Search Results (221)

Rolling bearings, as essential parts of rotating machinery, face significant challenges in fault diagnosis due to limited fault samples and high noise interference, both of which reduce the effectiveness of traditional methods. To tackle this, this study proposes a fault diagnosis approach that combines Digital Twin (DT) and deep learning. First, actual bearing vibration data were collected using an experimental platform. After denoising the data, a high-fidelity digital twin system was built by integrating the bearing dynamics model with a Generative Adversarial Network (GAN), thereby effectively increasing the fault data. Next, the Wavelet Synchro-Extracting Transform (WSET) is used for high-resolution time-frequency analysis, and convolutional neural networks (CNNs) are employed to extract deep fault features adaptively. The fully connected layer of the CNN is then combined with a Least Squares Support Vector Machine (LSSVM), with key parameters optimized through an Improved Pelican Optimization Algorithm (IPOA) to improve classification accuracy significantly. Experimental results based on both simulated and publicly available datasets show that the proposed model has excellent generalizability and operational flexibility, surpassing existing deep learning-based diagnostic methods in complex industrial settings. Full article

This paper proposes a rolling bearing fault diagnosis method based on HFMD and a dual-branch parallel network, aiming to address the issue of diagnostic accuracy being compromised by the disparity in data quality across different source domains due to sparse feature separation in rolling bearing acoustic signals. Traditional methods face challenges in feature extraction, sensitivity to noise, and difficulties in handling coupled multi-fault conditions in rolling bearing fault diagnosis. To overcome these challenges, this study first employs the HawkFish Optimization Algorithm to optimize Feature Mode Decomposition (HFMD) parameters, thereby improving modal decomposition accuracy. The optimal modal components are selected based on the minimum Residual Energy Index (REI) criterion, with their time-domain graphs and Continuous Wavelet Transform (CWT) time-frequency diagrams extracted as network inputs. Then, a dual-branch parallel network model is constructed, where the multi-scale residual structure (Res2Net) incorporating the Efficient Channel Attention (ECA) mechanism serves as the temporal branch to extract key features and suppress noise interference, while the Swin Transformer integrating multi-stage cross-scale attention (MSCSA) acts as the time-frequency branch to break through local perception bottlenecks and enhance classification performance under limited resources. Finally, the time-domain graphs and time-frequency graphs are, respectively, input into Res2Net and Swin Transformer, and the features from both branches are fused through a fully connected layer to obtain comprehensive fault diagnosis results. The research results demonstrate that the proposed method achieves 100% accuracy in open-source datasets. In the experimental data, the diagnostic accuracy of this study demonstrates significant advantages over other diagnostic models, achieving an accuracy rate of 98.5%. Under few-shot conditions, this study maintains an accuracy rate no lower than 95%, with only a 2.34% variation in accuracy. HFMD and the dual-branch parallel network exhibit remarkable stability and superiority in the field of rolling bearing fault diagnosis. Full article

The Zhag Cave in western Tibet, dated to the 11th to 12th centuries, features four walls fully adorned with images of the Thousand Buddhas of the Bhadrakalpa (Fortunate Aeon). According to the Tibetan inscriptions, the arrangement of the Thousand Buddhas creates a circumambulatory space for worship and confession, enabling practitioners to purify their sins. Four aspects of the Zhag Cave are comparable to those of Dunhuang. First, among the inscriptions is the Pratītyasamutpāda-gāthā, elaborated in the Śālistamba Sūtra, the Tibetan manuscripts of which have been unearthed in both western Tibet and Dunhuang. Second, the way of depicting Thousand Buddhas on four walls inside the cave could be found in earlier caves from the 5th to 6th centuries at Dunhuang. Third, the specific practice of only depicting the Bhadrakalpa Thousand Buddhas on the walls parallels similar caves from the mid-10th to early 13th centuries at Dunhuang. Fourth, the motifs depicted along the wall edges correspond with the prevalent themes found in the Bhadrakalpa Thousand Buddhas transformation tableaux during the 9th to 13th centuries, reflecting the apogee of Bhadrakalpa Thousand Buddhas devotion. These connections prompt us to think about the ways in which Western Tibet was part of the Silk Road network. I argue that this shared iconographic and ritual framework embodies the intertwined religious practices of the Dharma-ending Age (Mofa 末法) thought and Buddhist revival movements along the Silk Road, explaining these complex interconnections between the Zhag Cave and the Dunhuang relics within the broader context of religious beliefs and socio-cultural patterns. Full article

