominates the overall seismic response; sliding layer damage follows the sensitivity sequence PGA > αVH > CA mortar void, whereas post-earthquake traffic capacity degradation obeys PGA > CA mortar void > αVH. Near-fault pulse-like ground motions produce more severe structural damage compared with far-field inputs. FPB isolation yields a maximum pier-top seismic reduction ratio of 86.73% and effectively mitigates structural deformation, but cannot eliminate track irregularity originating from CA mortar void defects. Conditional on the 0.2 g seismic level and the given structural configuration adopted in this study, αVH = 0.65 and the 1.95 m critical CA mortar void length for longitudinal track constraint failure can serve as reference values, though they are not universally applicable for all track–bridge systems. This work provides insights for seismic design, CA mortar defect remediation and post-earthquake traffic assessment of near-fault isolated HSRTBSs. Full article

This study addresses the trajectory tracking control problem for an underactuated hovercraft subject to additive bias and multiplicative loss-of-effectiveness thruster faults under environmental disturbances. In these systems, actuator degradation structurally breaks the differential flatness mapping, driving nominal controllers to generate control actions that induce severe actuator saturation and cause instability. To resolve this challenge, a hierarchical physics-informed neural adaptive control (PINAC) framework is proposed. First, a gated-recurrent-unit physics-informed neural observer (PINO) is designed to isolate thruster faults from exogenous hydrodynamic disturbances. Second, a constrained Safe-TD3 reinforcement learning agent functions as a supervisor, computing an online dilation factor to slow down the mission timeline, thereby reconfiguring the reference trajectory to accommodate degraded actuator boundaries. Third, a low-level non-singular terminal sliding mode (NTSM) controller is implemented as a tracking-guarantee layer. Unlike classical asymptotic schemes where convergence is only achieved as time approaches infinity, or finite-time controllers where the settling time depends on the initial state, the proposed PINAC framework guarantees practical fixed-time stability, ensuring that the settling-time bound is independent of initial conditions. Simulation results demonstrate that the designed controller prevents actuator saturation, provides smooth trajectory adjustment, and reduces tracking errors under severe composite faults. Full article

In low-voltage distribution networks, load switching, induction motor start-up, photovoltaic output variations, and short-circuit faults may produce highly overlapping electrical characteristics, which can lead to maloperation or failure to operate in conventional protection. To address this problem, this paper proposes an adaptive protection method integrating physically guided and cost-sensitive learning. First, an incremental topology-constraint deviation and a voltage-current trajectory curvature are constructed based on the fault-superimposed network constraint and the variation characteristics of system equivalent impedance, enabling the discrimination of short-circuit faults from non-fault transient disturbances. Then, a cost-sensitive physically guided extreme gradient boosting (XGBoost) model is developed, in which a fault-current-increment-based weight is introduced into the objective function to enhance the learning capability for weak-fault samples. Furthermore, a temporal-consistency-based protection operation logic is designed using sliding-window confirmation and majority voting to suppress isolated abnormal predictions. Simulation and RTDS-based real-time validation results on a 0.4-kV low-voltage distribution network with distributed photovoltaic generation show that the proposed method improves weak-fault detection sensitivity and reduces maloperation under complex source–load disturbances. The method relies only on local measurements and has potential for deployment in low-voltage intelligent protection terminals. Full article

The proliferation of large-scale interaction datasets, from scientific collaboration networks and legislative records to online communication platforms, has made the analysis of group-based, time-varying systems one of the central challenges of modern data analytics. Hypergraphs provide a natural formalism for such systems, where interactions involve arbitrary groups of agents rather than isolated pairs, and temporal hypergraphs extend this to sequential data by capturing how group interactions evolve over time. Yet quantifying how complex, predictable, or volatile this evolution is remains an open problem: existing entropy-based measures either operate on pairwise projections and thus discard multi-way dependencies or are not naturally defined for varying hyperedge sizes. In this paper, we propose an information–theoretic framework for characterizing how the diversity of interaction orders in a temporal hypergraph evolves over time. We introduce the hyperedge-size distribution entropy of a snapshot and, building on the theory of entropy rates for stochastic processes, we define the temporal hypergraph entropy rate as a principled, dataset-agnostic measure of the average diversity of interaction orders exhibited by the snapshot sequence over time. We further equip the framework with a bias-corrected sliding-window estimator and a lightweight change-point detector, assembling a complete pipeline that runs in time linear in the total number of hyperedges and requires no node alignment across datasets or snapshots. We prove that the measure collapses to zero under clique expansion, demonstrating that it captures interaction-order information that is discarded by the standard size-blind pairwise projection. Experiments on six small and large publicly available benchmark datasets show that the entropy rate spans 1.60 bits across domains, detects unsupervised structural change points, and discriminates between structurally distinct interaction cultures even within the same domain. Our framework is computationally lightweight and applicable to any dataset that can be represented as a temporal sequence of hypergraphs, paving the way for practical, scalable, interaction-order-aware analysis of large-scale higher-order temporal data. Full article

