Search Results (37)

Recent advancements in deep learning have spurred significant research interest in fault diagnosis for elevator systems. However, conventional approaches typically require substantial labeled datasets that are often impractical to obtain in real-world industrial environments. This limitation poses a fundamental challenge for developing robust diagnostic models capable of performing reliably under data-scarce conditions. To address this critical gap, we propose MetaRes-DMT-AS (Meta-ResNet with Dynamic Meta-Training and Adaptive Scheduling), a novel meta-learning framework for few-shot fault diagnosis. Our methodology employs Gramian Angular Fields to transform 1D raw sensor data into 2D image representations, followed by episodic task construction through stochastic sampling. During meta-training, the system acquires transferable prior knowledge through optimized parameter initialization, while an adaptive scheduling module dynamically configures support/query sets. Subsequent regularization via prototype networks ensures stable feature extraction. Comprehensive validation using the Case Western Reserve University bearing dataset and proprietary elevator acceleration data demonstrates the framework’s superiority: MetaRes-DMT-AS achieves state-of-the-art few-shot classification performance, surpassing benchmark models by 0.94–1.78% in overall accuracy. For critical few-shot fault categories—particularly emergency stops and severe vibrations—the method delivers significant accuracy improvements of 3–16% and 17–29%, respectively. Full article

This study proposes MSFF-Net, a lightweight deep learning framework for bearing fault diagnosis based on frequency-domain multi-sensor fusion. The vibration and acoustic signals are initially converted into the frequency domain using the fast Fourier transform (FFT), enabling the extraction of temporally invariant spectral features. These features are processed by a compact one-dimensional convolutional neural network, where modality-specific representations are fused at the feature level to capture complementary fault-related information. The proposed method demonstrates robust and superior performance under both full and scarce data conditions, as verified through experiments on a publicly available dataset. Experimental results on a publicly available dataset indicate that the proposed model attains an average accuracy of 99.73%, outperforming state-of-the-art (SOTA) methods in both accuracy and stability. With only about 70.3% of the parameters of the SOTA model, it offers faster inference and reduced computational cost. Ablation studies confirm that multi-sensor fusion improves all classification metrics over single-sensor setups. Under few-shot conditions with 20 samples per class, the model retains 94.69% accuracy, highlighting its strong generalization in data-limited scenarios. The results validate the effectiveness, computational efficiency, and practical applicability of the model for deployment in data-constrained industrial environments. Full article

To address the challenges associated with insufficient bearing fault feature extraction under small sample sizes and variable working conditions, as well as the limited generalization capability of diagnostic models, this paper proposes an intelligent diagnostic method that integrates an Artificial Lemming Algorithm (ALA) for feature mode decomposition parameter optimization (ALA-FMD) with a multi-scale coordinate attention relation network (MSCA-RN). This method employs the ALA to dynamically adjust the model’s parameter optimization strategy, effectively balancing global exploration and local exploitation capabilities. It optimizes the parameters of the feature mode decomposition algorithm to enhance decomposition accuracy, utilizing the minimum residual index as the selection criterion for optimal modal components, thereby facilitating signal denoising. Subsequently, the optimal components are transformed into time–frequency maps. Through a multi-scale coordinate attention (MSCA) mechanism, the global energy distribution and local fault texture features of the bearing vibration signal’s time–frequency maps are captured in parallel. Coupled with the nonlinear metric capability of a relation network (RN), this method enables the discrimination of fault sample similarity, thus improving model robustness under small sample conditions. Experimental results obtained from the Case Western Reserve University (CWRU) bearing dataset under small sample sizes and variable operating conditions demonstrate that the proposed method achieves a maximum accuracy of 96.8%, with an average accuracy of 92.83% on the test data. These results indicate the method’s superior classification capability in the domain of bearing fault diagnosis. Full article