To tackle the limitations in simultaneously modeling long-term dependencies in the time dimension and nonlinear interactions in the feature dimension, as well as their inability to fully reflect the impact of real-time load changes on spatial dependencies, a short-term multi-energy load forecasting method based on Transformer Spatio-Temporal Graph neural network (TSTG) is proposed. This method employs a multi-head spatio-temporal attention module to model long-term dependencies in the time dimension and nonlinear interactions in the feature dimension in parallel across multiple subspaces. Additionally, a dynamic adaptive graph convolution module is designed to construct adaptive adjacency matrices by combining physical topology and feature similarity, dynamically adjusting node connection weights based on real-time load characteristics to more accurately characterize the spatial dynamics of multi-energy interactions. Furthermore, TSTG adopts an end-to-end spatio-temporal joint optimization framework, achieving synchronous extraction and fusion of spatio-temporal features through an encoder–decoder architecture. Experimental results show that TSTG significantly outperforms existing methods in short-term load forecasting tasks, providing an effective solution for refined forecasting in integrated energy systems. Full article

This paper addresses the problem of recognising and classifying hand movements to control an upper-limb exoskeleton. To solve this problem, a multisensory system based on the fusion of data from electromyography (EMG) sensors, inertial measurement units (IMUs), and virtual reality (VR) trackers is proposed, which provides highly accurate detection of users’ movements. Signal preprocessing (noise filtering, segmentation, normalisation) and feature extraction were performed to generate input data for regression and classification models. Various machine learning algorithms are used to recognise motor activity, ranging from classical algorithms (logistic regression, k-nearest neighbors, decision trees) and ensemble methods (random forest, AdaBoost, eXtreme Gradient Boosting, stacking, voting) to deep neural networks, including convolutional neural networks (CNNs), gated recurrent units (GRUs), and transformers. The algorithm for integrating machine learning models into the exoskeleton control system is considered. In experiments aimed at abandoning proprietary tracking systems (VR trackers), absolute position regression was performed using data from IMU sensors with 14 regression algorithms: The random forest ensemble provided the best accuracy (mean absolute error = 0.0022 metres). The task of classifying activity categories out of nine types is considered below. Ablation analysis showed that IMU and VR trackers produce a sufficient informative minimum, while adding EMG also introduces noise, which degrades the performance of simpler models but is successfully compensated for by deep networks. In the classification task using all signals, the maximum result (99.2%) was obtained on Transformer; the fully connected neural network generated slightly worse results (98.4%). When using only IMU data, fully connected neural network, Transformer, and CNN–GRU networks provide 100% accuracy. Experimental results confirm the effectiveness of the proposed architectures for motor activity classification, as well as the use of a multi-sensor approach that allows one to compensate for the limitations of individual types of sensors. The obtained results make it possible to continue research in this direction towards the creation of control systems for upper exoskeletons, including those used in rehabilitation and virtual simulation systems. Full article

With the widespread implementation of bridge structural health monitoring (SHM) systems, monitored bridge networks have gradually formed. Understanding vehicle loads and considering spatio-temporal correlations within bridge networks is critical for structural condition assessment and maintenance decision making. This study aims to predict traffic flows by investigating traffic flow correlations within a bridge network using multi-bridge data, thereby supporting bridge network-level SHM. A transformer-based traffic flow prediction model considering spatio-temporal correlations of bridge networks (ST-TransNet) is proposed. It integrates external factors (processed via fully connected networks) and multi-period traffic flows of input bridges (captured by self-attention encoders) to generate traffic flow predictions through a self-attention decoder. Validated using weigh-in-motion data from an 8-bridge network, the proposed ST-TransNet reduces prediction root mean square error (RMSE) to 12.76 vehicles/10 min, outperforming a series of baselines—SVR, CNN, BiLSTM, CNN&BiLSTM, ST-ResNet, transformer, and STGCN—with significant relative reductions of 40.5%, 36.9%, 36.6%, 37.3%, 35.6%, 31.1%, and 22.8%, respectively. Ablation studies confirm the contribution of each component of the external factors and multi-period traffic flows, particularly the recent traffic flow data. The proposed ST-TransNet effectively captures underlying the spatio-temporal correlations of traffic flow within bridge networks, offering valuable insights for enhancing bridge assessment and maintenance. Full article

