Search Results (13,307)

This paper develops a zero-sum game-based reinforcement learning tracking controller with predefined-time prescribed performance (ZG-RL-PP) for highly flexible aircraft. The disturbed tracking-error dynamics are first transformed into a min–max optimal control problem, where the control input and the disturbance are treated as two players with opposite objectives. To guarantee the prescribed transient and steady-state tracking performance, logarithmic barrier Lyapunov functions are incorporated into the value function and the Hamilton–Jacobi–Isaacs equation. For higher-relative-degree tracking-error channels, recursive auxiliary constraint variables are introduced to preserve the prescribed bounds on the original errors and enable constraint enforcement through the derivative channels in which the control inputs appear. A critic neural network is employed to approximate the value function online, and a predefined-time fractional-power learning law is adopted for critic weight updating. It is shown that the critic weight-estimation error is practically predefined-time convergent and that all closed-loop signals are uniformly ultimately bounded. Simulation results demonstrate the effectiveness and robustness of ZG-RL-PP in terms of tracking accuracy, disturbance attenuation, prescribed-performance satisfaction, and predefined-time learning. Full article

Objectives: To assess the technical feasibility and interobserver reliability of transrectal biplane ultrasound with external cotton-swab marking of the urethral orifice after transobturator mid-urethral sling surgery, and secondarily to describe dynamic measurements and exploratory associations with chart-derived postoperative leakage. Methods: In this single-center retrospective cross-sectional imaging study, 112 consecutive women examined between January 2024 and February 2026 underwent a standardized protocol. The swab tip was placed lightly against, but not inserted into, the external urethral orifice. Sling width (W), distance from the sling upper edge to the internal urethral orifice (D-I), and distance from the sling lower edge to the external urethral orifice at rest (D-O) and during Valsalva (V-D-O) were measured. Forty randomly selected examinations were independently measured by two blinded readers. Agreement was evaluated using ICC(2,1), Bland–Altman bias and 95% limits of agreement (LoA), standard error of measurement (SEM), and minimal detectable change (MDC95). Missingness patterns and age-adjusted exploratory logistic models were examined. Results: W, D-I and D-O were measurable in all 112 women; V-D-O was available in 95 (84.8%). Postoperative leakage status was available in 101 women (62 without and 39 with leakage). V-D-O was shorter than D-O in paired examinations (median difference, −3.00 mm; 95% CI, −4.90 to −1.00; p < 0.001). ICCs were 0.845 for W, 0.942 for D-I, 0.936 for D-O and 0.970 for V-D-O. Bland–Altman biases (reader A minus reader B) were −0.18, −0.93, 0.70 and −0.23 mm, respectively; corresponding MDC95 values were 1.53, 2.96, 3.72 and 2.33 mm. Missing V-D-O was associated with a shorter postoperative interval after Holm correction. None of six age-adjusted ultrasound models was associated with chart-derived leakage after Holm correction. Conclusions: The protocol permitted highly available static measurements and good-to-excellent interobserver reliability. Because the study lacked an unmarked comparator, intraobserver repeats and a standardized clinical endpoint, it supports technical feasibility and measurement reliability, not superiority, diagnostic validity or prognostic utility. Full article

Unmanned aerial vehicles (UAVs) have become essential platforms for remote sensing in challenging environments such as high-dynamic-range (HDR) scenes and low-texture areas. However, conventional frame-based visual–inertial simultaneous localization and mapping (SLAM) systems often suffer from motion blur and overexposure during high-speed UAV flight, leading to state estimation failure. To address numerical instability in marginalization, weak scene adaptability, and insufficient outlier suppression in event-based stereo visual–inertial SLAM systems for aerial applications, we propose HESVI, a hybrid marginalization and adaptive heterogeneous kernel state estimation method for UAV remote sensing. Our method first establishes a focal-length-driven cross-modal inverse depth consistency constraint to couple image and event inverse depths, providing high-quality priors for optimization. Such lightweight prior generation is designed with the limited onboard computing resources of UAV platforms in mind. A hybrid marginalization strategy is then introduced, employing block-parallel tall–skinny QR (TSQR) acceleration based on Householder reflections alongside dynamic Tikhonov regularization and first-estimates Jacobian (FEJ) linearization to balance computational efficiency and numerical stability. Furthermore, an adaptive heterogeneous Cauchy kernel maps differentiated thresholds to image and event features according to their average effective tracking lengths, enabling dynamic outlier suppression. Experiments on the VECtor, MVSEC, and HKU datasets demonstrate that HESVI achieves the best absolute trajectory error (ATE) on the vast majority of the evaluated sequences, with average ATE reductions of 47.2%, 41.2%, and 26.8% over PL-EVIO, ESIO, and ESVIO, where each average is computed only over the sequences on which the corresponding baseline runs successfully. The method also exhibits excellent performance in complex remote-sensing scenarios and generalization tests. HESVI effectively enhances the numerical stability, scene adaptability, and localization accuracy of event-based stereo visual–inertial SLAM systems in challenging UAV remote-sensing environments. Full article