Reliable fault diagnosis in aero-engine bearing systems is essential for maintaining process stability and safety. However, acquiring fault samples in aerospace applications is costly and difficult, resulting in severely limited data for model training. Traditional methods often perform poorly under such constraints, lacking the ability to extract discriminative features or effectively correlate observed signal changes with underlying process faults. To address this challenge, this study presents a process-oriented framework—WSET-CNN-OOA-LSSVM—designed for effective fault recognition in small-sample scenarios. The framework begins with Wavelet Synchroextracting Transform (WSET), enhancing time–frequency resolution and capturing energy-concentrated fault signatures that reflect degradation along the process timeline. A tailored CNN with asymmetric pooling and progressive dropout preserves temporal dynamics while preventing overfitting. To compensate for limited labels, confidence-based pseudo-labeling is employed, guided by Mahalanobis distance and adaptive thresholds to ensure reliability. Classification is finalized using an Osprey Optimization Algorithm (OOA)-enhanced Least Squares SVM, which adapts decision boundaries to reflect subtle process state transitions. Validated on both test bench and real aero-engine data, the framework achieves 93.4% accuracy with only five fault samples per class and 100% in full-scale scenarios, outperforming eight existing methods. Therefore, the experimental results confirm that the proposed framework can effectively overcome the data scarcity challenge in aerospace bearing fault diagnosis, demonstrating its practical viability for few-shot learning applications in industrial condition monitoring. Full article

To address the limited generalization capability of data-driven fault diagnosis models caused by scarce gearbox fault samples in engineering practice, this paper proposes a hierarchical attention-guided data–knowledge dual-driven fusion network for intelligent fault diagnosis under few-shot conditions. Distinct from traditional single data-driven paradigms, this method breaks through the constraints of limited samples through the synergy of prior knowledge and monitoring data. First, domain knowledge of gearbox fault diagnosis is utilized to construct prior features of monitoring data. Second, a deep convolutional neural network is designed to hierarchically capture abstract features from monitoring data. Subsequently, a hierarchical attention module is proposed to realize adaptive fusion of prior features and abstract features through hierarchical feature weight allocation, generating highly discriminative fused features for accurate gearbox fault identification. Experimental results on gearbox fault data demonstrate that the proposed method achieves 0.9880 recognition accuracy with less than 10% of the training samples, significantly outperforming purely data-driven models such as MGAN and CNET, thus verifying its superior generalization ability to train despite data scarcity. This approach establishes a novel data–knowledge dual-driven fusion paradigm for intelligent fault diagnosis of mechanical equipment under few-shot conditions. Full article

Fault diagnosis in large-scale systems presents significant challenges due to the complexity and high dimensionality of data, as well as the scarcity of labeled fault data, which are hard to obtain during the practical operation process. This paper proposes a novel approach, called Multi-Variable Meta-Transformer (MVMT), to tackle these challenges. In order to deal with the multi-variable time series data, we modify the Transformer model, which is the currently most popular model on feature extraction of time series. To enable the Transformer model to simultaneously receive continuous and state inputs, we introduced feature layers before the encoder to better integrate the characteristics of both continuous and state variables. Then, we adopt the modified model as the base model for meta-learning—more specifically, the Model-Agnostic Meta-Learning (MAML) strategy. The proposed method leverages the power of Transformers for handling multi-variable time series data and employs meta-learning to enable few-shot learning capabilities. The case studies conducted on the Tennessee Eastman Process database and a Power-Supply System database demonstrate the exceptional performance of fault diagnosis in few-shot scenarios, whether based on continuous-only data or a combination of continuous and state variables. Full article

The diagnostic performance of deep learning models is heavily reliant on large volumes of labeled training data. However, in practical applications, bearing fault samples are relatively scarce, and the availability of samples for effective model training is even more limited, leading to the suboptimal performance of traditional deep learning methods in bearing fault diagnosis. To address the issue of poor performance in few-shot bearing fault diagnosis, a novel Adaptive Deep Siamese Residual Network (ADSRN) is proposed in this study. Frequency-domain information is extracted using the Fourier Transform, and training samples are randomly paired according to the matching criteria defined by the Siamese network to augment the dataset. A novel Dynamic Time Warping (DTW) technique is applied to non-linearly adjust the sequence information, allowing for the precise calculation of the optimal match between two sequences by detecting subtle differences. Additionally, inspired by the concept of dynamic soft-hard threshold matching in unsupervised learning, an innovative strategy for dynamically adjusting the adaptive threshold has been developed to enhance the generalization capability of the proposed ADSRN. Multiple few-shot fault diagnosis experiments were conducted on two bearing datasets and compared with several state-of-the-art methods. Through rigorous experimental evaluations, the effectiveness and superiority of the proposed ADSRN, as well as the advantages of DTW, were validated. Full article

