Search Results (56)

Control valves in nuclear systems operate under high-pressure differentials generating intense transient fluid forces that induce destructive structural vibrations, risking resonance and the valve stem fracture. In this study, computational fluid dynamics (CFD) was employed to characterize the internal flow dynamics of the valve, supported by experiment validation of the fluid model. To account for nonlinear structural effects such as contact and damping, a coupled fluid–structure interaction approach incorporating nonlinear perturbation analysis was applied to evaluate the dynamic response of the valve core assembly under fluid excitation. The results indicate that flow separation, re-circulation, and vortex shedding within the throttling region are primary contributors to structural vibrations. A comparative analysis of stability coefficients, modal damping ratios, and logarithmic decrements under different valve openings revealed that the valve core assembly remains relatively stable overall. However, critical stability risks were identified in the lower-order modal frequency range at 50% and 70% openings. Notably, at a 70% opening, the first-order modal frequency of the valve core assembly closely aligns with the frequency of fluid excitation, indicating a potential for critical resonance. This research provides important insights for evaluating and enhancing the vibration stability and operational safety of control valves under complex flow conditions. Full article

The proliferation of power electronics in renewable-integrated grids exacerbates the challenges of nonlinearity and multivariable coupling. While the modal series method (MSM) offers theoretical foundations, it fails to provide tools to systematically quantify dynamic interactions in these complex systems. This study proposes a unified nonlinear modal analysis framework integrating second-order analytical solutions with novel nonlinear indices. Validated across diverse systems (DC microgrids and grid-connected PV), the framework yields significant findings: (1) second-order solutions outperform linearization in capturing critical oscillation/damping distortions under realistic disturbances, essential for fault analysis; (2) nonlinear effects induce modal dominance inversion and generate governing composite modes; (3) key interaction mechanisms are quantified, revealing distinct voltage regulation pathways in DC microgrids and multi-path dynamics driving DC voltage fluctuations. This approach provides a systematic foundation for dynamic characteristic assessment and directly informs control design for power electronics-dominated grids. Full article

The spread of COVID-19 is influenced by multiple factors, including control policies, virus characteristics, individual behaviors, and environmental conditions, exhibiting highly complex nonlinear dynamic features. The time series of new confirmed cases shows significant nonlinearity and non-stationarity. Traditional prediction methods that rely solely on one-dimensional case data struggle to capture the multi-dimensional features of the data and are limited in handling nonlinear and non-stationary characteristics. Their prediction accuracy and generalization capabilities remain insufficient, and most existing studies focus on single-step forecasting, with limited attention to multi-step prediction. To address these challenges, this paper proposes a multi-module fusion prediction model—TSMixer-BiKSA network—that integrates multi-feature inputs, Variational Mode Decomposition (VMD), and a dual-branch parallel architecture for 1- to 3-day-ahead multi-step forecasting of new COVID-19 cases. First, variables highly correlated with the target sequence are selected through correlation analysis to construct a feature matrix, which serves as one input branch. Simultaneously, the case sequence is decomposed using VMD to extract low-complexity, highly regular multi-scale modal components as the other input branch, enhancing the model’s ability to perceive and represent multi-source information. The two input branches are then processed in parallel by the TSMixer-BiKSA network model. Specifically, the TSMixer module employs a multilayer perceptron (MLP) structure to alternately model along the temporal and feature dimensions, capturing cross-time and cross-variable dependencies. The BiGRU module extracts bidirectional dynamic features of the sequence, improving long-term dependency modeling. The KAN module introduces hierarchical nonlinear transformations to enhance high-order feature interactions. Finally, the SA attention mechanism enables the adaptive weighted fusion of multi-source information, reinforcing inter-module synergy and enhancing the overall feature extraction and representation capability. Experimental results based on COVID-19 case data from Italy and the United States demonstrate that the proposed model significantly outperforms existing mainstream methods across various error metrics, achieving higher prediction accuracy and robustness. Full article

