Prediction of shear capacity of steel channel sections using machine learning algorithms

Dissanayake, Madhushan; Nguyễn, Xuân Hùng; Poologanathan, Keerthan; Gatheeshgar, Perampalam; Upasiri, Irindu; Rajanayagam, Heshachanaa; Suntharalingam, Thadshajini

doi:10.1016/j.tws.2022.109152

Cited by 24 publications

(3 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each hyperparameter is then assigned a value from the set of potential values to form a different combination of hyperparameters. Then, the machine learning model is trained and evaluated for each hyperparameter combination, and the optimal combination is found during the tuning process [ 65 ]. Table 1 lists the major hyperparameter potential values used by each ML model in grid search.…”

Section: Model Results and Discussionmentioning

confidence: 99%

Ensemble Machine-Learning-Based Prediction Models for the Compressive Strength of Recycled Powder Mortar

et al. 2023

View full text Add to dashboard Cite

Recycled powder (RP) serves as a potential and prospective substitute for cementitious materials in concrete. The compressive strength of RP mortar is a pivotal factor affecting the mechanical properties of RP concrete. The application of machine learning (ML) approaches in the engineering problems, particularly for predicting the mechanical properties of construction materials, leads to high prediction accuracy and low experimental costs. In this study, 204 groups of RP mortar compression experimental data are collected from the literature to establish a dataset for ML, including 163 groups in the training set and 41 groups in the test set. Four ensemble ML models, namely eXtreme Gradient-Boosting (XGBoost), Random Forest (RF), Light Gradient-Boosting Machine (LightGBM) and Adaptive Boosting (AdaBoost), were selected to predict the compressive strength of RP mortar. The comparative results demonstrate that XGBoost has the highest prediction accuracy when the a10-index, MAE, RMSE and R2 of the training set are 0.926, 1.596, 2.155 and 0.950 and the a10-index, MAE, RMSE and R2 of the test set are 0.659, 3.182, 4.285 and 0.842, respectively. SHapley Additive exPlanation (SHAP) is adopted to interpret the prediction process of XGBoost and explain the influence of influencing factors on the compressive strength of RP mortar. According to the importance of influencing factors, the order is the mass replacement rate of RP, the size of RP, the kind of RP and the water binder ratio of RP. The compressive strength of RP mortar decreases with the increase in the RP mass replacement rate. The compressive strength of RBP mortar is slightly higher than that of RCP mortar. Machine learning technologies will benefit the construction industry by facilitating the rapid and cost-effective evaluation of RP material properties.

show abstract

Section: Model Results and Discussionmentioning

confidence: 99%

Ensemble Machine-Learning-Based Prediction Models for the Compressive Strength of Recycled Powder Mortar

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Extreme Learning Machines (ELMs) were optimized by Shariati et al [29] to estimate the moment and rotation in steel rack connection based on variable input characteristics such as beam depth, column thickness, connector depth, moment and loading. Madhushan et al [30] presented the application of four popular machine-learning algorithms in the prediction of the shear resistance of steel channel sections. The results indicated that the implemented machine-learning models exceeded the prediction accuracy of the available design equations.…”

Section: Related Workmentioning

confidence: 99%

A Study on the Man-Hour Prediction in Structural Steel Fabrication

Wei,

Li,

Niu

et al. 2024

Processes

View full text Add to dashboard Cite

Longitudinal cutting is the most common process in steel structure manufacturing, and the man-hours of the process provide an important basis for enterprises to generate production schedules. However, currently, the man-hours in factories are mainly estimated by experts, and the accuracy of this method is relatively low. In this study, we propose a system that predicts man-hours with history data in the manufacturing process and that can be applied in practical structural steel fabrication. The system addresses the data inconsistency problem by one-hot encoding and data normalization techniques, Pearson correlation coefficient for feature selection, and the Random Forest Regression (RFR) for prediction. Compared with the other three Machine-Learning (ML) algorithms, the Random Forest algorithm has the best performance. The results demonstrate that the proposed system outperforms the conventional approach and has better forecast accuracy so it is suitable for man-hours prediction.

show abstract

“…Machine learning is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention (Han et al ., 2021; Reich, 1997; Dissanayake et al ., 2022). ANN is a subset of machine learning consisting of deep learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

Determination of elevated temperature material properties by ANN-based FE model

Upasiri

Konthesingha

Nanayakkara

et al. 2023

JSFE

View full text Add to dashboard Cite

PurposeElevated temperature material properties are essential in predicting structural member's behavior in high-temperature exposures such as fire. Even though experimental methodologies are available to determine these properties, advanced equipment with high costs is required to perform those tests. Therefore, performing those experiments frequently is not feasible, and the development of numerical techniques is beneficial. A numerical technique is proposed in this study to determine the temperature-dependent thermal properties of the material using the fire test results based on the Artificial Neural Network (ANN)-based Finite Element (FE) model.Design/methodology/approachAn ANN-based FE model was developed in the Matlab program to determine the elevated temperature thermal diffusivity, thermal conductivity and the product of specific heat and density of a material. The temperature distribution obtained from fire tests is fed to the ANN-based FE model and material properties are predicted to match the temperature distribution.FindingsElevated temperature thermal properties of normal-weight concrete (NWC), gypsum plasterboard and lightweight concrete were predicted using the developed model, and good agreement was observed with the actual material properties measured experimentally. The developed method could be utilized to determine any materials' elevated temperature material properties numerically with the adequate temperature distribution data obtained during a fire or heat transfer test.Originality/valueTemperature-dependent material properties are important in predicting the behavior of structural elements exposed to fire. This research study developed a numerical technique utilizing ANN theories to determine elevated temperature thermal diffusivity, thermal conductivity and product of specific heat and density. Experimental methods are available to evaluate the material properties at high temperatures. However, these testing equipment are expensive and sophisticated; therefore, these equipment are not popular in laboratories causing a lack of high-temperature material properties for novel materials. However conducting a fire test to evaluate fire performance of any novel material is the common practice in the industry. ANN-based FE model developed in this study could utilize those fire testing results of the structural member (temperature distribution of the member throughout the fire tests) to predict the material's thermal properties.

show abstract

Prediction of shear capacity of steel channel sections using machine learning algorithms

Cited by 24 publications

References 64 publications

Ensemble Machine-Learning-Based Prediction Models for the Compressive Strength of Recycled Powder Mortar

Ensemble Machine-Learning-Based Prediction Models for the Compressive Strength of Recycled Powder Mortar

A Study on the Man-Hour Prediction in Structural Steel Fabrication

Determination of elevated temperature material properties by ANN-based FE model

Contact Info

Product

Resources

About