The fuel system serves as the core component of marine diesel engines, and timely and effective fault diagnosis is the prerequisite for the safe navigation of ships. To address the challenge of current data-driven fault-diagnosis-based methods, which have difficulty in feature extraction and low accuracy under small samples, this paper proposes a fault diagnosis method based on digital twin (DT), Siamese Vision Transformer (SViT), and K-Nearest Neighbor (KNN). Firstly, a diesel engine DT model is constructed by integrating the mathematical, mechanism, and three-dimensional physical models of the Medium-speed diesel engines of 6L21/31 Marine, completing the mapping from physical entity to virtual entity. Fault simulation calculations are performed using the DT model to obtain different types of fault data. Then, a feature extraction network combining Siamese networks with Vision Transformer (ViT) is proposed for the simulated samples. An improved KNN classifier based on the attention mechanism is added to the network to enhance the classification efficiency of the model. Meanwhile, a Weighted-Similarity loss function is designed using similarity labels and penalty coefficients, enhancing the model’s ability to discriminate between similar sample pairs. Finally, the proposed method is validated using a simulation dataset. Experimental results indicate that the proposed method achieves average accuracies of 97.22%, 98.21%, and 99.13% for training sets with 10, 20, and 30 samples per class, respectively, which can accurately classify the fault of marine fuel systems under small samples and has promising potential for applications. Full article

To tackle the issue of limited sample data in small sample fault diagnosis for rolling bearings using deep learning, we propose a fault diagnosis method that integrates a KANs-CNN network. Initially, the raw vibration signals are converted into two-dimensional time-frequency images via a continuous wavelet transform. Next, Using CNN combined with KANs for feature extraction, the nonlinear activation of KANs helps extract deep and complex features from the data. After the output of CNN-KANs, an FAN network module is added. The FAN module can employ various feature aggregation strategies, such as weighted averaging, max pooling, addition aggregation, etc., to combine information from multiple feature levels. To further tackle the small sample issue, data generation is performed on the original data through diffusion networks under conditions of fewer samples for bearings and tools, thereby increasing the sample size of the dataset and enhancing fault diagnosis accuracy. Experimental results demonstrate that, under small sample conditions, this method achieves higher accuracy compared to other approaches. Full article

In few-shot fault diagnosis tasks in which the effective label samples are scarce, the existing semi-supervised learning (SSL)-based methods have obtained impressive results. However, in industry, some low-quality label samples are hidden in the collected dataset, which can cause a serious shift in model training and lead to the performance of SSL-based method degradation. To address this issue, the latest prototypical network-based SSL techniques are studied. However, most prototypical network-based scenarios consider that each sample has the same contribution to the class prototype, which ignores the impact of individual differences. This article proposes a new SSL method based on pseudo-labeling multi-screening for few-shot bearing fault diagnosis. In the proposed work, a pseudo-labeling multi-screening strategy is explored to accurately screen the pseudo-labeling for improving the generalization ability of the prototypical network. In addition, the AdaBoost adaptation-based weighted technique is employed to obtain accurate class prototypes by clustering multiple samples, improving the performance that deteriorated by low-quality samples. Specifically, the squeeze and excitation block technique is used to enhance the useful feature information and suppress non-useful feature information for extracting accuracy features. Finally, three well-known bearing datasets are selected to verify the effectiveness of the proposed method. The experiments illustrated that our method can receive better performance than that of the state-of-the-art methods. Full article

This study proposes an improved few-shot learning model of the Siamese network residual Visual Geometry Group (VGG). This model combined with time–frequency domain transformation techniques effectively enhances the performance of across-load fault diagnosis for induction motors with limited data conditions. The proposed residual VGG-based Siamese network consists of two primary components: the feature extraction network, which is the residual VGG, and the merged similarity layer. First, the residual VGG architecture utilizes residual learning to boost learning efficiency and mitigate the degradation problem typically associated with deep neural networks. The employment of smaller convolutional kernels substantially reduces the number of model parameters, expedites model convergence, and curtails overfitting. Second, the merged similarity layer incorporates multiple distance metrics for similarity measurement to enhance classification performance. For cross-domain fault diagnosis in induction motors, we developed experimental models representing four common types of faults. We measured the vibration signals from both healthy and faulty models under varying loads. We then applied the proposed model to evaluate and compare its effectiveness in cross-domain fault diagnosis against conventional AI models. Experimental results indicate that when the imbalance ratio reached 20:1, the average accuracy of the proposed residual VGG-based Siamese network for fault diagnosis across different loads was 98%, closely matching the accuracy of balanced and sufficient datasets, and significantly surpassing the diagnostic performance of other models. Full article

