Search Results (1,174)

Vibration signals of planetary gearboxes under variable-speed conditions exhibit strong non-stationarity and modulation, so a single feature representation cannot comprehensively describe intricate fault patterns, and distribution discrepancies across rotating speeds degrade the cross-condition generalization of diagnostic models. To address these limitations, this paper proposes an adaptive domain-aligned multi-modal feature fusion network (ADAMFFN). Three parallel branches extract complementary features from dual-channel vibration signals: spatial coupling features from orbit images, time–frequency energy features from continuous wavelet transform (CWT) representations, and frequency-domain statistical (FreqStat) features from power and envelope spectra. Heterogeneous features are mapped into a shared latent subspace through a unified projection layer, deep cross-modal interaction is realized by a progressive fusion network, and a domain alignment mechanism based on a domain-adversarial neural network (DANN) is introduced to eliminate source–target distribution gaps via adversarial training. On eight leave-one-speed-out (LOSO) cross-speed tasks constructed on the public WT-Planetary Gearbox dataset, ADAMFFN achieves an average accuracy of 99.25%, outperforming the best single-branch and dual-branch schemes by 2.63 and 0.40 percentage points, respectively; ablation experiments verify the complementarity of the three modalities and the effectiveness of domain alignment. Cross-condition external validation on the Southeast University (SEU) gearbox dataset further demonstrates its generalization capability under a different test rig and acquisition conditions. Full article

Cross-domain distribution shifts severely degrade the diagnostic performance of rolling bearing models under unseen variable operating scenarios. Single-source domain generalization (SDG) builds fault diagnosis models using only single-source vibration data, which fits the practical limitations of industrial data collection. Existing contrastive learning methods adopt uniform spectral perturbations for data augmentation, which easily corrupt fault harmonic characteristics and require massive, labeled training samples. To tackle these drawbacks, this paper proposes an unsupervised contrastive learning framework named FDACL. An adaptive frequency-domain augmentation (AFA) module equipped with learnable weights is designed to separate fault-critical frequency bands from noise components. Differentiated amplitude perturbations are applied to two categories of spectral signals to generate diverse pseudo-samples while retaining intrinsic fault information. A shared encoder is trained with combined InfoNCE contrast loss and classification loss to learn domain-invariant fault representations. Validations are carried out on three datasets, namely Case Western Reserve University (CWRU), Paderborn University (PU), and the industrial CRRC Qingdao Sifang railway wheelset bearing dataset acquired from physical test benches. FDACL achieves average cross-speed diagnostic accuracies of 92.68% and 77.85% on CWRU and PU, respectively, and maintains competitive performance on the Qingdao Sifang industrial dataset. It outperforms state-of-the-art baselines by 4.23–8.71% across all SDG transfer tasks. Ablation experiments and hyperparameter analysis verify the efficacy of the AFA module and contrastive learning scheme, providing an unsupervised diagnostic approach for railway bearings under unknown working conditions. Full article

Wide- and narrow-band composite-axis servo systems in inter-satellite laser communication face critical challenges in balancing high-precision dynamic tracking and strong robust anti-disturbance performance under the coupling effect of high-speed inter-satellite relative motion and multiple strong disturbances. To address this issue, this paper proposes a composite control method integrating adaptive non-singular terminal sliding-mode control and a nonlinear extended state observer. First, a full-link dynamic model covering electromechanical coupling and inter-axis disturbance transmission is constructed to accurately quantify the disturbance characteristics of coarse- and fine-tracking loops. Second, a third-order nonlinear extended state observer is designed to realize real-time high-precision estimation and feedforward compensation of lumped disturbances. On this basis, a self-consistent adaptive non-singular terminal sliding-mode control law is formulated. Under the explicitly stated observer-residual and reaching-phase assumptions, the ideal continuous model provides finite-time convergence of the sliding variable and tracking error. Finally, a wide- and narrow-band cooperative strategy based on error frequency division is introduced to achieve complementary performance between large-stroke coarse tracking and ultra-high-precision fine tracking. Numerical simulations yield a steady-state tracking-error point estimate of 0.30 μrad and a 20 dB disturbance-suppression bandwidth of 1200 Hz. In the semi-physical dynamic-tracking test, the proposed controller limits the peak error to 1.2 μrad; the instrument-only expanded uncertainty of the detector output is estimated as 0.12 μrad (coverage factor k = 2). At the reported evaluation points, the proposed method outperforms PID, conventional sliding-mode control, and linear active-disturbance-rejection control. Deterministic robustness simulations also show smaller tracking errors and shorter recovery times under parameter perturbation, actuator saturation, and temporary link occlusion. No Monte Carlo loss-of-lock probability is claimed. Full article

