Study on GNSS Double Difference Attitude Determination Based Train Track Occupancy Discrimination Method

Abstract

In order to solve the problem of the train track occupancy discrimination and to meet the requirements of CTCS-4 train control system, a method was proposed based on GNSS double difference attitude determination for train track occupancy discrimination. A mathematical model of train GNSS double difference attitude determination was established, and a risk-sensitive filtering algorithm based on particle filter was proposed on the basis of obtaining the train baseline heading angle. The risk-sensitive factor was introduced to solve the problem of poor robustness and divergence of the filter caused by the uncertainty of the system. Meanwhile, a classification algorithm based on support vector machine was proposed by which, track occupancy was determined through data classification. Finally, the influence of the number of visible satellites and the HDOP value on the track occupancy discrimination was further studied and the optimization parameters were obtained. Experimental results show the feasibility and effectiveness of this method which provides reference value for the application of the satellite positioning technology in trains in the future.