Search Results (46,071)

In high-speed parachuting, complex turbulent phenomena (i.e., deadly vortices) may cause problems such as parachute inflation delay or even deployment failure. To address these issues, this study develops a high-precision numerical simulation dummy model in which adaptive mesh generation techniques, combined with Euler–Lagrange bidirectional coupling based on a large eddy simulation, are employed to model the multiphase flow field during parachute descent. The key parameters are adjusted, and the numerical model is refined based on wind tunnel experiments and User-Defined Functions. The bidirectional validation of the experimental and simulated data reveals the mechanism of turbulent flow formation and its evolutionary patterns around the parachutist–parachute system for different lateral and descent velocities during the high-speed descent phase. A prediction model based on a multi-information fusion neural network algorithm is further established to address the challenge in special parachuting scenarios whereby vortices in the flow field around the parachutist prevent the parachute from opening. The model integrates the Haar wavelet to extract global low-frequency features that characterize the overall structure and trends, an energy valley optimization algorithm, a convolutional neural network, a bidirectional long short-term memory network, and a self-attention mechanism to achieve one-second-ahead turbulence prediction. With nine physical quantities as inputs and descent velocity as the output indicator, the model has a Root Mean Square Error of 0.085, a Mean Absolute Error of 0.051, and a Mean Absolute Percentage Error of 0.0021. Full article

To address the practical engineering challenges of limited fault samples for high-voltage circuit breaker spring operating mechanisms and the inability of single features to fully reflect equipment status, this paper proposes a small-sample fault diagnosis method based on multi-source feature fusion and Stacking ensemble learning. First, a multi-source sensing system containing MEMS (Micro-Electro-Mechanical System) pressure and travel, coil, and motor current was constructed to achieve comprehensive monitoring of the mechanical and electrical states of a 220 kV circuit breaker; in particular, the introduction of non-invasive MEMS sensors effectively solves the difficulty of capturing static spring fatigue characteristics inherent in traditional methods. Second, a high-dimensional feature space was constructed using Savitzky–Golay filtering and physical feature extraction techniques. To address the characteristics of small-sample data distribution, a two-layer Stacking ensemble learning model based on 5-fold cross-validation was designed. This model utilizes the SVM (Support Vector Machine), RF (Random Forest), and KNN (K-Nearest Neighbors) as base classifiers and Logistic Regression as the meta-learner, achieving an adaptive fusion of the advantages of heterogeneous algorithms. True-type experimental results show that the average diagnostic accuracy of this method under normal conditions and four typical fault conditions reaches 96.1%, which is superior to single base models (the RF was 94.2%). Feature importance analysis further confirms that closing and opening pressures are the most critical features for distinguishing mechanical faults. This study provides effective theoretical basis and technical support for condition-based maintenance of high-voltage circuit breakers under small-sample conditions. Full article

Background: Age-related cognitive decline is linked to reduced gait complexity and higher fall risk. Traditional linear gait measures may miss subtle motor-cognitive deficits in older adults with dementia. This study examined whether an 8-week motor-cognitive exercise program could improve gait adaptability in institutionalized older adults with cognitive impairment. Gait complexity, measured using Sample Entropy, was the primary outcome. Methods: Forty-two institutionalized older adults completed follow-up assessments, including 26 with cognitive impairment and 16 controls. Gait was assessed during normal walking (single-task) and while performing cognitive tasks (dual-task), such as naming animals or counting backward. Inertial sensors recorded stride intervals, and Sample Entropy was calculated to evaluate gait regularity and adaptability, (gait complexity). The intervention included 24 structured sessions combining physical and cognitive exercises targeting balance, coordination, and executive function. Non-parametric tests (Wilcoxon) were used, with Bonferroni correction for multiple comparisons. Results: Participants with cognitive impairment showed increased gait complexity, especially during dual-task walking. Significant improvements were found in both limbs under dual-task conditions (left: p = 0.015, effect size = 0.34; right: p = 0.030, effect size = 0.31). During single-task walking, a significant improvement was observed in the left limb (p = 0.006, effect size = 0.39). Conclusions: Motor-cognitive exercise may enhance non-linear gait complexity in institutionalized older adults with cognitive impairment. The use of dual-task training in rehabilitation and highlight the value of entropy-based gait assessment for detecting subtle functional changes. However, the lack of a randomized non-exercising cognitive impairment control group limits definitive conclusions about causality. Full article