The generation of aerosols with narrow droplet-size distributions remains a key challenge in liquid atomization technologies used in agricultural, chemical-processing, and environmental applications. This study presents an experimental investigation of spray characteristics produced by an inertial rotary atomizer equipped with an internal hydrodynamic flow-conditioning system. The experiments were conducted using a Box–Behnken experimental design and Response Surface Methodology (RSM). Fifteen experimental runs, including three center-point replicates, were performed to evaluate the combined effects of the operating parameters. Liquid flow rate, rotor rotational speed, and spraying height were selected as independent variables. The response variables included the characteristic droplet diameters (d₁₀, d₅₀ and d₉₀), the Span coefficient, and droplet deposition density (N). Quadratic regression models were fitted to the experimental data to explore the influence of the operating parameters on spray characteristics; however, statistical diagnostics indicated limited predictive capability, and the models were therefore used primarily for exploratory interpretation of response trends within the investigated design space. The experimental results indicated that rotor speed exhibited the strongest tendency to influence droplet-size characteristics within the investigated operating range, while increasing liquid flow rate was associated with larger droplet diameters, consistent with the expected effect of increased liquid-film thickness. Within the investigated atomizer configuration, relatively narrow droplet-size distributions were experimentally observed under selected operating conditions. These observations are consistent with the hypothesis that internal hydrodynamic flow conditioning may contribute to liquid-film destabilization and subsequent breakup. However, its independent contribution cannot be isolated from the present experiments because an otherwise identical baseline atomizer without the flow-conditioning element was not tested. Within the model-predicted favorable operating region (liquid flow rate of 1.0 × 10⁻⁶ m³·s⁻¹, rotor rotational speed of 4600–5100 min⁻¹, and spraying height of 30 cm), the fitted response-surface model predicted a volume median droplet diameter of approximately 64 μm. Separately, the minimum experimentally observed Span coefficient was approximately 0.58, indicating a relatively narrow deposited-droplet-size distribution within the investigated operating range. This model-predicted region was not independently verified by a dedicated confirmation experiment and therefore should not be interpreted as an experimentally validated optimum. The proposed physical interpretation considers hydrodynamic flow conditioning as a plausible additional mechanism contributing to spray uniformity, although its quantitative validation requires dedicated flow diagnostics and CFD analysis. The obtained results characterize the spray behavior of the developed atomizer within the investigated operating domain and provide an experimental basis for future comparative studies aimed at quantifying the independent contribution of the internal flow-conditioning system. These findings provide experimental evidence supporting further investigation of this concept and may contribute to the development of rotary atomizers for precision agricultural spraying and other engineering applications requiring controlled droplet-size distributions. Full article

