Boosting machines for predicting shear strength of CFS channels with staggered web perforations

Degtyarev, Vitaliy V.; Naser, M.Z.

doi:10.1016/j.istruc.2021.09.060

Cited by 35 publications

(16 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the Gradient-based One-Side Sampling (GOSS) method, LightGBM can handle large datasets. The Exclusive Feature Bundling (EFB) method makes it possible to handle datasets with a large number of design features in a more efficient way compared to the basic gradient boosting decision tree [ 43 , 44 , 45 ].…”

Section: Methods Of Optimization and Predictive Model Developmentmentioning

confidence: 99%

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

This paper develops predictive models for optimal dimensions that minimize the construction cost associated with reinforced concrete retaining walls. Random Forest, Extreme Gradient Boosting (XGBoost), Categorical Gradient Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM) algorithms were applied to obtain the predictive models. Predictive models were trained using a comprehensive dataset, which was generated using the Harmony Search (HS) algorithm. Each data sample in this database consists of a unique combination of the soil density, friction angle, ultimate bearing pressure, surcharge, the unit cost of concrete, and six different dimensions that describe an optimal retaining wall geometry. The influence of these design features on the optimal dimensioning and their interdependence are explained and visualized using the SHapley Additive exPlanations (SHAP) algorithm. The prediction accuracy of the used ensemble learning methods is evaluated with different metrics of accuracy such as the coefficient of determination, root mean square error, and mean absolute error. Comparing predicted and actual optimal dimensions on a test set showed that an R2 score of 0.99 could be achieved. In terms of computational speed, the LightGBM algorithm was found to be the fastest, with an average execution speed of 6.17 s for the training and testing of the model. On the other hand, the highest accuracy could be achieved by the CatBoost algorithm. The availability of open-source machine learning algorithms and high-quality datasets makes it possible for designers to supplement traditional design procedures with newly developed machine learning techniques. The novel methodology proposed in this paper aims at producing larger datasets, thereby increasing the applicability and accuracy of machine learning algorithms in relation to optimal dimensioning of structures.

show abstract

Section: Methods Of Optimization and Predictive Model Developmentmentioning

confidence: 99%

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Wu et al [ 16 ] established a tensile strength prediction model for X70 pipeline steel based on support vector regression (SVR) and RF. Degtyarev et al [ 17 ] explored different ML boosting algorithms to predict the elastic shear buckling loads and the ultimate shear strength of cold‐formed steel, e.g., gradient boosting regression (GBR) and extreme gradient boosting (XGB). Xie et al [ 18 ] developed a deep neural network (DNN) model to predict the mechanical properties of four different types of hot‐rolled steel plates, and this model was adopted for an actual production line.…”

Section: Introductionmentioning

confidence: 99%

“…Xie et al [ 18 ] developed a deep neural network (DNN) model to predict the mechanical properties of four different types of hot‐rolled steel plates, and this model was adopted for an actual production line. However, in these works, [ 13–26 ] most of the computational analysis systems achieved accurate property prediction based on a simple database with a single or a few specific steel grades, and few studies paid attention to establishing the universal prediction framework regarding a complex industrial database containing various kinds of commercial steels. Thus, the extensibility of prediction models is limited and hinders the wide applications of ML‐based methods in actual industries.…”

Section: Introductionmentioning

confidence: 99%

“…All the data in the database were extracted from the actual hot rolling production line of Benxi Iron and Steel Co., Ltd., China, to guarantee the adaptability of the model to real industrial data. Unlike previous works that performed a direct analysis on a database containing samples of multiple types of steels, [ 13,15–22 ] in this work, the whole database was first classified into different categories using a K‐nearest neighbor (KNN) model. Then, the accurate prediction models were established by selecting the appropriate ML algorithms for each category, finally contributing to improving the extensibility and universality of the modeling framework.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Physical Metallurgy Guided Industrial Big Data Analysis System with Data Classification and Property Prediction

Huang

et al. 2022

steel research int.

View full text Add to dashboard Cite

show abstract

“…Many publications described ML models considered in this study for predicting properties of concrete and reinforced concrete structures . Fewer papers have been published on ML applications to steel structures, including buckling analysis of beam-columns [66], cold-formed steel (CFS) space structure optimization [67], web crippling strength prediction [68], elastic distortional buckling stress determination [69,70], rotation capacity prediction [71], strength prediction of concrete-filled steel tubular columns [72], failure mode identification of column base plate connection [73], capacity prediction of cold-formed stainless steel tubular columns [74], seismic drift demand estimation for steel moment frame buildings [75], and shear strength of CFS channels with staggered perforated webs [76][77][78][79]. ML techniques were previously applied to steel cellular beams.…”

Section: Introductionmentioning

confidence: 99%

Buckling and ultimate load prediction models for perforated steel beams using machine learning algorithms

Degtyarev¹,

Tsavdaridis²

2021

Preprint

View full text Add to dashboard Cite

Large web openings introduce complex structural behaviors and additional failure modes of steel cellular beams, which must be considered in the design using laborious calculations (e.g., exercising SCI P355). This paper presents seven machine learning (ML) models, including decision tree (DT), random forest (RF), k-nearest neighbor (KNN), gradient boosting regressor (GBR), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and gradient boosting with categorical features support (CatBoost), for predicting the elastic buckling and ultimate loads of steel cellular beams. Large datasets of finite element (FE) simulation results, validated against experimental data, were used to develop the models. The ML models were fine-tuned via an extensive hyperparameter search to obtain their best performance. The elastic buckling and ultimate loads predicted by the optimized ML models demonstrated excellent agreement with the numerical data. The accuracy of the ultimate load predictions by the ML models exceeded the accuracy provided by the existing design provisions for steel cellular beams published in SCI P355 and AISC Design Guide 31. The relative feature importance and feature dependence of the models were evaluated and discussed in the paper. An interactive Python-based notebook and a user-friendly web application for predicting the elastic buckling and ultimate loads of steel cellular beams using the developed optimized ML models were created and made publicly available. The web application deployed to the cloud allows for making predictions in any web browser on any device, including mobile. The source code of the application available on GitHub allows running the application locally and independently from the cloud service.

show abstract

Boosting machines for predicting shear strength of CFS channels with staggered web perforations

Cited by 35 publications

References 51 publications

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

Physical Metallurgy Guided Industrial Big Data Analysis System with Data Classification and Property Prediction

Buckling and ultimate load prediction models for perforated steel beams using machine learning algorithms

Contact Info

Product

Resources

About