Search Results (2,292)

Power flow analysis of low-voltage network (LVN) is one of the most crucial methods for achieving refined management of such networks. To accurately calculate the three-phase (TP) probabilistic power flow (PPF) distribution in LVN, this paper first draws on the injection-type Newton method; by leveraging TP power measurements relative to the neutral point obtained from smart meters, the injected power is expressed in terms of injected current equations, thereby establishing TP power flow models for various components within the low-voltage distribution transformer area grid. Subsequently, addressing the stochastic fluctuation models of load power and photovoltaic output, this paper employs conventional numerical methods and an improved Latin hypercube sampling technique. Utilizing linearized power flow equations and based on the improved semi-invariant method (SIM) and Gram–Charlier (GC) series fitting, a calculation method for three-phase PPF in low-voltage distribution transformer area grids using the improved semi-invariant is proposed. Finally, simulations of the proposed three-phase PPF method are conducted using the IEEE-13 node distribution system. The simulation results demonstrate that the proposed method can effectively perform three-phase PPF calculations for the distribution transformer area grid and accurately obtain probabilistic distribution information of the TP power flow within the grid. Full article

With the accelerating global energy transition, wind power has become a core pillar of renewable energy systems. However, its inherent intermittency and volatility pose significant challenges to the safe, stable, and economical operation of power grids—making ultra-short-term wind power prediction a critical technical link in optimizing grid scheduling and promoting large-scale wind power integration. Current forecasting techniques are plagued by problems like the inadequate representation of features, the poor separation of features, and the challenging clarity of deep learning models. This study introduces a method for the prediction of wind energy using spatiotemporal contrastive learning, employing seasonal trend decomposition to encapsulate the diverse characteristics of time series. A contrastive learning framework and a feature disentanglement loss function are employed to effectively decouple spatiotemporal features. Data on geographical positions are integrated to simulate spatial correlations, and a convolutional network of spatiotemporal graphs, integrated with a multi-head attention system, is crafted to improve the clarity. The proposed method is validated using operational data from two actual wind farms in Northwestern China. The research indicates that, compared with typical baselines (e.g., STGCN), this method reduces the RMSE by up to 38.47% and the MAE by up to 44.71% for ultra-short-term wind power prediction, markedly enhancing the prediction precision and offering a more efficient way to forecast wind power. Full article

Background: Regional cerebral blood flow (rCBF) is a putative biomarker for neuropsychiatric disorders, including major depressive disorder (MDD). Methods: Here, we show that rCBF can be predicted from resting-state functional MRI (rsfMRI) at the voxel level while correcting for partial volume averaging (PVA) artifacts. Cortical patterns of MDD-related CBF differences decoded from rsfMRI using a PVA-corrected approach showed excellent agreement with CBF measured using single-photon emission computed tomography (SPECT) and arterial spin labeling (ASL). A support vector machine algorithm was trained to decode cortical voxel-wise CBF from temporal and power-spectral features of voxel-level rsfMRI time series while accounting for PVA. Three datasets, Amish Connectome Project (N = 300; 179 M/121 F, both rsfMRI and ASL data), UK Biobank (N = 8396; 3097 M/5319 F, rsfMRI data), and Amen Clinics Inc. datasets (N = 372: N = 183 M/189 F, SPECT data), were used. Results: PVA-corrected CBF values predicted from rsfMRI showed significant correlation with the whole-brain (r = 0.54, p = 2 × 10⁻⁵) and 31 out of 34 regional (r = 0.33 to 0.59, p < 1.1 × 10⁻³) rCBF measures from 3D ASL. PVA-corrected rCBF values showed significant regional deficits in the UKBB MDD group (Cohen’s d = −0.30 to −0.56, p < 10⁻²⁸), with the strongest effect sizes observed in the frontal and cingulate areas. The regional deficit pattern of MDD-related hypoperfusion showed excellent agreement with CBF deficits observed in the SPECT data (r = 0.74, p = 4.9 × 10⁻⁷). Consistent with previous findings, this new method suggests that perfusion signals can be predicted using voxel-wise rsfMRI signals. Conclusions: CBF values computed from widely available rsfMRI can be used to study the impact of neuropsychiatric disorders such as MDD on cerebral neurophysiology. Full article