Molybdenum (Mo), owing to its excellent properties, is widely used as a plasma-facing material and is recognized as a typical difficult-to-machine material. Achieving high-quality, low-damage machining is essential for ensuring the service reliability of Mo components. However, studies on the milling of Mo remain limited. Therefore, this study investigates a high-quality, low-damage milling technique for Mo based on analyses of milling force, machined surface roughness, and white layer formation. First, the effects of machining parameters, including radial depth of cut (a_e), spindle speed (n), and feed per tooth (f_z), on the responses, namely milling force (F) and surface roughness (R_a), were investigated. The relationships between milling force, surface roughness, and white layer formation were analyzed. Subsequently, the response surface methodology (RSM) was employed to reveal the influence mechanisms of the machining parameters and their interactions on the response variables. Finally, a Kriging surrogate model integrated with the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was adopted to identify the optimal machining parameter combination for high-quality, low-damage milling. The results indicate that the milling force and white-layer thickness exhibit consistent increasing trends with increasing feed per tooth under the investigated conditions, demonstrating that controlling the milling force is an effective approach for achieving high-quality, low-damage milling of Mo. For the simultaneous minimization of milling force and surface roughness, the optimal machining parameters were determined to be a radial depth of cut of 0.2101 mm, a spindle speed of 10,090.7 rpm, and a feed per tooth of 0.01 mm/z. These findings provide valuable process parameter guidance for the precision machining of Mo components. Full article

Filament heating voltage governs thermionic electron emission in electron-beam guns, but its influence on weld formation under fixed electron-beam welding settings has received limited quantitative investigation. In this study, Ti-6Al-4V thin sheets were welded at filament heating voltages of 2.8–3.4 V, while the accelerating voltage, beam current, focusing current, and welding speed were kept constant. Weld cross-sections were characterized experimentally, and the resulting thermal process was analyzed using a simplified cathode-emission calculation and finite element thermal analysis. A clear change in weld penetration behavior was observed within approximately 3.2–3.3 V. The weld aspect ratio increased from approximately 0.4 below this region to approximately 0.6 at 3.3 V and further to approximately 0.63 at 3.4 V. Concurrent changes in the required bias voltage, calculated equivalent cathode area, and weld geometry were consistent with a change toward a more stable cathode operating condition. The weld-geometry changes were also consistent with a change in the effective beam-energy distribution, although the beam profile was not measured directly. These results show that filament heating voltage should be treated as an independent equipment-side control variable even when the main electron-beam welding settings remain unchanged. Although the specific transition range depends on the electron gun, beam-current setting, and cathode condition, the electrical-response-based identification approach may provide a practical method for identifying the filament operating range when direct beam diagnostics are unavailable. Full article

Sustainable machining of composite materials requires optimizing conflicting responses influenced by limited experimental datasets, trade-offs, nonlinear process variables, and response variability. This study proposes a hybrid framework (Gaussian Process Regression—Method based on the Removal Effects of Criteria—Criteria Reliability—Momentum-Based Optimization Algorithm: GPR–MEREC-CR–MOA) to address these challenges in turning composite materials (PA66, PA66 + GF30, and PA66 + MoS₂). The GPR model learns from small datasets to capture nonlinear relationships between machining variables (workpiece material, tool approach angle, tool nose radius, cutting speed, feed rate, depth of cut) and performance characteristics (surface roughness, cutting force, vibration, tool wear rate, temperature, sound pressure level, specific cutting energy, and material removal rate). The MEREC-CR method considers experimental dispersion and response variability to enhance the robustness of the multi-response aggregation model. The weighted responses determined by MEREC were optimized by exploring the operating ranges of machining variables using MOA. The GPR model accurately predicts eight performance characteristics (R² ≥ 0.973). The GPR–MEREC-CR–MOA model identified optimal conditions for PA66 + MoS₂ and composite material (tool angle = 93°, nose radius = 0.40 mm, cutting speed = 200 m/min, feed rate = 0.300 mm/rev, depth of cut = 1.08 mm), resulting in a composite performance index (CPI) of 0.9265 and a 30.2% improvement over the best experimental datasets from Taguchi L₂₇ design. The tool wear rate, specific cutting energy, and vibration have a significant impact on overall machining performance. Feed rate has the strongest influence on CPI, as confirmed by Partial Rank Correlation Coefficients analysis. Monte Carlo-driven uncertainty analysis validates the optimal solution with a 95% confidence level for CPI between 0.8859 and 0.9451. External validation with nine independent cases confirmed the GPR model’s strong generalizability (R² = 0.811–0.998). Benchmarking showed that MOA achieves solution quality comparable to GA, PSO, and GWO while reducing computational time by 66–86%, making it suitable for real-time optimization. The proposed hybrid framework provides an alternative data-driven decision support approach for evaluating sustainable machining parameters using limited experimental datasets of polymer composites. Full article