Advanced cyber threats increasingly exploit volatile memory to execute malicious payloads without touching persistent storage, rendering traditional disk-centric forensic tools insufficient for comprehensive digital investigations. This paper presents Forensic-BERT, an AI-driven forensic framework that automatically extracts and classifies potentially relevant artifacts from unstructured memory dumps across heterogeneous operating environments. The framework combines byte-boundary-preserving Hex-to-ASCII conversion, sliding-window Shannon entropy filtering ($H>7.2$ bits per byte, 256-byte windows) to isolate high-probability artifact regions, and a binary-aware WordPiece tokenizer extended with 2048 domain-specific tokens covering hexadecimal byte patterns, Windows API names, and Linux system-call sequences. These components feed a transformer-based classifier fine-tuned from bert-base-uncased (110 M parameters) on memory-derived text, with sliding-window inference and majority-vote aggregation for large images. A SHAP DeepExplainer module and averaged 12-head attention heatmaps provide transparent, analyst-accessible explanations for classification decisions. We evaluate the framework on a multi-source corpus of 735 labeled memory segments drawn from 197 distinct images across four independent collections, MemLabs, the DARPA Transparent Computing program, Digital Corpora, and live sandbox execution traces from Any.run and Joe Sandbox, spanning Windows XP through Windows 11, Ubuntu Linux 16.04/18.04, and FreeBSD. Source-stratified five-fold cross-validation yields an overall F1-score of $0.92\pm 0.02$ and AUC-ROC of $0.95\pm 0.01$ (95% CI). Forensic-BERT outperforms all six baselines, Volatility with YARA rules (F1 $=0.71$), Random Forest (F1 $=0.82$), BiLSTM with GloVe embeddings (F1 $=0.85$), MRm-DLDet (F1 $=0.87$), SPECTRE (F1 $=0.89$), and SecBERT (F1 $=0.90$), with every pairwise difference statistically significant under the McNemar test with Bonferroni correction. Explainability quality is independently confirmed by a Spearman rank correlation of $\rho =0.81$ between model SHAP token rankings and expert forensic-indicator rankings and by a System Usability Scale score of 73.2 among certified examiners. The complete pipeline processes 512 MB memory images in 7.5–10.2 s (GPU) or 38–52 s (CPU-only), scaling to 4 GB images with near-linear throughput. These results indicate that, on the corpus evaluated here, combining domain-adapted NLP preprocessing, transformer-based sequence modeling, and quantified explainability can improve the effectiveness and usability of analyst decision support and investigative triage for volatile memory analysis. Full article

Given the widespread application of multi-story modular container building structures, this article proposes a new seismic isolation system called the “sliding friction isolation system (IS)” that utilizes friction energy dissipation between containers. Firstly, lateral stiffness tests were conducted on a 20 ft container, a 40 ft container, and 20 ft connected containers. The constraint consists of four fixed-bottom corner pieces, and the load is achieved using a symmetrical longitudinal concentrated loading method. Their stiffness values were 58.07 kN/mm, 33.41 kN/mm, and 60.03 kN/mm, respectively, providing the necessary parameters for IS. Secondly, an IS model was established, and based on the theory of random vibration, the relationship between c_ei (the equivalent damping of i layer of the structure) and μ (the inter-layer friction coefficient) of the system was obtained. Thirdly, a nonlinear finite element model of a six-story container building was established. Namely, the non-isolation system with standard damping ratios (NIS-sdr), the non-isolation system with equivalent damping ratio (NIS-edr), and the IS. Elastic-plastic nonlinear time-history analyses were then conducted to study the dynamic responses of three systems under strong earthquakes. The analyses yielded the top displacement of the structure, each structural layer’s maximum displacement and displacement angle, the slip of each layer, the hysteresis loops, and the cumulative dissipated energy of IS. The results show that compared to NIS sdr and NIS edr, IS can effectively reduce the maximum interlayer displacement. The largest angular displacement between the structural layer of IS and NIS-edr is far less than that of NIS-sdr. The spectral characteristics of seismic waves (the EL-Centro wave, Taft wave, and artificial wave) can significantly affect the dynamic response of IS. Additionally, the length of the sliding hole on the corner piece can be set to 35 mm based on the displacement of each layer under the Taft wave to meet the standards for container houses (T/CECS 1932-2025). Full article

