Engineering control network coordinate system establishment method and system based on machine learning

Abstract

The invention discloses an engineering control network coordinate system establishment method based on machine learning. The method comprises the following steps: establishing a high-precision side length projection deformation calculation model; establishing an optimization function; initializing a solution space, and initializing a group of initial solutions in the solution space; obtaining coordinates of all points in the initial solution, substituting the coordinates into an optimization evaluation formula in the optimization function, and calculating a function value of each point coordinate; comparing the function value of each point coordinate to obtain a position coordinate corresponding to a minimum value of the function, and marking the position coordinate as an optimal solution of initial iteration; iteratively updating all real-time point coordinates of the engineering control network, calculating to obtain target optimal solution position coordinates, and taking the target optimal solution position coordinates as global optimal solution position coordinates; and judging whether the position coordinate of the global optimal solution meets the tolerance requirement or not. The invention also discloses an engineering control network coordinate system establishment system based on machine learning. According to the method, the accuracy and the calculation efficiency of coordinate system optimization selection are improved.

Description

technical field [0001] The invention relates to the technical field of engineering control network, in particular to a method and system for establishing a coordinate system of an engineering control network based on machine learning. Background technique [0002] At present, the coordinate system of my country's engineering control network is a plane Cartesian coordinate system with a Gaussian 3° zone. Therefore, the ground distance observations of the engineering control network must be uniformly reduced to the earth ellipsoid of the CGCS2000 coordinate system, and then projected onto the corresponding Gaussian plane according to the Gauss-Krüger projection rule. In this reduction process, the measured side length of the ground is first reduced to the length of the ellipsoidal geodetic line, and then further projected as the length of the chord line between corresponding points on the Gaussian plane. There are two side length deformations in total. And the specification r...

AI Technical Summary

Problems solved by technology

The applicability of the previous coordinate system establishment algorithm is not high. At this time, in order to facilitate the real-time performance of mine measurement, it is necessary to establish a unified construction control measurement coordinate system for the underground and the underground.

Images