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

An extension method of artificial neural network training data in geological orientation

An artificial neural network, training data technology, applied in the fields of geology and artificial intelligence, to achieve the effect of increasing accuracy, fully learning, and improving accuracy

Active Publication Date: 2021-06-18
THE FIRST INST OF OCEANOGRAPHY SOA
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to aim at the deficiencies in the prior art, and provide a kind of extension method of artificial neural network training data in geological direction, this extension method can analyze, process and expand limited small amount of data, reach the existing artificial neural network Training model learning needs to obtain accurate prediction models

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 extension method of artificial neural network training data in geological orientation
  • An extension method of artificial neural network training data in geological orientation
  • An extension method of artificial neural network training data in geological orientation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described in detail below in conjunction with specific examples, but this does not constitute any limitation on the present invention.

[0045] The expansion method of the artificial neural network training data of a kind of geological direction of present embodiment is as follows figure 1 and Figure 4 shown, including the following steps:

[0046] Step A, acquisition of geological data:

[0047] In this embodiment, earthquake liquefaction prediction based on CPT data is used. After screening, there are earthquake magnitude, penetration depth, total vertical stress, effective vertical stress, cone end resistance and surface normalized peak acceleration. These 6 parameters are For calculation, there are 166 groups of seismic liquefaction measured data (ie, original data) from all over the world.

[0048] Step B, data analysis and screening:

[0049]The penetration depth, total vertical stress, and effective vertical stress are s...

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 present invention relates to the technical fields of geology and artificial intelligence, in particular to a method for expanding training data of artificial neural networks in the direction of geology, including step A, acquisition of geological data, step B, data analysis and screening, step C, data expansion and preprocessing, Step D, model training and step E, accuracy verification, this extension method is applicable to the field of marine geology and similar fields with a small amount of training data, through analysis, processing and expansion of a limited amount of existing data to meet the current large The demand for training data meets the learning needs of the existing artificial neural network training model and obtains an accurate prediction model. Therefore, through the method of the present invention, in artificial intelligence learning, the data can be expanded when the amount of sample data is small, the accuracy of training with a small amount of data can be improved, and the limited data can be deeply excavated to achieve full learning and increase purpose of accuracy.

Description

technical field [0001] The invention relates to the technical fields of geology and artificial intelligence, in particular to a method for expanding training data of artificial neural networks in the direction of geology. Background technique [0002] Artificial intelligence technology is currently widely used in various fields around the world. Whether it is image recognition, voice recognition, automatic driving or the use of search engines, it has brought great convenience to people's lives. In the geological field, artificial intelligence technology has gradually been widely used, such as satellite image recognition, disaster early warning, and various geological data predictions. The most basic idea of ​​artificial intelligence algorithm is to use the existing model, learn and correct the training data, and finally obtain the appropriate internal parameters of the model, and use it in the next step. Among them, artificial neural network, as a supervised machine learnin...

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): G06K9/62G06N3/04G06N3/08G06Q50/02
CPCG06N3/08G06Q50/02G06N3/045G06F18/214
Inventor 杜星赵晓龙
Owner THE FIRST INST OF OCEANOGRAPHY SOA