Abstract
Corrugated webs are used to increase the shear stability of steel webs of beam-like members and to eliminate the need of transverse stiffeners. Previously developed formulas for predicting the shear strength of trapezoidal corrugated steel webs, along with the corresponding theory, are summarized. An artificial neural network (ANN)-based model is proposed to estimate the shear strength of steel girders with a trapezoidal corrugated web, and under a concentrated load. 210 test results from previous published research were collected into a database according to relevant test specimen parameters in order to feed the simulated ANNs. Seven (geometrical and material) parameters were identified as input variables and the ultimate shear stress at failure was considered the output variable. The proposed ANN-based analytical model yielded maximum and mean relative errors of 0.0% for the 210 points from the database. Moreover, still based on those points, it was illustrated that the ANN-based model clearly outperforms the other existing analytical models, which yield mean errors larger than 13%.
Highlights
Corrugated steel plates without additional stiffeners are characterized by high shear buckling strength and out-of-plane flexural stiffness, having been widely used in structural engineering applications, such as large span roof, steel plate shear walls, and bridge girders (Wu et al 2006, He et al 2012, Emami et al 2013, Jiang et al 2015)
This paper focuses on the shear strength of steel webs with trapezoidal corrugations, a topic that has been extensively studied since the end of 20th century, covering both buckling and plasticity phenomena (e.g., Bergfelt & Leiva-Aravena, 1984, Leiva-Aravena & Edlund 1987, Johnson & Cafolla 1997, Metwally 1998, Sayed-Ahmed 2001, 2007, Abbas 2003)
In order to effectively estimate the shear capacity of corrugated web steel girders, this paper proposes the use of artificial neural networks, a popular machine learning technique
Summary
Corrugated steel plates without additional stiffeners are characterized by high shear buckling strength and out-of-plane flexural stiffness, having been widely used in structural engineering applications, such as large span roof, steel plate shear walls, and bridge girders (Wu et al 2006, He et al 2012, Emami et al 2013, Jiang et al 2015). Yamazaki (2001) proposed formulae for the computation of the buckling strength of corrugated webs, based on results from 6 full-scale models of steel bridge girder webs. Driver et al (2006) tested full-scale corrugated web girders made of HPS 485W steel, assessed the effect of web initial geometric imperfections through measurements of the out-of-plane displacements, and proposed a lower bound design equation that accounts for both local and global buckling of the web in the elastic and inelastic domains. Leblouba et al (2017a, b) conducted laboratory tests on a series of corrugated steel web beams to investigate their shear behaviors; three typical failure modes were observed and the failure mechanisms on the post-buckling phase were assessed; besides, five analytical models for the estimation of the critical shear buckling stress based on FE analysis results were proposed and validated against test data. The focus of this study was not to understand the mechanics underlying the shear behavior of corrugated steel webs, but parametric studies by means of accurate and robust ANN-based models make it possible to evaluate and improve existing mechanical models
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