Path flow always plays a critical role in extracting vehicle travel patterns and reflecting network-scale traffic features. However, the comprehensive topological structure of urban road networks induces massive route choices, so frequent travel routes have been gradually regarded as an ideal countermeasure to represent traffic states. Widely used license plate recognition (LPR) devices can collect the abundant traffic features of all vehicles, but their sparse spatial distributions restrict the conventional models in frequent travel identification. Therefore, this study develops a network reconstruction method to construct a topological network from the LPR dataset, avoiding the adverse effects caused by the sparse distribution of detectors on the road network and further uses the Snake algorithm to fully utilize the road network structure and traffic attributes for clustering to obtain various travel patterns, with frequent routes under different travel patterns finally identified based on Steiner trees and frequent item recognition. To address the sparse spatial distribution of LPR devices, we utilize the word2vec model to extract spatial correlations among intersections. A threshold-based method is then applied to transform the correlation matrix into a reconstructed network, connecting intersections with strong vehicle transition relationships. This community structure can be interpreted as representing different travel patterns. Consequently, the Snake algorithm is employed to cluster intersections into distinct categories, reflecting these varied travel patterns. By leveraging the word2vec model, the detector installation rate requirement for Snake is significantly reduced, ensuring that the clustering results accurately represent the intrinsic relevance of traffic roads. Subsequently, frequent routes are identified from both macro- and micro-perspectives using the Steiner tree and Frequent Pattern Growth (FP Growth) algorithm, respectively. Validated on the LPR dataset in Changsha, China, the experiment results demonstrate that the proposed method can effectively identify travel patterns and extract frequent routes in the sparsely installed LPR devices. Full article

This study investigates the impact of Time-of-Use (TOU) scheduling and battery energy storage systems (BESS) on voltage stability in a typical Malaysian medium-voltage distribution network with high photovoltaic (PV) system penetration. The analyzed network comprises 110 nodes connected via eight feeders to a pair of 132/11 kV, 15 MVA transformers, supplying a total load of 20.006 MVA. Each node is integrated with a 100 kW PV system, enabling up to 100% PV penetration scenarios. A hybrid mitigation strategy combining TOU-based load shifting and BESS was implemented to address voltage violations occurring, particularly during low-load night hours. Dynamic simulations using DIgSILENT PowerFactory were conducted under worst-case (no load and peak load) conditions. The novelty of this research is the use of real rural network data to validate a hybrid BESS–TOU strategy, supported by detailed sensitivity analysis across PV penetration levels. This provides practical voltage stabilization insights not shown in earlier studies. Results show that at 100% PV penetration, TOU or BESS alone are insufficient to fully mitigate voltage drops. However, a hybrid application of 0.4 MWh BESS with 20% TOU load shifting eliminates voltage violations across all nodes, raising the minimum voltage from 0.924 p.u. to 0.951 p.u. while reducing active power losses and grid dependency. A sensitivity analysis further reveals that a 60% PV penetration can be supported reliably using only 0.4 MWh of BESS and 10% TOU. Beyond this, hybrid mitigation becomes essential to maintain stability. The proposed solution demonstrates a scalable approach to enable large-scale PV integration in dense rural grids and addresses the specific operational characteristics of Malaysian networks, which differ from commonly studied IEEE test systems. This work fills a critical research gap by using real local data to propose and validate practical voltage mitigation strategies. Full article

