• Steel and Composite Structures
• /
• v.49 no.4
• /
• pp.419-430
• /
• 2023

This paper is aimed at investigating the effect of multiple longitudinal stiffeners on the patch loading resistance of slender steel plate girders. Firstly, a numerical study is conducted through geometrically and materially nonlinear analysis with imperfections included (GMNIA), the model is validated with experimental results taken from the literature. The structural responses of girders with multiple longitudinal stiffeners are compared to the one of girders with a single longitudinal stiffener. Thereafter, a patch loading resistance model is developed through machine learning (ML) using symbolic regression (SR). An extensive numerical dataset covering a wide range of bridge girder geometries is employed to fit the resistance model using SR. Finally, the performance of the SR prediction model is evaluated by comparison of the resistances predicted using available formulae from the literature.

• Steel and Composite Structures
• /
• v.29 no.3
• /
• pp.309-318
• /
• 2018

Steel girders are the structural members often used for passing long spans. Mostly being subjected to patch loading, or concentrated loading, steel girders are likely to face sudden deformation or damage e.g., web breathing. Horizontal or vertical stiffeners are employed to overcome this phenomenon. This study aims at assessing the feasibility of a machine learning method, namely the support vector machines (SVM) in predicting the patch loading resistance of longitudinally stiffened webs. A database consisting of 162 test data is utilized to develop SVM models and the model with best performance is selected for further inspection. Existing formulations proposed by other researchers are also investigated for comparison. BS5400 and other existing models (model I, model II and model III) appear to yield underestimated predictions with a large scatter; i.e., mean experimental-to-predicted ratios of 1.517, 1.092, 1.155 and 1.256, respectively; whereas the selected SVM model has high prediction accuracy with significantly less scatter. Robust nature and accurate predictions of SVM confirms its feasibility of potential use in solving complex engineering problems.

• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.159-173
• /
• 2022

This paper proposes a hybrid machine-learning model, which is called DANN-IP, that combines a deep artificial neural network (DANN) and an interior-point (IP) algorithm in order to improve the prediction capacity on the patch loading resistance of steel plate girders. For this purpose, 394 steel plate girders that were subjected to patch loading were tested in order to construct the DANN-IP model. Firstly, several DANN models were developed in order to establish the relationship between the patch loading resistance and the web panel length, the web height, the web thickness, the flange width, the flange thickness, the applied load length, the web yield strength, and the flange yield strength of steel plate girders. Accordingly, the best DANN model was chosen based on three performance indices, which included the R^2, RMSE, and a20-index. The IP algorithm was then adopted to optimize the weights and biases of the DANN model in order to establish the hybrid DANN-IP model. The results obtained from the proposed DANN-IP model were compared with of the results from the DANN model and the existing empirical formulas. The comparison showed that the proposed DANN-IP model achieved the best accuracy with an R^2 of 0.996, an RMSE of 23.260 kN, and an a20-index of 0.891. Finally, a Graphical User Interface (GUI) tool was developed in order to effectively use the proposed DANN-IP model for practical applications.

• Structural Engineering and Mechanics
• /
• v.71 no.4
• /
• pp.407-416
• /
• 2019

Novel steel fibre reinforced ultra-lightweight cement composite (ULCC) with compressive strength of 87.3MPa and density of $1649kg/m^3$ was developed for the flat slabs in civil buildings. This paper investigated structural behaviours of ULCC flat slabs according to a 4-specimen test program under concentrated loading and some reported test results. The investigated governing parameters on the structural behaviours of the ULCC slabs include volume fraction of the steel fibre and the patch loading area. The test results revealed that ULCC flat slabs with and without flexure reinforcement failed in different failure mode, and an increase in volume fraction of the steel fibre and loading area led to an increase in flexural resistance for the ULCC slabs without flexural reinforcement. Based on the experiment results, the analytical models were developed and also validated. The validations showed that the analytical models developed in this paper could predict the ultimate strength of the ULCC flat slabs with and without flexure reinforcement reasonably well.

• Structural Engineering and Mechanics
• /
• v.91 no.2
• /
• pp.135-147
• /
• 2024

The objective of this study is to analyze, using the finite element method, the durability of damaged and repaired structures under the effect of mechanical loading coupled with environmental conditions (water absorption and/or temperature). The study is based on the hybrid patch repair technique, considering several parameters based on the J integral to observe the behavior of the adhesive in transferring load from a damaged plate to the repair patch. The results clearly show that water absorption and increased temperature cause degradation of the mechanical properties of the adhesive, leading to an increase in its plasticization, which is beneficial for the assembly's strength. However, the degradation of the adhesive's properties due to aging in the repair results in poor load transfer from the damaged area to the patch. The findings of this study allowed the authors to conclude that the [0°]8 sequence consistently offers the best performance, with the lowest J integral values and superior crack resistance. The lowest the J integral for the [0°]8 stacking sequence is typically 3-7% lower than that of the [0/-45/45/90]S and [0/-45/90/45]S sequences at elevated temperatures. At 60℃, the J integral increases by approximately 3-6% compared to 40℃ and 20, depending on the aging duration and stacking sequences.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.2
• /
• pp.218-227
• /
• 2014

In this paper, it performed to the elastic-plastic large deflection series analysis using the experimental model and predicted a failure mode and ultimate strength. The collapse mode of numerical analysis model is formed a plastic hinge on loaded flange and consistent with the collapse mode of experimental model. Also, The yield line is formed in the web could observed that have occurred the crippling collapse mode and the ultimate loads of the experimental model and numerical analysis model have maintained linearly Means 1.07, Standard deviation 0.04, Coefficient of variation(COV) 0.04 and the result of ultimate loads have appeared approximately 8% error rate. it was found that very satisfied to the experimental results and the applied rules. if it is considered to be maintain a reasonable safety level, it is possible to predict the failure modes of aluminium alloy plate girders and ultimate loads.