Bearing fault vibration signals collected in real engineering cases often contain environmental noise which can easily mask the fault type characteristics of vibration signals, making it difficult to determine the corresponding fault type when traditional deep learning methods are used for fault diagnosis. To solve the above problem, a neural network model named multiscale CNN-LSTM (convolutional neural network-long short-term memory) and a deep residual learning model was designed, which combines a multiscale wide CNN-LSTM module and a deep residual module for rolling bearing fault diagnosis. In this model, a wide convolution kernel CNN-LSTM structure with different convolution scales is used to extract a variety of different types of frequency and sequential features from vibration signals. It is worth noting that the wide convolution kernel CNN-LSTM structure not only has stronger feature extraction performance compared with the common convolution layer but can also reduce the interference of high-frequency noise. Moreover, the deep residual module with a wide convolution kernel CNN-LSTM structure is used to further improve the feature expression ability of the proposed model. The above algorithm enables the proposed model to better extract the fault features hidden in the noise signal. When compared with some state-of-the-art methods, the experimental results showed that this model has better anti-noise performance and better generalization ability for rolling bearing fault diagnosis.

The fault information of rolling bearings is generally contained in vibration signals. How to efficiently unearth fault information from the raw signals is the key to detecting and evaluating the health condition of mechanical equipment. Therefore, a hierarchical dispersion Lempel–Ziv complexity (HDLZC) feature extraction method is developed in this paper to improve the accuracy of fault diagnosis. In this method, dispersion theory addresses the deficiency of Lempel–Ziv complexity, and can obtain more fault features from the raw signal. Second, the hierarchical extraction of high- and low-frequency components from time series can improve the ability to describe dynamic features. Simulations and experiments respectively demonstrate the predominance of HDLZC. The experimental results reveal that this method is significantly better than multiscale dispersive Lempel–Ziv complexity, hierarchical Lempel–Ziv complexity, multiscale dispersion entropy, and multiscale permutation entropy in extracting fault information.

When rolling bearings fail, it is usually difficult to determine the degree of damage. To address this problem, a new fault diagnosis method was developed to perform feature extraction and intelligent classification of various fault position and damage degree of rolling bearing signals. Firstly, Multifractal Detrended Fluctuation Analysis (MFDFA) was used to compute five MFDFA features while five Alpha Stable Distribution (ASD) features were obtained by fitting the distribution to the vibration signals of each status and calculating the Probability Density Function (PDF). Secondly, Kernel Principle Component Analysis (KPCA) was used to achieve dimensionality reduction fusion of the combination of original features to gain the Kernel Principle Component Fusion Features (KPCFFs). Thirdly, the KPCFFs served as the input of Least Squares Support Vectors Machine (LSSVM) based on Particle Swarm Optimization (PSO) to assess rolling bearings’ fault position and damage severity. Finally, the effectiveness of the method was validated by bench test data. The results demonstrated that the developed method can achieve intelligent diagnosis of rolling bearings’ fault position and damage degree and can yield better diagnosis accuracy than single feature method or corresponding single feature fusion method.

Multiscale dispersion entropy (MDE) is a common method for measuring the complexity of nonlinear time series. However, the uncertainty results by the MDE tool may be unreliable as the coarse-graining procedure will reduce the number of data points at a large scale. In addition, the essential differences between the matching patterns cannot be extracted by MDE. To effectively alleviate the above limitations of MDE, an improved multiscale weighted-dispersion entropy (IMWDE) method is proposed in this article. Weight coefficients and weight probabilities were assigned to each vector to consider the amplitude information, and an improved coarse grained process is proposed for entropy value refinement. The performance of the IMWDE method is evaluated with synthetic data. Based on a powerful algorithm for key feature extraction, a novel intelligent diagnosis technique is proposed by combining classifiers. Finally, real vibration signals collected from axle-box bearings are used to demonstrate the effectiveness of the diagnosis scheme. Compared with MDE and IMWDE, the results indicate that the proposed method achieves smaller errors, and the highest diagnosis accuracy.

Graph neural networks (GNNs) have unique advantages in terms of processing non-Euclidean spatial data with significant differences and effectively diagnosing faults. However, GNNs typically rely on high-quality graph structures. The current graph construction methods often fail to capture the complexity and global features of vibration signals. To address this shortcoming, a graph construction method called GAFGraph based on a Gramian angular field (GAF) is introduced. GAFGraph offers a more nuanced representation strategy by transforming time series data into a Gramian matrix and then extracting more comprehensive fault node similarity features. It effectively captures the deep internal correlations and long-term dependencies within the input data, enhancing the global nature of the associated graph. Moreover, a feasible graph connectivity evaluation metric is proposed to calculate the relationships among various adjacency parameters, thereby effectively assessing the quality of the constructed graph. In addition, the featurewise linear modulation (FiLM) technique is integrated into a GNN-based fault diagnosis model. This technique dynamically adjusts the feature representations of the target nodes and edges by computing transformations for all incoming information based on the representations of the target nodes, modulating the feature propagation process and enhancing the adaptability and generalization capabilities of the model. Finally, experiments are conducted to validate the GAFGraph and FiLM modules on two datasets with significant differences: one under variable speeds and the other under constant speed conditions.

A railway vehicle’s key components, such as wheelset treads and axle box bearings, often suffer from fatigue failures. If these faults are not detected and dealt with in time, the running safety of the railway vehicle will be seriously affected. To detect these components’ early failure and extend their fatigue life, a regular maintenance becomes critical. Currently, the regular maintenance of axle box bearings mainly depends on manual off‐line inspection, which has low working efficiency and precision of fault diagnosis. In order to improve the maintenance efficiency and effectiveness of railway vehicles, this study proposes a method of integrating the vibration monitoring system of the axle box bearing in the underfloor wheelset lathe, where the integration scheme and work flow of the system are introduced followed by the detailed fault diagnosis method and application examples. Firstly, the band‐pass filter and envelope analysis is successively performed on the original signal acquired by an accelerometer. Secondly, the alpha‐stable distribution (ASD) and multifractal detrended fluctuation analysis (MFDFA) analysis of the envelope signal are performed, and five characteristic parameters with significant stability and sensitivity are extracted and then brought into the least squares support vectors machine based on particle swarm optimization to determine the state of the bearing quantitatively. Finally, the effectiveness of the method is validated by bench test data. The results demonstrated that the proposed method can accomplish effective diagnosis of axle box bearings’ fault location and fault degree and can yield better diagnosis accuracy than the single method of ASD or MFDFA.