As a result of long-term pressure from train operations and direct exposure to the natural environment, rails, fasteners, and other components of railway track lines inevitably produce defects, which have a direct impact on the safety of train operations. In this study, a multiobject detection method based on deep convolutional neural network that can achieve nondestructive detection of rail surface and fastener defects is proposed. First, rails and fasteners on the railway track image are localized by the improved YOLOv5 framework. Then, the defect detection model based on Mask R-CNN is utilized to detect the surface defects of the rail and segment the defect area. Finally, the model based on ResNet framework is used to classify the state of the fasteners. To verify the robustness and effectiveness of our proposed method, we conduct experimental tests using the ballast and ballastless railway track images collected from Shijiazhuang-Taiyuan high-speed railway line. Through a variety of evaluation indexes to compare with other methods using deep learning algorithms, experimental results show that our method outperforms others in all stages and enables effective detection of rail surface and fasteners.

No abstract

No abstract

Pantograph catenary contact point is an important monitoring object during pantograph catenary operation, which reflects the state of pantograph catenary operation. However, due to the relatively small contact area of the target area, it is still a challenge to locate the contact point quickly and accurately. Therefore, we propose a two-stage detection method of rigid pantograph catenary contact points based on deep convolution neural network. Firstly, yolov3 network is used to locate the pantograph catenary contact part, which can obtain the target area including contact points. Then, four key points generated by the intersection of rigid pantograph and catenary can be obtained by using the key point detection network in the target area. Finally, the positioning of pantograph catenary contact points is obtained by geometric calculation. The experimental results on the railway operation data set collected by the traction Laboratory of Southwest Jiaotong University show the effectiveness of the method.

Response selection in retrieval-based chatbot aims to find the most relevant response in a candidate repository given the conversation context. A key technique to this task lies in how to measure the matching degree between conversation context and response at rich semantic information. In this paper, we propose a hierarchical residual matching network (HRMN) to fully extract and make use of the rich semantic information in the conversation history and response for themulti-turn response selection task. We empirically verify HRMN on two benchmark data sets and compare against advanced approaches. Evaluation results demonstrate that HRMN outperforms strong baselines and has a distinct improvement in response selection.