Fault diagnosis of wheelset bearings in high-speed trains has attracted constant interest in the scientific community and industrial field. Under the harsh working condition, e.g., time-varying speed and load, most existing methods are hindered by the limited and unknown situations of wheelset bearings. Although the self-calibrated convolution is proven to effectively expand the receptive field with more accurate discriminative regions, its use in fault diagnosis still lacks needed physical interpretation as well as computational efficiency. To this end, this article presents a novel framework by using the logarithmic short-time Fourier transform and the modified self-calibrated convolution. It first manifests a time-frequency map that has explicit physics meaning while reducing the gap between high energy and detailed characteristics in the masking of interfering signals. To simplify redundant kernels, a modified self-calibrated residual block is proposed without introducing any more parameters, while preserving an interpretable and simple structure. The effectiveness and robustness of the proposed method are verified by the experimental data collected from an industrial railway axle bearing test rig. Results are found superior to those of five state-of-art methods, which are more practical in terms of accuracy, cost time, and model size.

Vehicle detection and identification techniques have been widely applied in traffic scene to acquire traffic information depending on various sensors, such as video camera, induction loop, and magnetic sensor. The quantity and category of vehicles are the key components of the intelligent transportation systems as they provide original data for further analysis. Compared with the inductive loop and video camera, magnetic sensor can measure magnetic field distortion caused by the movement of vehicles. The precise amount and category of a vehicle can be obtained through reasonable data analysis. A novel vehicle detection algorithm is proposed based on the short-term variance sequence transformed from raw magnetic signal. The parking-sensitive module is introduced to enhance the robustness and adaptability of a detection method. With abundant signal data, 42-D features are extracted from every vehicle signal comprising statistical features of whole waveform and short-term features of fragment signal. The Gradient Tree Boosting algorithm is employed to identify four vehicle categories. The effectiveness of the proposed approach is validated by the data collected at a freeway exit of Beijing. According to the experiential results based on 4507 vehicles, the vehicle detection algorithm proves to have 99.8% accurate rate and can be highly practical in site traffic environment. The 80.5% accuracy rate on vehicle identification approves the effectiveness of the proposed features on recognizing vehicles.

Traction converters are safety-critical parts of traction drive systems on high-speed trains. Considering the complicated interconnections in the traction converter, it is imperative to utilize multi-sensors rather than single-sensor for fault diagnosis. However, the multi-sensor-based traction converter fault diagnosis is barely discussed by now. Concerning this issue, this paper proposes a novel intelligent diagnosis framework based on Long Short-term Memory network, which deals with extracting long-term dependencies in time series effectively and learns hidden fault characteristics from traction converter multi-sensor signals adaptively, without needs of expert knowledge or system modeling. Experiments were designed to verify the model's sensitivity on different signals as single-sensor respectively, and as multi-sensors integrally. Nine kinds of measured fault signals from actual High-speed Trains in operation were utilized for verification. Results show that the proposed method has the highest sensitivity to different signals compared to conventional models, and the crucial fault modes were identified accurately, which implies the high reliability of multi-fault identification. In addition, experiments on different scales of training sets also suggest that the model accuracy can be improved by increasing the training data scale appropriately. Besides, this method can be further applied to other train systems with similar data characteristics in the future.

The bogie system is a critical system for a high-speed train, which is composed of various mechanical parts. Therefore, the health of the bogie can directly affect the health of high-speed train. Temperature signals, speed signals and pressure signals are collected from the bogie can reflect its health. Hence, the multi-sensor fault diagnosis methods can provide novel solutions for the bogie health monitoring tool. This paper presents a novel bogie fault diagnosis scheme named the AttGGCN model, using graph convolutional network (GCN), gated recurrent unit (GRU) and attention mechanism. In this fault diagnosis scheme, the bogie data network is established firstly. Then, temporal and spatial features are extracted and fused using GCG unit. Finally, the GCN are used for fault identification. Twenty-four kinds of measured signals and seven types of faults from actual High-speed train in operation are utilized for verification. Results show that the AttGGCN model has the highest accuracy compared to conventional models. In addition, experiments on different scales of training sets suggest that the AttGGCN model has strong robustness in small-scale datasets. Besides, ablation experiments certificate that the attention mechanism is able to strengthen the feature extraction ability.

Turnouts are crucial to the safety of high-speed railways. Due to the intensive use and complex environment, breakdowns caused by different faults occur frequently in practice. Considering that the operation of turnouts is a multi-stage process during which each stage has its specific health characteristics, this paper proposes segmentalized maximal-relevancy and minimal-redundancy (mRMR) for feature extraction from each stage separately. Based on mathematical analysis of the turnout mechanism, the electric power curve is segmented into four stages, from which time-domain analysis and mRMR are combined to extract valid features corresponding to different movements respectively. Then, a novel classifier named cost-sensitive Extreme Learning Machine with fixed inputs (cf-ELM) is proposed for fault classification. We modify the inputs of ELM and define a new formula to limit the input weights and biases for the sake of stability of the network structure. Besides, a cost-sensitive optimization method is also presented in this classifier to embed the failure degree and data proportion into cost calculation rules to deal with data imbalance. To verify our proposed method, real data collected from a turnout of Beijing-Shanghai high-speed railway is used. It is proven by comparisons that the accuracy of our method has achieved 100% with fast running speed and also outperforms traditional methods in terms of stability and generalization remarkably.

Automatic operation of high speed trains (HSTs) requires dedicated control schemes to tackle uncertain dynamics, unknown resistive forces, coupling nonlinearities, interactive in-train forces, unexpected disturbances, and faults. This paper addresses the problem of position and velocity tracking control of HSTs with multiple vehicles connected through elastic couplers. A neuro-adaptive fault tolerant control scheme is developed to compensate the input nonlinearities due to traction or braking notches, uncertain impacts from in-train forces, resistive aerodynamic drag forces, traction or braking faults, and adherence-antiskid constraints. High precision velocity and position tracking is achieved by using the proposed control scheme that combines the robust adaptive control with nonlinearly layered neural networks. Closed-loop stability is ensured with strict mathematical analysis. The effectiveness of the proposed approach is also validated through numerical simulations with considering the adherence-antiskid constraints.