A Train Integrated Positioning Method Based On Received Signal Strength For Urban Rail Transit

In recent years,urban rail transit has been developing rapidly,which provides great convenience for passengers.Nevertheless,it consumes vast amounts of energy.Accordingly,the energy-efficient operation of metro trains is an essential energy-saving technology.And it needs the data of train operation energy consumption with a unified time and space scale as the basis for analysis.However,among the required data,the train position cannot be directly measured and is difficult to be acquired from other systems,such as the on-board signaling equipment.Therefore,a relatively independent train positioning method should be designed.Considering the particular operation environment of metro train,the positioning method needs to avoid interference with the safety of train operation and be suitable for both ground and underground.Besides,it also should be low-cost and accurate enough for energy-saving analysis.To satisfy these requirements,this thesis mainly does the following research:(1)This thesis compares the characteristics of different positioning methods applied in railway and other fields.The development of wireless positioning and its application in railway are reviewed;meanwhile,train integrated position methods are introduced.Then,the RSS(Received Signal Strength)/IN S(Inerti al Navigation System)/GNSS(Global Navigation Satellite System)-based train integrated positioning method is proposed,which comprises the RSS-based train positioning method and its integration with other train positioning methods.(2)In the RSS-based metro train positioning method,this thesis firstly presents the characteristics of different wireless positioning techniques.Then a fingerprint positioning algorithm for metro train based on deep learning is proposed.Finally,the model of fingerprint positioning and the simulation environment are established to verify the effectiveness of the algorithm.(3)In the RSS/INS/GNSS-based integrated positioning method,first,the preprocessing methods for positioning data is introduced.Second,the "current" statistical model is used to represent the train state equation,then the INS/GNSS-based data fusion algorithm is designed on adaptive Kalman filter.Finally,the fused train position is further corrected to obtain the final train position.Moreover,the train integrated positioning method under special conditions is discussed.(4)Based on the proposed method,the train positioning module has been implemented in the train energy measurement device.And some experiments have been conducted on Yizhuang line of Beijing subway during non-operational hours.The data obtained by the device and some simulation data are together used to verify the accuracy of the proposed method under different conditions.Between the specific stations,the RSS-based metro train integrated positioning method has the smallest mean absolute error,which is 5.54 meters.The maximum mean absolute error of different integrated positioning methods under special conditions is 18.97 meters.The results satisfy the accuracy requirements for train positioning in the research on the energy-efficient operation of metro train,so it can be used as analysis basis for the research.