Reliability is a fundamental aspect of modern structural engineering due to the inherent randomness of materials, loads, and environmental conditions. However, as system complexity increases, a substantial computational cost is typically required to evaluate the failure probability, often involving 10⁵–10⁶ limit state function evaluations in a conventional Monte Carlo simulation. To address this challenge, this study presents an active-learning-driven deep neural network (ALDNN) meta model algorithm to improve both efficiency and accuracy in reliability analysis. To substantially reduce the computational costs, a multi-phase active learning framework incorporating weighted sampling and adaptive threshold-based candidate filtering is implemented by iteratively selecting more important points and adaptively training deep neural networks. Thresholds for candidate sample points and training datasets are gradually adjusted based on feedback from estimated responses. The proposed method reduces the number of true limit state evaluations to the order of 10² in the benchmark problems considered, while maintaining high accuracy. Its performance is assessed using widely referenced benchmark problems, and finite-element-method-based implicit examples for frame structures are further employed to verify applicability. The results demonstrate the high efficiency, accuracy, and scalability of the ALDNN meta model as system complexity increases. Full article

Green chemistry is built on twelve guiding principles intended to reduce waste, energy use, and hazardous substances in chemical manufacturing. These principles have inspired more sustainable practices, yet their implementation in real-world industrial contexts reveals significant limitations and internal contradictions. This position paper critically examines each principle’s practical challenges, with an emphasis on Principle 6 (design for energy efficiency) and its relationship to process complexity and resource intensity. Using concepts from complexity theory—notably simplexity and complixity—the analysis highlights how chemical production systems behave as complex adaptive networks, where straightforward “green” solutions can trigger emergent trade-offs. Industrial case studies from pharmaceuticals, microelectronics, and large chemical producers (e.g., BASF and Dow) illustrate successes and setbacks in applying green chemistry: catalytic routes that improve yields but rely on scarce elements, solvent recovery systems that save waste at the cost of energy and capital, and integrated processes that achieve remarkable efficiency gains while introducing control complexity. These examples underscore that the principles cannot be treated as isolated absolutes; instead, a holistic, systems-thinking approach is required. The discussion calls for expanding the Green Chemistry framework with new or revised principles that account for lifecycle complexities, adaptive process design, and socio-technical factors. By confronting the gaps between the idealized principles and industrial reality, this analysis offers insight into how green chemistry can evolve—guided by both scientific rigor and practical pragmatism—to better meet the sustainability challenges of modern chemical production. The novelty of this work resides in its systems oriented analysis of the Twelve Principles of Green Chemistry when applied to complex industrial processes. By integrating industrial examples with concepts from complexity theory, the manuscript clarifies limitations and trade offs that are not evident in principle based or metric focused approaches. Full article

Background/Objectives: This study proposes a comprehensive classification framework for the automatic detection of Alzheimer’s disease using handwriting data. An enriched feature space is constructed by combining 18 baseline features extracted from raw handwriting signals with 30 additional features derived from established handwriting analysis studies, resulting in a total of 48 features. To enhance clinical practicality, a task reduction analysis is conducted by comparing the full dataset containing 25 handwriting tasks with a reduced dataset comprising 14 selected tasks. Methods: The proposed framework employs a two-stage evaluation strategy involving four feature selection methods (Random Forest Feature Importance, Extreme Gradient Boosting Feature Importance, L1 Regularization and Recursive Feature Elimination), three normalization techniques (Unnormalized, Min–Max and Z-Score), and five baseline machine learning classifiers (Random Forest, Logistic Regression, Multilayer Perceptron, XGBoost and Support Vector Machines). In the second stage, a dynamic ensemble learning strategy is introduced, where the most effective classifiers are adaptively selected for each cross-validation fold and integrated using soft and hard voting schemes. Results: The experimental results demonstrate that reducing the number of tasks leads to an improvement in average classification accuracy from 79.47% to 81.03%, while simultaneously decreasing training time and memory consumption by approximately 40% and 35%, respectively. The highest classification performance, achieving an accuracy of 94.20%, is obtained using the Hard Ensemble combined with L1-based feature selection. Conclusions: These findings highlight that the joint use of enriched feature representations, task reduction, and dynamic ensemble learning provides an effective and computationally efficient solution for handwriting-based Alzheimer’s disease detection. Full article

To fill hydrogen fuel cell vehicles quickly and safely, the SAE J2601 protocol has published the MC method, which includes control of the filling speed and pressure target. The filling speed depends on the final filling time, the formula for which is obtained by fitting simulated data. The pressure target depends on the final hydrogen temperature, whose analytical solution is derived from a thermodynamic tank model. This article derives new analytical solutions of the final filling time and hydrogen temperature based on an established lumped-parameter model of the storage tank. Based on the original MC method’s control logic, a new filling method that directly uses the analytical solutions of the final filling time and hydrogen temperature was proposed. The simulation results of the new filling method and the validated model (zone-dimensional gas and a one-dimensional tank wall, 0D1D) are compared. Under the ambient temperature conditions of the 0–20 °C and precooling temperature conditions of −20–0 °C set in this article, results show that the new filling method achieves maximum errors of 4.3 °C in its final hydrogen temperature and 0.9% in a state of charge (SOC) compared to the 0D1D model. Parameter sensitivity analysis reveals that initial pressure has the most significant impact on computational accuracy, followed by ambient and precooling temperatures. Future work may further improve prediction accuracy by incorporating correction factors for initial pressure and ambient temperature. Moreover, since the analytical solution of the final hydrogen temperature inherently includes the precooling temperature parameter, the new filling method can automatically adapt to precooling temperature variations. Full article