Audio-driven emotional talking face generation aims to generate talking face videos with rich facial expressions and temporal coherence. Current diffusion model-based approaches predominantly depend on either single-label emotion annotations or external video references, which often struggle to capture the complex relationships between modalities, resulting in less natural emotional expressions. To address these issues, we propose MF-ETalk, a multimodal feature-guided method for emotional talking face generation. Specifically, we design an emotion-aware multimodal feature disentanglement and fusion framework that leverages Action Units (AUs) to disentangle facial expressions and models the nonlinear relationships among AU features using a residual encoder. Furthermore, we introduce a hierarchical multimodal feature fusion module that enables dynamic interactions among audio, visual cues, AUs, and motion dynamics. This module is optimized through global motion modeling, lip synchronization, and expression subspace learning, enabling full-face dynamic generation. Finally, an emotion-consistency constraint module is employed to refine the generated results and ensure the naturalness of expressions. Extensive experiments on the MEAD and HDTF datasets demonstrate that MF-ETalk outperforms state-of-the-art methods in both expression naturalness and lip-sync accuracy. For example, it achieves an FID of 43.052 and E-FID of 2.403 on MEAD, along with strong synchronization performance (LSE-C of 6.781, LSE-D of 7.962), confirming the effectiveness of our approach in producing realistic and emotionally expressive talking face videos. Full article

Exploring the dynamics of nonlinear nanofluidic flow-induced vibrations, this work focuses on single-walled branched carbon nanotubes (SWCNTs) operating in a thermal–magnetic environment. Carbon nanotubes (CNTs), renowned for their exceptional strength, conductivity, and flexibility, are modeled using Euler–Bernoulli beam theory alongside Eringen’s nonlocal elasticity to capture nanoscale effects for varying downstream angles. The intricate interactions between nanofluids and SWCNTs are analyzed using the Differential Transform Method (DTM) and validated through ANSYS simulations, where modal analysis reveals the vibrational characteristics of various geometries. To enhance predictive accuracy and system stability, machine learning algorithms, including XGBoost, CATBoost, Random Forest, and Artificial Neural Networks, are employed, offering a robust comparison for optimizing vibrational and thermo-magnetic performance. Key parameters such as nanotube geometry, magnetic flux density, and fluid flow dynamics are identified as critical to minimizing vibrational noise and improving structural stability. These insights advance applications in energy harvesting, biomedical devices like artificial muscles and nanosensors, and nanoscale fluid control systems. Overall, the study demonstrates the significant advantages of integrating machine learning with physics-based simulations for next-generation nanotechnology solutions. Full article

Background: Sensorimotor beta oscillations are critical for motor control and become synchronized with muscle activity during sustained contractions, forming corticomuscular coherence (CMC). Although beta activity manifests in transient bursts, suggesting nonlinear behavior, most studies rely on linear analyses, leaving the underlying dynamic structure of brain–muscle interactions underexplored. Objectives: To investigate the nonlinear dynamics underlying beta oscillations during isometric contraction. Methods: MEG and EMG were recorded from 17 right-handed healthy adults performing a 10 min isometric pinch task. Lyapunov exponent (LE), fractal dimension (FD), and correlation dimension (CD) were computed in 10 s windows to assess temporal stability. Signal similarity was assessed using Pearson correlation of amplitude envelopes and the nonlinear features. Burstiness was estimated using the coefficient of variation (CV) of the beta envelope to examine how transient fluctuations in signal amplitude relate to underlying nonlinear dynamics. Phase-randomized surrogate signals were used to validate the nonlinearity of the original data. Results: In contrast to FD, LE and CD revealed consistent, structured dynamics over time and significantly differed from surrogate signals, indicating sensitivity to non-random patterns. Both MEG and EMG signals demonstrated temporal stability in nonlinear features. However, MEG–EMG similarity was captured only by linear envelope correlation, not by nonlinear features. CD was strongly associated with beta burstiness in MEG, suggesting it reflects information similar to that captured by the amplitude envelope. In contrast, LE showed a weaker, inverse relationship, and FD was not significantly associated with burstiness. Conclusions: Nonlinear features capture intrinsic, stable dynamics in cortical and muscular beta activity, but do not reflect cross-modal similarity, highlighting a distinction from conventional linear analyses. Full article

