Search Results (552)

Rolling bearing fault diagnosis is critical for ensuring the safe operation of rotating machinery, yet it faces significant challenges in noisy environments. This paper proposes BEAM-Net (Bearing-spectrum Enhanced by EMA and Weighted Spectral Convolution Network), a lightweight neural network designed specifically for rolling bearing fault diagnosis under strong noise conditions. Classifying bearing faults from vibration signals remains a challenging task when fault-related features are subtle and easily submerged in background noise—especially when the signal-to-noise ratio (SNR) is low. To address this challenge, BEAM-Net adopts a “decompose–enhance–extract” pipeline: first, an Exponential-Moving-Average Trend Decomposer (ETD) splits the frequency spectrum into a smooth trend component and a fault-sensitive residual component; second, a Spectral Residual Gate (SRG) reinjects detailed residual information through a learnable gating mechanism; finally, a Weighted Spectrum Convolution block (WSC) incorporates a symmetric center-emphasizing prior into the convolution kernel, ensuring that local spectral patterns receive greater attention. Experimental results on the Case Western Reserve University (CWRU) bearing dataset at SNR = −6 dB show that BEAM-Net achieves an F1 score of 99.15% with only 2835 parameters. Compared to the single-convolution baseline, this represents a $+0.78\%$ improvement in F1 score and a 50% reduction in the false positive rate (from $0.18\%$ to $0.09\%$). Cross-dataset validation on the Paderborn University (PU) and Machinery Failure Prevention Technology (MFPT) datasets further confirms the generalizability of the proposed approach, achieving F1 scores of 97.83% and 98.46%, respectively, under comparable noise conditions. These findings demonstrate that combining explicit spectral trend modeling with weighted convolution is not only effective but also parameter-efficient, making it well-suited for noise-robust rolling bearing fault diagnosis. It should be noted that the current method is primarily validated on spectral-analysis-based diagnostics of rolling bearings; its applicability to other vibroacoustic diagnostic modalities (e.g., tapping or nonlinear vibration excitation) and to quantitative defect severity grading remains to be investigated in future work. Full article

To address the frequent occurrence of multiple fault types, the difficulty of feature extraction, and the susceptibility to noise interference in rolling bearings under complex operating conditions, this paper proposes a fault diagnosis method based on an improved one-dimensional convolutional neural network (1DCNN) integrated with a Transformer architecture. This approach leverages the 1DCNN to efficiently extract local impact and energy features from vibration signals, while the improved Transformer enables global modeling of long-range temporal dependencies, thereby significantly enhancing the recognition accuracy for multi-class fault signals and the generalization capability of the model. Experimental data are sourced from the Case Western Reserve University bearing fault dataset, with multi-channel vibration signals subjected to preprocessing and balanced sampling, and various types of simulated noise systematically introduced to comprehensively verify the noise robustness of the proposed model. Experimental results on the public dataset demonstrate that the improved 1DCNN-Transformer model achieves a classification accuracy of 99.43%, markedly outperforming traditional methods such as ANN, CNN, LeNet, and SVM. Further t-SNE visualizations and confusion matrix analyses reveal the method’s superior feature discrimination and high-precision performance across multiple fault categories. Tests under strong noise conditions further indicate that the model exhibits high robustness and excellent potential for engineering applications. In summary, the proposed method provides an efficient and reliable solution for intelligent fault diagnosis of rolling bearings in complex environments and lays a solid foundation for future model development and industrial deployment. Full article

To address the problem of fault-related structures and noise disturbances in rolling bearing vibration signals being highly coupled in the original one-dimensional signal domain under severe noise conditions, in this study, we propose a Phase-space adaptive Expert Denoising Network (PaEDNet), a robust fault diagnosis framework that integrates representation construction, adaptive restoration, and condition discrimination. Unlike existing methods that mainly enhance network modelling directly in the original signal domain, the proposed framework first constructs a spatially organised two-dimensional similarity representation through phase-space reconstruction, which further unfolds fault-related dynamic structures from temporal entanglement and provides a more suitable preliminary representation domain for subsequent restoration. On this basis, a CoPaMoE-augmented adaptive denoising module is introduced into the representation domain to improve structural restoration capability under heterogeneous noise and different local patterns. DenseNet is then employed for fault classification, thereby forming an integrated fault diagnosis framework combining representation reconstruction, noise restoration, and condition discrimination. The resulting pipeline performs end-to-end diagnosis from raw vibration signals to fault labels at inference, while training is conducted in a stage-wise manner. Experimental results derived using the two public datasets, CWRU and PU, show that the proposed method consistently outperforms multiple comparative models under different signal-to-noise ratio conditions and maintains stronger robustness in low-SNR scenarios. Under the −6 dB condition, PaEDNet achieves classification accuracies of 93.98% and 90.45% on the two datasets, respectively. Further ablation studies and expert-routing analysis demonstrate that the combination of structured representation construction and adaptive expert restoration jointly enables the improved performance of the model. In this study, we provide a new modelling perspective for the fault diagnosis of vibration signals in complex noisy environments. Full article