Aimed at mitigating DC bus voltage fluctuations in electrolytic capacitor-less (ECL) motor drive systems caused by insufficient damping, conventional model predictive control (MPC) offers a fast dynamic response but fails to enhance the inherent damping or fully suppress such voltage variations. To address this limitation, this paper proposes a model predictive control strategy with adaptive virtual resistance adjustment (AVR-MPC). First, a virtual resistance loop is embedded into the active power decoupling circuit to reshape the system impedance and improve the damping characteristics at the model level. Subsequently, the state equations incorporating the virtual resistance are derived using small-signal modeling, and a Lyapunov function is constructed to determine its stable operating range. Based on this analysis, a dynamic relationship between the virtual resistance and the predicted current deviation is established, enabling adaptive tuning of the virtual resistance in response to the current deviation, thereby enhancing system stability under transient conditions. Finally, experimental results validate the effectiveness of the proposed control strategy. Full article

With the prosperity of e-commerce applications, the web data of products are presented by multiple modalities, e.g., vision and language. For mining the product characteristics, multimodal attribute values are crucial, which are extracted from textual descriptions, assisted by helpful image regions. However, most previous works (1) fuse the multimodal information within a newly learned range based on co-occurrence rather than language meanings and (2) predict the outputs within a range of all attributes rather than the product-related ones. These issues yield unsatisfactory results; thus, we propose a novel approach via Dynamic Range Modulation (DRAM): (1) First, we propose an Information Range Calibration (IRC) method to dynamically fuse multimodal features of related meanings as Text-Related Embeddings (TEM) within a language range, which is calibrated from the range to fuse language features by a powerful attention mechanism of a pretrained language model. (2) Moreover, an Attribute Range Minimization (ARM) method is proposed to minimize the output attribute range based on the adaptive selection of product-related attribute prototypes. Experiments on the popular multimodal e-commerce benchmarks show that our DRAM performs well compared with previous methods. Full article

Modern power networks contain an increasing amount of renewable energy resources that are connected to the grid via inverters (Inverter-Based Resources, IBR). As highlighted in the recent IEEE Standard 2800-2022, these resources behave differently compared to conventional power plants, which impact protection systems. For networks with a high proportion of IBR, existing protection systems may no longer be dependable and reliable. This research project investigated the behaviour of commercially available relays for distance protection applied to a power grid with a high proportion of IBR. A detailed numerical model was established for the power grid of the Gaspesian Peninsula in Québec, Canada, where there are numerous wind farms. Five power lines with different characteristics were selected, and 700 fault events were generated in COMTRADE format. These events were then converted into analog signals, applied to commercially available relays, and their tripping actions were analyzed. Several misoperations could be identified and classified. Proposals for improving protection performance were developed and validated with the experimental setup. This project highlights the importance of validating and eventually adapting the protection systems in power grids with a high proportion of IBR, as existing protection systems may be prone to misoperate. Various solutions are proposed to ensure the dependability and reliability of protection systems in modern power grids. Full article

Ultrasonic wind speed measurements performed in complex flow fields face challenges related to low signal-to-noise ratio (SNR) and non-stationary waveform distortion. In this study, we aim to address this issue by proposing a measurement system that employs a polyvinylidene fluoride (PVDF) piezoelectric film ultrasonic transducer integrated with a microphone (MIC). In addition, a signal processing framework is proposed based on the joint optimization of variational mode decomposition (VMD) and an extended Kalman filter (EKF) and integrating cross-correlation interpolation. By leveraging the low Q-factor and wide bandwidth characteristics of the PVDF, the system achieved omnidirectional transmission and high-fidelity reception within a compact structural design. The experimental results demonstrated that the proposed VMD-reference signal-assisted EKF method enhanced the SNR by approximately 26% and reduced the wind speed measurement error by approximately 35% compared with the conventional EKF. The proposed system exhibited superior robustness and measurement linearity across a wide wind speed range of 0–60 m/s. The proposed scheme significantly enhances the accuracy and environmental adaptability of ultrasonic wind speed measurements and provides an essential theoretical basis and engineering reference for the development of precision instruments in fields such as meteorological monitoring and wind energy assessment. Full article

