Search Results (717)

Fault diagnosis methods for rolling bearings are frequently constrained to the automatic extraction of single-scale features from raw vibration signals, overlooking crucial information embedded in data of other scales, which often results in unsatisfactory diagnostic outcomes. To address this, a lightweight neural network model is proposed, which incorporates an improved Inception module for multi-scale convolutional feature fusion. Initially, this model generates time–frequency maps via continuous wavelet transform. Subsequently, it integrates the Fused-conv and Mbconv modules from the EfficientNet V2 architecture with the Inception module to conduct multi-scale convolution on input features, thereby comprehensively capturing fault information of the bearing. Additionally, it substitutes traditional convolution with depthwise separable convolution to minimize training parameters and introduces an attention mechanism to emphasize significant features while diminishing less relevant ones, thereby enhancing the accuracy of bearing fault diagnosis. Experimental findings indicate that the proposed fault diagnosis model achieves an accuracy of 100% under single-load conditions and 96.2% under variable-load conditions, demonstrating its applicability across diverse data sets and robust generalization capabilities. Full article

This paper addresses the issue of fault diagnosis in high-speed train bogie bearings under complex working conditions and proposes a method for calculating the characteristic frequency of rolling bearings that takes into account the influence of radial clearance. By establishing a five-degree-of-freedom nonlinear dynamic model, this study systematically analyzes the modulation mechanism of radial clearance on the fault characteristic frequency of bearings and verifies the findings through an experimental platform. The results indicate that an increase in clearance not only leads to significant attenuation of the fault characteristic frequency amplitude, but also induces sideband modulation effects, thereby interfering with fault diagnosis accuracy. The experimental data show good agreement with the theoretical calculations, verifying the effectiveness of the proposed method. Specifically, the nonlinear stiffness-based characteristic frequency calculation reduces the prediction error from 6.9–5.7% under traditional theory to 2.3–3.4% across a wide range of rotational speeds. Meanwhile, the clearance-induced amplitude attenuation predicted by the model is also experimentally confirmed, with measured amplitude reductions of 35–42% as clearance increases from 0.2 μm to 0.5 μm. These results not only demonstrate the accuracy and engineering applicability of the method but also provide new theoretical foundations and practical references for health monitoring and early fault diagnosis of high-speed train bearings. Full article

Predictive maintenance in industrial machinery relies on the timely detection of component faults to prevent costly downtime. Rolling bearings, being critical elements, are particularly prone to defects such as outer race faults and ball spin defects, which manifest as characteristic vibration patterns. In this study, we introduce a novel bearing vibration dataset collected on a testbench under both constant and variable rotational speeds (0–5000 rpm), encompassing healthy and faulty conditions. The dataset was used for failure classification and further enriched through feature engineering, resulting in input features that include raw acceleration, signal envelopes, and time- and frequency-domain statistical descriptors, which capture fault-specific signatures. To quantify prediction uncertainty, two different approaches are applied, providing confidence measures alongside model outputs. Our results demonstrate the progressive improvement of classification accuracy from 87.2% using only raw acceleration data to 99.3% with a CNN-BiLSTM (Convolutional Neural Network–Bidirectional Long Short-Term Memory) ensemble and advanced features. Shapley Additive Explanation (SHAP)-based explainability further validates the relevance of frequency-domain features for distinguishing fault types. The proposed methodology offers a robust and interpretable framework for industrial fault diagnosis, capable of handling both stationary and non-stationary operating conditions. Full article

This manuscript presents a study on the application of blind source separation (BSS) techniques, specifically the Independent Component Analysis (ICA) method, for the detection and identification of localized faults in rolling element bearings. Bearing defects typically manifest as distinct harmonics of characteristic fault frequencies, accompanied by modulation sidebands in the vibration signal spectrum. The accurate extraction and isolation of these components are crucial for reliable fault diagnosis, particularly in systems where multiple vibration sources overlap. In this work, a linear ICA algorithm was applied to vibration signals acquired from a simplified rotating machinery setup designed to emulate common bearing fault conditions. The study investigates the effect of ICA-based signal decomposition on the statistical distribution of selected diagnostic indicators and evaluates its ability to enhance the detectability of fault-related components. The experimental results demonstrate that the application of ICA significantly improves the separation of vibration sources, leading to a more distinct representation of fault signatures. The findings confirm the effectiveness of blind source separation methods in vibration-based diagnostics and highlight the potential of ICA as a complementary tool for improving the accuracy and robustness of bearing fault detection systems in rotating machinery. Full article

