Search Results (61)

Efficient spectrum utilization is critical for meeting the growing data demands of modern wireless communication networks. Automatic Modulation Classification (AMC) plays a key role in enhancing spectrum efficiency by accurately identifying modulation schemes in received signals—an essential capability for dynamic spectrum allocation and interference mitigation, particularly in cognitive radio (CR) systems. With the increasing deployment of smart edge devices, such as IoT nodes with limited computational and memory resources, there is a pressing need for lightweight AMC models that balance low complexity with high classification accuracy. In this study, we propose a low-complexity, lightweight deep learning (DL) AMC model optimized for resource-constrained edge devices. We introduce a dual-path deep residual shrinkage network (DP-DRSN) with garrote thresholding for effective signal denoising, and we designed a compact hybrid CNN-LSTM architecture comprising only 27,072 training parameters. The proposed model achieved average classification accuracies of 61.20%, 63.78%, and 62.13% on the RML2016.10a, RML2016.10b, and RML2018.01a datasets, respectively, demonstrating a strong balance between model efficiency and classification performance. These results highlight the model’s potential for enabling accurate and efficient AMC on edge devices with limited resources, despite not surpassing state-of-the-art accuracy owing to its deliberate emphasis on computational efficiency. Full article

Partial discharge (PD) is not only a critical indicator but also a major accelerating factor of insulation degradation in power transformers. Accurate identification of PD types is essential for diagnosing insulation defects and locating faults in transformers. Traditional methods based on phase-resolved partial discharge (PRPD) patterns typically rely on expert interpretation and manual feature extraction, which are increasingly being supplanted by Convolutional Neural Networks (CNNs) due to their ability to automatically extract features and deliver high classification accuracy. However, the inherent subtlety and diversity of characteristic differences among PRPD patterns, coupled with substantial noise resulting from complex electromagnetic interference, present significant hurdles to achieving accurate identification. This paper proposes a transformer partial discharge identification method based on Deep Residual Shrinkage Network (DRSN) to address these challenges. The method integrates dual-path feature extraction to capture both local and global features, incorporates a channel-domain adaptive soft-thresholding mechanism to effectively suppress noise interference, and utilizes the Focal Loss function to enhance the model’s attention to hard-to-classify samples. To validate the proposed method, given the scarcity of diverse real-world transformer PD data, an experimental platform was utilized to generate and collect PD data by artificially simulating various discharge defect models, including tip discharge, surface discharge, air-gap discharge and floating discharge. Data diversity was then enhanced through sample augmentation and noise simulation, to minimize the gap between experimental data and real-world on-site data. Experimental results demonstrate that the proposed method achieves superior partial discharge recognition accuracy and strong noise robustness on the experimental dataset. For future work, it is essential to collect more real transformer PD data to further validate and strengthen the model’s generalization capability, thereby ensuring its robust performance and applicability in practical scenarios. Full article

Mycelium-based composites (MBCs) have emerged as eco-friendly alternatives, utilizing fungal mycelium as a natural binder for agro-industrial residues. This study focuses on developing an MBC based on abundant waste in Colombia, pith Arboloco (A) (Montanoa quadrangularis), a plant endemic to the Colombian–Venezuelan Andes with outstanding insulating properties, and natural fiber of Kikuyu grass (G) (Cenchrus clandestinus), utilizing Ganoderma lucidum as an agent to form a mycelium network in the MBC. Three formulations, T (100% A), F1 (70% A/30% G), and F2 (30% A/70% G), were evaluated under two different Arboloco particle size ranges (1.0 to 5.6 mm) for their physical, mechanical, and thermal properties. The Arboloco particle sizes did not show significant differences in the MBC properties. An increase in Kikuyu grass proportion (F2) demonstrated superior density (60.4 ± 4.5 kg/m³), lower water absorption (56.6 ± 18.4%), and better compressive strength (0.1686 MPa at 50% deformation). Both mixing formulations (F1–F2) achieved promising average thermal conductivity and specific heat capacity values of 0.047 ± 0.002 W m⁻¹ K⁻¹ and 1714 ± 105 J kg⁻¹ K⁻¹, comparable to commercial insulation materials. However, significant shrinkage (up to 53.6%) and high water absorption limit their scalability for broader applications. These findings enhance the understanding of MBC’s potential for non-structural building materials made of regional lignocellulosic waste, promoting a circular economy in waste management for developing countries. Full article