In the present paper, a mathematical analysis of the Gardner equation with varying coefficients has been performed to give a more realistic model of physical phenomena, especially in regards to plasma physics. First, a Lie symmetry analysis was carried out, as a result of which a symmetry classification following the different representations of the variable coefficients was systematically derived. The reduced ordinary differential equation obtained is solved using the power-series method and solutions to the equation are represented graphically to give an idea of their dynamical behavior. Moreover, a fully connected neural network has been included as an efficient computation method to deal with the complexity of the reduced equation, by using traveling-wave transformation. The validity and correctness of the solutions provided by the neural networks have been rigorously tested and the solutions provided by the neural networks have been thoroughly compared with those generated by the Runge–Kutta method, which is a conventional and well-recognized numerical method. The impact of a variation in the loss function of different coefficients has also been discussed, and it has also been found that the dispersive coefficient affects the convergence rate of the loss contribution considerably compared to the other coefficients. The results of the current work can be used to improve knowledge on the nonlinear dynamics of waves in plasma physics. They also show how efficient it is to combine the approaches, which consists in the use of analytical and semi-analytical methods and methods based on neural networks, to solve nonlinear differential equations with variable coefficients of a complex nature. Full article

In the task of PolSAR image classification, effectively utilizing convolutional neural networks and vision transformer models with limited labeled data poses a critical challenge. This article proposes a novel method for PolSAR image classification that combines channel-wise convolutional local perception, detachable self-attention, and a residual feedforward network. Specifically, the proposed method comprises several key modules. In the channel-wise convolutional local perception module, channel-wise convolution operations enable accurate extraction of local features from different channels of PolSAR images. The local residual connections further enhance these extracted features, providing more discriminative information for subsequent processing. Additionally, the detachable self-attention mechanism plays a pivotal role: it facilitates effective interaction between local and global information, enabling the model to comprehensively perceive features across different scales, thereby improving classification accuracy and robustness. Subsequently, replacing the conventional feedforward network with a residual feedforward network that incorporates residual structures aids the model in better representing local features, further enhances the capability of cross-layer gradient propagation, and effectively alleviates the problem of vanishing gradients during the training of deep networks. In the final classification stage, two fully connected layers with dropout prevent overfitting, while softmax generates predictions. The proposed method was validated on the AIRSAR Flevoland, RADARSAT-2 San Francisco, and RADARSAT-2 Xi’an datasets. The experimental results demonstrate that the proposed method can attain a high level of classification performance even with a limited amount of labeled data, and the model is relatively stable. Furthermore, the proposed method has lower computational costs than comparative methods. Full article

In response to the issues of severe pitch oscillation and unstable roll attitude present in existing reinforcement learning-based aircraft cruise control methods during dynamic maneuvers, this paper proposes a precise control method for aircraft cruising based on proximal policy optimization (PPO) with nonlinear attitude constraints. This method first introduces a combination of long short-term memory (LSTM) and a fully connected layer (FC) to form the policy network of the PPO method, improving the algorithm’s learning efficiency for sequential data while avoiding feature compression. Secondly, it transforms cruise control into tracking target heading, altitude, and speed, achieving a mapping from motion states to optimal control actions within the policy network, and designs nonlinear constraints as the maximum reward intervals for pitch and roll to mitigate abnormal attitudes during maneuvers. Finally, a JSBSim simulation platform is established to train the network parameters, obtaining the optimal strategy for cruise control and achieving precise end-to-end control of the aircraft. Experimental results show that, compared to the cruise control method without dynamic constraints, the improved method reduces heading deviation by approximately 1.6° during ascent and 4.4° during descent, provides smoother pitch control, decreases steady-state altitude error by more than 1.5 m, and achieves higher accuracy in overlapping with the target trajectory during hexagonal trajectory tracking. Full article