Feature Mode Decomposition (FMD) can effectively extract bearing fault features even in the case of strong interference noise by means of adaptive finite impulse response filter banks along with correlated kurtosis. Nevertheless, the filter length L and the number of decomposition modes K need to be predefined carefully in a manual way. Otherwise, mismatched parameters could lead to redundant components or even missed detection of fault information. To mitigate the reliance on manual parameter setting, recent studies have introduced optimization algorithms such as the Whale Optimization Algorithm and the Crested Porcupine Optimizer to find the optimal parameters for FMD. However, such methods usually suffer from the dilemma of easily premature convergence in global search and long-time consumption in local fine adjustment, rendering them with difficulty in meeting the requirements of real-time and accurate diagnosis. Therefore, this paper proposes an improved Crested Porcupine Optimizer (ICPO), which can dynamically balance global and local exploitation. Furthermore, a bearing fault diagnosis method named ICPO-FMD is constructed, wherein the optimal parameter combination of K and L obtained using ICPO is provided to FMD in order to decompose bearing signals into a family of intrinsic mode functions (IMFs), and then fault sensitive components are extracted according to the proposed IMF screening principle. Finally, a reconstructed signal is obtained, followed by an envelope demodulation analysis. Experiments on simulation, laboratory and engineering signals demonstrate that the proposed method can accurately extract the fault characteristic frequency and its harmonics. Full article

A bearing intelligent fault diagnosis method based on an improved convolutional neural network is proposed to address the problems of high noise, difficult fault feature extraction, and low fault diagnosis recognition rate in rolling bearing vibration signals collected under complex working conditions. Firstly, in the data preprocessing stage, the wavelet denoising method is used to preprocess the data to obtain higher-quality signals. Then, the convolutional neural network LeNet-5 model was improved through batch normalization, Dropout, and L2 regularization methods. The wavelet denoised signal was input into the optimized LeNet-5 model to achieve more accurate fault diagnosis output for rolling bearings. Finally, to demonstrate the generalization ability of the model, this paper uses publicly available rolling bearing data from a university as the dataset and conducts experimental verification of the model using MATLAB-2023b software under different loads. The experimental results show that the improved neural network model has a fault diagnosis accuracy of 94.27%%, which is 17.84% higher than the traditional neural network model in terms of accuracy. Moreover, for different loads, the improved convolutional neural network model still maintains good fault diagnosis accuracy. Full article

Rolling bearings are critical components in rotating machinery, and their performance degrades over time due to operational wear, which may compromise the safety and efficiency of mechanical systems. Therefore, accurate and timely fault diagnosis of rolling bearings is crucial. In real-world industrial environments, such diagnosis remains challenging owing to complex and varying operating conditions. Conventional single-modality deep learning methods often face limitations and fail to satisfy practical demands. To overcome these challenges, this paper proposes a novel fault diagnosis approach based on a Parallel Heterogeneous Deep Network (PHDN-FD). First, the original vibration signals are segmented according to signal pattern similarity. The continuous wavelet transform (CWT) using the Morse wavelet is applied to convert one-dimensional signal segments into two-dimensional time–frequency representations. Subsequently, each signal segment and its corresponding time–frequency representation are paired to form input data for a dual-branch parallel network. One branch, based on the ConvNeXt architecture, extracts spatial features from the time–frequency images, while the other branch employs a 1D-ResNet to capture temporal features from the raw signal segments. The features from both branches are then fused and fed into a three-layer feedforward neural network for final fault classification. Experimental results on the Case Western Reserve University (CWRU) bearing dataset and Korean Academy of Science and Technology (KAIST) bearing datasets show that the proposed method achieves high diagnostic accuracy even under adverse conditions, such as noise interference, limited training samples, and variable load levels. Moreover, the model exhibits strong cross-load transferability. By effectively integrating multimodal feature representations, the PHDN-FD framework improves both diagnostic accuracy and model robustness in complex operational scenarios, establishing a solid foundation for industrial deployment and demonstrating significant potential for practical applications. Full article