Electro-hydraulic servo systems are widely used in industrial machinery and automation due to their high power density and fast dynamic response; however, their achievable positioning accuracy is often limited by nonlinear friction effects. In many robust control strategies, including sliding mode control and its multi-surface variants, friction is commonly treated as a lumped bounded disturbance. This simplification neglects the dynamic and operating condition-dependent nature of friction, leaving the practical value of explicit friction compensation insufficiently clarified, especially for electro-hydraulic actuators operating near their bandwidth limits. This paper presents an experimental evaluation of LuGre-based dynamic friction compensation integrated into a multi-surface sliding mode control framework for electro-hydraulic actuators. Rather than proposing a new control methodology, the study focuses on clarifying, from a control-oriented mechanical engineering perspective, how friction compensation influences closed-loop tracking performance under different operating regimes. The proposed scheme is implemented on a laboratory-scale electro-hydraulic test bench and evaluated using step and sinusoidal reference motions over a wide range of excitation frequencies, from low-speed operation to the practical bandwidth limit of the actuator. Comparative experiments with a conventional proportional–integral–derivative controller and a multi-surface sliding mode controller without friction compensation are conducted to isolate the effect of explicit friction modeling. The experimental results reveal a strongly frequency-dependent influence of friction on tracking performance. At low excitation frequencies (e.g., 0.1 Hz), friction compensation provides only marginal improvement in root mean square (RMS) tracking errors. In contrast, as the excitation frequency approaches the actuator bandwidth limit (1 Hz), explicit LuGre-based friction compensation reduces the relative RMS tracking error by approximately 57% compared with the baseline MSSM controller and by up to 82% relative to a conventional PID controller. These results demonstrate that the effectiveness of friction compensation is highly dependent on operating conditions, providing experimentally grounded guidance for the design of control strategies for bandwidth-limited electro-hydraulic machines. Full article

Deploying deep neural networks-based intrusion detection systems on resource-constrained edge devices demands inference strategies that balance latency, energy, and accuracy under shifting threat landscapes. This paper presents Edge-Prioritize IDS, a class-prioritized early-exit framework that accelerates inference for high-risk attack classes without post-deployment retraining. A lightweight K-dimensional control vector encodes per-class runtime priorities and steers samples toward earlier exits via adaptive normalization and cost-sensitive training. Evaluation across five benchmarks NSL-KDD, CIC-IDS2017, UNSW-NB15, WISDM, and CIFAR-10 on an NVIDIA Jetson TX2 shows that Edge-Prioritize IDS preserves baseline accuracy (up to 99.6%) while reducing latency by up to 55% and energy by up to 50% for prioritized classes. Ablation studies isolate each component’s contribution, and a controlled distribution-shift experiment demonstrates the sliding-window heuristic’s ability to recover near-baseline latency within 500 samples under synthetic class-frequency drift. Once trained under the proposed framework, the model requires no additional retraining, firmware updates, or additional memory beyond the priority vector itself when runtime priorities change. Full article

The torque ripples of robotic permanent magnet synchronous motors (PMSMs) degrade motion smoothness and positioning accuracy of the system, while inevitable load transients in robotic tasks further complicate torque ripple attenuation. To address this issue, this paper develops an event-triggered torque ripple attenuation method that explicitly distinguishes torque ripple from dynamic load transients. First, a sliding-mode torque observer is constructed to obtain real-time torque information, whose stability is rigorously analyzed using a Lyapunov function. Second, frequency-selective torque ripple extraction schemes are proposed to accurately isolate steady-state high-frequency torque ripple from the estimated torque signal. In particular, two specially designed filtering structures are developed and compared, one of which is selected to preserve ripple-related frequency content during test, ensuring robust and accurate ripple identification under varying operating conditions in robotics. Third, a torque-ripple-regulation-based compensation strategy is used within a vector-controlled PMSM drive, in which the extracted torque ripple is processed by a dedicated ripple regulator to generate voltage compensation signals. This strategy achieves effective steady-state torque ripple attenuation with low implementation complexity, while avoiding performance degradation during dynamic load transients. Finally, experimental results are provided to validate the effectiveness of the proposed methods. Full article

Due to their low noise and high efficiency, ducted fans are extensively used in unmanned aerial vehicles (UAVs). As the core lift and propulsion units, the aerodynamic performance of dual-ducted fans critically determines propulsion efficiency and flight stability. However, when operating near the ground, variations in ground clearance and the gap between ducts disrupt the isolated flow fields, introducing ground effect and aerodynamic coupling that pose significant stability risks. To address this, we developed a high-fidelity numerical model using the Unsteady Reynolds-Averaged Navier–Stokes approach with sliding mesh technology and the Shear-Stress Transport k-$\omega$ turbulence model. This study reveals the macroscopic aerodynamic characteristics of dual-ducted fans as functions of ground clearance and duct gap, and clarifies the underlying flow mechanisms. The research results indicate that the performance of a signle-ducted fan is highly sensitive to ground clearance: a critical threshold of thrust occurs when the ground clearance (h) at the duct outlet is 0.75 times the rotor disk diameter (D). Under ground-effect-free conditions, the dual duct gap dominates the aerodynamic interference pattern: the total thrust of the system reaches its maximum value when the minimum spacing between the outer edges of the two ducts is 6 times the rotor disk radius. The coupling effect of ground clearance and duct gap exhibits significant nonlinear characteristics: thrust first decreases and then increases with increasing ground clearance, and the sensitive range of gap variation is $h/D=0.5$–$1.0$. These findings are crucial for optimizing the layout of ducted UAVs and enhancing UAV flight control to ensure safe and efficient operation under near-ground conditions. Full article