Rolling bearing fault diagnosis is essential for ensuring the safety and reliability of rotating machinery. Although deep learning-based methods have achieved promising performance, they usually require sufficient labeled data, which is difficult to obtain in practical industrial scenarios where fault samples are scarce and data sharing across sites is restricted by privacy and confidentiality constraints. Federated learning enables collaborative model training without transmitting raw data, but existing federated fault diagnosis methods often degrade under few-shot conditions. Moreover, current federated meta-learning approaches mainly focus on model-level adaptation and lack explicit class-level representation alignment, leading to prototype drift across heterogeneous operating conditions. To address these challenges, this paper proposes ProtoFed, a prototype-enhanced federated meta-learning framework for few-shot rolling bearing fault diagnosis. ProtoFed converts raw vibration signals into time–frequency representations using continuous wavelet transform and performs local episodic learning with prototypical networks. A Global Prototype Calibration mechanism aggregates local class prototypes into stable global prototypes with exponential moving average smoothing, while a Prototype-Distance Aware Aggregation strategy adaptively adjusts client aggregation weights according to local–global prototype divergence. Experiments on the CWRU and Paderborn University bearing datasets under non-IID 5-shot and 10-shot settings show that ProtoFed consistently outperforms standard federated learning, prototype-based federated learning, and federated meta-learning baselines. Under the 5-shot setting, ProtoFed achieves 95.63% and 91.35% accuracy on CWRU and PU, respectively, approaching centralized few-shot upper-bound performance while preserving the federated training paradigm. Full article

The health status of rolling bearings is critical to the normal operation of rotating machinery. To effectively extract vibration signal features and accurately identify different fault types, a novel method based on enhanced composite multi-scale slope entropy (ECMSE) and a honey badger algorithm-optimized kernel extreme learning machine (HBA–KELM) is proposed. Specifically, ECMSE integrates high-order differences into the composite multi-scale framework to capture high-frequency information while preserving low-frequency characteristics, thereby enhancing the discriminability of time-series representations. Meanwhile, an average coarse-graining strategy is incorporated to achieve a more comprehensive characterization of the signals. The extracted features are then input into the HBA–KELM classifier for fault identification. Experiments conducted on two public and private rolling bearing datasets demonstrate that our method achieves superior performance in distinguishing different fault types and damage levels compared with several existing approaches. Full article

This paper proposes a novel rolling bearing fault diagnosis method to address the difficulty of accurate feature extraction from nonlinear and non-stationary vibration signals. First, a Levy–Cauchy Optimized Sparrow Search Algorithm (LOCSSA) is developed to optimize the two core parameters (decomposition level and penalty factor) of Variational Mode Decomposition (VMD), and the optimized VMD is used to decompose raw vibration signals to obtain optimal intrinsic mode functions (IMFs). Second, the extracted IMF features are fed into a convolutional neural network (CNN) for local pattern extraction, followed by a bidirectional long short-term memory (BiLSTM) network to model temporal dependencies, with the final fault classification completed via a fully connected layer. Comparative experiments and ablation studies with five benchmark models are conducted to verify the effectiveness of the proposed framework. The results show that the proposed method achieves 96.33% accuracy, 96.67% recall, and 96.54% F1-score, outperforming all benchmark models. Ablation analysis confirms that both LOCSSA-optimized VMD and BiLSTM contribute significantly to performance improvement (p < 0.05), validating the rationality of the proposed method. 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

In the field of industrial equipment condition monitoring, accurate rolling bearing fault diagnosis is critical yet challenging due to high-dimensional vibration signals and complex operating conditions. Traditional machine learning methods often struggle with insufficient feature separability and sensitivity to model parameters, leading to fluctuating diagnostic accuracy. To address these challenges, this study introduces the whale optimization algorithm-guided symplectic geometry matrix machine (WOA-SGMM) and proposes the application of the whale optimization algorithm (WOA) to optimize the symplectic geometry matrix machine (SGMM), forming a WOA-SGMM diagnostic framework. (1) The symplectic geometry spectral transformation (SGST) effectively converts high-dimensional vibration signals into low-dimensional feature matrices while preserving intrinsic geometric and topological structures, enhancing noise robustness. (2) Leveraging WOA, we adaptively search for the optimal hyperparameters of the proposed SGMM, specifically addressing the limitations of traditional SMM, to mitigate the risk of overfitting. (3) Experimental validation on three benchmark datasets demonstrates that WOA-SGMM achieves superior multi-class fault diagnosis accuracy (up to 100%) under varying operating conditions. Compared to traditional methods, the proposed WOA-SGMM demonstrates improved classification accuracy and enhanced robustness against noise interference in the tested experimental scenarios, highlighting its potential for real-world industrial applications. Full article