Research on biomarkers reflecting tumor biology and systemic metabolism is crucial for improving the accuracy and personalization of breast cancer (BC) prognosis. We investigated circulating dodecanoic acid in 229 patients undergoing radiotherapy (RT) and assessed its association with progression-free survival and overall survival over six years. Patients were classified into two phenotypes based on post-RT changes in dodecanoic acid: The Increase Phenotype (IP) had lower baseline concentrations and showed a post-RT rise, whereas the Decrease Phenotype (DP) had higher pre-RT levels and declined after treatment. Dodecanoic acid levels were lower in tumors than in peritumoral samples, and their association with phenotypes varied by sampling region, suggesting that systemic changes reflect broader metabolic adaptations rather than local tissue concentrations. Post-RT increases in dodecanoic acid were associated with higher paraoxonase-1 activity, suggesting a link with antioxidant status. Patients in the IP group had a significantly lower risk of progression than those in the DP group, whereas no significant differences in overall survival were observed. These findings highlight the potential utility of dodecanoic acid measurement as a prognostic biomarker and suggest that modulating fatty acid metabolism could be explored as a therapeutic strategy. Full article

Hydraulic systems are pivotal components in safety-critical aerospace and industrial applications, making reliable health monitoring essential. However, traditional data-driven diagnosis methods typically rely on static graph structures that fail to capture evolving sensor correlations during different fault modes. Furthermore, existing grid-based models often struggle to extract multi-resolution features and maintain performance under data-limited conditions. To address these challenges, this paper proposes a novel Dynamic Multi-Scale Graph Neural Network (DMS-GNN) for hydraulic system fault diagnosis. The framework integrates a hierarchical multi-scale feature extraction module to capture diverse fault signatures across different frequency bands. Crucially, a self-attention-based dynamic graph learner is introduced to adaptively infer latent sensor topologies end-to-end, eliminating the reliance on predefined physical connections. Experimental validation on a dedicated electro-hydraulic test bench demonstrates that the proposed DMS-GNN achieves a superior diagnostic accuracy of 98.47%, outperforming state-of-the-art baselines such as GraphSAGE, Static GCN, and GAT. The result confirms the efficacy of combining multi-scale temporal learning with dynamic spatial reasoning for robust multi-sensor fusion diagnosis. Full article

The Northeast China Cold Vortex (NCCV) is a crucial local synoptic system influencing the weather and climate of Northeast China. However, the application of artificial intelligence techniques in NCCV prediction remains limited. Based on ERA5 reanalysis data from the European Centre for Medium-Range Weather Forecasts (ECMWF), this study constructs a 23-year multi-modal spatiotemporal sequence dataset of NCCV via an objective identification method, focusing on NCCV trajectory prediction. An improved generative adversarial network model is proposed, which adopts a multi-encoder architecture to extract spatiotemporal features of multi-modal NCCV data and introduces a multi-generator structure to address the insufficient prediction capability of a single generator. A selector module is added to enable the model to adaptively select the optimal generation path. Ablation experiments show that compared with single-trajectory data input, multi-modal data input in our model reduces the average prediction error by 67.96 km, representing a 34.0% improvement, and the 24-h prediction error improvement reaches 39.7%. Ultimately, the proposed model achieves superior prediction accuracy and stability in the NCCV trajectory prediction tasks at 6 h, 12 h, 18 h, and 24 h, with prediction distance errors reduced by 21.4%, 29.2%, 34.0%, and 37.0% compared to LSTM. Full article

Cryptocurrency trading presents significant challenges due to extreme market volatility, rapid regime transitions, and non-stationary dynamics that render traditional trading strategies ineffective. Existing reinforcement learning approaches for cryptocurrency trading typically employ simplistic profit-based reward functions that fail to adequately capture risk management considerations, market microstructure costs, temporal dependencies, and regime-specific optimal behaviors. This limitation often results in strategies that perform well during favorable market conditions but suffer catastrophic losses during downturns. This paper introduces five novel reward functions grounded in economic utility theory, market microstructure, behavioral finance, adaptive risk management, and regime-conditional optimization. We systematically evaluate these reward functions across three reinforcement learning algorithms (Deep Q-Network, Proximal Policy Optimization, and Advantage Actor–Critic) and four distinct market regimes (bull, bear, high volatility, and recovery), using Bitcoin hourly data from 2018–2022. Our comprehensive experimental evaluation demonstrates that the Adaptive Risk Control reward function achieves exceptional performance, with a Sharpe ratio of 2.47, cumulative return of 26.4%, and maximum drawdown of only 16.8% during the predominantly bearish 2022 test period. Critically, regime-specific analysis reveals substantial performance heterogeneity: Adaptive Risk Control excels during high volatility (Sharpe ratio 3.21), while Temporal Coherence and Asymmetric Market-Conditional rewards dominate in trending and bear markets, respectively. These findings establish that sophisticated, theory-grounded reward engineering—rather than algorithmic innovations alone—constitutes the primary lever for improving RL trading systems, enabling positive risk-adjusted returns even during severe market downturns. Full article