Jul 2026· Engineering Research Express· Vol 8, pp. 155523· 0 citations· 35 references
Physics
TL;DR
MAML is enhanced by incorporating a Sample Relationship Exploration module that learns intra-class similarity to improve class separability and replaces the fixed inner-loop update scheme in MAML with a trapezoidal gradient descent scheduler that adapts the number of inner-loop update steps across training.
Abstract
Deep learning has led to notable progress in fault diagnosis. However, many approaches still rely on the availability of abundant fault samples and on matched train-test distributions, conditions that are seldom met in industrial settings. Although model-agnostic meta-learning (MAML) enables rapid adaptation with limited labeled data, existing fault diagnosis methods based on MAML generally lack explicit modeling of intra-class sample relationships and commonly employ a fixed inner-loop update strategy. To address cross-domain diagnosis with few samples, we enhance MAML by incorporating a Sample Relationship Exploration module that learns intra-class similarity to improve class separability. Specifically, the Sample-level Attention component discovers task-specific affinities, the Explicit Guidance component provides an ideal affinity map to supervise similarity learning, and the Channel-wise Adaptive Fusion component fuses original features with category-aggregated features for classification. In addition, to mitigate overfitting, we replace the fixed inner-loop update scheme in MAML with a trapezoidal gradient descent scheduler that adapts the number of inner-loop update steps across training. Experiments on public and self-collected datasets under multiple cross-domain few-shot settings demonstrate that the proposed method achieves better or more stable diagnostic performance in most evaluated settings.
Deep learning achieves widespread success in fault diagnosis. However, its effectiveness is hindered in practical industrial environments due to complex operating conditions and data sparsity. This article proposes a novel model-agnostic meta-learning framework based on a selective state space model (MAML-S3M) to address the challenge of cross-condition few-shot bearing fault diagnosis. The framework introduces three core innovations. First, the continuously stacked selective state space module dynamically adjusts its receptive field, enabling precise feature extraction under varying conditions. Second, the channel attention mechanism is combined with the selective state space model to capture multi-scale features, thereby enhancing the feature extraction capability of the model. Third, the introduction of an explicit information discarding strategy during meta-task optimization refines the meta-learning process, thereby yielding optimal parameters. Extensive experiments on bearing datasets across different operating conditions demonstrate that the proposed MAML-S3M achieves superior diagnostic accuracy, with an average accuracy of 99.18% across six cross-condition tasks, outperforming state-of-the-art methods such as generalized model-agnostic meta-learning (GMAML) by at least 1.1%. The improvements are particularly helpful in scenarios with complex operating conditions and scarce samples, maintaining over 94% accuracy even in the challenging “10-way 1-shot” setting. We have made the paper’s results publicly available on GitHub. The link is as follows:
https://github.com/12138250/MAML-S3M
.
Siyu Liu, Nan Wang, Xueyi Li et al.· Structural Health Monitoring· 0 citations
The inconsistency in bearing data distributions under diverse conditions often affects the representations of the faulty data and leads to indistinct decision boundaries and even negative transfer resulted from overlapping class distributions, greatly limiting the accuracy of the diagnosis model. To cope with the challenge, a pseudo-label-guided dual-supervised alignment (PDSA) method is developed for bearing fault diagnosis across diverse operating scenarios in this paper. To address the fixed alignment strategy issue, an adaptive distribution alignment layer is incorporated to ResNet18 to achieve dynamic data distribution alignment under varying condition, To enhance classification performances, a dual-supervised mechanism, comprising shallow-layer supervised contrastive learning is introduced through target domain pseudo-labels in target domain and deep-layer regularization class consistency. Experiments on two publicly available bearing datasets demonstrated this model realizes refined class-level alignment, strengthens fault states representation, and shows notable superiority in both accuracy and robustness.