To address the issue of low recognition accuracy caused by incomplete information, a CNN-based fault diagnosis method for rolling bearings using multi-source resonance sparse component feature fusion (RSSD-P) is proposed in this paper, which effectively resolves the problem of impact features being masked. In noise-contaminated environments, bearing vibration signals exhibit nonstationarity, obscuring fault characteristics. To overcome this, resonance sparse decomposition was employed to extract impact-related fault features. Furthermore, to fully utilize multi-sensor information and enhance fault representation, a symmetric dot pattern (SDP) method was introduced to fuse multi-source fault impact features, achieving effective integration of impact characteristics from multi-source vibration signals. A CNN-based approach incorporating multi-source resonance sparse component and SDP feature fusion was developed, and a bearing fault diagnosis model was established accordingly. Experimental results demonstrate that the proposed method achieves a fault recognition accuracy of 98.63% under varying operating conditions. Compared with other bearing fault diagnosis methods, the recognition precision is improved by 8.49%~17.8%, confirming its superior performance. Full article

Intelligent fault diagnosis of rolling bearings under high-noise industrial conditions remains a significant challenge. Traditional attention-based deep learning models often rely on global average pooling, which may inadvertently smooth out high-frequency transient impulses essential for fault identification, potentially leading to degraded performance in low signal-to-noise ratio (SNR) environments. To address this, we propose a Multi-Scale Temporal Coordinate Attention Network (MS-TCANet). The framework introduces a Peak-Aware Coordinate Attention (PACA) mechanism that combines max-pooling and average-pooling along directional coordinates. This dual-pooling design aims to better preserve transient impact features while maintaining a stable global representation, thereby mitigating the feature over-smoothing issue common in conventional attention modules. Additionally, an asymmetric multi-scale convolution block is incorporated to capture both short-term impacts and long-range periodic signatures. Experiments on three benchmark datasets (CWRU, Paderborn University, and XJTU-SY) indicate that the proposed MS-TCANet achieves favorable diagnostic accuracy compared to several representative and advanced methods, particularly under severe noise conditions (e.g., −10 dB SNR). t-SNE and Grad-CAM visualizations further suggest that the model can capture fault-related signatures more reliably than standard architectures in noisy environments. Full article

As a critical element of the drive motor, rolling bearings are susceptible to localized defects under complex loads and varying operating conditions. Such defects typically generate periodic transient shocks, which reflect bearing fault features. However, the accurate extraction of fault-related transient components becomes challenging due to strong noise influence. To address this issue, a concave sparsity-assisted generalized dispersive mode decomposition (CSA-GDMD) method is developed to enhance fault feature extraction. This method introduces a non-convex sparse model based on generalized mini-max concave (GMC) regularization to preprocess the vibration signal. The GMC penalty effectively suppresses background noise while better preserving the amplitude characteristics of the transient shocks. Subsequently, GDMD is applied to progressively extract transient shock components from the preprocessed signal and reconstruct the signal, resulting in more prominent fault-related transient components. The simulation results show that CSA-GDMD significantly improves the signal-to-noise ratio (SNR), from 6.5905 dB at −15 dB to 9.5122 dB at 5 dB, and reduces the root mean square error (RMSE) from 0.0280 to 0.0196. Consequently, the fault feature frequencies can be identified more clearly in the envelope spectrum, further confirming the accurate fault diagnosis capability of the proposed method for bearing faults under strong noise conditions. Full article

Rolling bearings represent one of the core functional components of rotating machinery, with their application scope continuously expanding into various sectors of modern social production and life, making the research on fault diagnosis of rolling bearings increasingly significant. Effective vibration feature extraction and improved classification models are crucial to achieving accurate and automated fault diagnosis of rolling bearings. We proposed a fault diagnosis approach based on a Swin Transformer–Improved ResNet module. In the data preprocessing stage, the frequency-domain features and time-domain multi-scale features of fault signals are extracted using FFT and VMD methods, respectively. And then, dual-channel feature extraction is employed using both the Swin Transformer and Improved ResNet module, followed by feature fusion through an ECA module, thereby enhancing diagnostic accuracy and model robustness. The architecture retains shallow-level feature details while incorporating global contextual information, improving feature representation and detection precision. Extensive experiments were carried out on data collected from an SEU bearing dataset, including model validation, ablation analysis, comparative evaluation and simulated noise testing. An average classification accuracy of 99.41% was achieved by the proposed model under uniform experimental conditions, as evidenced by the obtained experimental results, outperforming other models by at least 0.96%. Even under severe noise interference with a signal-to-noise ratio of −4, the model maintained an average accuracy of 91.92%, exceeding that of noise-resistant counterparts. Moreover, generalization experiments on the CWRU bearing dataset under varying load conditions revealed an average fault diagnosis accuracy exceeding 98%, confirming the model’s strong cross-domain adaptability. Full article