Accurate detection of slope cracks plays a crucial role in early landslide disaster warning; however, traditional approaches often struggle to identify fine and irregular cracks. This study introduces a novel deep learning model, Crack-Net, which leverages a multi-modal feature fusion mechanism and is developed using transfer learning. To resolve the blurred representation of small-scale cracks, a nonlinear frequency-domain mapping module is employed to decouple amplitude and phase information, while a cross-domain attention mechanism facilitates adaptive feature fusion. In addition, a deep feature fusion module integrating deformable convolution and a dual attention mechanism is embedded within the encoder–decoder architecture to enhance multi-scale feature interactions and preserve crack topology. The model is pre-trained on the CrackVision12K dataset and fine-tuned on a custom dataset of slope cracks, effectively addressing performance degradation in small-sample scenarios. Experimental results show that Crack-Net achieves an average accuracy of 92.1%, outperforming existing models such as DeepLabV3 and CrackFormer by 9.4% and 5.4%, respectively. Furthermore, the use of transfer learning improves the average precision by 1.6%, highlighting the model’s strong generalization capability and practical effectiveness in real-world slope crack detection. Full article

This study presents high-fidelity numerical simulations of the shock-accelerated single-mode Richtmyer–Meshkov instability (RMI) in a light helium layer confined between two interfaces and surrounded by nitrogen gas. A high-order modal discontinuous Galerkin method is employed to solve the two-dimensional compressible Euler equations, enabling detailed investigation of interface evolution, vorticity dynamics, and flow structure development under various physical conditions. The effects of helium layer thickness, initial perturbation amplitude, and incident shock Mach number are systematically explored by analyzing interface morphology, vorticity generation, enstrophy, and kinetic energy. The results show that increasing the helium layer thickness enhances vorticity accumulation and interface deformation by delaying interaction with the second interface, allowing more sustained instability growth. Larger initial perturbation amplitudes promote earlier onset of nonlinear deformation and stronger baroclinic vorticity generation, while higher shock strengths intensify pressure gradients across the interface, accelerating instability amplification and mixing. These findings highlight the critical interplay between layer confinement, perturbation strength, and shock strength in governing the nonlinear evolution of RMI in light fluid layers. Full article

Under cyclic moving load action, tensile-dominant structures are prone to crack initiation due to cumulative damage effects. The presence of cracks leads to structural stiffness degradation and nonlinear redistribution of dynamic characteristics, thereby compromising str18uctural integrity and service performance. The current research on the dynamic behavior of cracked structures predominantly focuses on transient analysis through high-fidelity finite element models. However, the existing methodologies encounter two critical limitations: computational inefficiency and a trade-off between model fidelity and practicality. Thus, this study presents an innovative analytical framework to investigate the dynamic response of cracked simply supported beams subjected to moving loads. The proposed methodology conceptualizes the cracked beam as a system composed of multiple interconnected sub-beams, each governed by the Euler–Bernoulli beam theory. At crack locations, massless rotational springs are employed to accurately capture the local flexibility induced by these defects. The transfer matrix method is utilized to derive explicit eigenfunctions for the cracked beam system, thereby facilitating the formulation of coupled vehicle–bridge vibration equations through modal superposition. Subsequently, dynamic response analysis is conducted using the Runge–Kutta numerical integration scheme. Extensive numerical simulations reveal the influence of critical parameters—particularly crack depth and location—on the coupled dynamic behavior of the structure subjected to moving loads. The results indicate that at a constant speed, neither crack depth nor position alters the shape of the beam’s vibration curve. The maximum deflection of beams with a 30% crack in the middle span increases by 14.96% compared to those without cracks. Furthermore, crack migration toward the mid-span results in increased mid-span displacement without changing vibration curve topology. For a constant crack depth ratio (γ_i = 0.3), the progressive migration of the crack position from 0.05 L to 0.5 L leads to a 26.4% increase in the mid-span displacement (from 5.3 mm to 6.7 mm). These findings highlight the efficacy of the proposed method in capturing the complex interactions between moving loads and cracked concrete structures, offering valuable insights for structural health monitoring and assessment. Full article

To address modality heterogeneity and accelerate large-scale retrieval, cross-modal hashing strategies generate compact binary codes that enhance computational efficiency. Existing approaches often struggle with suboptimal feature learning due to fixed activation functions and limited cross-modal interaction. We propose Unsupervised Contrastive Graph Kolmogorov–Arnold Networks (GraphKAN) Enhanced Cross-modal Retrieval Hashing (UCGKANH), integrating GraphKAN with contrastive learning and hypergraph-based enhancement. GraphKAN enables more flexible cross-modal representation through enhanced nonlinear expression of features. We introduce contrastive learning that captures modality-invariant structures through sample pairs. To preserve high-order semantic relations, we construct a hypergraph-based information propagation mechanism, refining hash codes by enforcing global consistency. The efficacy of our UCGKANH approach is validated by thorough tests on the MIR-FLICKR, NUS-WIDE, and MS COCO datasets, which show significant gains in retrieval accuracy coupled with strong computational efficiency. Full article