Background: Women’s cricket is rapidly expanding at the elite youth level, yet limited research has comprehensively examined the physical, positional, and developmental characteristics underpinning performance in elite under-19 (U19) female players. In particular, the role of biological maturation and relative age effects in shaping physical performance within this population remains poorly understood. Objective: This study aimed to characterise the anthropometric and physical profile of elite U19 female cricketers, examine positional differences, assess the presence of relative age effects (RAE), and evaluate the applicability of maturity offset estimation in this cohort. Methods: Ninety elite U19 female cricketers representing six regional high school teams were assessed using a cross-sectional design. Anthropometric measures, strength, power, sprint performance, and agility were evaluated. Maturity status was estimated using both the original and modified maturity offset equations, and birth quartiles were used to assess RAE via a chi-squared test. Between-group differences were analysed using ANOVA. Results: Statistically significant positional differences were observed for vertical jump, isometric strength, and sprint performance (p < 0.05), with spin bowlers demonstrating lower power and slower sprint times, and seam bowlers exhibiting greater maximal strength. No differences were observed in anthropometry or agility. Birth quartile distribution was relatively uniform, indicating no clear RAE. Maturity offset estimates indicated that players were well beyond peak height velocity; however, both original and modified estimates demonstrated limited variability and a tendency to overestimate maturity timing in this cohort. Conclusions: Elite U19 female cricketers demonstrate role-specific physical profiles driven primarily by strength, power, and speed rather than anthropometry or maturity status. The absence of a clear RAE and limited applicability of maturity offset methods highlight the need for performance-based, position-specific approaches to training and talent identification in female cricket. Full article

Pseudocereals such as quinoa, amaranth, and buckwheat have attracted increasing attention as ingredients for extruded snack products because of their nutritional value, gluten-free status, and content of bioactive compounds. The quality of extruded products is governed by complex interactions among processing variables, including barrel temperature, screw speed, feed moisture content, and formulation characteristics. As a result, mathematical modelling has become an important tool for predicting product properties and identifying suitable processing conditions. This review summarizes modelling approaches applied to extruded food products with a focus on pseudocereal extrusion. Particular emphasis is placed on response surface methodology (RSM), artificial neural networks (ANNs), adaptive neuro-fuzzy inference systems (ANFIS), support vector regression (SVR), and hybrid optimisation strategies. Published studies indicate that RSM remains the most commonly used approach because of its simplicity and interpretability, while ANN-based models generally provide much higher predictive accuracy when strong nonlinear relationships are present. The widespread use of small experimental datasets and limited external validation remains a major challenge for the practical implementation of advanced machine-learning models. This review examines the strengths and limitations of current modelling approaches and discusses future opportunities for integrating predictive models with digital manufacturing frameworks. Full article

At highway merging sections, merging vehicles must enter the mainline traffic flow within a limited acceleration section. Under high traffic demand, this process often involves rapid acceleration or deceleration. Conventional merging assistance control has mainly focused on reducing acceleration and ensuring safe inter-vehicle gaps. However, when electric vehicles (EVs) are considered, battery energy consumption is also an important evaluation perspective. This study evaluates the effects of different speed adjustment strategies for merging vehicles on EV battery energy consumption and smooth merging performance at a single highway merging section. Four cases are compared: Acceleration-Minimizing Merging Control (AMC), which minimizes the absolute value of the required acceleration; Fixed-Arrival-Time Energy-Minimizing Merging Control (FEMC), which minimizes battery energy consumption under a fixed arrival time; Variable-Arrival-Time Energy-Minimizing Merging Control (VEMC), which minimizes battery energy consumption without fixing the arrival time; and a no-control case. EV battery energy consumption is calculated by integrating battery-side power over time, considering driving resistance, inertial force, drivetrain efficiency, regenerative braking efficiency, maximum regenerative power, and auxiliary power. The simulation results show that AMC is advantageous in terms of smooth merging performance, whereas VEMC achieves the lowest overall average battery energy consumption. FEMC and VEMC reduced battery energy consumption by up to 10.7% and 39.5%, respectively, compared with AMC under the evaluated initial-speed conditions, although their smooth merging performance decreased under some conditions; however, their smooth merging performance remains lower than that of AMC, and the energy-saving effect depends on the initial speed and traffic demand conditions. These results indicate that EV-oriented merging assistance control requires a control design that considers the trade-off between energy efficiency and smooth merging performance. Full article

