Search Results (39)

Soybean is an important food and oil crop, and rapid nondestructive identification of seed cultivars is crucial for seed purity inspection, varietal certification, breeding management and food-quality control. However, the global spectral profiles of individual soybean seeds from different cultivars are often highly similar, making it difficult for single-representation models to simultaneously capture spectral sequential dependency and inter-band relational structure. To address this issue, this study proposes a GADF–Mamba Fusion Network (GMFNet) for soybean seed hyperspectral classification. Hyperspectral images of 24,800 seeds from eight cultivars were acquired, and reflectance spectra in the range of 900–1700 nm were collected. After preprocessing, 200 effective bands were retained. The preprocessed one-dimensional spectral sequence was fed into a Mamba-based branch to model continuous wavelength dependency and global spectral evolution, while the same sequence was transformed into a GADF image, resized to 208 × 208, and input into a ResNet18-based structural branch to extract inter-band relational features. The two heterogeneous representations were then integrated through a weighted feature fusion module for final classification. Experimental results showed that Mamba achieved the best test accuracy (0.8721) among the raw spectral models, whereas ResNet18 achieved the best test accuracy (0.8737) among the GADF-based structural models. More importantly, the proposed weighted fusion strategy achieved the best overall performance, reaching validation and test accuracies of 0.9039 and 0.9011, respectively. These results demonstrate that spectral sequential information and GADF-based structural semantics are highly complementary. Overall, the proposed framework provides an effective hyperspectral solution for single-seed soybean cultivar identification and shows potential for non-destructive automated quality control in food-industry applications. Full article

Background: Pump unit vibration signals are typically characterized by non-stationarity and nonlinearity, which makes direct extraction of fault-related information from raw one-dimensional signals difficult, especially under small-sample conditions. Methods: To address this issue, a fault diagnosis method is proposed based on Harris Hawks Optimization for Variational Mode Decomposition, composite-index selection, Symmetric Dot Pattern representation, and deep fusion classification. First, the minimum envelope entropy is used as the fitness function, and HHO is employed to optimize VMD parameters for better decomposition. Then, a composite index CI is constructed to rank and select representative modes for reconstruction. The reconstructed modal signals are mapped into two-dimensional images by SDP, and the representation parameters are optimized using SSIM to enhance structural differences among fault states. Results: Experimental results on the bearing dataset and the pump unit fault dataset show that the proposed method outperforms GADF, GASF, and the original SDP method, achieving diagnosis accuracies of 92.69% and 88.94%, respectively. Conclusions: These results indicate that the proposed framework can effectively improve the clarity, stability, and separability of fault features for small-sample fault diagnosis of pump units. Full article

In-wheel motor bearings in electric vehicles operate in harsh environments where strong background noise often masks early fault features, limiting the accuracy of traditional diagnostic methods. This study proposes an intelligent fault diagnosis framework integrating improved Successive Variational Mode Decomposition (SVMD) with a ResNet–Kolmogorov–Arnold Network (ResNet-KAN). To enhance feature extraction, a multi-strategy Crested Porcupine Optimizer (CPO) is employed to adaptively optimise SVMD parameters. Subsequently, a Gramian angular difference field (GADF) reconstruction strategy transforms one-dimensional vibration signals into two-dimensional images to improve spatial distinguishability. Finally, a ResNet-KAN model, featuring a ReLU-based non-linear classification head, is developed to capture complex fault boundaries more effectively than traditional linear layers. Experimental results demonstrate that the CPO-SVMD method increases the kurtosis of extracted components by at least 25.6% compared to traditional optimisation methods. Furthermore, the ResNet-KAN model achieves an identification accuracy exceeding 98% on the in-wheel motor bearing dataset, outperforming 2DCNN, ResNet, and ViT models by at least 2%. This integrated approach provides a robust, high-precision solution for the intelligent condition monitoring and early warning of in-wheel motor drive systems under complex, high-noise operating conditions. Full article

To address the drawbacks of traditional convolutional neural network-based rolling bearing fault diagnosis techniques, including poor feature extraction, low diagnostic accuracy, and poor generalization capability, a dual-channel rolling bearing fault diagnosis model based on VMD-BiGRU and GADF-ResNet-CBAM was proposed. Variational mode decomposition (VMD) was used to first break down and reconstruct the original vibration signal. The rebuilt signal was then input into a bidirectional gated recurrent unit (BiGRU) network in order to extract temporal information. Second, the Gramian angular difference field (GADF) transformed the one-dimensional vibration signal into a two-dimensional picture. This image was then fed into a residual network that was merged with the convolutional block attention module (CBAM) in order to extract spatial characteristics. After concatenating and fusing the data from the two channels, Softmax was finally employed at the output layer to classify different types of faults. The Case Western Reserve University (CWRU) bearing dataset and a self-collected independent dataset from the Xinjiang University experimental rig were utilized for validation. The model achieved diagnosis accuracies of 99.39% and 99.58%, respectively. These results demonstrate the robustness and practical applicability of the proposed method on data acquired from distinct hardware sources and experimental environments, outperforming alternative approaches. Full article

