The health management of railway vehicles is crucial to secure safety and efficiency in the long-term operation of high-speed trains. Meanwhile, complex components put forward a higher requirement for the robustness of condition monitoring systems, especially abilities to identify unexpected faults. The misidentification of infrequent faults could lead to unpredictable consequences to the vehicle's safety. This paper proposes a novel method for detecting unexpected faults of high-speed train bogie based on Bayesian deep learning. First, a Monte Carlo-Based perturbation is imposed on input samples, which can magnify the difference between unexpected faults and known ones. Then, through dropout-based Bayesian deep learning, the diagnosis result can be obtained as well as a Bayesian indicator of whether the anomalies belong to known classes. The proposed method can capture the uncertainty of model outputs and identify unexpected faults, with only a few samples of unexpected anomalies for calibration. Also, it is compatible with most existing neural network structures. The experiments compare the proposed method with existing methods on two real-world applications, which demonstrates the effectiveness and superiority of the proposed scheme.

This paper addresses the problem of performance degradation estimation of high-speed train lateral damper based on SDS-CNN. The proposed SDS-CNN consists of two types convolution modules, i.e., DA-Module and FE-Module, where the DA-Module is used to adjust data dimension and map original vibration signals into high dimensional space, while the FE-Module is employed to extract features of different frequencies from different scales adaptively. Experimental results on CRH380A high speed train vibration signals validate the superiority of the proposed structure over FCN, MCNN, Time-CNN, ResNet, ResNext, Xception, and EfficientNet, with the minimum MAE (0.46) and minimum RMSE (0.63).

High-speed train bogies are essential for the safety and comfort of train operation. The performance of the bogie usually degrades before it fails, so it is necessary to detect the performance degradation of a high-speed train bogie in advance. In this paper, with two key dampers on the bogie taken as experimental objects (lateral damper and yaw damper), a novel 1D-ConvLSTM time-distributed convolutional neural network (CLTD-CNN) is proposed to estimate the performance degradation of a high-speed train bogie. The proposed CLTD-CNN is an encoder-decoder structure. Specifically, the encoder part of the proposed structure consists of a time-distributed 1D-CNN module and a 1D-ConvLSTM. The decoder part consists of a 1D-ConvLSTM and a simple time-CNN with residual connections. In addition, an auxiliary training part is introduced into the structure to support CLTD-CNN in learning the performance degradation trend characteristic, and a special input format is designed for this structure. The whole structure is end-to-end and does not require expert knowledge or engineering experience. The effectiveness of the proposed CLTD-CNN is tested by the high-speed train CRH380A under different performance states. The experimental results demonstrate the superiority of CLTD-CNN. Compared to other methods, the estimation error of CLTD-CNN is the smallest.

The safe and comfortable operation of high-speed trains has attracted extensive attention. With the operation of the train, the performance of high-speed train bogie components inevitably degrades and eventually leads to failures. At present, it is a common method to achieve performance degradation estimation of bogie components by processing high-speed train vibration signals and analyzing the information contained in the signals. In the face of complex signals, the usage of information theory, such as information entropy, to achieve performance degradation estimations is not satisfactory, and recent studies have more often used deep learning methods instead of traditional methods, such as information theory or signal processing, to obtain higher estimation accuracy. However, current research is more focused on the estimation for a certain component of the bogie and does not consider the bogie as a whole system to accomplish the performance degradation estimation task for several key components at the same time. In this paper, based on soft parameter sharing multi-task deep learning, a multi-task and multi-scale convolutional neural network is proposed to realize performance degradation state estimations of key components of a high-speed train bogie. Firstly, the structure takes into account the multi-scale characteristics of high-speed train vibration signals and uses a multi-scale convolution structure to better extract the key features of the signal. Secondly, considering that the vibration signal of high-speed trains contains the information of all components, the soft parameter sharing method is adopted to realize feature sharing in the depth structure and improve the utilization of information. The effectiveness and superiority of the structure proposed by the experiment is a feasible scheme for improving the performance degradation estimation of a high-speed train bogie.