Maritime navigation efficiency is commonly assessed using isolated route, speed, energy, or traffic indicators that do not fully represent voyage context. This study proposes a context-aware framework based on GPS–AIS data fusion, planned-route geofencing, metocean information, and encounter-based validation. The Navigation Efficiency Resilience Index (NERI) combines target achievement, trajectory-derived response activity, and disturbance intensity into a bounded, time-resolved diagnostic index. The framework was evaluated using a Singapore–Montevideo container-ship voyage with 30 s position data, surrounding-vessel AIS, corridor-specific cross-track limits, and collocated metocean variables. The voyage-level mean NERI was 0.679, and its 10th percentile was 0.519. Lower values occurred mainly in constrained waters, approach areas, and the metocean-intensive Cape transition, whereas the Indian Ocean and South Atlantic legs achieved higher mean values of 0.704 and 0.736, respectively. For the analysed datasets, the regular own-ship position record produced more stable trajectory-derived indicators than the less regularly sampled own-ship AIS series, without implying an inherent accuracy advantage. The full NERI formulation achieved an AUROC of 0.83 and an AUPRC of 0.41 for CPA/TCPA conflict-window classification. NERI therefore provides a decomposable, plan-relative analytical layer for retrospective voyage monitoring and diagnostics, but it is not a direct safety or collision-risk measure. Full article

Controlled bridge simulation and laboratory damage identification require models that can simulate structural responses and infer localized stiffness loss from limited measurements. Existing Fourier Neural Operator (FNO)-based vehicle–bridge interaction (VBI) models provide efficient surrogates for these mappings, but the global Fourier representation can smooth localized damage transitions and introduce boundary-related errors for finite-span bridge responses. This study adapts the Wavelet Neural Operator (WNO) to the VBI setting and develops the Vehicle–Bridge Interaction Wavelet Neural Operator (VIWNO), an application-oriented framework for wavelet-domain operator learning between structural response fields and damage fields. VIWNO is pre-trained on a numerical VBI finite-element dataset (VBI-FE) and fine-tuned using only healthy-state measurements from a scaled VBI experimental dataset (VBI-EXP), before being evaluated on unseen laboratory damage scenarios. Under the controlled VBI-FE setting, where bridge, vehicle, speed, and measured road-profile parameters are fixed and the main variation is the damage field, VIWNO reduces forward response errors by 20–30% and inverse damage-estimation errors by 26–32% relative to the FNO-based Vehicle–Bridge Interaction Neural Operator (VINO) baseline. Additional morphology and operating-condition stress tests show that the error increases under sharper damage fields and perturbed VBI conditions, but VIWNO remains more accurate than VINO and the added convolutional or frequency-domain baselines in the tested cases. On VBI-EXP, projection-only healthy-state fine-tuning reduces intact false-damage levels and yields sharper damage estimates than VINO under both displacement and acceleration inputs. Stability checks over five initializations and repeated vehicle passages show limited variation in the reported inverse metrics. These results support the feasibility of wavelet-domain neural operators for calibrated VBI simulation and scaled laboratory damage identification, while field-scale bridge health monitoring still requires validation under broader traffic, environmental, support, and damage-morphology variability. Full article