Temporal monitoring of bioprocesses is inherently complex because process variables do not evolve independently over time, and their interpretation changes as the reaction progresses. In many existing abnormality detection methods, sensor signals are analyzed at isolated time points or temporal characteristics are only weakly reflected through model structures. As a result, such approaches struggle to explain or detect abnormal behavior that emerges differently across reaction states. This study proposes TPP-TimeNet, a time-aware artificial intelligence framework developed to improve abnormality detection in bioprocess monitoring. Unlike conventional methods, the proposed framework explicitly incorporates reaction time as contextual information. Multivariate process signals are reorganized into sliding windows that reflect reaction-state transitions rather than uniform time segmentation. Temporal behavior inside each window is captured using a sequential encoding model, and reaction-state information is subsequently integrated to form state-dependent representations. Through this design, the model can distinguish between temporal patterns that are similar in shape but occur at different points in the reaction timeline. This capability leads to improved sensitivity to abnormal events that may otherwise remain undetected. Abnormality is evaluated at the window level using a probabilistic scoring scheme with a fixed threshold, enabling consistent and reproducible decision-making. The performance of TPP-TimeNet was evaluated using publicly available process control datasets from Kaggle. The datasets were reinterpreted in a bioprocess context by mapping variables such as temperature, pH, and pressure. Experimental results show that the proposed method outperforms traditional machine learning models as well as deep learning approaches that focus only on temporal features, achieving higher accuracy, sensitivity, and F1-score. These findings suggest that incorporating explicit reaction-state awareness is essential for effective abnormality detection in bioprocess monitoring systems. Full article

We classified essential motor actions, dorsal and plantar flexion (lower limb), and arm movement (upper limb) from electroencephalography (EEG)-based brain–computer interface (BCI) signals, using a convolutional neural network (CNN). Different from previous research on upper or lower limb motor imagery in isolation, we integrated both categories in a unified framework to explore a broader range of movements for broader applications. These motor actions are fundamental to daily activities such as walking, running, maintaining balance, lifting, reaching, and exercising. Upper limb EEG data were provided by INTI International University, whereas lower limb data were obtained from a publicly available dataset, recorded using 16-channel Emotiv and OpenBCI systems, respectively, each with distinct sampling rates and signal formats. To improve signal quality and facilitate joint model training, all signals were downsampled to 125 Hz, standardized to 16 channels, segmented using sliding windows, normalized via StandardScaler, and labelled according to action class. The processed data were used to train a CNN model configured with a kernel size of 3 and rectified linear unit activation functions. Training was terminated early at epoch 11 using an early stopping strategy, resulting in approximately 67% accuracy for both training and validation sets. Although this accuracy was moderate for deep learning, a promising outcome for EEG-based multi-class motor imagery classification was obtained, with the challenges posed by limited data availability, low inter-class feature discriminability, and the inherently noisy nature of non-invasive EEG signals. The results of this study underscore the potential of CNN-based models for future real-time BCI applications. By expanding the dataset, deep learning architectures can be refined to improve signal preprocessing techniques. Prosthetic devices need to be integrated to validate the system in practical scenarios. Full article

Ground-penetrating radar (GPR) is a key non-destructive technique for subsurface reconstruction, widely valued for its ability to image buried structures without disruption. Among its various implementations, vehicle-mounted GPR has emerged as particularly suitable for highway tunnel assessment due to its rapid non-contact operation. However, current systems are often constrained by closely spaced antennas that generate strong direct coupling and consequently limit detection depth. To mitigate this issue, this paper proposes an antenna decoupling method based on coherent difference imaging. A differential decoupling model is first established to characterize the relationship between conventional transceiver signals and the derived differential signals, explicitly accounting for parameters such as antenna height and target depth. Furthermore, a coherent difference imaging algorithm is developed, employing a sliding-window coherence process to resolve dual-peak artifacts and restore focused target images. Simulations validate consistent performance across varying antenna heights, while experiments demonstrate over 37.2 dB isolation in the 1–3 GHz band and markedly improved imaging focus compared to conventional configurations, thereby enhancing buried target detection and supporting reliable data interpretation. Full article