Massive and complex unstructured fault text data will be generated during the operation of subway trains. A named entity recognition model of subway on-board equipment based on Multiheaded Self-attention mechanism and CNN-BiLSTM-CRF is proposed to address the issue of low recognition accuracy and incomplete recognition features of unstructured fault data named entity recognition task of subway on-board equipment: BiLSTM-CNN parallel network extracts context feature information and local attention information, respectively; In the MHA layer, the features learned from different dimensions are fused through the Multiheaded Self-attention mechanism, and the dependencies of various ranges in the sequence are captured to yield the internal structure information of the features. The conditional random field CRF is used to learn the internal relationship between tags to ensure their sequence. This model is tested with other named entity recognition models on the marked subway on-board fault data. The experimental results demonstrate that this model is able to recognize 10 kinds of labels in the dataset. Moreover, the recognition effect of each label has a good performance in the three evaluation indexes of P, R, and F1 score. Moreover, the weighted average evaluation indexes , , and of 10 labels in this model reach the highest 95.39%, 95.48%, and 95.37%, which has high evaluation indexes and can be applied to the named entity recognition of Metro on-board equipment.

Correlation filter (CF) is widely used in unmanned aerial vehicle (UAV) tracking because of its efficient performance. However, due to the existence of edge effects, CF will be confused so that the peak of the response is no longer obvious, resulting in tracking drift and template degradation, thereby degrading CF performance. To handle the problem, we propose a new CF for this problem. First, we introduce a response-weighted background residual term to make CF learn the background in a targeted manner according to the strength of the response. Secondly, a history filter model is constructed and a spatio-temporal regularization term is introduced to improve the robustness of CF. Finally, we conduct experiments on two challenging UAV benchmarks, DTB70 and UAV123_10fps. The results show that our tracker achieves state-of-the-art performance compared with 15 other SOTA trackers, and can run at 58 FPS on a single CPU, meeting the needs of UAV real-time tracking.

This paper presents an improved virtual coupling train set (VCTS) operation control framework to deal with the lack of optimization of speed curves in the traditional techniques. The framework takes into account the temporary speed limit on the railway line and the communication delay between trains, and it uses a VCTS consisting of three trains as an experimental object. It creates the virtual coupling train tracking and control process by improving the driving strategy of the leader train and using the leader–follower model. The follower train uses the improved speed curve of the leader train as its speed reference curve through knowledge migration, and this completes the multi-objective optimization of the driving strategy for the VCTS. The experimental results confirm that the deep reinforcement learning algorithm effectively achieves the optimization goal of the train driving strategy. They also reveal that the intrinsic curiosity module prioritized experience replay dueling double deep Q-network (ICM-PER-D3QN) algorithm outperforms the deep Q-network (DQN) algorithm in optimizing the driving strategy of the leader train. The ICM-PER-D3QN algorithm enhances the leader train driving strategy by an average of 57% when compared to the DQN algorithm. Furthermore, the particle swarm optimization (PSO)-based model predictive control (MPC) algorithm has also demonstrated tracking accuracy and further improved safety during VCTS operation, with an average increase of 37.7% in tracking accuracy compared to the traditional MPC algorithm.

The operation and maintenance of railway signal systems create a significant and complex quantity of text data about faults. Aiming at the problems of fuzzy entity boundaries and low accuracy of entity recognition in the field of railway signal equipment faults, this paper provides a method for entity recognition of railway signal equipment fault information based on RoBERTa-wwm and deep learning integration. First, the model utilizes the RoBERTa-wwm pretrained language model to get the word vector of text sequences. Second, a parallel network consisting of a BiLSTM and a CNN is constructed to obtain the context feature information and the local attention information, respectively. Third, the feature vectors output from BiLSTM and CNN are combined and fed into MHA, focusing on extracting key feature information and mining the connection between different features. Finally, the label sequences with constraint relationships are outputted in CRF to complete the entity recognition task. The experimental analysis is carried out with fault text of railway signal equipment in the past ten years, and the experimental results show that the model has a higher evaluation index compared with the traditional model on this dataset, in which the precision, recall and F₁ value are 93.25%, 92.45%, and 92.85%, respectively.

Predicting the remaining useful life (RUL) of track circuits is essential to ensure the safe and reliable operation of high-speed railways. In response to the challenges faced by current machine-learning-based RUL prediction methods, which struggle to represent the uncertainty in the probability distribution of RUL predictions, this paper suggests a hybrid-driven method for estimating remaining life. Firstly, the track circuit Health Index is constructed by feature dimensionality reduction and fusion of the original multivariate monitoring data through kernel principal component analysis and Autoencoder; Secondly, the degraded state of the rail circuit is modelled using a nonlinear Wiener degradation model. Finally, the principle of first hitting time is used to derive the probability density function of the anticipated RUL. The efficacy and superiority of the approach presented in this paper are validated by experimental research on the track circuit monitoring dataset. The method enhances forecast accuracy and reduces prediction uncertainty, offering robust technical support for track circuit maintenance decision-making.