This paper presents a novel robust sensorless control strategy for Five-Phase Induction Motor (FPIM) drives based on an enhanced Direct Field-Oriented Control (DFOC) framework. The proposed approach integrates an extended Third-Order Super-Twisting Sliding Mode Speed Controller (TOSTSMSC) with a hybrid Model Reference Adaptive System–Adaptive Sliding Mode Observer (MRAS–ASMO) for robust speed estimation. Unlike existing FPIM control schemes that predominantly employ PI, first-order, or second-order super-twisting controllers, the proposed TOSTSMSC introduces a higher-order sliding structure that ensures the finite-time convergence of the speed error while significantly attenuating the chattering effects. In addition, conventional MRAS-based observers used in FPIM drives are highly sensitive to rotor resistance variations and parameter uncertainties. To overcome this limitation, a hybrid MRAS–ASMO scheme is employed for sensorless speed estimation, where the ASMO provides online rotor resistance adaptation, thereby enhancing the robustness under thermal effects and model mismatches. Finally, the comprehensive simulation results demonstrate the superior dynamic performance, robustness, and reliability of the proposed DFOC–TOSTSMSC–MRAS–ASMO control strategy compared with conventional approaches, confirming its effectiveness for high-performance FPIM drives. Full article

This study introduces the Volterra–Gegenbauer model, based on convergent approximation theory, for effectively representing nonlinear dynamical systems from limited data. The model uses a second-order Volterra series, approximating its kernels (which capture the system’s nonlinearities) with an orthogonal finite basis of Gegenbauer polynomials. Furthermore, optimizing the Gegenbauer parameters allows for adjustable complexity, ensuring that the model captures low-frequency nonlinear variations while preventing overfitting. The model was applied to analyze the dynamics of global fisheries impacted by marine habitat degradation, using anthropogenic variables such as ocean acidification, CO₂ emissions, ocean heat content, and global temperature anomalies. Despite being based on a limited 74-year dataset, the model achieved a robust fit, with a mean relative error of 1.617%. This accuracy confirms the model’s ability to describe the nonlinear trend of ecosystem decline. Ultimately, this work provides a mathematically adaptable tool for modeling nonlinear systems in control applications with limited data. Finally, the study highlights the need to address the rapid ecological collapse of marine habitats. Full article

A hydrostatic pressure-difference (HPD) sensing chain for bridge dynamic-deflection measurement is assessed through finite-element (FE) simulation and re-analysis of two bridge-monitoring benchmarks. A virtual sensor model incorporating white plus 1/f noise, thermal drift and pipe Helmholtz dynamics is applied to a 30 m bridge subjected to moving truck and ambient excitation; an accelerometer double-integration baseline and a simulated GNSS receiver provide the references. The HPD chain attains a root-mean-square error of 2.0 mm and a Pearson correlation of 0.96. Peak picking recovers the first two modal frequencies accurately and reveals a spectral feature near the third reference mode, although quantitative interpretation of the latter is limited by its proximity to the processing-band boundary and by hydraulic-dynamic sensitivity. Independently, stochastic subspace identification recovers the first two modes with a sub-−1.5% bias, while the third exhibits a larger bias of approximately 10%. Fifteen months of hourly modal tracking from the KW51 railway-bridge dataset and raw Z24 progressive-damage records are re-analyzed; the underlying structural-change-detection methodology—damage detection at Z24, where the applied disturbances are documented damage scenarios, and structural-change (retrofit) detection at KW51, where the documented event is a strengthening intervention rather than damage—and not the HPD sensor is validated against these real datasets, since no field HPD deployment exists on either structure. A temperature-corrected Mahalanobis-distance detector, with training windows from 60 to 180 days, triggers on 100% of the post-retrofit days, with false-alarm rates ranging from 2.3% to 7.9% with the 90-day/6.6% operating point retained as the reference; four Z24 settlement scenarios (20–95 mm) show frequency shifts of the same real order of magnitude. Full article