In modern industrial systems, diagnosing faults in the rolling bearings of high-speed rotating machinery remains a considerable challenge due to the scarcity of reliable fault samples and the inherent complexity of the diagnostic task. To address these limitations, this study proposes an intelligent fault diagnosis method that integrates a generative adversarial network (GAN) with a convolutional block attention mechanism (CBAM). First, after systematically evaluating several loss functions, a GAN based on the Wasserstein distance loss function was adopted to generate high-quality synthetic vibration samples, effectively augmenting the training dataset. Subsequently, a convolutional block attention mechanism-based convolutional neural network (CBAM-CNN) was developed. By adaptively emphasizing salient features through channel and spatial attention modules, the CBAM-CNN improves feature extraction and recognition performance under limited-sample conditions. To validate the proposed method, an experimental platform for a two-speed automatic mechanical transmission (2AMT) of an electric vehicle was developed, and diagnostic experiments were conducted on high-speed rolling bearings. The results indicate that, under extremely severe conditions, CBAM-CNN achieves a diagnostic accuracy of 96.64% for rolling element pitting defects using only 10% of authentic samples. For composite faults, the model maintains an average accuracy above 97%, demonstrating strong generalization capability. These findings provide solid theoretical support and practical engineering guidance for rolling bearing fault diagnosis under few-shot conditions. Full article

Rolling element bearing failure in industrial robots can cause system downtime, high repair costs, and significant economic losses. Traditional fault diagnosis methods assume that training and testing data follow the same distribution, requiring extensive historical data, which is often impractical in dynamic operational environments. Digital twin and transfer learning technologies offer a new approach for intelligent fault diagnosis, addressing these limitations. This paper combines model knowledge and data-driven approaches using digital twin and transfer learning for bearing fault diagnosis. First, a dynamic twin model of the bearing is developed using MATLAB/Simulink (R2018a), simulating fault data under various operating conditions that are difficult to obtain in real-world scenarios. A multi-level construal neural network algorithm is then proposed to minimize cumulative errors in data preprocessing. The digital twin technology generates a balanced dataset for pre-training the model, which is subsequently applied to real-time fault diagnosis in industrial robot bearings via transfer learning, bridging the gap between virtual and physical entities. Experimental results demonstrate the feasibility of the method, with a diagnostic accuracy of 96.95%, marking a 15% improvement over traditional convolutional neural network methods without digital twin enhancement. Full article

Fault diagnosis of rolling bearings is crucial for ensuring the maintenance and reliability of industrial equipment. Existing cross-domain diagnostic methods often struggle to maintain performance under evolving mechanical and environmental conditions. This limits their robustness in long-term real-world deployments. To address this, we propose a novel online learning framework that continuously adapts to distribution shifts using streaming vibration data. Specifically, the proposed framework consists of three core modules: the Feature Extraction Module that encodes raw vibration signals into low-dimensional latent representations; the Fault Sample Generation Module (comprising a generator and discriminator network) that synthesizes diverse fault samples conditioned on normal-condition data; and the Classification Module that incrementally adapts by leveraging both synthesized fault samples and streaming normal-condition signals. We also introduce a domain-shift indicator ScoreODS to dynamically control the transition between prediction and fine-tuning phases during deployment. Extensive experiments on both public and private datasets demonstrate that the proposed method outperforms the most competitive method, achieving about a 4% improvement in diagnostic accuracy and enhanced robustness for long-term fault diagnosis under distribution shifts. Full article

Aiming to tackle the challenge of feature transfer in cross-domain fault diagnosis for rolling bearings, an enhanced domain adaptation-based intelligent fault diagnosis method is proposed. This method systematically combines multi-layer multi-core MMD with adversarial domain classification. Specifically, we will extend alignment to multiple network layers, while previous work typically applied MMD to fewer layers or used single core variants. Initially, a one-dimensional convolutional neural network (1D-CNN) is utilized to extract features from both the source and target domains, thereby enhancing the diagnostic model’s cross-domain adaptability through shared feature learning. Subsequently, to address the distribution differences in feature extraction, the multi-layer multi-kernel maximum mean discrepancy (ML-MK MMD) method is employed to quantify the distribution disparity between the source and target domain features, with the objective of extracting domain-invariant features. Moreover, to further mitigate domain shift, a novel loss function is developed by integrating ML-MK MMD with a domain classifier loss, which optimizes the alignment of feature distributions between the two domains. Ultimately, testing on target domain samples demonstrates that the proposed method effectively extracts domain-invariant features, significantly reduces the distribution gap between the source and target domains, and thereby enhances cross-domain diagnostic performance. Full article