To address the challenges of extracting mechanical fault features in Gas Insulated Switchgear (GIS) under complex operating conditions and the insufficient diagnostic accuracy associated with traditional one-dimensional time-series signals, this paper proposes a GIS fault-classification method based on composite dimensional upscaling images of vibration signals and the Vision Transformer (ViT) algorithm. This method first employs a sliding window slicing strategy to segment the raw long-sequence vibration signals into multiple overlapping time segments. Then, it utilizes the Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), and Markov Transition Field (MTF) to perform composite dimensional upscaling on these segmented signals, projecting the resulting features into a three-channel RGB composite two-dimensional image. Subsequently, the global self-attention mechanism of the Vision Transformer (ViT) processes the dimensionally upscaled data to achieve the fault classification of the GIS equipment. Experimental results demonstrate that, compared to single-channel ViT variants, Convolutional Neural Networks (CNN), and Residual Networks (ResNet), the proposed algorithm achieves the highest overall performance in the training set experiments, and the superiority of this method is verified through ablation studies and comparative experiments. Furthermore, the average accuracy of the algorithm on the testing set reaches 95.63%, proving the reliability and accuracy of the proposed method. Full article

Bearings serve as vital components in rotating machinery. Fault diagnosis of bearings constitutes an essential area within mechanical health monitoring. However, most existing methods rely solely on single-modal data or employ a single signal-to-image conversion technique, leading to insufficient information dimensionality and inadequate feature representation, which ultimately limits diagnostic accuracy. To address these challenges, this paper proposes a bearing fault diagnosis method (GADF-MTF-RP-VGG16, GMRVGG) based on tri-modal image feature fusion. Specifically, three image conversion techniques—Gramian Angular Difference Field (GADF), Markov Transition Field (MTF), and Recurrence Plot (RP)—are utilized to first convert 1D vibration signals into 2D images. Subsequently, shallow to deep features are extracted and fused through the VGG16 backbone network. Finally, fault diagnosis is achieved by integrating a fully connected classifier layer. The proposed methodology was comprehensively validated on both the Case Western Reserve University (CWRU) and the University of Ottawa datasets, which were augmented with severe 6 dB Gaussian white noise and 6 dB pink noise to simulate complex industrial environments. Under these harsh conditions, the proposed method achieved superior overall accuracies (up to 96.9% on the CWRU dataset and consistently 95.8% on the Ottawa dataset), significantly surpassing conventional single-modal approaches. This effectively addresses the limitations of insufficient feature dimensionality and inadequate representation, establishing a highly reliable and robust solution for intelligent bearing fault diagnosis. Full article

This paper presents a Load-Dependent Multimodal Vibration Signal Enhancement and Fusion Framework (LD-MVSEFF) for load-specific condition monitoring, building on the Customised Load Adaptive Framework (CLAF). The proposed approach enhances the classification of CLAF load-dependent subclasses, namely, Healthy, Mild, Moderate, and Severe, by integrating complementary information from raw vibration signals and encoded signal representations. Three input channels are employed, combining time–frequency domain features with Continuous Wavelet Transform (CWT) and Gramian Angular Difference Field (GADF) image encodings, with each channel independently trained and evaluated to identify its most effective classifiers. To address the reduced separability of the Mild and Moderate fault subclasses under varying load conditions, a weighted decision-fusion strategy is introduced, assigning classifier contributions according to their class-specific strengths. Experimental evaluation over five runs demonstrates high and stable performance, with the best configuration achieving an overall accuracy of 99.04% ± 0.22% and an average training time of 18 min and 30 s. The results confirm the effectiveness of LD-MVSEFF as a robust multimodal methodology for load-specific condition monitoring. Full article

Accurate assessment of hypoxia-related fetal risk during labour is essential for improving perinatal outcomes while avoiding unnecessary operative interventions. Although deep learning has shown promise for automated fetal risk assessment, most existing approaches rely on cardiotocography (CTG) alone; CTG interpretation is known to suffer from a high false-positive rate and may not fully reflect fetal status without complementary clinical context. To address this limitation, we propose MIRF-Net, a multimodal intrapartum fetal risk assessment framework that jointly models (i) CTG time-series signals, (ii) Gramian Angular Difference Field (GADF) images that encode global correlation structure of fetal heart rate, and (iii) structured maternal metadata. MIRF-Net combines a PatchTST encoder for CTG, a pretrained ResNet101 for GADF images, and an autoencoder for maternal metadata and then performs cross-modal interaction learning with a fusion Transformer for final risk prediction. Using 552 eligible CTG recordings from the public CTU-UHB intrapartum database, which were split into training, validation, and test sets at a ratio of 6:2:2, MIRF-Net outperforms representative baselines on the test set, achieving a quality index (QI) of 74.76%, AUC of 0.7413, and Brier score of 0.2537, indicating improved discrimination and better-calibrated risk probabilities. Ablation studies further confirm the complementary contributions of each modality and show that Transformer-based fusion yields the most consistent overall gains. These results suggest that MIRF-Net provides reliable decision support for intelligent intrapartum monitoring. Full article