The advent of quantum computing has introduced new opportunities for enhancing classical machine learning architectures. In this study, we propose a novel hybrid model, the HQDNN (Hybrid Quantum–Deep Neural Network), designed for the automatic detection of fake news. The model integrates classical fully connected neural layers with a parameterized quantum circuit, enabling the processing of textual data within both classical and quantum computational domains. To assess its effectiveness, we conducted experiments on the widely used LIAR dataset utilizing Term Frequency–Inverse Document Frequency (TF-IDF) features, as well as transformer-based DistilBERT embeddings. The experimental results demonstrate that the HQDNN achieves a superior recall performance—92.58% with TF-IDF and 94.40% with DistilBERT—surpassing traditional machine learning models such as Logistic Regression, Linear SVM, and Multilayer Perceptron. Additionally, we compare the HQDNN with SetFit, a recent CPU-efficient few-shot transformer model, and show that while SetFit achieves higher precision, the HQDNN significantly outperforms it in recall. Furthermore, an ablation experiment confirms the critical contribution of the quantum component, revealing a substantial drop in performance when the quantum layer is removed. These findings highlight the potential of hybrid quantum–classical models as effective and compact alternatives for high-sensitivity classification tasks, particularly in domains such as fake news detection. Full article

Heterogeneous information network (HIN) embedding transforms multi-type nodes into low-dimensional vectors to preserve structural and semantic information for downstream tasks. However, it struggles with multiplex networks where nodes connect via diverse semantic paths (metapaths). Information fusion mainly improves the quality of node embedding by fully exploiting the structure and hidden information within the network. Current metapath-based methods ignore information from intermediate nodes along paths, depend on manually defined metapaths, and overlook implicit relationships between nodes sharing similar attributes. Our objective is to develop an adaptive framework that overcomes limitations in existing metapath-based embedding (incomplete information aggregation, manual path dependency, and ignorance of latent semantics) to learn more discriminative embeddings. We propose an adaptive multi-hop neighbor information fusion model for heterogeneous network embedding (ANHNE), which: (1) autonomously extracts composite metapaths (weighted combinations of relations) via a multipath aggregation matrix to mine hierarchical semantics of varying lengths for task-specific scenarios; (2) projects heterogeneous nodes into a unified space and employs hierarchical attention to selectively fuse neighborhood features across metapath hierarchies; and (3) enhances semantics by identifying potential node correlations via cosine similarity to construct implicit connections, enriching network structure with latent information. Extensive experimental results on multiple datasets show that ANHNE achieves more precise embeddings than comparable baseline models. Full article

Multi-channel LED drivers are crucial for high-power lighting applications. Maintaining a constant average forward current is essential for stable LED luminous intensity, necessitating drivers capable of consistent current delivery across wide operating ranges. Meanwhile, achieving precise current sharing among channels without incurring high costs and system complexity is a significant challenge. Leveraging the constant-current characteristics of the LCL-T network, this paper presents a multi-channel DC/DC LED driver comprising a full-bridge inverter, a transformer, and a passive resonant rectifier. The driver generates a high-frequency AC bus with series-connected diode rectifiers, a structure that guarantees excellent current sharing among all output channels using only a single control loop. Fully considering the impact of higher harmonics, this paper derives an exact solution for the output current. A step-by-step parameter design methodology ensures soft switching and enhanced switch utilization. Finally, experimental verification was conducted using a prototype with five channels and 200 W, confirming the correctness and accuracy of the theoretical analysis. The experimental results showed that within a wide input voltage range of 380 V to 420 V, the driver was able to provide a stable current of 700 mA to each channel, and the system could achieve a peak efficiency of up to 94.4%. Full article

Automatic modulation classification (AMC) is a fundamental technique in wireless communication systems, as it enables the identification of modulation schemes at the receiver without prior knowledge, thereby promoting efficient spectrum utilization. Recent advancements in deep learning (DL) have significantly enhanced classification performance by enabling neural networks (NNs) to learn complex decision boundaries directly from raw signal data. However, many existing NN-based AMC methods employ deep or specialized network architectures, which, while effective, tend to involve substantial structural complexity. To address this issue, we present a simple NN architecture that utilizes features derived from Hankelized matrices to extract informative signal representations. In the proposed approach, received signals are first transformed into Hankelized matrices, from which informative features are extracted using singular value decomposition (SVD). These features are then fed into a compact, fully connected (FC) NN for modulation classification across a wide range of signal-to-noise ratio (SNR) levels. Despite its architectural simplicity, the proposed method achieves competitive performance, offering a practical and scalable solution for AMC tasks at the receiver in diverse wireless environments. Full article