Polymer viscoelasticity is crucial for mechanical performance, but conventional low-frequency methods struggle to isolate viscous loss—a key viscosity indicator. This study introduces a high-frequency ultrasonic method to differentiate the polymer viscous dissipation index by analyzing acoustic phase shifts. We employ ultrasonic phase-shift thermometry to measure localized temperature increases resulting from minute variations in sound velocity during controlled heating. This allows for the quantification of viscous loss, which is then used to distinguish between different polymer formulations. Experimental and simulation results on a series of polyurethane specimens with varying Shore hardness levels demonstrate that decawatt-range (10–20 W) ultrasonic irradiation enables sensitive and precise differentiation. Notably, the Shore A70 polyurethane sample exhibited a significantly higher viscous dissipation index, evidenced by the largest temperature rise (27.5 °C) and the highest proportion of viscous heating to total power dissipation (93.1%) under 17 W acoustic irradiation. While this study focuses on commercially available polymers, the method can be extended to evaluate key performance parameters, such as tensile modulus and glass transition temperature, in polymers fabricated under various processing conditions, thereby offering a powerful tool for material quality assessment. Full article

To enhance the accuracy and precision of fault diagnosis and location for the collector lines in wind farms under complex operating conditions, an intelligent combined method based on CNN-LSTM and ICEEMDAN-PE-improved wavelet threshold denoising is proposed. A wind power plant model is established using the PSCADV46/EMTDC software. In response to the issue of indistinct fault current signal characteristics under complex fault conditions, a hybrid fault diagnosis model is constructed using CNN-LSTM. The convolutional neural network is utilized to extract the local time-frequency features of the current signals, while the long short-term memory network is employed to capture the dynamic time series patterns of faults. Combined with the improved phase-mode transformation, various types of faults are intelligently classified, effectively resolving the problem of fault feature extraction and achieving a fault diagnosis accuracy rate of 96.5%. To resolve the problem of small fault current amplitudes, low fault traveling wave amplitudes, and difficulty in accurate location due to noise interference in actual wind farms with high-resistance grounding faults, a combined denoising algorithm based on ICEEMDAN-PE-improved wavelet threshold is proposed. This algorithm, through the collaborative optimization of modal decomposition and entropy threshold, significantly improves the signal-to-noise ratio and reduces the root mean square error under simulated conditions with injected Gaussian white noise, stabilizing the fault location error within 0.5%. Extensive simulation results demonstrate that the fault diagnosis and location method proposed in this paper can effectively meet engineering requirements and provide reliable technical support for the intelligent operation and maintenance system of a wind farm. Full article

Accurate and stable power-load forecasting is crucial for optimizing generation scheduling and ensuring the economic and secure operation of power grids. To address the issues of low prediction accuracy and poor robustness during abrupt load changes, this study proposes a Bayesian-optimized GCN-BiLSTM-Adaboost model (abbreviated as GCN-BiLSTM-AB). It combines Graph Convolutional Networks (GCN), Bidirectional Long Short-Term Memory Networks (BiLSTM), and a Bayesian-optimized AdaBoost framework. Firstly, the GCN is employed to capture the spatial correlation features of the input data. Then, the BiLSTM is employed to extract the long-term dependencies of the data time series. Finally, the AdaBoost framework is used to dynamically adjust the base learner weights, and a Bayesian method is employed to optimize the weight adjustment process and prevent overfitting. The experiment results on actual load data from a regional power grid show the GCN-BiLSTM-AB outperforms other compared models in prediction error metrics, with $MAE$, $MAPE$, and $RMSE$ values of 1.86, 3.13%, and 2.26, respectively, which improve the prediction robustness during load change periods. Therefore, the proposed method shows that the synergistic effect of spatiotemporal feature extraction and dynamic weight adjustment improves prediction accuracy and robustness, which provides a new forecasting model with high precision and reliability for power system dispatch decisions. Full article