Power demand forecasting is a critical and challenging task for modern power systems and integrated energy systems. Due to the absence of well-established theoretical frameworks and publicly available feature databases on power demand changes, the known interpretable features of power demand fluctuations are primarily derived from expert experience and remain significantly limited. This substantially hinders advancements in power demand forecasting accuracy. Emerging multimodal learning approaches have demonstrated great promise in machine learning and AI-generated content (AIGC). In this paper, we propose, for the first time, a textual-knowledge-guided numerical feature discovery (TKNFD) framework for short-term power demand forecasting by interacting text modal data—a potentially valuable yet long-overlooked resource in the field of power demand forecasting—with numerical modal data. TKNFD systematically and automatically aggregates qualitative textual knowledge, expands it into a candidate feature-type set, collects corresponding numerical data for these features, and ultimately constructs four-dimensional multivariate source-tracking databases (4DM-STDs). Subsequently, TKNFD introduces a two-stage quantitative feature identification strategy that operates independently of forecasting models. The essence of TKNFD lies in achieving reliable and comprehensive feature discovery by fully exploiting the dual relationships of synonymy and complementarity between text modal data and numerical modal data in terms of granularity, scope, and temporality. In this study, TKNFD identifies 38–50 features while further interpreting their contributions and dependency correlations. Benchmark experiments conducted in Maine, Texas, and New South Wales demonstrate that the forecasting accuracy using TKNFD-identified features consistently surpasses that of state-of-the-art feature schemes by up to 36.37% MAPE. Notably, driven by multimodal interaction, TKNFD can discover previously unknown interpretable features without relying on prior empirical knowledge. This study reveals 10–16 previously unknown interpretable features, particularly several dominant features in integrated energy and astronomical dimensions. These discoveries enhance our understanding of the origins of strong randomness and non-linearity in power demand fluctuations. Additionally, the 4DM-STDs developed for these three regions can serve as public baseline databases for future research. Full article

Multimodal medical image fusion plays a critical role in enhancing diagnostic accuracy by integrating complementary information from different imaging modalities. However, existing methods often suffer from issues such as unbalanced feature fusion, structural blurring, loss of fine details, and limited global semantic modeling, particularly in low signal-to-noise modalities like PET. To address these challenges, we propose PPMF-Net, a novel progressive and parallel deep learning framework for PET–MRI image fusion. The network employs a hierarchical multi-path architecture to capture local details, global semantics, and high-frequency information in a coordinated manner. Specifically, it integrates three key modules: (1) a Dynamic Edge-Enhanced Module (DEEM) utilizing inverted residual blocks and channel attention to sharpen edge and texture features, (2) a Nonlinear Interactive Feature Extraction module (NIFE) that combines convolutional operations with element-wise multiplication to enable cross-modal feature coupling, and (3) a Transformer-Enhanced Global Modeling module (TEGM) with hybrid local–global attention to improve long-range dependency and structural consistency. A multi-objective unsupervised loss function is designed to jointly optimize structural fidelity, functional complementarity, and detail clarity. Experimental results on the Harvard MIF dataset demonstrate that PPMF-Net outperforms state-of-the-art methods across multiple metrics—achieving SF: 38.27, SD: 96.55, SCD: 1.62, and MS-SSIM: 1.14—and shows strong generalization and robustness in tasks such as SPECT–MRI and CT–MRI fusion, indicating its promising potential for clinical applications. Full article