Accurate and robust detection of fabric defects under noisy conditions is a major challenge in textile quality control systems. To address this issue, we introduce a new model called the Logarithmic Deep Residual Shrinkage Network (Log-DRSN), which integrates a deep attention module. Unlike standard residual shrinkage networks, the proposed Log-DRSN applies logarithmic transformation to improve resistance to noise, particularly in cases with subtle defect features. The model is trained and tested on both clean and artificially noised images to mimic real-world manufacturing conditions. The experimental results reveal that Log-DRSN achieves superior accuracy and robustness compared to the classical DRSN, with performance scores of 0.9917 on noiseless data and 0.9640 on noisy data, whereas the classical DRSN achieves 0.9686 and 0.9548, respectively. Despite its improved performance, the Log-DRSN introduces only a slight increase in computation time. These findings highlight the model’s potential for practical deployment in automated fabric defect inspection. Full article

Noises on the field can affect the electromechanical system characteristics in the bearing fault diagnostic process. This paper presents a deep learning-based fault-diagnosis model DRSN–GCE (Deep Relative Shrinkage Network with Gated Convolutions and Enhancements), which is designed to deal with noise and improve noise resistance. In the first step, the data are preprocessed by adding different noises with different ratios of signal to noise and different frequencies to the vibration signals. This simulates the field noise environments. The continuous wavelet transformation (CWT), which converts the time-series signal from one dimension to a time-frequency two-dimensional image, provides rich data input for the deep learning model. Secondly, a convolutional gated layer is added to the deep residual network (DRSN), which suppresses the noise interference. The residual connection structure has also been improved in order to improve the transfer of features. In complex signals, the Gated Convolutional Shrinkage Module is used to improve feature extraction and suppress noise. The experiments on the Case Western Reserve University bearing dataset show that the DRSN–GCE exhibits high diagnostic accuracy and strong noise immunity in various noise environments such as Gauss, Laplace, Salt-and-Pepper, and Poisson. DRSN–GCE is superior to other deep learning models in terms of noise suppression, fault detection accuracy, and rolling bearing fault diagnoses in noisy environments. Full article

In the operation process of modern industrial equipment, as the core transmission component, the operation state of the gearbox directly affects the overall performance and service life of the equipment. However, the current gear operation is still faced with problems such as poor monitoring, a single detection index, and low data utilization, which lead to incomplete evaluation results. In view of these challenges, this paper proposes a shape and property integrated gearbox monitoring system based on digital twin technology and artificial intelligence, which aims to realize real-time fault diagnosis, performance prediction, and the dynamic visualization of gear through virtual real mapping and data interaction, and lays the foundation for the follow-up predictive maintenance application. Taking the QPZZ-ii gearbox test bed as the physical entity, the research establishes a five-layer architecture: functional service layer, software support layer, model integration layer, data-driven layer, and digital twin layer, forming a closed-loop feedback mechanism. In terms of technical implementation, combined with HyperMesh 2023 refinement mesh generation, ABAQUS 2023 simulates the stress distribution of gear under thermal fluid solid coupling conditions, the Gaussian process regression (GPR) stress prediction model, and a fault diagnosis algorithm based on wavelet transform and the depth residual shrinkage network (DRSN), and analyzes the vibration signal and stress distribution of gear under normal, broken tooth, wear and pitting fault types. The experimental verification shows that the fault diagnosis accuracy of the system is more than 99%, the average value of the determination coefficient (R²) of the stress prediction model is 0.9339 (driving wheel) and 0.9497 (driven wheel), and supports the real-time display of three-dimensional cloud images. The advantage of the research lies in the interaction and visualization of fusion of multi-source data, but it is limited to the accuracy of finite element simulation and the difficulty of obtaining actual stress data. This achievement provides a new method for intelligent monitoring of industrial equipment and effectively promotes the application of digital twin technology in the field of predictive maintenance. Full article

