Deflection prediction analysis of corrugated steel web composite box-girder bridge based on MEC-BP neural network

Wanpeng Ren; Yunteng Bai; Baoping Liu; Benjin Pan

doi:10.1117/12.2613628

10 November 2021 Deflection prediction analysis of corrugated steel web composite box-girder bridge based on MEC-BP neural network

Wanpeng Ren, Yunteng Bai, Baoping Liu, Benjin Pan

Author Affiliations +

Proceedings Volume 12050, International Conference on Smart Transportation and City Engineering 2021; 120500S (2021) https://doi.org/10.1117/12.2613628
Event: 2021 International Conference on Smart Transportation and City Engineering, 2021, Chongqing, China

Abstract

Corrugated steel web continuous rigid frame bridge has the advantages of low resource consumption and low environmental impact. It will become an important part of low-carbon construction of civil engineering. This paper presents an effective method for predicting the deflection of continuous rigid frame bridges with corrugated steel webs. The method includes three analysis stages: (1) obtain the data set to establish the prediction model (2) establish the optimized neural network model combined with mind evolutionary computation (MEC) algorithm and back propagation (BP) algorithm. (3) The optimized mec-bp model is used to predict the deflection of CSWS PC bridge construction. The feasibility of this method is verified by an actual CSWS PC bridge. The results show that compared with the traditional BP model, this method has better prediction performance, can accurately predict the deflection of CSWS PC Bridge in the construction process, and provide effective help for construction control.

Citation Download Citation

Wanpeng Ren, Yunteng Bai, Baoping Liu, and Benjin Pan "Deflection prediction analysis of corrugated steel web composite box-girder bridge based on MEC-BP neural network", Proc. SPIE 12050, International Conference on Smart Transportation and City Engineering 2021, 120500S (10 November 2021); https://doi.org/10.1117/12.2613628

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available