Unlock instant, AI-driven research and patent intelligence for your innovation.

An Interpolation Calculation Method for Elevation Anomaly Fitting Based on Mobile Neural Network

An abnormal elevation and neural network technology, applied in biological neural network models, neural architectures, etc., can solve problems such as model errors and errors, and achieve the effect of reducing model errors and high precision

Inactive Publication Date: 2017-12-08
SHANDONG JIAOTONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Interpolation of elevation anomalies in low-resolution quasi-geoids will bring large errors. Surface fitting interpolation uses regular surfaces to fit irregular quasi-geoids, and the interpolation process will also bring model error

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Interpolation Calculation Method for Elevation Anomaly Fitting Based on Mobile Neural Network
  • An Interpolation Calculation Method for Elevation Anomaly Fitting Based on Mobile Neural Network
  • An Interpolation Calculation Method for Elevation Anomaly Fitting Based on Mobile Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0023] see figure 1 , figure 2 with image 3 . figure 1 It is a schematic block diagram of an elevation anomaly fitting interpolation calculation method based on a mobile neural network in a preferred embodiment of the present invention, figure 2 It is a schematic structural diagram of a mobile neural network in a preferred embodiment of the present invention, image 3 It is a schematic diagram of the mobile neural network interpolation method in the preferred embodiment of the present invention.

[0024] The height anomaly fitting and interpolation calculation method based on the mobile neural network in the embodiment of the present invention comprises steps:

[0025] S1: construct a BP neural network model, wherein the BP neural network model includes an input layer, a hidden layer comprising neurons and an output layer, and each elem...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an elevation anomaly fitting interpolation calculation method based on a mobile neural network, which includes constructing a BP neural network model, the BP neural network model includes an input layer, a hidden layer with neurons, and an output layer, and each element of the input layer passes a weight The value matrix is ​​connected to the neuron; with the discrete GPS point as the center, select the grid node whose geodetic longitude difference and geodetic latitude difference with the point are less than a predetermined number of grid intervals in the quasi-geoid grid numerical model The geodetic coordinates and elevation anomalies of points; use the geodetic coordinates and elevation anomalies of a predetermined number of grid nodes to form a learning set sample, train the neural network, and generate a network weight matrix when the network performance index reaches the preset extreme value; In the neural network weight matrix, the geodetic coordinates of the discrete GPS points are input, and the elevation anomalies of the points are calculated and generated. The method of the embodiment of the present invention has the advantage of high precision in fitting and interpolating calculation of elevation anomalies.

Description

technical field [0001] The invention relates to the field of geodesy, in particular to an elevation anomaly fitting interpolation calculation method based on a mobile neural network. Background technique [0002] In engineering applications, my country uses the normal height as the legal height system. The normal height is an elevation system defined based on the quasi-geoid. The elevation information obtained by GPS (GPS, Global Positioning System) technology is relative to the WGS-84 ellipsoid. Only when the earth height is converted into a normal height can it be directly applied to engineering construction. In today's GPS positioning era, establishing and refining a quasi-geoid model is establishing and maintaining a national elevation reference frame. The high-precision and high-resolution quasi-geoid numerical model can give the elevation anomaly at any point, which can be regarded as a reference frame for measuring the normal height. If the accuracy of GPS geodetic h...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/04
Inventor 宋雷王德保李晋周保兴
Owner SHANDONG JIAOTONG UNIV