Amidst global economic fluctuations and escalating geopolitical risks, gold futures, as a pivotal safe-haven asset, demonstrate price dynamics that directly impact investor decision-making and risk mitigation effectiveness. Traditional forecasting models face significant limitations in capturing long-term trends, addressing abrupt volatility, and mitigating multi-source noise within complex market environments characterized by nonlinear interactions and extreme events. Current research predominantly focuses on single-model approaches (e.g., ARIMA or standalone neural networks), inadequately addressing the synergistic effects of multimodal market signals (e.g., cross-market index linkages, exchange rate fluctuations, and policy shifts) and lacking the systematic validation of model robustness under extreme events. Furthermore, feature selection often relies on empirical assumptions, failing to uncover non-explicit correlations between market factors and gold futures prices. A review of the global literature reveals three critical gaps: (1) the insufficient integration of temporal dependency and global attention mechanisms, leading to imbalanced predictions of long-term trends and short-term volatility; (2) the neglect of dynamic coupling effects among cross-market risk factors, such as energy ETF-metal market spillovers; and (3) the absence of hybrid architectures tailored for high-frequency noise environments, limiting predictive utility for decision support. This study proposes a three-stage LSTM–Transformer–XGBoost fusion framework. Firstly, XGBoost-based feature importance ranking identifies six key drivers from thirty-six candidate indicators: the NASDAQ Index, S&P 500 closing price, silver futures, USD/CNY exchange rate, China’s 1-year Treasury yield, and Guotai Zhongzheng Coal ETF. Second, a dual-channel deep learning architecture integrates LSTM for long-term temporal memory and Transformer with multi-head self-attention to decode implicit relationships in unstructured signals (e.g., market sentiment and climate policies). Third, rolling-window forecasting is conducted using daily gold futures prices from the Shanghai Futures Exchange (2015–2025). Key innovations include the following: (1) a bidirectional LSTM–Transformer interaction architecture employing cross-attention mechanisms to dynamically couple global market context with local temporal features, surpassing traditional linear combinations; (2) a Dynamic Hierarchical Partition Framework (DHPF) that stratifies data into four dimensions (price trends, volatility, external correlations, and event shocks) to address multi-driver complexity; (3) a dual-loop adaptive mechanism enabling endogenous parameter updates and exogenous environmental perception to minimize prediction error volatility. This research proposes innovative cross-modal fusion frameworks for gold futures forecasting, providing financial institutions with robust quantitative tools to enhance asset allocation optimization and strengthen risk hedging strategies. It also provides an interpretable hybrid framework for derivative pricing intelligence. Future applications could leverage high-frequency data sharing and cross-market risk contagion models to enhance China’s influence in global gold pricing governance. Full article

Curve squeal is a highly disturbing tonal noise produced by railway vehicles on tight curves, primarily attributed to lateral sliding at the wheel–rail interface. An essential step to estimate curve squeal noise levels is to determine the nonlinear self-sustained vibrations, for which time integration is a commonly used method. However, although it is known that the initial conditions affect the solutions obtained with time integration, their impact on the limit cycles is often overlooked. This study investigates this aspect for a curve squeal model based on falling friction and a modal reduction of the wheel and provides some insights on the mode competition phenomena and the nature of the final limit cycles obtained. The paper first details the curve squeal model, stability analysis, as well as the initial condition derivation, and then discusses the time integration and limit cycle results in both time and frequency domains. The results reveal two primary families of limit cycles that can be obtained for both types of initial conditions. The cases where stationary vibrations result in a quasi-periodic regime converge to a unique limit cycle which displays three fundamental frequencies corresponding to specific wheel modes, plus harmonic interactions among them. Full article

The stability and behavior of jet flows are critical in various engineering applications, yet many aspects remain insufficiently understood. Previous studies predominantly relied on modal methods to describe small perturbations on jet flow surfaces through the linear superposition of modal waves. However, these approaches largely neglected the interaction between different modes, which can lead to transient energy growth and significantly impact jet stability. This work addresses this gap by focusing on the transient growth of disturbances in jet flows through a comprehensive non-modal analysis, which captures the short-term energy evolution. Unlike modal analysis, which provides insights into the overall trend of energy changes over longer periods, non-modal analysis reveals the instantaneous dynamics of the disturbance energy. This approach enables the identification of transient growth mechanisms that are otherwise undetectable using modal methods, which treat disturbance waves as independent and fail to account for their coupling effects. The results demonstrate that non-modal analysis effectively quantifies the interplay between disturbance waves, capturing the nonlinearity inherent in transient energy growth. This method highlights the short-term amplification of disturbances, providing a more accurate understanding of jet flow stability. Furthermore, the impact of dimensionless parameters such as the Reynolds number, Weber number, and initial wave number on transient energy growth is systematically analyzed. Key findings reveal the optimal conditions for maximizing energy growth and elucidate the mechanisms driving these phenomena. By integrating non-modal analysis, this study advances the theoretical framework of transient energy growth, offering new insights into jet flow stability and paving the way for practical improvements in fluid dynamic systems. Full article