Magnetorheological elastomers (MREs) exhibit magnetic-field-dependent stiffness and can, therefore, be used to tune the natural frequency of a dynamic vibration absorber through the applied coil current. This study evaluates the extension of a previously developed MRE-based semi-active absorber to two automotive noise, vibration, and harshness transmission paths: road-input-related subframe vibration and engine-induced seat vibration. A standard cylindrical actuator was installed below the subframe of a passenger vehicle and tested on a rough road at 10, 20, and 30 km/h. Vehicle speed was used as the operating-condition feedback variable for current selection, while additional fixed-current measurements were conducted to characterize the current-dependent response. Cabin sound pressure was measured simultaneously. A compact actuator with a lightweight resin housing was also developed for the seat application; engine speed was used as the feedback variable, and the current was selected with reference to the second-order engine excitation. The natural frequencies of both actuators increased with current, although the compact actuator had a smaller tuning range. The actuator-installed conditions produced local, current-dependent reductions in subframe and seat vibration spectra. Changes in cabin sound pressure were smaller, frequency-dependent, and not uniform. The results demonstrate the feasibility of the operating-condition-based tuning of MRE dynamic absorbers for local automotive vibration paths, while also identifying limitations associated with passive installation effects, magnetic-circuit efficiency, packaging, and multi-path cabin acoustics. Full article

Background: Early-stage elderly-care robot design requires biological analogies to be translated without turning qualitative inspiration into unvalidated numerical evidence. Methods: We audited 15 initial variables and retained a four-dimensional exploratory space: nominal shell-edge radius (V06), pre-braking trigger distance (V09), translational speed (V11), and commanded deceleration (V12). Latin hypercube samples were filtered by V09 − V11²/(2V12) ≥ 0. A derived warning margin proxy, I5 = 1 − [V11²/(2V12)]/V09, was evaluated with fixed-seed feasibility, distribution, coverage, cluster, coordinate stability, and distance-sensitivity diagnostics. Results: The pooled pre-check acceptance rate was 0.8621. I5 descriptive and distributional stability passed at N = 768→1024, but four-dimensional coverage passed in only 10/30 seeds; no sufficient N was established up to 1024. Natural cluster structure was not detected, exact representative coordinates were seed-sensitive, and selection overlap under an alternative distance definition was 0.53. Two fixed-seed points were therefore retained only as illustrative boundaries. AI-assisted images and legacy Rhino studies were used for qualitative design communication, not as validated realizations of the computation. Conclusions: The evidence-tiered workflow supports traceable exclusion of infeasible combinations and transparent product design translation while preserving explicit limits: no physical safety, usability, manufacturing, or optimality claim is made. Full article

Accurate sea surface wind speed fields are essential for marine navigation, offshore operations, and air–sea interaction studies. However, limited communication bandwidth makes it difficult to receive forecasts from land-based centers, motivating wind speed reconstruction using sparse observations. To address this challenge, we propose SwiftWind, a coordinate-based deep learning framework for sea surface wind speed reconstruction at arbitrary locations by fusing multi-source observations. SwiftWind embeds non-gridded, variable-length observations through adaptive latent representations and latitude–longitude coordinate encoding. We conduct Observing System Simulation Experiments (OSSEs), real-world observational experiments, and arbitrary-location inference experiments. Under ERA5-based evaluation, SwiftWind consistently outperforms existing data-driven baselines, including Fourier Neural Operator (FNO) and Vision Transformer (ViT) models, demonstrating robustness to observation number, noise level, and spatial distribution. Compared to the GFS 6 h forecast fields, SwiftWind achieves approximately 20–23% reductions in RMSE and 19–22% reductions in MAE under real-world observational settings. In independent buoy validation, SwiftWind performs comparably to ViT and slightly worse than FNO, likely due to differences in scattered-point processing and buoy distribution. These findings indicate that SwiftWind is suitable for near-real-time onboard wind speed reconstruction under sparse-observation conditions. Full article