The axle box bearing of bogie is one of the key components of the rail transit train, which can ensure the rotary motion of wheelsets and make the wheelsets adapt to the conditions of uneven railways. At the same time, the axle box bearing also exposes most of the load of the car body. Long-time high-speed rotation and heavy load make the axle box bearing prone to failure. If the bearing failure occurs, it will greatly affect the safety of the train. Therefore, it is extremely important to monitor the health status of the axle box bearing. At present, the health status of the axle box bearing is mainly monitored by vibration information and temperature information. Compared with the temperature data, the vibration data can more easily detect the early fault of the bearing, and early warning of the bearing state can avoid the occurrence of serious fault in time. Therefore, this paper is based on the vibration data of the axle box bearing to carry out adaptive fault diagnosis of bearing. First, the AR model predictive filter is used to denoise the vibration signal of the bearing, and then the signal is whitened in the frequency domain. Finally, the characteristic value of vibration data is extracted by energy operator demodulation, and the fault type is determined by comparing with the theoretical value. Through the analysis of the constructed simulation signal data, the characteristic parameters of the data can be effectively extracted. The experimental data collected from the bearing testbed of high-speed train are analyzed and verified, which further proves the effectiveness of the feature extraction method proposed in this paper. Compared with other axle box bearing fault diagnosis methods, the innovation of the proposed method is that the signal is denoised twice by using AR filter and spectrum whitening, and the adaptive extraction of fault features is realized by using energy operator. At the same time, the steps of setting parameters in the process of feature extraction are avoided in other feature extraction methods, which improves the diagnostic efficiency and is conducive to use in online monitoring system.

Bearings are key components of modern mechanical equipment. To address the issue that the limited information contained in the single-source signal of the bearing leads to the limited accuracy of the single-source fault diagnosis method, a multi-sensor fusion fault diagnosis method is proposed to improve the reliability of bearing fault diagnosis. Firstly, the feature extraction process of the convolutional neural network (CNN) is improved based on the theory of variational Bayesian inference, which forms the variational Bayesian inference convolutional neural network (VBICNN). VBICNN is used to obtain preliminary diagnosis results of single-channel signals. Secondly, considering the redundancy of information contained in multi-channel signals, a voting strategy is used to fuse the preliminary diagnosis results of the single-channel model to obtain the final results. Finally, the proposed method is evaluated by an experimental dataset of the axlebox bearing of a high-speed train. The results show that the average diagnosis accuracy of the proposed method can reach more than 99% and has favorable stability.

Bearings of rail vehicles bear various dynamic forces. Any fault of the bearing seriously threatens running safety. For fault diagnosis, vibration and temperature measured from the bogie and acoustic signals measured from trackside are often used. However, installing additional sensing devices on the bogie increases manufacturing cost while trackside monitoring is susceptible to ambient noise. For other application, structural displacement based on computer vision is widely applied for deflection measurement and damage identification of bridges. This article proposes to monitor the health condition of the rail vehicle bearings by detecting the displacement of bolts on the end cap of the bearing box. This study is performed based on an experimental platform of bearing systems. The displacement is monitored by computer vision, which can image real-time displacement of the bolts. The health condition of bearings is reflected by the amplitude of the detected displacement by phase correlation method which is separately studied by simulation. To improve the calculation rate, the computer vision only locally focuses on three bolts rather than the whole image. The displacement amplitudes of the bearing system in the vertical direction are derived by comparing the correlations of the image’s gray-level co-occurrence matrix (GLCM). For verification, the measured displacement is checked against the measurement from laser displacement sensors, which shows that the displacement accuracy is 0.05 mm while improving calculation rate by 68%. This study also found that the displacement of the bearing system increases with the increase in rotational speed while decreasing with static load.

The operating state of axle box bearings is crucial to the safety of high-speed trains, and the vibration acceleration signal is a commonly used bearing-health-state monitoring signal. In order to extract hidden characteristic frequency information from the vibration acceleration signal of axle box bearings for fault diagnosis, a method for extracting the fault characteristic frequency based on principal component analysis (PCA) fusion and the optimal bandpass filtered denoising signal analytic energy operator (AEO) demodulation spectrum is proposed in this paper. PCA is used to measure the dimension reduction and fusion of three-direction vibration acceleration, reducing the interference of irrelevant noise components. A new type of multi-channel bandpass filter bank is constructed to obtain filtering signals in different frequency intervals. A new, improved average kurtosis index is used to select the optimal filtering signals for different channel filters in a bandpass filter bank. A dimensionless characteristic index characteristic frequency energy concentration coefficient (CFECC) is proposed for the first time to describe the energy prominence ability of characteristic frequency in the spectrum and can be used to determine the bearing fault type. The effectiveness and applicability of the proposed method are verified using the simulation signals and experimental signals of four fault bearing test cases. The results demonstrate the effectiveness of the proposed method for fault diagnosis and its advantages over other methods.

As a critical mechanical component, the operational integrity of rolling bearings is essential for equipment safety. However, under strong noise interference, the weak fault features in vibration signals are difficult to extract. To address this issue, a novel fault diagnosis method is proposed in this paper, which integrates an improved speed time-varying filtering empirical mode decomposition (ISTVF-EMD) with an adaptive sine–cosine optimization algorithm (A-SCA), enabling precise and efficient extraction of fault features. The core of the proposed method lies in improving the conventional time-varying filtering empirical mode decomposition (TVF-EMD) by setting a maximum decomposition layer limit, effectively addressing issues of excessive components and low computational efficiency during the decomposition of low signal-to-noise ratio (SNR) signals. Furthermore, a multi-characteristic frequency energy concentration centrality (MCFECC) index is employed as a fitness function to guide A-SCA in adaptively searching for the optimal bandwidth threshold and fitting order parameters of ISTVF-EMD, thereby extracting components with the most enriched fault information. Validated through simulation and multiple test bench cases, the results indicate that the proposed method can not only significantly enhance the fault characteristic frequencies and their harmonics in the envelope spectrum, successfully diagnosing outer race, inner race, and rolling element faults, but also, compared with the original method, ISTVF-EMD substantially reduces the computational time while ensuring or even improving the decomposition quality. The method presented in this paper provides an effective solution for achieving precise and adaptive fault diagnosis of rolling bearings under strong noise interference.