Railcar iterative optimization positioning system, method and program product

Abstract

This invention discloses an iterative optimization positioning system, method, and program product for a railcar. The system includes constructing a training dataset of phase difference and distance; using phase difference as input and distance as output; constructing a Gaussian process prior equation based on the training dataset; determining the nonlinear mapping relationship between phase difference and distance in the Gaussian process prior equation; optimizing the Gaussian process prior equation; constructing a marginal likelihood maximization function with the objective of maximizing the logarithmic marginal likelihood; solving the marginal likelihood maximization function using a finite-memory quasi-Newton optimization algorithm; obtaining the optimal hyperparameters of the optimized Gaussian process prior equation; forming a Gaussian process model based on the nonlinear mapping relationship between phase difference and distance and the optimal hyperparameters; and using the Gaussian process model and the real-time phase difference between the railcar and two preset positioning points to predict the distance between the railcar and the destination.

Images