To address the challenges that rolling bearing vibration signals are easily affected by noise and that traditional single-channel methods cannot fully exploit multi-channel information, this paper proposes a multi-channel fault diagnosis method combining Whale Optimization Algorithm-assisted Variational Mode Decomposition (WOA-VMD) with Tucker tensor decomposition. In this method, multi-channel vibration signals are first adaptively decomposed using WOA-VMD, with optimized decomposition parameters to effectively extract weak fault features. The resulting intrinsic mode functions (IMFs) are then structured into a third-order tensor to preserve inter-channel correlations. Tucker decomposition is subsequently applied to extract robust feature vectors from the tensor factor matrices, achieving dimensionality reduction, redundancy suppression, and enhanced noise mitigation. Finally, statistical features such as standard deviation, kurtosis, and waveform factor are computed from the denoised signals and fed into a Support Vector Machine (SVM) classifier for precise fault identification. Experimental results show that the proposed method outperforms traditional approaches in extracting weak fault features, effectively leveraging correlations among multi-channel signals to extract meaningful features from noise-corrupted signals, and achieving efficient and reliable fault diagnosis. Full article

Bearing fault diagnosis encounters limitations including insufficient accuracy, elevated model complexity, and demanding hyperparameter optimization. This research introduces a diagnostic framework combining variational mode decomposition (VMD) and fast Fourier transform (FFT) for extracting comprehensive temporal–spectral characteristics from vibration data. The methodology employs a hybrid deep learning architecture integrating convolutional neural networks (CNNs) with Transformers, where CNNs identify local features while Transformers capture extended dependencies. Meta-learning-enhanced Bayesian optimization and HyperBand (Meta-BOHB) is utilized for efficient hyperparameter selection. Evaluation on the Case Western Reserve University (CWRU) dataset using 5-fold cross-validation demonstrates a mean classification accuracy of 99.91% with exceptional stability (±0.08%). Comparative analysis reveals superior performance regarding precision, convergence rate, and loss metrics compared to existing approaches. Cross-dataset validation using Mechanical Fault Prevention Technology (MFPT) and Paderborn University (PU) datasets confirms robust generalization capabilities, achieving 100% and 98.75% accuracy within 5 and 7 iterations, respectively. Ablation studies validate the contribution of each component. Results demonstrate consistent performance across diverse experimental conditions, indicating significant potential for enhancing reliability and reducing operational costs in industrial fault diagnosis applications. The proposed method effectively addresses key challenges in bearing fault detection through advanced signal processing and optimized deep learning techniques. Full article

The planetary bearing looseness fault can cause the planetary gear train to fail. Conventional modeling methods do not consider complex component-coupling relationships for fault feature analysis. As a result, a joint model is developed to examine the dominant relationship between planetary bearings and the planetary gear train. Firstly, the planetary bearing is modeled in the normal and fault states. Then, a refined joint planetary gear train dynamic model is constructed, which is composed of the planetary gears, the ring gear, the carrier, the sun gear, and the planetary bearings. Finally, the simulation results show that, when the planetary bearing is in the looseness fault state, its fault characteristic presents as the rotation frequency of the carrier and its harmonics. The on-site signal of a 2.0 MW wind turbine is used to verify the effectiveness of the model. The proposed model can provide the basis for the fault mechanism analysis and fault diagnosis of rolling bearing outer ring looseness. Full article

Conventional signal-to-image conversion methods often overlook the physical correspondence of vibration signals, limiting diagnostic interpretability. To address this, we propose a physics-guided image construction strategy that incorporates dimensionless indicators to adaptively weight grayscale regions, enhancing the physical consistency and the discriminability among different fault types. Furthermore, a novel Cheap Channel Obfuscation module is introduced to suppress noise, decouple feature channels, and preserve the critical information within lightweight models. Integrated with ShuffleNetV2, our method achieves high diagnostic accuracy. Experimental validation for CWRU and SEU bearing datasets yields accuracies of 100% and 99.91%, respectively, demonstrating superior performance with minimal parameters. This approach offers a technically robust and computationally efficient fault diagnosis solution, with promising potential for deployment in resource-limited industrial environments. Full article