A novel machine learning model, eXtreme Gradient Boosting (XGBoost), was used for the purpose of evaluating the moment capacity of cold-formed steel (CFS) channel beams with edge-stiffened web holes subject to bending. A total of 1620 data points were generated for training the XGBoost model, using an elasto-plastic finite element model which was validated against 12 sets of test data taken from the existing literature. The R2 score of XGBoost predictions for the moment capacity was around 99%. The performance of current design equations was evaluated through the comparison of their results against those obtained from the XGBoost model. The moment capacities obtained from the XGBoost testing dataset were also compared with that determined from the existing design equations for un-stiffened holes (USH) and edge-stiffened holes (ESH). The moment capacities determined from the current design equations for USH and ESH were found to be excessively conservative by 38.3%, and unconservative by 36.2% on average, respectively. Therefore, new design equations were proposed based on the results of parametric study using the XGBoost model. In the detailed parametric analysis, the effects of web depth, section thickness, and beam length on the moment capacity of channel beams (CFSCB) with ESH were considered. From the results of XGBoost outputs, the absolute percentage error of new design equations for that based on the strengths of unperforated CFSCB was 8.78%, and for that based on the strengths of CFSCB with USH, the absolute percentage error was 13.7%. Additionally, a reliability analysis was performed to evaluate the accuracy of the proposed equations that were used to predict the moment capacity of CFS channel beams with ESH subject to bending. The reliability indices of all the proposed equations were greater than 2.5 which can be reliable as per the guidelines of AISI. 

A novel machine learning model to predict the moment capacity of cold-formed steel channel beams with edge-stiffened and un-stiffened web holes

This paper investigates the structural behaviour of cold-formed steel (CFS) back-to-back (BTB) channel sections subjected to axial compression at elevated temperatures. The stress-strain curves of G250 grade CFS channels at ambient and elevated temperatures were taken from the literature, where the temperature varied from 20 to 700 °C. A detailed parametric analysis comprising 1554 validated finite element models was studied to investigate the effect of section size, web openings and elevated temperature on the structural behaviour of such channel sections. Based on the parametric analysis results, the design equations for axial strength reduction factors for CFS BTB channel sections at elevated temperatures were proposed, which outperformed the equations available in the design guidelines of American standard (AISI S100-16) and Australian/New Zealand standard (AS/NZS 4600:2018). Reliability analysis was then conducted, the results of which showed that the proposed design equations could closely predict the axial strength of CFS BTB channel sections at elevated temperatures. 

Structural behaviour of back-to-back cold-formed steel channel sections with web openings under axial compression at elevated temperatures

/pdf/an-improved-and-robust-finite-element-model-for-simulation-234udn9r.pdf

Guan Quan

Papers

An improved and robust finite element model for simulation of thin-walled steel bolted connections

An improved and robust finite element model for simulation of thin-walled steel bolted connections

Computational modelling of Cold-formed steel lap joints with screw fasteners

Digital and automatic design of free-form single-layer grid structures

A practical shear wall layout optimization framework for the design of high-rise buildings