GNSS Data Mining for Train Positioning Test Case Generation

GNSS (Global Navigation Satellite System) for train positioning has been applied in advanced train control systems. GNSS as the input for train localization, testing GNSS positioning for train localization as function and performance is a necessary procedure throughout the entire lifecycle of the train control system, from design to operation. To generate corresponding GNSS for train localization test cases, it is essential and beneficial to go through data mining of various train operation records and analyze the failure modes of the GNSS for train localization operations. This paper focuses on analyzing the GNSS data recorded during train operation, considering both textual records and numerical data generated by GNSS receivers. The textual records comes from regular records logged by the trainborne equipment of ITCS (Incremental Train Control System) collected on the Qinghai-Tibet railway line, while the numerical data is extracted from the processed NMEA (National Marine Electronics Association) data and RINEX (Receiver INdependent EXchange) format files. A semantic analysis method based on the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm is used to mine the textual records, identifying important feature words and utilizing fault tree analysis to determine the causes of the failure modes. For the numerical data, a machine learning approach based on SSA-XGBoost (Sparrow Search Algorithm-eXtreme Gradient Boosting) is employed, followed by the application of the Shapley additive explanation method to identify the most important parameters. Through the mining and analysis of textual records, we identified that “Bad satellite geometry” “Poor satellite signal quality” and “Insufficient Number of visible satellites” are important fault causes when compiling test cases. FTA (Fault Tree Analysis) modelling method is used to determine the root cause of these failures as “positioning environment is restricted”. Through the mining and analysis of numerical data, we have determined that it is crucial to model the 3 key parameters of SNR_mean, HDOP, and PRerror_mean during the testing process. By mining and analyzing these textual records and numerical data, the paper provides clear directions and effective foundations for the generation of GNSS test cases for train localization. Based on the mining results, key failure modes and parameters to design more targeted and comprehensive test cases, improving testing effectiveness and comprehensiveness.