In order to study the safety and the comfort of high-speed trains running on a single-tower cable-stayed bridge under spatial gust,a dynamic model of wind-train-bridge analysis model is built based on the autoregressi...In order to study the safety and the comfort of high-speed trains running on a single-tower cable-stayed bridge under spatial gust,a dynamic model of wind-train-bridge analysis model is built based on the autoregressive method,the multi-body dynamics method and the finite element method.On this basis,the influence of spatial gust model loading,the suspension parameters change,wind attack angle and speed on the train-bridge system are analyzed by combining the time/frequency domain analysis and statistical methods.The results show that the spatial gust environment is one of the most important factors affecting safety and comfort and can make the calculation result tend to be conservative and more conducive.The response changes caused by K_(py),K_(px) and K_(sx) changes are nearly linear,while Ksy shows nonlinear characteristics and the most sensitivity.Wind attack angle at 75°and 90°has the greatest influence on the vehicle-bridge system.For ride comfort index,when pre-set wind speed(α=75°)reaches 20 m/s,the vertical acceleration firstly exceeds the limit value;when wind speed(α=90°)reaches 21.5 m/s,the lateral acceleration firstly exceeds the limit value,and the ride comfort of the vehicle cannot be guaranteed.For running safety index,when pre-set wind speed(α=75°)reaches 24.6 m/s,the wheel unloading coefficient firstly exceeds the limit;when pre-set wind speed(α=90°)reaches 24.5 m/s,the derailment coefficient firstly exceeds the limit,and the running safety cannot be guaranteed.The results can provide a suitable reference for the safe and stable operation of trains on the bridge.展开更多
Accurate prediction of wind power is significant for power system dispatching as well as safe and stable operation. By means of BP neural network, radial basis function neural network and support vector machine, a new...Accurate prediction of wind power is significant for power system dispatching as well as safe and stable operation. By means of BP neural network, radial basis function neural network and support vector machine, a new combined method of wind power prediction based on cooperative game theory is proposed. In the method, every single forecasting model is regarded as a member of the cooperative games, and the sum of square error of combination forecasting is taken as the result of cooperation. The result is divided among the members according to Shapley values, and then weights of combination forecasting can be obtained. Application results in an actual wind farm show that the proposed method can effectively improve prediction precision.展开更多
基金Project(20ZR1460700) supported by the Natural Science Foundation of Shanghai,ChinaProject supported by Shanghai Collaborative Innovation Research Center for Multi-network&Multi-modal Rail Transit,China。
文摘In order to study the safety and the comfort of high-speed trains running on a single-tower cable-stayed bridge under spatial gust,a dynamic model of wind-train-bridge analysis model is built based on the autoregressive method,the multi-body dynamics method and the finite element method.On this basis,the influence of spatial gust model loading,the suspension parameters change,wind attack angle and speed on the train-bridge system are analyzed by combining the time/frequency domain analysis and statistical methods.The results show that the spatial gust environment is one of the most important factors affecting safety and comfort and can make the calculation result tend to be conservative and more conducive.The response changes caused by K_(py),K_(px) and K_(sx) changes are nearly linear,while Ksy shows nonlinear characteristics and the most sensitivity.Wind attack angle at 75°and 90°has the greatest influence on the vehicle-bridge system.For ride comfort index,when pre-set wind speed(α=75°)reaches 20 m/s,the vertical acceleration firstly exceeds the limit value;when wind speed(α=90°)reaches 21.5 m/s,the lateral acceleration firstly exceeds the limit value,and the ride comfort of the vehicle cannot be guaranteed.For running safety index,when pre-set wind speed(α=75°)reaches 24.6 m/s,the wheel unloading coefficient firstly exceeds the limit;when pre-set wind speed(α=90°)reaches 24.5 m/s,the derailment coefficient firstly exceeds the limit,and the running safety cannot be guaranteed.The results can provide a suitable reference for the safe and stable operation of trains on the bridge.
文摘Accurate prediction of wind power is significant for power system dispatching as well as safe and stable operation. By means of BP neural network, radial basis function neural network and support vector machine, a new combined method of wind power prediction based on cooperative game theory is proposed. In the method, every single forecasting model is regarded as a member of the cooperative games, and the sum of square error of combination forecasting is taken as the result of cooperation. The result is divided among the members according to Shapley values, and then weights of combination forecasting can be obtained. Application results in an actual wind farm show that the proposed method can effectively improve prediction precision.
