Research On Speed Measurement And Positioning Method Of Train Multi-information Fusion Based On RBFNN Optimization

With the development of Global Navigation Satellite System(GNSS)and Inertial Navigation System(INS),the GNSS/INS integrated navigation system composed of them is playing an increasingly important role in the fields of military,navigation,highway and railway.Compared with a single system,the integrated navigation system has improved positioning accuracy and stability.However,during train operation,due to special line conditions such as tunnels,the GNSS signal will be interrupted.In this scenario,part of the measurement information will be missing in the GNSS/INS integrated navigation system,resulting in only INS working in the system.The pure INS positioning error will continue to diverge over time,and the overall navigation accuracy will also decrease.Aiming at this practical problem,this paper conducts related research in two major aspects of integrated navigation system modeling and neural network optimization integrated navigation.The main work is as follows:Firstly,according to the structure of the integrated navigation system and the functional characteristics of the subsystems,this paper analyzes the errors of GNSS and INS.On this basis,the error source model is established,the error equation and measurement equation of the integrated navigation system are deduced,and a GNSS/INS loosely coupled integrated navigation scheme is proposed.Then,in order to improve the navigation accuracy after GNSS interruption,the Radial Basis Function Neural Network(RBFNN)is introduced into the integrated navigation system,and a RBFNN optimized integrated navigation algorithm is studied.This algorithm can use the trained neural network to estimate the error of the INS after the GNSS signal is missing,and to compensate the error of the INS,so as to achieve the purpose of improving the overall navigation accuracy of the integrated navigation system.Finally,the simulation test is carried out by using the MATLAB toolbox,the simulation inertial device is designed,and a variety of operating scenarios with missing GNSS signals are built.The performance test of the integrated navigation system and integrated navigation algorithm proposed in this paper is carried out by using the navigation information obtained from the simulation trajectory.The experimental results show that the integrated navigation algorithm optimized by RBFNN can provide better accuracy when the GNSS signal is missing for a short time.There are 41 pictures,14 tables and 64 references.