An intelligent landslide monitoring device and method based on an LSTM long short-term memory network

A long-term and short-term memory and monitoring device technology, applied in neural learning methods, biological neural network models, forecasting, etc., can solve the problem of selection of methods, adjustment of parameters, optimization and implementation of early warning products, and does not take into account the timing of landslide monitoring data. , Landslide early warning technology is not in-depth and other problems, to achieve high accuracy and convenience, improve performance, improve the effect of accuracy

Inactive Publication Date: 2019-04-02
HOHAI UNIV
View PDF2 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Intelligent prediction and early warning technology supported by big data is rapidly emerging with the advent of the era of artificial intelligence, but the landslide early warning technology generally does not take into account the timing of landslide monitori

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 intelligent landslide monitoring device and method based on an LSTM long short-term memory network
  • An intelligent landslide monitoring device and method based on an LSTM long short-term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Such as figure 1 As shown, the monitoring device of the present invention includes: a data input module, a model training module, a model optimization module, a model visualization module and a user operation module; wherein the data input module is connected with the model training module; the model training module is connected with the model optimization module; the model optimization The module is connected with the model visualization module; the model visualization module is connected with the user operation module.

[0039] The data input module is responsible for the extraction of landslide historical monitoring data, the calibration of prediction results, and the division of data sets; the model training module is responsible for training data on the LSTM network and generating training models; the model optimization module is responsible for optimizing the training model and optimizing the data. The adjustment of the set division; the model visualization module...

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 discloses an intelligent landslide monitoring device and method based on an LSTM long and short term memory network, and relates to the field of landslide monitoring early warning and artificial intelligence. The method comprises the following steps of obtaining different input characteristic values of landslide historical monitoring data, such as surface deformation, deep displacement, underground water level, pore water pressure, seepage flow velocity and landslide instability, adding a data label, and dividing the monitoring data into a training set, a verification set and a test set according to a certain proportion; carrying out gradient descent training on the training set under an LSTM network to obtain a training model; using the verification set and the test set operate in the training model to obtain an accuracy result, determining the model and the data set adjustment direction through result analysis, and obtaining a monitoring model with high accuracy throughcontinuous debugging. By combining an artificial intelligence optimization algorithm, the accuracy of landslide disaster prediction is improved, the cost of the landslide disaster monitoring device is reduced, and the landslide disaster monitoring device is popularized to monitoring of other types of landslides in a large range after being combined with transfer learning.

Description

technical field [0001] The invention relates to the field of artificial intelligence deep learning in geological disaster landslide prediction and early warning, in particular to an intelligent landslide monitoring device and method based on LSTM long-short-term memory network. Background technique [0002] Because landslide disasters will bring serious life and economic losses to people, landslide disaster monitoring has always been a key research and development project, among which the prediction of landslide damage is to reduce the effective loss of landslide disasters. [0003] Intelligent prediction and early warning technology supported by big data is rapidly emerging with the advent of the era of artificial intelligence, but the early warning technology for landslides generally does not take into account the timing of landslide monitoring data, so the effect is not ideal. [0004] At present, the landslide early warning technology based on machine learning is general...

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
IPC IPC(8): G06Q10/04G06Q50/26G06N3/04G06N3/08
CPCG06N3/084G06Q10/04G06Q50/26G06N3/045
Inventor 王如宾祁健徐卫亚王环玲孟庆祥
Owner HOHAI UNIV
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