With the continuous development of actuator technology, the Electro-Mechanical Actuator (EMA) is gradually becoming the first choice in the aviation field. Permanent Magnet Synchronous Motor (PMSM) is one of the core components of EMA, and its healthy state determines the working performance of EMA. In this paper, the interturn short-circuit fault of PMSM is taken as the typical fault, and a new fault diagnosis framework is proposed based on a wide-kernel convolutional neural network (WCNN) and few-shot learning. Firstly, the wide convolution kernel is added as the first layer to extract short-time features while automatically learning deeply oriented features oriented to diagnosis and removing useless features. Then, the twin neural network is introduced to establish a wide kernel convolutional neural network, which can also achieve good diagnostic results under a few-shot learning framework. The effectiveness of the proposed method is verified by the general data set. The results show that the accuracy of few-shot learning is 9% higher than that of WCNN when the fault data are small. Finally, a fault test platform was built for EMA to collect three-phase current data under different fault states, and the collected data were used to complete the fault diagnosis of PMSM. With limited data, the accuracy of few-shot learning increased by 8% on average compared with WCNN, which has good engineering value. Full article

Achieving accurate equipment fault diagnosis relies heavily on the availability of extensive, high-quality training data, which can be difficult to obtain, particularly for models with new equipment. The challenge is further compounded by the need to protect sensitive data during the training process. This paper introduces a pioneering federated transfer fault diagnosis method that integrates Variational Auto-Encoding (VAE) for robust feature extraction with few-shot learning capabilities. The proposed method adeptly navigates the complexities of data privacy, diverse working conditions, and the cross-equipment transfer of diagnostic models. By harnessing the generative power of VAE, our approach extracts pivotal features from signals, effectively curbing overfitting during training, a common issue when dealing with limited fault samples. We construct a federated learning model comprising an encoder, variational feature generator, decoder, classifier, and discriminator, fortified with an advanced training strategy that refines federated averaging and incorporates regularization when handling non-independent data distributions. This strategy ensures the privacy of data while enhancing the model’s ability to discern subtleties in fault signatures across different equipment and operational settings. Our experiments, conducted across various working conditions and devices, demonstrate that our method significantly outperforms traditional federated learning techniques in terms of fault recognition accuracy. The innovative integration of VAE within a federated learning framework not only bolsters the model’s adaptability and accuracy but also upholds stringent data privacy standards. Full article

This study introduces the Adversarial Task Augmented Sequential Meta-Learning (ATASML) framework, designed to enhance fault diagnosis in industrial processes. ATASML integrates adversarial learning with sequential task learning to improve the model’s adaptability and robustness, facilitating precise fault identification under varied conditions. Key to ATASML’s approach is its novel use of adversarial examples and data-augmentation techniques, including noise injection and temporal warping, which extend the model’s exposure to diverse operational scenarios and fault manifestations. This enriched training environment significantly boosts the model’s ability to generalize from limited data, a critical advantage in industrial applications where anomaly patterns frequently vary. The framework’s performance was rigorously evaluated on two benchmark datasets: the Tennessee Eastman Process (TEP) and the Skoltech Anomaly Benchmark (SKAB), which are representative of complex industrial systems. The results indicate that ATASML outperforms conventional meta-learning models, particularly in scenarios characterized by few-shot learning requirements. Notably, ATASML demonstrated superior accuracy and F1 scores, validating its effectiveness in enhancing fault-diagnosis capabilities. Furthermore, ATASML’s strategic incorporation of task sequencing and adversarial tasks optimizes the training process, which not only refines learning outcomes but also improves computational efficiency. This study confirms the utility of the ATASML framework in significantly enhancing the accuracy and reliability of fault-diagnosis systems under diverse and challenging conditions prevalent in industrial processes. Full article

Ensuring the safe and stable operation of high-speed trains necessitates real-time monitoring and diagnostics of their suspension systems. While machine learning technology is widely employed for industrial equipment fault diagnosis, its effective application relies on the availability of a large dataset with annotated fault data for model training. However, in practice, the availability of informational data samples is often insufficient, with most of them being unlabeled. The challenge arises when traditional machine learning methods encounter a scarcity of training data, leading to overfitting due to limited information. To address this issue, this paper proposes a novel few-shot learning method for high-speed train fault diagnosis, incorporating sensor-perturbation injection and meta-confidence learning to improve detection accuracy. Experimental results demonstrate the superior performance of the proposed method, which introduces perturbations, compared to existing methods. The impact of perturbation effects and class numbers on fault detection is analyzed, confirming the effectiveness of our learning strategy. Full article