Single-phase ground faults account for more than 80% of total faults in distribution networks. However, the introduction of distributed generation complicates power grid topology, leading to strong nonlinearity and non-stationarity in the zero-sequence current. This limits the accuracy of traditional faulted line selection methods. To address this problem, a CNN–ResNet-based method for faulted line selection for single-phase ground faults in distribution networks is proposed. Firstly, a 10 kV arc ground fault simulation test platform is built to analyze the nonlinear distortion characteristics of fault current. The WOA–VMD algorithm, optimized by permutation entropy, is used to denoise the zero-sequence current signal. The Gram Angular Difference Field (GADF) is then adopted to convert the one-dimensional signal into a two-dimensional image that retains its temporal characteristics. A hybrid deep learning model is constructed by fusing the one-dimensional time-domain features extracted by CNN and the two-dimensional time-frequency image features extracted by ResNet34. Matlab/Simulink simulations and physical experimental verification demonstrate that the proposed method achieves a training accuracy of over 97%, with zero misjudgments recorded in 15 arc grounding fault tests, representing a significant improvement in accuracy compared with existing diagnostic algorithms. It can adapt to complex scenarios such as high-resistance grounding and changes in neutral point grounding mode, effectively improving the accuracy and robustness of faulted line selection and providing technical support for the safe operation of distribution networks. Full article

Multi-point flexible die (MPFD) exhibits broad application potentials for efficient and controllable forming of curved sheets due to its rapid reconfigurability. Nevertheless, the relatively poor surface accuracy and geometrical accuracy of the fiber-reinforced composite components formed by MPFDs limit the widespread application of this technology. In this study, a novel gas-assisted diaphragm forming (GADF) process based on MPFDs for curved basalt fiber/epoxy resin composite sheets was proposed. The precise control of temperature, pressure and MPFD configuration in the process was realized and verified. The effects of different process parameter configurations on dimple defects and geometrical accuracy were analyzed, and the mechanism of defect generation was investigated. A response surface-based forming accuracy prediction model was developed to analyze the influence of component structural parameters on geometrical accuracy. Based on the predictive model, compensation reconfiguration of MPFDs was carried out to achieve high-accuracy sheet forming. Results demonstrated that increasing pressure exacerbated the dimple while reducing shape accuracy. A moderate temperature (120 °C) was proved optimal for component forming, as both excessively low and high temperatures aggravated dimple and induced geometrical errors. Increasing interpolator thickness effectively reduced dimple defects, but excessive thickness adversely affected component geometrical accuracy. Considering both dimple suppression and geometrical accuracy, the optimal process parameters were determined to be 5 kPa, 120 °C, and 2 mm of interpolator thickness. Through MPFD modification based on the response surface model, the geometrical accuracy of the formed components was improved by 38.85%, achieving high-quality forming of the curved composite sheets. Full article

In the context of bearing anomaly detection, challenges such as imbalanced sample distribution and complex operational conditions present significant difficulties for data-driven deep learning models. These issues often result in overfitting and high false positive rates in complex real-world scenarios. This paper proposes a strategy that leverages multimodal fusion and Self-Adversarial Training (SAT) to construct and train a deep learning model. First, the one-dimensional bearing vibration time-series data are converted into Gramian Angular Difference Field (GADF) images, and multimodal feature fusion is performed with the original time-series data to capture richer spatiotemporal correlation features. Second, a composite data augmentation strategy combining time-domain and image-domain transformations is employed to effectively expand the anomaly samples, mitigating data scarcity and class imbalance. Finally, the SAT mechanism is introduced, where adversarial samples are generated within the fused feature space to compel the model to learn more generalized and robust feature representations, thereby significantly enhancing its performance in realistic and noisy environments. Experimental results demonstrate that the proposed method outperforms traditional baseline models across key metrics such as accuracy, precision, recall, and F1-score in abnormal bearing anomaly detection. It exhibits exceptional robustness against rail-specific interferences, offering a specialized solution strictly tailored for the unique, high-noise operational environments of intelligent railway maintenance. Full article

