Earthquake prediction system based on neural network

An earthquake prediction and neural network technology, applied in the field of earthquake prediction system based on neural network, can solve problems such as psychological burden, economic damage, casualties, etc., and achieve the effect of simple operation, strong generalization ability and wide application

Inactive Publication Date: 2016-10-12
INSPUR GROUP CO LTD
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] According to statistics, there are more than 5 million earthquakes every year on the earth, among which there are more than 10 earthquakes that can cause serious harm to human beings. bring a serious burden
[0003] The current level of science and technology cannot accurately predict the arrival of earthquakes, so a new type of earthquake prediction device is urgently needed

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
  • Earthquake prediction system based on neural network
  • Earthquake prediction system based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The content of the present invention is described in more detail below:

[0023] The acquisition devices can be distributed in places where earthquakes are frequent across the country. The acquisition devices contain network modules and seismographs, which can send the collected seismic wave information and location information to the earthquake prediction device through the network.

[0024] The generation of the earthquake prediction device is mainly by constructing a convolutional neural network and training it, and it can be formed after the training is completed. The convolutional neural network includes an input layer, a first convolutional layer, a first sampling layer, a second convolutional layer, a second sampling layer, a fully connected layer, an output layer, and so on. First, a large number of seismic wave information pictures during and without earthquakes are input into the neural network. After a large number of iterations, the neural network reaches co...

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 earthquake prediction system based on a neural network, and belongs to the field of artificial intelligence. The system comprises a data acquisition device, an earthquake prediction device and a monitoring alarm center. The data acquisition device is mainly formed by a seismometer and a network module, and is used for collecting seismic waves and transmitting the data through a network. The earthquake prediction device is generated through the following steps: to begin with, selecting a lot of training sample sets, which are mainly related to seismic wave pictures; then, constructing a convolution neural network system; and training the neural network through training data, and when training is finished, generating the earthquake prediction system. The monitoring alarm center is mainly used for analyzing the output of the neural network and the data of the data acquisition device to predicate which place is about to have an earthquake. Through the universal convolution neural network model, the earthquake prediction system overcomes the defect that a feature matching algorithm is not completely considered, has good generalization ability and improves predication accuracy.

Description

technical field [0001] The invention relates to artificial intelligence technology, in particular to an earthquake prediction system based on a neural network. Background technique [0002] According to statistics, there are more than 5 million earthquakes every year on the earth, among which there are more than 10 earthquakes that can cause serious harm to human beings. pose a serious burden. [0003] The current level of science and technology cannot accurately predict the arrival of earthquakes, so a new type of earthquake prediction device is urgently needed. Contents of the invention [0004] Nowadays, with the rise of artificial intelligence neural networks, it is possible for machines to abstract themselves and learn the characteristics of things. Therefore, the present invention proposes an earthquake prediction system based on a neural network. Machines can help us predict earthquakes by analyzing data from earthquakes over the years. [0005] The solution of ...

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 Applications(China)
IPC IPC(8): G01V1/00G06N3/02
CPCG01V1/008G06N3/02
Inventor 尹超李朋姜凯
Owner INSPUR GROUP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap