Fault frequency of catenary is related to meteo-rological conditions. In this work, based on the historical data, catenary fault frequency and weather-related fault rate are introduced to analyse the correlation betwe...Fault frequency of catenary is related to meteo-rological conditions. In this work, based on the historical data, catenary fault frequency and weather-related fault rate are introduced to analyse the correlation between catenary faults and meteorological conditions, and further the effect of meteorological conditions on catenary oper-ation. Moreover, machine learning is used for catenary fault prediction. As with the single decision tree, only a small number of training samples can be classified cor-rectly by each weak classifier, the AdaBoost algorithm is adopted to adjust the weights of misclassified samples and weak classifiers, and train multiple weak classifiers. Finally, the weak classifiers are combined to construct a strong classifier, with which the final prediction result is obtained. In order to validate the prediction method, an example is provided based on the historical data from a railway bureau of China. The result shows that the mapping relation between meteorological conditions and catenary faults can be established accurately by AdaBoost algorithm. The AdaBoost algorithm can accurately predict a catenary fault if the meteorological conditions are provided.展开更多
Construction issues of high-speed rail infrastructures have been increasingly concerned worldwide,of which the subgrade settlement in soft soil area becomes a particularly critical problem.Due to the high compressibil...Construction issues of high-speed rail infrastructures have been increasingly concerned worldwide,of which the subgrade settlement in soft soil area becomes a particularly critical problem.Due to the high compressibility and low permeability of soft soil,the post-construction settlement of the subgrade is extremely difficult to control in these regions,which seriously threatens the operation safety of high-speed trains.In this work,the significant issues of high-speed railway subgrades in soft soil regions are discussed.The theoretical and experimental studies on foundation treatment methods for ballasted and ballastless tracks are reviewed.The settlement evolution and the settlement control effect of different treatment methods are highlighted.Control technologies of subgrade differential settlement are subsequently briefly presented.Settlement calculation algorithms of foundations reinforced by different treatment methods are discussed in detail.The defects of existing prediction methods and the challenges faced in their practical applications are analyzed.Furthermore,the guidance on future improvement in control theories and technologies of subgrade settlement for high-speed railway lines and the corresponding challenges are provided.展开更多
There has been rapid development of high-speed railway lines, especially passenger-dedicated railway lines, in China. Trains are traveling at speeds exceeding 250 km per hour and they require highly smooth tracks to e...There has been rapid development of high-speed railway lines, especially passenger-dedicated railway lines, in China. Trains are traveling at speeds exceeding 250 km per hour and they require highly smooth tracks to ensure safety. However, there have been no in-depth studies on the early warning of the settlement of high-speed railway lines in China or abroad. Most methods use a simple model based on data processing and decision rules. The core issues of early warning lie in the science and rationality of decision rules. The present paper therefore investigates novel and critical indexes for the warning of settlement under high-speed railway lines according to existing norms and field data, and several essential indexes of deformation warning are suggested through theoretical and experimental analysis.展开更多
In this paper, we present a comprehensive model for the prediction of the evolution of high-speed train wheel profiles due to wear. The model consists of four modules： a multi-body model implemented with the commerci...In this paper, we present a comprehensive model for the prediction of the evolution of high-speed train wheel profiles due to wear. The model consists of four modules： a multi-body model implemented with the commercial multi-body software SIMPACK to evaluate the dynamic response of the vehicle and track; a local contact model based on Hertzian theory and a novel method, named FaStrip （Sichani et al., 2016）, to calculate the normal and tangential forces, respectively; a wear model proposed by the University of Sheffield （known as the USFD wear function） to estimate the amount of material removed and its distribution along the wheel profile; and a smoothing and updating strategy. A simulation of the wheel wear of the high-speed train CRH3 in service on the Wuhan-Guangzhou railway line was performed. A virtual railway line based on the statistics of the line was used to represent the entire real track. The model was validated using the wheel wear data of the CRH3 operating on the Wuhan- Guangzhou line, monitored by the authors＇ research group. The results of the predictions and measurements were in good agreement.展开更多
