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

Building earthquake damage early warning method and system based on feedforward neural network

A feedforward neural network and architecture technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as long duration and long computing time, and achieve the effect of rapid damage and reduced computing time.

Pending Publication Date: 2022-04-12
YANGZHOU UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For a destructive earthquake, its duration is long, while the traditional finite element calculation method is slow, the calculation time is long, and the remaining time is not enough to carry out early warning and implement safety measures such as evacuation before the earthquake is transmitted to the building

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
  • Building earthquake damage early warning method and system based on feedforward neural network
  • Building earthquake damage early warning method and system based on feedforward neural network
  • Building earthquake damage early warning method and system based on feedforward neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be further described below in conjunction with the accompanying drawings.

[0061] Such as figure 1 As shown, a kind of building earthquake damage early warning method based on feedforward neural network described in the present invention comprises the following steps:

[0062] 1. Collect the acceleration signal of the earthquake and the displacement between the floors of the building due to the earthquake

[0063] Acquisition of seismic acceleration signals at different times by using seismic sensors a i , i represents the moment, i=1...n, n is a natural number greater than 1; obtain the ground motion matrix A, A=[a 1 ...a n ];

[0064] Use the displacement sensor to acquire and collect the displacement along the length direction of the floor and the displacement along the width direction of the floor of different floors at different times, and obtain the displacement matrix D between floors.

[0065] The number of floors of the target b...

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 a building earthquake damage early warning method and system based on a feedforward neural network. The building earthquake damage early warning method comprises the steps that (1) an earthquake motion matrix A and an initial state interlayer displacement matrix D initial are acquired; (2) fusing the seismic oscillation matrix A, the initial state interlayer displacement matrix D and the initial state matrix to obtain input data I; (3) taking the input data I as the input of the feedforward neural network for training, and outputting an interlayer deformation matrix U; performing goodness of fit test on the output interlayer deformation matrix U and the target matrix T, and stopping training when the fitting precision is greater than a preset threshold value to obtain a trained feedforward neural network; (4) obtaining to-be-tested input data I ', and inputting the to-be-tested input data I' into the trained feedforward neural network to obtain an output interlayer deformation matrix U '; and (5) selecting the maximum value in the interlayer deformation matrix U ', and comparing the maximum value with a building structure critical value to obtain an analysis result. According to the invention, the damage condition of the earthquake to the building can be analyzed in a short time.

Description

technical field [0001] The invention relates to the field of building earthquake damage early warning and monitoring, in particular to a building earthquake damage early warning method and system based on a feedforward neural network. Background technique [0002] The same earthquake causes different levels of damage to different building structures, and the early warning of earthquake damage should be predicted according to the actual situation of the building. Seismic signals are collected by multiple detection points and can be directly transmitted to the building computing center at the speed of light at 3×105km / s. Taking the epicenter distance of 100km as an example, the signal transmission speed is 3×10-4s, and the earthquake transmission time to the building is 10-100s, that is, there is a time difference of 10-100s for the earthquake damage judgment and early warning evacuation of the building. For destructive earthquakes, the duration is long, while the traditional...

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): G06N3/04G06N3/08G06Q10/04G06Q50/26
Inventor 张贺姜治军张磊
Owner YANGZHOU UNIV