In bearing fault diagnosis, small-sample and class-imbalance issues are highly challenging, severely constraining the generalization capability of deep learning models in practical applications. Generalized stochastic resonance (GSR) has demonstrated significant potential in enhancing weak fault features, yet its effective integration with data-driven deep learning frameworks remains insufficiently explored. To address these challenges, this study proposes a GSR-enhanced robust sparse feature learning framework (RGSRNet). Specifically, the framework derives stability control conditions for the GSR system, integrates a lightweight dual-branch architecture to fuse global convolutional features and local sparse spectral peak features, and constructs a Wasserstein-regularized dual-loss function to optimize the feature space distribution. Experimental results confirm that RGSRNet consistently outperforms mainstream baseline methods under few-shot, class-imbalanced, noisy, and variablespeed conditions. In particular, RGSRNet achieves 99.92% accuracy with only 9 training samples per class and maintains a 99.89% F1-score under an extreme 1:10 class-imbalance scenario. It also achieves over 94% accuracy under strong noise interference and retains more than 91% accuracy under variable-speed conditions with only 3% training data. In addition, RGSRNet requires only 0.2423 M parameters and 9.0516 M FLOPs, indicating its potential for lightweight industrial deployment.
Xue Wen, Xuerui Zhang, Lifeng Lin et al.· Measurement science and tech...· 0 citations
Meta-learning-based few-shot cross-domain fault diagnosis faces significant challenges in cross-speed scenarios due to extreme data scarcity and speed-induced distribution shifts. To address these issues, this paper proposes a dual-modal feature pyramid fusion and distribution alignment (DA) framework. First, a hybrid feature extraction architecture integrating time–frequency images and temporal signals is designed. By combining Swin Transformer, multi-scale ResNet, and GRU, a pyramidal tri-branch network extracts complementary features from time and frequency domains, significantly enhancing the characterization of complex fault patterns. Building on this, pseudo-feature prototypes are constructed via a dual-clustering strategy using Isolation Forest and K-means. It constrains distribution shifts and thereby improves cross-domain generalization. Finally, a training protocol combining meta-learning pre-training and targeted fine-tuning is developed to address extreme data scarcity. It introduces KL-divergence loss to supervise feature alignment, thereby stabilizing fine-tuning and suppressing overfitting. Single-shot cross-domain experiments on CWRU, JNU, and PU datasets achieve diagnostic accuracies of 99.32%, 95.52%, and 93.62%, respectively, demonstrating superior performance over state-of-the-art meta-learning methods.
Danfeng Chen, Tengyun Li, C. Yuan et al.· Measurement science and tech...· 0 citations
A novel and robust Source-Free Domain Adaptation (SFDA) framework equipped with post-hoc explainability for bearing fault diagnosis is proposed, and a post-hoc visualization mechanism is incorporated to explain the model's decision-making process, enhancing the transparency and credibility of the diagnosis for practical industrial deployment.
chenghao yan, Dongsheng Liu, Tong Wu et al.· Measurement science and tech...· 0 citations
In response to the challenges of sparsely labeled samples and complex feature distribution in bearing fault diagnosis, a novel few-shot bearing fault diagnosis method is proposed by integrating spatio-temporal feature fusion with a Siamese-based learnable metric framework. A multi-scale residual network-Convolutional Block Attention Module network is adopted as the feature extractor, where channel-space attention enhancement and multi-level feature fusion are employed to improve the effective representation of spatio-temporal information in the time–frequency diagrams. To overcome the limitations of fixed distance metrics, a Siamese learnable metric network is introduced to enable adaptive similarity modeling. In addition, a local-global dual-branch fusion mechanism is designed to combine local similarity metrics with global context matching information, thereby enhancing the model’s robustness and generalization performance in few-shot scenarios. Experiments conducted on the Case Western Reserve University and Intelligent Maintenance Systems bearing datasets show that the proposed method achieves superior diagnostic performance under few-shot conditions compared with other approaches. The visualization results using confusion matrices and t-SNE further confirm the method’s strong interclass separability.
Xinyu Mo, Deqiang He, Haiyuan Zhao et al.· Engineering Research Express· 0 citations