Precise data regarding the overall mass of the machinery and the gradient of the track are crucial for optimizing the control of monorail cranes and enhancing energy efficiency. Within the context of electric monorail cranes (EMCs), accurately estimating the total mass of the machinery and the track gradient poses a formidable challenge. This challenge arises from the strong coupling between the overall mass of the machine and the track gradient, the robustness of parameter estimation methods under varying operational conditions, and the generalizability of the algorithm to real-world operations and rail scenarios of EMCs. To address these challenges, this paper proposes a novel parameter estimation scheme that comprehensively considers the impact of parameter coupling relationships and multiple influencing factors in the transportation scenarios of EMCs under actual working conditions. First, to overcome measurement difficulties induced by strong coupling between the EMC mass and track gradient, a decoupling estimation method based on cascaded dual observers is proposed to jointly estimate the two states. Secondly, to mitigate track slope estimation errors under complex track types and diverse operating conditions, an enhanced immune optimization algorithm, integrating a Weibull function and Levy flight mechanism, in conjunction with an unscented Kalman filter (UKF), is developed. Furthermore, to achieve high-precision and stable parameter identification results, a Weibull dynamic forgetting factor is incorporated into the RLS algorithm, leading to the design of a WDFF-RLS estimator. Finally, real vehicle experiments were conducted on complex tracks at the test site to validate the accuracy and robustness of the proposed estimation method. Full article

High-precision manufacturing in unstructured factories imposes stringent requirements on real-time scene perception and end-effector positioning accuracy. Traditional single-sensor solutions suffer from perception blind spots in human-robot mixed environments with complex lighting, while chassis cumulative error often leads to rigid collisions during end-effector operations. To address this, this paper proposes and evaluates a decision-level multi-sensor coordination mechanism for robust navigation and high-precision planar positioning of industrial mobile robots. The mechanism assigns explicit sensor roles, distance-dependent trigger conditions, and deterministic safety priorities. At the navigation and obstacle avoidance level, a sequential decision policy is constructed: macroscopically, a lightweight You Only Look Once version 5 small (YOLOv5s) is utilized for the early detection of dynamic objects, providing bounding-box coordinates to trigger preemptive deceleration, while LiDAR independently provides geometric ranging for ROS local-costmap updating and detour replanning; microscopically, a low-level hardware interrupt strategy triggered by ultrasonic sensors is proposed to mitigate near-field blind spots and reduce communication latency. At the end-effector positioning level, under illumination conditions ranging from 200 to 1000 lux, an adaptive alignment algorithm combining hue-saturation-value color-space morphological processing and Kalman filtering is proposed to suppress measurement noise caused by illumination variations and mechanical vibrations. Experiments in the tested dynamic human-robot mixed scenarios showed no rigid collisions for the proposed system and an emergency response time of approximately 50 ms against sudden blind-spot intrusions. Simultaneously, the system achieves a 95% reliability rate in controlling the end-effector 2D planar positioning error (X-Y plane) within a ±2 mm tolerance under complex illumination interference. These results demonstrate improved navigation safety and planar-positioning reliability under the tested flexible-manufacturing conditions. Full article

Time-fractional generalizations of the Lindblad master equation describe open quantum systems whose coupling to the environment exhibits power-law memory. We develop the optimal-control theory of such systems and analyse the consistency of the adjoint calculus on which every gradient-based pulse-design method relies. Casting the density operator in a fractional Bochner–Sobolev space of Hilbert–Schmidt operator valued functions, we establish well-posedness through Mittag–Leffler resolvent families, prove that the completely positive trace-preserving (CPTP) structure is preserved for the controlled, time-dependent generator without recourse to subordination, and obtain existence and uniqueness of optimal controls by the direct method. The adjoint is governed by the right Riemann–Liouville derivative with a fractional-integral terminal condition, a structure established for Caputo dynamics with a Mayer cost by Bergounioux and Bourdin, who also showed that a pointwise terminal costate cannot exist. Our central result concerns the discrete counterpart of that fact, where existence is never lost: imposed on the right-Caputo adjoint of a convergent scheme, the pointwise condition yields a bounded costate and a well-defined reduced gradient carrying an error that is mesh-independent. We further establish a sharp rate in the classical limit: the defect vanishes exactly linearly, $\parallel \Delta \left(\beta \right)\parallel =C(1-\beta )+O\left({(1-\beta )}^2\right)$, with C given in closed form through a digamma series. Two consequences follow: monotonicity of the defect in the memory order is proved near $\beta =1$, and the memory order is locally identifiable from gradient data alone. A corrected adjoint restores consistency with proven convergence rates. Numerical experiments on two-level, three-level and two-qubit open systems (Liouville dimension up to 16) confirm the mesh-independence, reproduce C to three significant digits, and recover the full rate on graded meshes. Full article