Partial shading conditions cause current mismatches between series-connected panels in photovoltaic (PV) arrays, significantly reducing power efficiency. To mitigate this limitation, reconfiguration methods based on dynamically changing the electrical connections within the PV array have been proposed. In recent years, adaptive and dual-adaptive PV connection structures, which particularly balance the line currents and aim to restore current symmetry under irregular shading conditions, have gained prominence due to their notable efficiency improvements. The dual nature of these structures inherently supports this symmetry by enabling balanced reconfigurations on both sides of the array. However, the dual-adaptive structure expands the solution space due to the exponential growth of the connection combinations with the increasing number of lines, and this makes real-time optimization difficult. In fact, this structure has been optimized with genetic algorithm (GA) before; however, the convergence time of GA exceeds acceptable limits in large arrays. In this study, a Particle Swarm Optimization (PSO) algorithm is applied to solve the dual-adaptive PV array reconfiguration problem. Particle Swarm Optimization (PSO) is a metaheuristic algorithm that utilizes swarm intelligence to efficiently explore large solution spaces. PSO’s fast convergence capability and low computational cost enable real-time applications by enabling optimization in acceptable times even for larger PV arrays. Simulation results reveal that PSO successfully manages the exponential growth in the solution space and significantly increases the real-time applicability of the reconfiguration process by effectively increasing the efficiency. In this respect, PSO is considered a powerful and practical solution for reconfiguration problems in large-scale PV arrays. Full article

Hybrid thermoelectric generators (HTEGs) play a pivotal role in sustainable energy conversion by harnessing waste heat through the Seebeck effect, contributing to global efforts in energy efficiency and environmental sustainability. In practical sustainable energy systems, HTEG output performance is significantly influenced by uncertainties in the operational parameters (such as temperature differences and load resistance), material properties (including Seebeck coefficient and resistance), and structural configurations (like the number of series/parallel thermoelectric components), which impact both efficiency and system stability. This study employs the Sobol-sequence-sampling method to characterize these parameter uncertainties, analyzing their effects on HTEG output power and conversion efficiency using mean values and standard deviations as evaluation metrics. The results show that higher temperature differences enhance output performance but reduce stability, a larger load resistance decreases performance while improving stability, thermoelectric materials with high Seebeck coefficients and low resistance boost efficiency at the expense of stability, increasing series-connected components elevates performance but reduces stability, parallel configurations enhance power output yet decrease efficiency and stability, and greater contact thermal resistances diminish performance while enhancing system robustness. This research provides theoretical guidance for optimizing HTEGs in sustainable energy applications, enabling the development of more reliable, efficient, and eco-friendly thermoelectric systems that balance performance with environmental resilience for long-term sustainable operation. Full article

Rod pump systems are complex nonlinear processes, and conventional efficiency prediction methods for such systems typically rely on high-order fractional partial differential equations, which severely constrain real-time inference. Motivated by the increasing availability of measured electrical power data, this paper introduces a series of prediction models for nonlinear fractional-order PDE systems efficiency based on multimodal feature fusion. First, three single-model predictions—Asymptotic Cross-Fusion, Adaptive-Weight Late-Fusion, and Two-Stage Progressive Feature Fusion—are presented; next, two ensemble approaches—one based on a Parallel-Cascaded Ensemble strategy and the other on Data Envelopment Analysis—are developed; finally, by balancing base-learner diversity with predictive accuracy, a multi-strategy ensemble prediction model is devised for online rod pump system efficiency estimation. Comprehensive experiments and ablation studies on data from 3938 oil wells demonstrate that the proposed methods deliver high predictive accuracy while meeting real-time performance requirements. Full article

Concrete compressive strength is a critical property for structural performance and construction scheduling. Traditional non-destructive testing (NDT) methods, such as rebound hammer and ultrasonic pulse velocity, offer limited reliability and resolution, particularly at early ages. This study presents an AI-powered structural health monitoring (SHM) framework that integrates multi-type and multi-position piezoelectric (PZT) sensor networks with machine learning for in situ prediction of concrete compressive strength. Signals were collected from various PZT types positioned on the top, middle, bottom, and surface sides of concrete cubes during curing. A series of machine learning models were trained and evaluated using both the full and selected feature sets. Results showed that combining multiple PZT types and locations significantly improved prediction accuracy, with the best models achieving up to 95% classification accuracy using only the top 200 features. Feature importance and PCA analyses confirmed the added value of sensor heterogeneity. This study demonstrates that multi-sensor AI-enhanced SHM systems can offer a practical, non-destructive solution for real-time strength estimation, enabling earlier and more reliable construction decisions in line with industry standards. Full article