基金supported by the Scientific and Technological Research and Development Program of China Railway Corporation under Grant N2018G023by the Science and Technology Projects of Sichuan Province under Grants 2018RZ0075
文摘Fault frequency of catenary is related to meteo-rological conditions. In this work, based on the historical data, catenary fault frequency and weather-related fault rate are introduced to analyse the correlation between catenary faults and meteorological conditions, and further the effect of meteorological conditions on catenary oper-ation. Moreover, machine learning is used for catenary fault prediction. As with the single decision tree, only a small number of training samples can be classified cor-rectly by each weak classifier, the AdaBoost algorithm is adopted to adjust the weights of misclassified samples and weak classifiers, and train multiple weak classifiers. Finally, the weak classifiers are combined to construct a strong classifier, with which the final prediction result is obtained. In order to validate the prediction method, an example is provided based on the historical data from a railway bureau of China. The result shows that the mapping relation between meteorological conditions and catenary faults can be established accurately by AdaBoost algorithm. The AdaBoost algorithm can accurately predict a catenary fault if the meteorological conditions are provided.
基金National Natural Science Foundation of China(No.51778485).
文摘Construction issues of high-speed rail infrastructures have been increasingly concerned worldwide,of which the subgrade settlement in soft soil area becomes a particularly critical problem.Due to the high compressibility and low permeability of soft soil,the post-construction settlement of the subgrade is extremely difficult to control in these regions,which seriously threatens the operation safety of high-speed trains.In this work,the significant issues of high-speed railway subgrades in soft soil regions are discussed.The theoretical and experimental studies on foundation treatment methods for ballasted and ballastless tracks are reviewed.The settlement evolution and the settlement control effect of different treatment methods are highlighted.Control technologies of subgrade differential settlement are subsequently briefly presented.Settlement calculation algorithms of foundations reinforced by different treatment methods are discussed in detail.The defects of existing prediction methods and the challenges faced in their practical applications are analyzed.Furthermore,the guidance on future improvement in control theories and technologies of subgrade settlement for high-speed railway lines and the corresponding challenges are provided.
文摘There has been rapid development of high-speed railway lines, especially passenger-dedicated railway lines, in China. Trains are traveling at speeds exceeding 250 km per hour and they require highly smooth tracks to ensure safety. However, there have been no in-depth studies on the early warning of the settlement of high-speed railway lines in China or abroad. Most methods use a simple model based on data processing and decision rules. The core issues of early warning lie in the science and rationality of decision rules. The present paper therefore investigates novel and critical indexes for the warning of settlement under high-speed railway lines according to existing norms and field data, and several essential indexes of deformation warning are suggested through theoretical and experimental analysis.
基金Project supported by the National Natural Science Foundation of China （Nos. U 1434201, 51275427, and 51605394）, and the Scientific Research Foundation of State Key Laboratory of Traction Power （No. 2015TPL_T01 ）, China
文摘In this paper, we present a comprehensive model for the prediction of the evolution of high-speed train wheel profiles due to wear. The model consists of four modules： a multi-body model implemented with the commercial multi-body software SIMPACK to evaluate the dynamic response of the vehicle and track; a local contact model based on Hertzian theory and a novel method, named FaStrip （Sichani et al., 2016）, to calculate the normal and tangential forces, respectively; a wear model proposed by the University of Sheffield （known as the USFD wear function） to estimate the amount of material removed and its distribution along the wheel profile; and a smoothing and updating strategy. A simulation of the wheel wear of the high-speed train CRH3 in service on the Wuhan-Guangzhou railway line was performed. A virtual railway line based on the statistics of the line was used to represent the entire real track. The model was validated using the wheel wear data of the CRH3 operating on the Wuhan- Guangzhou line, monitored by the authors＇ research group. The results of the predictions and measurements were in good agreement.
