Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for distinguishing seismic liquefaction and a seismic liquefaction potential model

A discrimination method and technology for liquefaction sites, applied in neural learning methods, biological neural network models, design optimization/simulation, etc., can solve problems such as missing index data, redundancy, and inconsistency in the definition of liquefaction discrimination indexes

Pending Publication Date: 2019-01-15
INST OF GEOPHYSICS CHINA EARTHQUAKE ADMINISTRATION
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] There are many factors that affect site liquefaction. Due to the limitation of objective physical conditions, there is not yet a set of recognized complete and unified liquefaction discrimination indicators. The definitions of liquefaction discrimination indicators in different regions or even between different earthquakes in the same region are inconsistent, and some index data are missing. surplus phenomenon

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
  • A method for distinguishing seismic liquefaction and a seismic liquefaction potential model
  • A method for distinguishing seismic liquefaction and a seismic liquefaction potential model
  • A method for distinguishing seismic liquefaction and a seismic liquefaction potential model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Embodiment 1 of the present invention provides a method for discriminating earthquake liquefaction, such as figure 1 As shown, the method includes the following steps:

[0036] Collecting seismic liquefaction site data as a training set, said seismic liquefaction site data including liquefaction discriminant indicators;

[0037] Use the liquefaction discrimination indicators in the training set to conduct deep learning seismic liquefaction discrimination training to generate a seismic liquefaction potential model;

[0038] According to the seismic liquefaction potential model, the liquefaction discrimination is carried out on the measured data, and the liquefaction discrimination results are obtained.

[0039] The invention provides an earthquake liquefaction discrimination method. The original data used in the invention include 382 cases of standard penetration test site data including China and the United States. Among them, the US liquefaction site database compreh...

Embodiment 2

[0041] Embodiment 2 of the present invention provides a method for discriminating earthquake liquefaction, which is basically the same as that of Embodiment 1, the difference is that, as image 3 As shown, using the training set for deep learning seismic liquefaction discrimination training, the generation of seismic liquefaction potential model includes:

[0042] The liquefaction discrimination indicators in the training set are used as the data of the input layer, among which there are 12 liquefaction discrimination indicators, which are magnitude (Mw), horizontal peak acceleration (PGA), critical depth of liquefaction (ds), and groundwater depth (dw) , the overlying total stress (σ v ), the overlying effective stress (σ v ’), equivalent clean sand corrected standard penetration number ((N1) 60CS ), fine particle content (FC), soil shear stress reduction factor (τ d ), overlying pressure correction factor (K σ ), the magnitude correction factor (MSF), and the soil cyclic...

Embodiment 3

[0047] Embodiment 3 of the present invention provides a seismic liquefaction discrimination method, which is basically the same as Embodiment 2, except that the number of nodes in each hidden layer is 7, 3, 4 and 3 respectively. By adjusting the number of nodes in each layer of the hidden layer, the systematic error of the network can be reduced, and the training time of the network can be kept short, the optimal point can be easily found during training, and the probability of "overfitting" in the training process can be reduced. When the number of nodes is adjusted The effects of the above nodes cannot be achieved during adjustment.

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 liquefaction judging method and an earthquake liquefaction potential model. The method includes collecting earthquake liquefaction site data as a training set; theseismic liquefaction potential model is generated by using the liquefaction discrimination indexes in the training set to discriminate the seismic liquefaction. According to the seismic liquefactionpotential model, the liquefaction data are judged and the liquefaction judgement results are obtained. Based on the depth-learning algorithm, this method realizes the high-precision nonlinear modelingof earthquake liquefaction with uncertainty, randomness and multi-factor coupling, and the discrimination accuracy is over 95%. It can be used as a supplement to the deterministic methods such as experience and laboratory tests, and can provide support for exploring the scientific problems of the deep mechanism of earthquake liquefaction.

Description

technical field [0001] The invention belongs to the technical field of seismic liquefaction discrimination, in particular to a seismic liquefaction discrimination method and a seismic liquefaction potential model. Background technique [0002] In the past two decades, catastrophic earthquakes around the world have frequently been accompanied by large-scale liquefaction and the serious damage to ground structures and underground facilities caused by it, such as the large-area liquefaction in the Osaka Bay area caused by the 1995 Hanshin Earthquake , The series of earthquakes in New Zealand in 2010-2011 caused repeated severe liquefaction in the coastal city of Christchurch, and the severe liquefaction in the Tokyo Bay area caused by the 2011 Japanese earthquake. The phenomenon of liquefaction and earthquake damage in the 2008 Wenchuan Ms8.0 earthquake in my country was remarkable, and it was the one with the most extensive area and the most abundant macroscopic phenomena sinc...

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): G06F17/50G06N3/04G06N3/08
CPCG06N3/084G06F30/20G06N3/045
Inventor 陈苏李小军周越戴志军高爽郑经纬
Owner INST OF GEOPHYSICS CHINA EARTHQUAKE ADMINISTRATION
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com