Background/Objectives: Gamma knife radiosurgery (GKRS) is widely performed as an adjuvant management of patients with residual or recurrent pituitary adenoma (PA). However, the variability in the tumor volume response to GKRS emphasizes the need for reliable predictors of treatment outcomes. The application of radiomics, an analytical approach for quantitative imaging, remains unexplored in predicting treatment responses for PAs. This study aimed to pioneer the use of radiomic MRI analysis to predict the volumetric response of PA to GKRS. Methods: This retrospective observational cohort study involved 81 patients who underwent GKRS for PA. Pre-treatment 3-Tesla MRI scans were used to extract radiomic features capturing the intensity, shape, and texture of the tumors. Radiomic signatures were generated using the least absolute shrinkage and selection operator (LASSO) for feature selection, in conjunction with several classifiers: random forest, naïve Bayes, kNN, logistic regression, neural network, and SVM. Results: The models demonstrated predictive performance in the test folds, with AUC values ranging from 0.759 to 0.928 and R² values between 0.272 and 0.665. Single-sequence T1w, dual-sequence T1w + CE-T1w, and multi-modality including clinicopathological (CP) parameters (CP + T1w + CE-T1w) achieved rather similar prognostic performance in the test folds, with respective AUCs of 0.928, 0.899, and 0.909. All these radiomics models significantly outperformed a benchmark model involving only CP features (AUC = 0.846). Conclusions: This study represents a radiomic analysis focused on predicting the volume response of PAs to GKRS to facilitate treatment individualization. The developed MRI-based radiomics models exhibited superior classification performance compared with the benchmark model composed solely of standard clinicopathological parameters. Full article

In laser-directed energy deposition (LDED) additive manufacturing, stress-induced deformation and cracking often occur unexpectedly, and, once initiated, they are difficult to remedy. To address this issue, we previously proposed the Dynamic Counter Method (DCM), which monitors internal stress based on deposition layer shrinkage, enabling real-time stress monitoring without damaging the component. To validate this method, we used AlSi10Mg material, which has a low melting point and high reflectivity, and developed a high-precision segmentation network based on DeeplabV3+ to test its ability to measure shrinkage in high-exposure images. Using a real-time reconstruction model, stress calculations were performed with DCM and thermal–mechanical coupling simulations, and the results were validated through XRD residual stress testing to confirm DCM’s accuracy in calculating internal stress in aluminum alloys. The results show that the DeeplabV3+ segmentation network accurately extracted deposition-layer contours and shrinkage information. Furthermore, DCM and thermal–mechanical coupling simulations showed good consistency in residual stress distribution, with all results falling within the experimental error range. In terms of stress evolution trends, DCM was also effective in predicting stress variations. Based on these findings, two loading strategies were proposed, and, for the first time, DCM’s application in online stress monitoring of large LDED components was validated, offering potential solutions for stress monitoring in large-scale assemblies. Full article

With the growing global focus on sustainable development and climate change mitigation, promoting the low carbonization of energy systems has become an inevitable trend. Power load monitoring is crucial to achieving efficient power management, and load identification is the key link. The traditional load identification method has the problem of low accuracy. It is assumed that the technique of fusing harmonic features through color coding can improve the accuracy of load identification. In this paper, the load’s instantaneous reactive power, power factor and current sequence distribution characteristics are used as the mapping characteristics of the R, G and B channels of the two-dimensional V–I trajectory color image of the load using color coding technology. The harmonic amplitude characteristics are integrated to construct the mixed-color image of the load. The void residual shrinkage neural network is selected as the classification training model. The advantages and disadvantages of two residual shrinkage construction units, RSBU-CS and RSBU-CW, are analyzed. A single-load identification model with three RSBU-CWs is built. Different datasets verify the performance of the model. Compared with the test results of the ordinary color image dataset, the accuracy of the mixed-color image dataset is above 98%, and the accuracy of load identification is improved. Full article