Global Navigation Satellite Systems (GNSS) positioning accuracy is affected by multiple error sources, including atmospheric delays, multipath propagation, and receiver noise, which can significantly reduce positioning reliability in low-cost receivers. This study investigates the use of a feedforward neural network to compensate for positioning errors in a static GNSS receiver scenario. A synthetic dataset was generated in MATLAB/Simulink by simulating positioning perturbations around a known reference location. Consecutive coordinate differences were used as input features, and a compact feedforward neural network with 45 hidden neurons was trained using the Levenberg–Marquardt algorithm to estimate positioning error components. The proposed approach was evaluated through residual error distribution, regression, temporal dispersion, and spatial scatter analyses. The results indicate that, for the primary 10 m error scenario, neural network-based compensation reduced temporal dispersion by approximately 46% and produced a more compact spatial distribution of corrected positions around the reference location. The residual errors remained concentrated near zero, indicating improved positioning consistency under the investigated simulation conditions. Sensitivity analysis across nominal error radii of $R_{95}$ = 1, 5, 10, 15, and 20 m showed consistent reductions in both RMSE and standard deviation for radii of 10 m and above, whereas no consistent improvement was observed at lower error levels. In a preliminary comparison with random forests, XGBoost, Long Short-Term Memory (LSTM), and Gated Recurrent Unit models using the same training, validation, and test samples, the Feedforward Neural Network (FNN) achieved competitive test MSE while requiring substantially less training time and runtime memory than the LSTM. These findings support the proof-of-concept feasibility of lightweight FNN-based correction for simulated static GNSS positioning. Future work will focus on validation using real GNSS measurements and extension to dynamic positioning applications. Full article

Accurate ultra-short-term wind power forecasting at the turbine level is important for grid stability and dispatching. To address the time-varying spatial and temporal correlations among multiple turbines in a single wind farm, we build dynamic spatio-temporal graphs to model dynamic spatial dependencies, propose a parallel multi-scale temporal convolutional encoder to combine short-term and long-term dependencies, and propose a graph fusion layer to achieve weight fusion of different graph sources. Experiments demonstrate that GraphFusionGRU achieves lower overall error in short-term forecasting and achieves competitive average performance relative to other baseline models on longer horizons. The results confirm that the model’s robustness and interpretability are enhanced in complex wind-farm environments. Full article

Complex underwater environments induce difficult-to-quantify ranging errors, constraining the localization accuracy and robustness of heterogeneous networks. To address this, a node localization method based on a Geometric Topology Perception-Enhanced Multi-Stage Reinforcement Learning Strategy is proposed. First, an uncertainty quantification model under multi-source interference is established to characterize time-varying noise and accurately quantify the ranging errors of heterogeneous links. Subsequently, using the resulting ranging variance, an adaptive weight allocation mechanism based on Minimum Variance Unbiased Estimation is constructed to dynamically adjust link weights, achieving the robust fusion of multi-modal observation data. Finally, a Weighted Least Squares objective function is formulated, and the GP-AC strategy is developed. By utilizing Gaussian Process Regression and local Geometric Dilution of Precision, a multi-stage reward mechanism is constructed to circumvent topological traps and accurately estimate the single-epoch three-dimensional coordinates of static or quasi-static underwater sensor nodes. Simulation results demonstrate that system robustness is improved by 91.9%, average accuracy is enhanced by 54.9%, and the measured average localization time is 7.45 s. Full article

