Research On The Intelligent Management System Of Field Test Data For Train Control System

CTCS-3 train control system is the key technology to ensure the safety and high efficiency of high speed train operation.In order to verify whether a CTCS-3 train control system is in compliance with related technical specifications,as well as to ensure the cross-the-line-operation of trains,it is necessary to carry out a series of testing including laboratory testing,field testing,integrated testing and commissioning,as well as interoperability testing,for which test sequences shall be prepared.The field testing is very complex,involving not only the operation of the whole train control system,but also the cooperation of other railway departments including rolling stock,power supply and transportation organization and so on.If the test sequences are not arranged properly,it may consume a lot of manpower,materials and financial resources,and have potential safety hazards.In the field testing,due to the need to improve the coverage of test cases and the arrangement of re-testing some important test cases,the people responsible for preparing the test sequences need to know in detail the progress of the testing.At present the statistics of testing situation is carried out manually,which is time consuming and of heavy workload.Therefore it is necessary to study an automatic statistics method for testing situation.To tackle this issue,on the basis of summarizing the previous researches,the image recognition technique is adopted to identify DMI interface information,based on which an intelligent field testing data management system is designed and implemented.The main works include:1.Based on the requirements of field testing,the function of the testing data management system is analyzed,and its overall scheme is proposed.2.The features of the DMI interface are analyzed,and accordingly the DMI interface information is divided into two categories,namely icons and characters.According to the types of elements needed to be identified,the method of DMI image recognition is designed,with the major processes including interface positioning and tilt correction,image preprocessing,feature extraction and feature recognition.The recognition methods for different types of DMI elements are specially studied,with template matching adopted for icon classification,and the K-Nearest Neighbor adopted for character identification.3.The requirements analysis and overall design of intelligent field testing data management system are carried out,and the DMI information recognition module,test cases management module,and intelligent field test data management module are designed in detail.The system is developed under Visual Studio 2013,with the combination of MFC and OpenCV(Open Source Computer Vision Library).Test cases database and test record database are designed,which can realize the retrieving,addtion,modifying,exporting of relevant data.