Single-sensor-based fault diagnosis of rolling bearings often suffers from noise sensitivity, installation-dependent performance, and incomplete fault characterization. To address these limitations, this paper proposes a multi-task multimodal attention graph convolutional network (MTMAGNet) that integrates acoustic and vibration signals for bearing fault diagnosis. First, one-dimensional convolutional neural networks are used to extract modality-specific features. These features are then fused through a multi-modal attention mechanism to exploit the complementary information contained in the two signal sources. Based on the fused representations, a dynamic k-nearest neighbor graph is constructed to model relationships among samples, and a graph convolutional network is employed to learn discriminative structural features. Moreover, a multi-task learning scheme is introduced, in which fault classification serves as the primary task and modal classification is used as an auxiliary task to enhance feature learning and improve model generalization. Experimental results on a self-built acoustic–vibration test bench collected under three rotational speeds (1800 rpm, 2400 rpm, and 3000 rpm) demonstrate that the proposed method achieves high diagnostic accuracy and strong generalization performance under different fault conditions. Full article

Early bearing faults are often difficult to identify because their characteristic components are weak and easily masked by strong interference. To improve weak-fault feature extraction, this paper proposes a particle-swarm-optimization-based FitzHugh–Nagumo stochastic resonance (FHN-SR) method for bearing vibration signals. The raw signal is first preprocessed by de-meaning, Hilbert envelope demodulation, and standardization to construct a stable stochastic resonance (SR) input. Then, the key model parameters are adaptively optimized by maximizing the output signal-to-noise ratio around the target fault characteristic frequency. To evaluate the proposed method comprehensively, comparisons are carried out with classical SR, underdamped bistable stochastic resonance (UBSR), and a Fast-Kurtogram-based envelope-analysis scheme. Experimental validation is performed on three fault cases, including the rolling element fault case from the Case Western Reserve University (CWRU) dataset and the inner-race and outer-race fault cases from the Machinery Comprehensive Diagnostics Simulator (MCDS) platform. The results show that FHN-SR produces a clearer concentration of fault-related energy and achieves a higher output signal-to-noise ratio (SNR) than the compared methods in most cases. In particular, under degraded noise conditions, FHN-SR maintains more stable enhancement performance, indicating stronger robustness to interference. These results demonstrate that the proposed method provides an effective approach for extracting weak bearing fault features under complex noise backgrounds. Full article

To address the challenges of sensor installation limitations, severe background noise interference, and low model deployment efficiency in rolling bearing fault diagnosis in industrial environments, this paper proposes a lightweight, progressive fusion and knowledge-distillation diagnostic framework that integrates vibration and sound signals. First, considering the differences in physical characteristics between vibration and sound signals, a feature-extraction network for heterogeneous modality perception is designed: the vibration branch employs a large-kernel one-dimensional convolutional neural network, while the sound branch uses a small-kernel stacked two-dimensional convolutional neural network, with depthwise separable convolutions introduced for lightweight modification. Second, an attention-gated progressive feedback fusion strategy is proposed. Learnable gating units are used to filter the confidence of the fused features, feeding them back to the original input as residuals, effectively suppressing noise accumulation and improving fusion quality. Finally, a cross-architecture knowledge-distillation scheme is constructed, transferring the fault feature-discrimination ability from the deep heterogeneous fusion network (teacher network GAF-Net) to the lightweight LightGBM (student network Distilled-LGB). Combined with a normal sample statistical feature alignment mechanism, the student model can independently complete end-to-end fault diagnosis only with online-extractable handcrafted features, achieving microsecond-level pure model inference speed while ensuring diagnostic accuracy, fully meeting industrial edge deployment requirements. Experiments on a self-built industrial dataset and the public UOEMD-VAFCVS dataset show that GAF-Net achieves 97.89% (A → B) and 96.72% (15 Hz → 30 Hz) accuracy. Distilled-LGB achieves 21 ms inference time and 4.2 MB model size with <1% accuracy loss, demonstrating noise robustness, cross-condition generalization, and edge deployment capability. Full article