Background: Alzheimer’s disease (AD) is largely linked with oxidative stress, the accumulation of amyloid-β plaques, and hyperphosphorylated τ-protein aggregation. Alterations in dopaminergic and serotonergic neurotransmission have also been implicated in various AD-related symptoms. Methods: To explore new therapeutic agents, a series of bicyclic and tricyclic thieno-oxazepine derivatives were synthesized as potential acetylcholinesterase (AChE) and butyrylcholinesterase (BChE) inhibitors. The resultant compounds were purified via HPLC and characterized using spectral analysis techniques. Histopathological examinations, other antioxidants, and anti-inflammatory biomarkers were evaluated, and in silico ADMET calculations were performed for synthetic hybrids. Molecular docking was utilized to validate the new drugs’ binding mechanisms. Results: The most powerful AChE inhibitors were 14 and 16, with respective values of IC₅₀ equal to 0.39 and 0.76 µM. Derivative 15 demonstrated remarkable BChE-inhibitory efficacy, on par with tacrine, with IC₅₀ values of 0.70 µM. Hybrids 13 and 15 showed greater selectivity towards BChE, despite substantial inhibition of AChE. Compounds 13 and 15 reduced escape latency and raised residence time, with almost equal activity to donepezil. Conclusions: According to these findings, the designed hybrids constitute multipotent lead compounds that could be used in the creation of novel anti-AD medications. Full article

Time-series forecasting is widely recognized as essential for integrating renewable energy, managing emissions, and optimizing demand across energy and environmental applications. Initially, traditional forecasting methods are hindered by limitations including poor interpretability, limited generalization to diverse scenarios, and substantial computational demands. Consequently, a novel minimum-variance self-tuning (MVST) method is proposed, grounded in adaptive control theory, to overcome these challenges. The method utilizes recursive least squares with self-tuning parameter updates, delivering high prediction accuracy, rapid computation, and robust multi-step forecasting without pre-training requirements. Testing is performed on CO₂ emissions (annual), transformer load (15 min), and building electric load (hourly) datasets, comparing MVST against LSTM, ARDL, fixed-PID, XGBoost, and Prophet across varied scales and contexts. Significant improvements are observed, with prediction errors reduced by 3–8 times and computational time decreased by up to 2000 times compared to these methods. Finally, these advancements facilitate real-time power system dispatch, enhance energy planning, and support carbon emission management, demonstrating substantial research and practical value. Full article

Kolmogorov–Arnold Networks (KANs) have recently emerged as a powerful alternative to traditional Artificial Neural Networks (ANNs), offering superior accuracy and interpretability, which are two critical requirements in healthcare applications. This study investigates the effectiveness of KANs across a range of clinical tasks by applying them to diverse medical datasets, including structured clinical data and time-series physiological signals. Compared with conventional ANNs, KANs demonstrate significantly improved performance, achieving higher predictive accuracy even with smaller network architectures. Beyond performance gains, KANs offer a unique advantage: the ability to extract symbolic expressions from learned functions, enabling transparent, human-interpretable models—a key factor in clinical decision-making. Through comprehensive experiments and symbolic analysis, our results reveal that KANs not only outperform ANNs in modeling complex healthcare data but also provide interpretable insights that can support personalized medicine and early diagnosis. There is nothing specific about the datasets or the methods employed, so the findings are broadly applicable and position KANs as a compelling architecture for the future of AI in healthcare. Full article

This paper introduces Neighborhood-Constrained Decomposition-based Prediction (NCD-Pred), the first system to leverage Neighborhood-Constrained Variational Mode Decomposition (NCVMD) for multichannel forecasting by integrating time series decomposition and neural networks. NCD-Pred leverages NCVMD to decompose a multichannel signal into simpler, band-limited components—referred to as intrinsic mode functions or simply modes—by prioritizing the most informative channel (the main channel) over less informative ones (the auxiliary channels) and bringing their central frequencies into alignment up to a tunable extent. This frequency synchronization provides a framework for cooperative mode forecasting, where predictions of signal components are recombined to produce the original signal prediction. For mode-level forecasting, Long Short-Term Memory (LSTM) networks are utilized. NCD-Pred’s performance is evaluated against similarly designed mode-level forecasting systems using a multichannel dataset with weak cross-correlation, representing power load on a large vessel. The results show that NCD-Pred outperforms benchmark methods, demonstrating its practical utility in real signal processing scenarios. Full article