Mycelium-based composites (MBCs) have a lot of potential as an alternative lightweight material due to their small environmental footprint and their biodegradability. The unique properties of cellulose-rich sewage sludge (SS) allow it to be used as a substrate for manufacturing MBCs. In order to examine the feasibility of creating MBCs using SS, this study used SS and bagasse as nutrient substrates and cultivated MBCs on ready-made mycelium (Pleurotus ostreatus). The physico-mechanical properties, morphological properties, and thermal stability of MBCs were tested and analyzed. The results show that both the bagasse and SS promoted fungal growth to create a dense mycelial network on day 10. Adding SS increased the density and compressive strength. The volume shrinkage of the MBCs first decreased and then increased. The optimal ratio of ready-made mycelium–sewage sludge was 2:1. The thermal conductivity of the bagasse-based MBCs was 0.12 Wm⁻¹K⁻¹ and that of the SS-based MBCs was 0.13 Wm⁻¹K⁻¹. These physico-mechanical characteristics satisfy the requirements of lightweight backfill materials for use in highways. Additionally, the SS supported more robust growth of hyphae and resulted in stronger MBCs. In comparison to bagasse, it also showed better thermal stability and a higher residual mass. It is feasible to produce MBCs with SS, and the biocomposite proposed in this study could be used as a lightweight backfill material of the type that is widely needed for use in highway construction and maintenance. Full article

Rolling bearing vibration signals in rotating machinery exhibit complex nonlinear and multi-scale features with redundant information interference. To address these challenges, this paper presents a multi-scale channel mixing convolutional network (MSCMN) and an enhanced deep residual shrinkage network (eDRSN) for improved feature learning and fault diagnosis accuracy in industrial settings. The MSCMN, applied in the initial and intermediate network layers, extracts multi-scale features from vibration signals, providing detailed information. By incorporating 1 × 1 convolutional blocks, the MSCMN mixes and reduces the feature dimensions, generating attention weights to suppress the interference from redundant information. Due to the high noise and nonlinear nature of industrial vibration signals, traditional linear layer representation is often inadequate. Thus, we propose an eDRSN with a Kolmogorov–Arnold Network–linear layer (KANLinear), which combines linear transformations with B-spline interpolation to capture both linear and nonlinear features, thereby enhancing threshold learning. Experiments on datasets from Case Western Reserve University and our laboratory validated the efficacy of the MSCMN-eDRSN model, which demonstrated improved diagnostic accuracy and robustness under noisy, real-world conditions. Full article

Due to the precision limitations of traditional fault location methods in identifying grounding faults in High-Voltage Direct Current (HVDC) transmission systems and considering the high occurrence probability of high-resistance grounding faults in practical engineering scenarios coupled with the sampling accuracy constraints of actual equipment, this article introduces a novel approach for high-resistance grounding fault location in HVDC transmission lines. This method integrates Variational Mode Decomposition (VMD) and Deep Residual Shrinkage Network (DRSN). Initially, VMD is employed to decompose double-ended high-resistance grounding fault signals, extracting the corresponding Intrinsic Mode Functions (IMF). These IMF signals are then preprocessed to construct the input data for the DRSN model. Upon training, the model outputs the precise fault location. To validate the effectiveness of the proposed method, a ±800 kV bipolar HVDC transmission system model is established using PSCAD/EMTDC version 4.6.2 software for simulating high-resistance grounding faults. The sampling accuracy of the model’s output signals is set to 10 kHz, aligning closely with actual engineering equipment specifications. Comprehensive simulation experiments and anti-interference analyses are conducted on the DRSN model. The results demonstrate that the fault location method based on the DRSN exhibits high accuracy in locating high-resistance grounding faults, with a maximum error of less than 1.5 km, even when considering factors such as engineering sampling frequency, fault types, and signal noise. Full article