As a core component of the gearbox, bearings are crucial to the stability and reliability of the transmission system. However, dynamic variations in operating conditions and complex noise interference present limitations for existing fault diagnosis methods in processing non-stationary signals and capturing complex features. To address the aforementioned challenges, this paper proposes a bearing fault diagnosis method based on a multi-feature fusion dual-channel CNN-Transformer-CAM framework. The model cross-fuses the two-dimensional feature images from Gramian Angular Difference Field (GADF) and Generalized S Transform (GST), preserving complete time–frequency domain information. First, a dual-channel parallel convolutional structure is employed to separately sample the generalized S-transform (GST) maps and the Gramian Angular Difference Field (GADF) maps, enriching fault information from different dimensions and effectively enhancing the model’s feature extraction capability. Subsequently, a Transformer structure is introduced at the backend of the convolutional neural network to strengthen the representation and analysis of complex time–frequency features. Finally, a cross-attention mechanism is applied to dynamically adjust features from the two channels, achieving adaptive weighted fusion. Test results demonstrate that under conditions of noise interference, limited samples, and multiple operating states, the proposed method can effectively achieve the accurate assessment of bearing fault conditions. Full article

Accurate estimation of the state of health (SOH) of lithium-ion batteries is crucial for the safe operation of electric vehicles and energy storage systems. However, most existing methods rely on complete charging curves or manual feature engineering, making them difficult to adapt to practical scenarios where only limited charging segments are available. To fully exploit degradation information from limited charging data, this paper proposes a dual-modal mixture of Kolmogorov–Arnold network (DM-MoKAN) for lithium-ion battery SOH estimation using only early-stage constant-current charging voltage data. The proposed method incorporates three synergistic modules: an image branch, a sequence branch, and a dual-modal fusion regression module. The image branch converts one-dimensional voltage sequences into two-dimensional Gramian Angular Difference Field (GADF) images and extracts spatial degradation features through a lightweight network integrating Ghost convolution and efficient channel attention (ECA). The sequence branch employs a patch-based Transformer encoder to directly model local patterns and long-range dependencies in the raw voltage sequence. The dual-modal fusion module concatenates features from both branches and feeds them into a MoKAN regression head composed of multiple KAN experts and a gating network for adaptive nonlinear mapping to SOH. Experimental results demonstrate that DM-MoKAN outperforms various baseline methods on both Oxford and NASA datasets, achieving average RMSE/MAE of 0.28%/0.19% and 0.89%/0.71%, respectively. Ablation experiments further verify the effective contributions of the dual-modal fusion strategy, ECA attention mechanism, and MoKAN regression head to estimation performance improvement. Full article

Accurate evaluation of demand response (DR) potential at the individual user level is critical for the effective implementation and optimization of demand response programs. However, existing data-driven methods often suffer from insufficient feature representation, limited characterization of load profile dynamics, and ineffective fusion of heterogeneous features, leading to suboptimal evaluation performance. To address these challenges, this paper proposes a novel demand response potential evaluation method based on multivariate heterogeneous features and a Stacking-based ensemble mechanism. First, multidimensional indicator features are extracted from historical electricity consumption data and external factors (e.g., weather, time-of-use pricing), capturing load shape, variability, and correlation characteristics. Second, to enrich the information space and preserve temporal dynamics, typical daily load profiles are transformed into two-dimensional image features using the Gramian Angular Difference Field (GADF), the Markov Transition Field (MTF), and an Improved Recurrence Plot (IRP), which are then fused into a single RGB image. Third, a differentiated modeling strategy is adopted: scalar indicator features are processed by classical machine learning models (Support Vector Machine, Random Forest, XGBoost), while image features are fed into a deep convolutional neural network (SE-ResNet-20). Finally, a Stacking ensemble learning framework is employed to intelligently integrate the outputs of base learners, with a Decision Tree as the meta-learner, thereby enhancing overall evaluation accuracy and robustness. Experimental results on a real-world dataset demonstrate that the proposed method achieves superior performance compared to individual models and conventional fusion approaches, effectively leveraging both structured indicators and unstructured image representations for high-precision demand response potential evaluation. Full article

Malicious traffic detection in IoT environments faces dual challenges: limited labeled data and heterogeneous, complex traffic patterns. To address these limitations, we propose a malicious traffic detection framework, GADF-SRGA, which integrates Gram-angle-difference-field (GADF) imaging with meta-learning. The framework first encodes raw IoT traffic into images via GADF, preserving the spatiotemporal characteristics of malicious traffic. It then employs meta-learning on these encoded images to enable feature-space learning under scarce data. In the inner loop, Sample-Relation Guided Attention (SRGA) leverages class-label-guided supervision graphs to learn sample similarity, improving intra-class compactness and inter-class separability in the feature space. Comprehensive evaluations on public IoT intrusion datasets Malicious_TLS and ToN_IoT demonstrate the framework’s superiority and robustness, particularly under class-imbalanced conditions, over baseline methods. Full article