Establishment and Optimization of Status Assessment Variables for Heavy Haul Railway Line Service Performance

In order to address the issues of complex system structure and variable selection difficulty for the current heavy haul railway line status evaluation system, a three-category and three-layer heavy-haul line status evaluation variable set construction and reduction optimization method is proposed. Firstly, the status of heavy haul railway line is analyzed, and an initial set of evaluation variables affecting the line status is constructed. Then, based on the association rule and the principal component analysis method, key variables are extracted from the initial variable set to establish the evaluation system. Finally, this method is verified with actual data of a line. The results show that the service performance of heavy haul railway line can still be evaluated accurately when the evaluation variables are reduced by 60% in the proposed method.

Numerical simulation of wheel wear evolution for heavy haul railway

The prediction of the wheel wear is a fundamental problem in heavy haul railway. A numerical methodology is introduced to simulate the wheel wear evolution of heavy haul freight car. The methodology includes the spatial coupling dynamics of vehicle and track, the three-dimensional rolling contact analysis of wheel-rail, the Specht's material wear model, and the strategy for reproducing the actual operation conditions of railway. The freight vehicle is treated as a full 3D rigid multi-body model. Every component is built detailedly and various contact interactions between parts are accurately simulated, taking into account the real clearances. The wheel-rail rolling contact calculation is carried out based on Hertz's theory and Kalker's FASTSIM algorithm. The track model is built based on field measurements. The material loss due to wear is evaluated according to the Specht's model in which the wear coefficient varies with the wear intensity. In order to exactly reproduce the actual operating conditions of railway,dynamic simulations are performed separately for all possible track conditions and running velocities in each iterative step.Dimensionless weight coefficients are introduced that determine the ratios of different cases and are obtained through site survey. For the wheel profile updating, an adaptive step strategy based on the wear depth is introduced, which can effectively improve the reliability and stability of numerical calculation. At last, the wear evolution laws are studied by the numerical model for different wheels of heavy haul freight vehicle running in curves. The results show that the wear of the front wheelset is more serious than that of the rear wheelset for one bogie, and the difference is more obvious for the outer wheels. The wear of the outer wheels is severer than that of the inner wheels. The wear of outer wheels mainly distributes near the flange and the root; while the wear of inner wheels mainly distributes around the nominal rolling circle. For the outer wheel of front wheelset of each bogie, the development of wear is gradually concentrated on the flange and the developing speed increases continually with the increase of traveled distance.

FE Analysis of Longitudinal Dynamic Response of Subgrade in Bridge-Subgrade Transition of Heavy Haul Railway

With the increase of axle load and the train speed, dynamic interaction of train-track system becomes so exacerbated that the deformation and dynamic response of subgrade are more aggravated. The differential settlement will be created in bridge-embankment transition section under such dynamic action, and an adverse effect on the train operation safety can be caused. Meanwhile, differential settlement will produce additional dynamic effect when high-speed trains go through the transition between bridge-embankment. Such dynamic action will aggravate the differential settlement and subgrade damage. This paper applies the methods of field test and finite-element to systematically study the dynamic response characteristics of subgrade in bridge-embankment transition section of heavy haul railway under dynamic load for the first time. This research is focused on the analysis of influence of the different axle load, train speed, filled soil modulus, etc.. At last, the dynamic response rules are systematically summarized.

Application Study on Elastomer Expansion Joint in Heavy Haul Railway

The article summarizes related research results and achievements of elastomer expansion device in railway bridge and puts forward a new idea of using polyurethane elastomer material to seal concrete bridge joints between adjacent spans in heavy haul railways. The new type expansion device is composed of polyurethane elastomer material and named TTXF （elastomer expansion joint）. In theory, researchers find out expansion joint deformation regularity between adjacent bridge spans through theoretical analysis and detection in heavy haul railways, such as Datong-Qinhuangdao Railway and Shenchi-Huanghua Port Railway. Fatigue tests prove that TTXF can adapt to permanent and dynamic deformation. On the other hand, it has been successfully applied in the test section of Central South of Shanxi Railway Passage and continuous monitoring has been conducted in extreme weather for over one year. The expansion joint has a good effect practically.

Rail fastener detection of heavy railway based on deep learning

Image detection based on machine learning and deep learning currently has a good application prospect for railway fault diagnosis,with good performance in feature extraction and the accuracy of image localization and good classification results.To improve the speed of locating small target objects of fasteners,the YOLOv5 framework model with faster algorithm speed is selected.To improve the classification accuracy of fasteners,YOLOv5-based heavy-duty railway rail fastener detection is proposed.The anchor size is modified on the original basis to improve the attention to small targets of fasteners.The CBAM(Convolutional Block Attention Module)module and TPH(Transformer Prediction Head)module are introduced to improve the speed and accuracy issues.The rail fasteners are divided into 6 categories.Experiment comparisons show that before the improvement,the MAP@0.5 value of all categories are close to the peak of 0.989 after the epoch of 150,and the F1 score approaches 1 with confidence in the interval(0.2,0.95).The improved mAP@0.5 value approached the highest value of 0.991 after the epoch of 75,and the F1 score approached 1 with confidence in the interval(0.01,0.95).The experiment results indicate that the improved YOLOv5 model proposed in this paper is more suitable for the task of detecting rail fasteners.