Method for calculating reliability of long-span bridge members under action of windmill load

A calculation method and a large-span technology, applied in the direction of calculation, computer-aided design, special data processing applications, etc., can solve the problems of large sample point error and network prediction result error, so as to improve efficiency, reduce error results, and improve applicability Effect

Active Publication Date: 2018-12-07
CHANGAN UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the traditional neural network has a high fitting ability, the network predicti

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
  • Method for calculating reliability of long-span bridge members under action of windmill load
  • Method for calculating reliability of long-span bridge members under action of windmill load
  • Method for calculating reliability of long-span bridge members under action of windmill load

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] 1) Select the frequency of wind speed Pi (i ranges from 1 to 8, a total of 8 wind speeds), the annual average daily traffic volume growth rate gf, and the mechanical performance parameters of bridge components (such as elastic modulus E, damping C, and moment of inertia I) for a total of 12 parameters as the independent variable X, and the bridge member response as the dependent variable Y, construct the limit state function of the bridge member:

[0039] Y=g(X)(2)

[0040]2) Combining parameter data and loading effect data into a matrix, and randomly classifying it into two parts, one is the training sample matrix and the other is the testing sample matrix. The normalization function is used to normalize the sample, and the processed data is saved.

[0041] 3) Set the input parameters of the bridge structure limit state function fitting program based on the thinking evolution algorithm and neural network, and its flow chart is as follows figure 1 As shown, the initia...

Embodiment 2

[0045] 1) Taking a typical 840m cable-stayed bridge as the engineering background, calculate the stress results of the mid-span and bottom end of the main girder of the bridge under different loads. Combine different load combinations and load effect results into a matrix, and then divide them into training data and test data and perform normalization.

[0046] 2) The parameters of the limit state function fitting program for bridge structures based on the thinking evolution algorithm and neural network: set the population size to 200, the number of winning subpopulations, the number of temporary subpopulations and the number of hidden layer neurons are all 5, input The number of layer neurons is 12, and the number of output layer neurons is 1. Generate initial population, superior subpopulation and temporary subpopulation, and perform convergence and dissimilation operations to obtain the optimal individual. The convergence process of the initial winning subpopulation is as ...

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 method for calculating the reliability of long-span bridge members under the action of a windmill load. The method comprises the steps of firstly, determining parameter typesof a target bridge structure limit state function, collecting parameter data, randomly grouping the collected data, and performing normalization processing on the data; secondly, establishing an optimized limit state function fitting program based on a thought evolution algorithm and a neural network, performing calculation by adopting the thought evolution algorithm in the program to obtain an optimal individual as an initial weight value and a threshold value of the next-step calculation, substituting input data of a test set into a trained neural network for performing simulation prediction, comparing load effect data obtained by prediction with expected data, calculating an error, and evaluating a fitting effect of the obtained neural network; and finally, combining the trained network with a Monte Carlo method optimized by a particle swarm algorithm, thereby establishing an optimized reliability calculation method for finishing the calculation of the reliability of the long-spanbridge members under the action of the windmill load.

Description

technical field [0001] The invention belongs to the technical field of construction and traffic bridges, and in particular relates to a method for calculating the reliability of long-span bridge components under windmill loads. Background technique [0002] Due to the unique structural form of long-span bridges, critical geographical location, and heavy traffic load, once damaged or collapsed, it will cause serious traffic congestion or a large number of casualties and property losses. Therefore, evaluating the safety of long-span bridges becomes Particularly important. Safety assessment of long-span bridges based on reliability is usually a practical method to evaluate the safety of long-span bridges. The limit state function in the calculation often has high nonlinearity, and it is difficult to express it with an exact expression. Therefore, it is very necessary to find a better method to fit the limit state function. [0003] In the current calculation and analysis 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
IPC IPC(8): G06F17/50
CPCG06F30/13G06F2119/06
Inventor 武隽徐鹏飞丁彬元刘冉冉杨帆
Owner CHANGAN 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

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