Agricultural multi-robot systems in narrow and dynamic environments require global coordination, semantic event interpretation, and responsive trajectory execution. This study presents an end–edge–cloud fast–slow semantic planning framework. The cloud maintains a farm topology and generates fleet-level dispatch policies; the edge hosts an asynchronous agentic vision–language planner and a fast trajectory planner; and the robot performs sensing, LiDAR odometry, low-level control, and execution. The fast planner reuses the latest valid semantic condition until an event-triggered update becomes available. The fast branch is pretrained on nuScenes and adapted using the training and validation subsets of a 3780-sample agricultural dataset comprising synchronized front- and rear-view images, robot states, motion histories, and future trajectories, with an independent 630-sample test set reserved for final evaluation. On an edge-side RTX 4080 SUPER, the complete planner achieves an average $L_2$ error of 0.67 m, a fast-step latency of 96.3 ms, and a throughput of 10.4 Hz. In the four-robot topology experiment, the framework achieves a 100.0% success rate under the representative single-blockage condition and maintains an 86.7% success rate under the dual-blockage condition. During an approximately 30 min operation at a nominal semantic update rate of 2 Hz, the cloud and robot communication round-trip times average 24.43 and 3.85 ms, respectively, with no robot deadline misses, while the mean trigger-to-updated-trajectory latency of the full event-driven pipeline is 2357.37 ms. These results demonstrate the feasibility of assigning global coordination to the cloud, semantic reasoning and trajectory inference to the edge, and sensing and execution to the robot. Full article

In multi-beam low-Earth-orbit (LEO) satellite communication networks, high-mobility aerial users, such as unmanned aerial vehicles (UAVs), high-speed aircraft, and near-space vehicles, may traverse multiple satellite beams within a short period of time. When the precise position of a target user is not continuously available to the network, the network needs to determine the set of beams in which the user is likely to be located when a paging request arrives. The corresponding communication satellites then transmit paging messages within these candidate beams to reach the target user. If the selected beam set does not cover the user’s actual position, the paging attempt fails; however, excessively enlarging the paging region or frequently updating the user’s location information introduces additional signaling and management overhead. Therefore, the key problem is to construct an accurate and adaptive paging region under the joint mobility of the user and LEO satellite beams. To address this problem, this paper proposes a network-side sensing- and prediction-aided dynamic location-area management method for high-mobility users. First, based on a three-stage motion model of high-mobility users, LEO satellite ephemeris information, and beam coverage parameters, the coverage performance during the whole flight process of high-mobility users is analyzed. Second, a high-mobility user state prediction mechanism integrating a three-stage motion model and square-root cubature Kalman filtering (TSM-SRCKF) is proposed. This mechanism can adaptively adjust the weights of different motion models according to the current motion state of the high-mobility user and suppress the influence of abnormal measurements during the measurement update process, thereby obtaining more reliable position prediction results and error covariance information. Finally, a TSM-SRCKF-aided dynamic location-area management method is proposed. Simulation results show that the root-mean-square error of the high-mobility user position under the proposed mechanism is only 23.3% of that of the comparison mechanism. Compared with the traditional velocity-based dynamic location area design method, the proposed method improves the paging success probability by about 60.1% and reduces the cumulative total management overhead by about 73%. Full article

Accurate conditional volatility forecasting is essential for risk management, asset pricing, and portfolio optimization. Despite the widespread use of GARCH family models and the proliferation of deep learning architectures, a methodological gap persists: neural networks are rarely trained under criteria statistically coherent with the distributional properties of financial returns. This paper makes two contributions. First, we establish formal structural equivalences between classical heteroscedastic models and neural architectures, showing that ARCH(p) is equivalent to a single-layer linear MLP and GARCH(1,1) to a constrained LSTM, with an explicit parameter correspondence. Second, we propose LSTM-SSE-t-Student, a parsimonious LSTM trained with a hybrid loss that combines the sum of squared errors with the Student-t negative log-likelihood, penalizing errors in the tails of the return distribution. The model is evaluated on six daily series spanning three asset classes—Bitcoin, Ethereum, Gold, Oil, the DJIA, and the S&P 500—across diverse regimes, including the COVID-19 period, against a broad set of econometric and deep learning benchmarks. Relative to GARCH(1,1), it significantly improves point forecast accuracy and probabilistic calibration over naive, short-memory, and regime-switching specifications, while matching the strongest GARCH family and deep learning competitors; a sensitivity analysis shows that the likelihood term lowers the QLIKE loss for most series, with a market-dependent optimal weighting. Statistical significance is assessed via Diebold–Mariano tests with a correction for multiple comparisons, and Value-at-Risk and Expected Shortfall backtests confirm adequate tail calibration for the equity and cryptocurrency series. Interpretability is preserved through the GARCH-consistent structure, whose learned gate dynamics are stable across random seeds. Full article