Figure - available from: Scientific Reports
This content is subject to copyright. Terms and conditions apply.
Source publication
In this paper, the prediction of flexural strength was investigated using machine learning methods for concrete containing supplementary cementitious materials such as silica fume. First, based on a database of suitable characteristic parameters, the flexural strength prediction was carried out using linear (LR) model, random forest (RF) model, and...
Similar publications
As a new type of environmentally friendly building material, cemented sand and gravel (CSG) has advantages distinct from those of concrete. Compressive strength is an important mechanical property of CSG. However, his method of testing is mainly by doing experiments. For this reason, a deep learning algorithm, long short-term memory (LSTM) model, w...
Citations
... Moreover, gradient-boosted algorithm (GB) can be considered similar to other boosting approaches but with certain limitations in regression [37]- [39]. In this approach, random selection is performed for each iteration of the training set and validation using the base model [40], [41].The GB regression requires adjusting factors such as the number of trees (n-trees) and the shrinkage rate, where n-trees represent the number of trees grown. In the research work conducted by Qian et al. [33], they obtained the following results by examining the data of the SVM model. ...
Concrete structures play a pivotal role in the realm of civil engineering, with reinforcement techniques employed to amplify their robustness and resilience. The utilization of steel fibers and polymer fibers, such as FRP sheets, has displayed auspicious outcomes in enhancing the properties of concrete. Nonetheless, the evaluation and comparison of the performance between reinforced and unreinforced concrete necessitate meticulous sampling and experimental examinations. This is precisely where artificial intelligence algorithms come to the fore. Artificial intelligence, particularly artificial neural networks (ANN), bestows a potent instrument for precise calculations and prognostications in civil engineering. Through training ANN models with pertinent data, engineers can accurately gauge the ductility and durability of reinforced concrete structures. This paper delves into the implementation of diverse artificial intelligence algorithms and places particular emphasis on the application of ANN in estimating flexural strength. Ultimately, it underlines the merits of ANN models in terms of assimilating, forecasting, and adapting to evolving data and environments.