Wind turbine gearbox fault diagnosis is critical to guarantee working efficiency and operational safety. However, the current diagnostic methods face enormous restrictions in handling nonlinear noise signals and intricate compound fault patterns. Herein, a compound fault diagnosis method based on modified signal quality coefficient (MSQC) and versatile residual shrinkage network (VRSN) is proposed to resolve these issues. In detail, the MSQC is designed to remove the noise components irrelevant to wind turbine operation status, and it has the ability to balance the denoised effect and signal fidelity. The VRSN is constructed for compound fault diagnosis, and it consists of two heterogeneous residual shrinkage networks. The former is designed to count the number of faults, and the latter is adopted to identify the single or compound fault pattern. Finally, a self-built wind turbine gearbox compound fault test rig is adopted to verify the proposed method’s effectiveness. The results demonstrate that the proposed method is competitive in terms of compound fault diagnosis accuracy. Full article

The robotic arm frequently performs grasping tasks in unstructured environments. However, due to the complex network architecture and constantly changing operational environments, balancing between grasping accuracy and speed poses significant challenges. Unlike fixed robotic arms, mobile robotic arms offer flexibility but suffer from relatively unstable bases, necessitating improvements in disturbance resistance for grasping tasks. To address these issues, this paper proposes a light-weight grasping pose estimation method called Grasp-DSC, specifically tailored for mobile robotic arms. This method integrates the deep residual shrinkage network and depthwise separable convolution. Attention mechanisms and soft thresholding are employed to improve the arm’s ability to filter out interference, while parallel convolutions enhance computational efficiency. These innovations collectively enhance the grasping decision accuracy and efficiency of mobile robotic arms in complex environments. Grasp-DSC is evaluated using the Cornell Grasp Dataset and Jacquard Grasp Dataset, achieving 96.6% accuracy and a speed of 14.4 ms on the former one. Finally, grasping experiments conducted on the MR2000-UR5 validate the practical applicability of Grasp-DSC in practical scenarios, achieving an average grasping success rate of 96%. Full article

Accurate photovoltaic (PV) power forecasting is crucial for effective smart grid management, given the intermittent nature of PV generation. To address these challenges, this paper proposes the Temporal Bottleneck-enhanced Bidirectional Temporal Convolutional Network with Multi-Head Attention and Autoregressive (TB-BTCGA) model. It introduces a temporal bottleneck structure and Deep Residual Shrinkage Network (DRSN) into the Temporal Convolutional Network (TCN), improving feature extraction and reducing redundancy. Additionally, the model transforms the traditional TCN into a bidirectional TCN (BiTCN), allowing it to capture both past and future dependencies while expanding the receptive field with fewer layers. The integration of an autoregressive (AR) model optimizes the linear extraction of features, while the inclusion of multi-head attention and the Bidirectional Gated Recurrent Unit (BiGRU) further strengthens the model’s ability to capture both short-term and long-term dependencies in the data. Experiments on complex datasets, including weather forecast data, station meteorological data, and power data, demonstrate that the proposed TB-BTCGA model outperforms several state-of-the-art deep learning models in prediction accuracy. Specifically, in single-step forecasting using data from three PV stations in Hebei, China, the model reduces Mean Absolute Error (MAE) by 38.53% and Root Mean Square Error (RMSE) by 33.12% and increases the coefficient of determination ($R^2$) by 7.01% compared to the baseline TCN model. Additionally, in multi-step forecasting, the model achieves a reduction of 54.26% in the best MAE and 52.64% in the best RMSE across various time horizons. These results underscore the TB-BTCGA model’s effectiveness and its strong potential for real-time photovoltaic power forecasting in smart grids. Full article