scholarly journals Prediction Compressive Strength of Concrete Containing GGBFS using Random Forest Model

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Hai-Van Thi Mai ◽  
Thuy-Anh Nguyen ◽  
Hai-Bang Ly ◽  
Van Quan Tran
Keyword(s):  
Compressive Strength ◽  
Random Forest ◽  
Leaf Size ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Granulated Blast Furnace Slag ◽  
Statistical Measures ◽  
Testing Dataset ◽  
Compressive Strength Of Concrete

Improvement of compressive strength prediction accuracy for concrete is crucial and is considered a challenging task to reduce costly experiments and time. Particularly, the determination of compressive strength of concrete using ground granulated blast furnace slag (GGBFS) is more difficult due to the complexity of the composition mix design. In this paper, an approach using random forest (RF), which is one of the powerful machine learning algorithms, is proposed for predicting the compressive strength of concrete using GGBFS. The RF model is first evaluated to determine the best architecture, which constitutes 500 growth trees and leaf size of 1. In the next step, the evaluation of the model is conducted over 500 simulations considering the effect of random sampling. Finally, the best prediction results are given in function of statistical measures such as the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE), respectively, which are 0.9729, 4.9585, and 3.9423 for the testing dataset. The results show that the RF algorithm is an excellent predictor and practically used for engineers to reduce experimental cost.

scholarly journals Investigation and Optimization of the C-ANN Structure in Predicting the Compressive Strength of Foamed Concrete

Materials ◽  
2020 ◽  
Vol 13 (5) ◽  
pp. 1072 ◽  
Author(s):  
Dong Van Dao ◽  
Hai-Bang Ly ◽  
Huong-Lan Thi Vu ◽  
Tien-Thinh Le ◽  
Binh Thai Pham
Keyword(s):  
Compressive Strength ◽  
Civil Engineering ◽  
Mean Squared Error ◽  
Model Performance ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Coefficient Of Determination ◽  
Dry Density ◽  
Statistical Measures ◽  
Foamed Concrete

Development of Foamed Concrete (FC) and incessant increases in fabrication technology have paved the way for many promising civil engineering applications. Nevertheless, the design of FC requires a large number of experiments to determine the appropriate Compressive Strength (CS). Employment of machine learning algorithms to take advantage of the existing experiments database has been attempted, but model performance can still be improved. In this study, the performance of an Artificial Neural Network (ANN) was fully analyzed to predict the 28 days CS of FC. Monte Carlo simulations (MCS) were used to statistically analyze the convergence of the modeled results under the effect of random sampling strategies and the network structures selected. Various statistical measures such as Coefficient of Determination (R2), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) were used for validation of model performance. The results show that ANN is a highly efficient predictor of the CS of FC, achieving a maximum R2 value of 0.976 on the training part and an R2 of 0.972 on the testing part, using the optimized C-ANN-[3–4–5–1] structure, which compares with previous published studies. In addition, a sensitivity analysis using Partial Dependence Plots (PDP) over 1000 MCS was also performed to interpret the relationship between the input parameters and 28 days CS of FC. Dry density was found as the variable with the highest impact to predict the CS of FC. The results presented could facilitate and enhance the use of C-ANN in other civil engineering-related problems.

Determination of Concrete Cube Strength from Used Samples / Určení Krychelné Pevnosti Betonu U Použitých Zkušebních Trámců

2012 ◽  
Vol 12 (2) ◽  
pp. 186-194 ◽  
Author(s):  
Oldřich Sucharda ◽  
David Mikolášek ◽  
Jiří Brožovský
Keyword(s):  
Compressive Strength ◽  
Concrete Beams ◽  
Linear Analysis ◽  
Bending Tests ◽  
Cube Strength ◽  
Non Linear ◽  
Compressive Strength Of Concrete ◽  
Concrete Cube

Abstract This paper deals with the determination of compressive strength of concrete. Cubes, cylinders and re-used test beams were tested. The concrete beams were first subjected to three-point or fourpoint bending tests and then used for determination of the compressive strength of concrete. Some concrete beams were reinforced, while others had no reinforcement. Accuracy of the experiments and calculations was verified in a non-linear analysis.

The effects of using Micro-SiO2 with Ground Granulated Blast-Furnace Slag of Esfahan Steel Company in Concrete

2015 ◽  
Vol 16 (SE) ◽  
pp. 509-517
Author(s):  
Fatemeh Sayyahi ◽  
Hamid Shirzadi
Keyword(s):  
Compressive Strength ◽  
Blast Furnace ◽  
Blast Furnace Slag ◽  
Cement Content ◽  
Harmful Effect ◽  
Maximum Size ◽  
Steel Company ◽  
Granulated Blast Furnace Slag ◽  
Compressive Strength Of Concrete ◽  
Furnace Slag

 In this study, the properties of concrete with different amounts of Ground Granulated Blast-Furnace Slag (GGBFS) has been studied. In another part, the test deals to assess the properties of concrete containing GGBFS with micro-SiO2. The results show that the slag has pozzolan properties and its use up to 20% in the concrete, has no harmful effect on concrete properties. The simultaneous use of micro-SiO2 with blast furnace slag have little effect, as well as micro-SiO2 covers the defects caused by the use of slag. The results indicate that the use of micro-SiO2 and slag has good effects on the strength of concrete up to a certain age, so that its compressive strength is increased. Water-cement ratio was 0.42 and 12.5 mm for maximum size of aggregate and cement content in concrete was 425 kg per cubic meter. Compressive strength of concrete samples was measured at ages 7, 28, 56 and 90-day and flexural and tensile strength and water absorption after 28-day and 90 days also was measured.

Determination of a Suitable Moment for Formwork Removal from a Concrete Structure Using Rebound Hammer Test Methods

2021 ◽  
Vol 322 ◽  
pp. 23-27
Author(s):  
Petr Misák ◽  
Dalibor Kocáb ◽  
Petr Cikrle
Keyword(s):  
Compressive Strength ◽  
Characteristic Curve ◽  
Test Methods ◽  
Rebound Hammer ◽  
Practical Applications ◽  
Relevant Topic ◽  
Compressive Strength Of Concrete ◽  
The Moment ◽  
Non Destructive

Determining the compressive strength of concrete in the early stages of ageing has been an increasingly relevant topic in recent years, particularly with regard to the safe removal of formwork from a structure or its part. The compressive strength of concrete which designates safe removal of formwork without damaging the structure can be referred to as "stripping strength". It is undoubtedly beneficial to be able to determine the moment of safe formwork removal in a non-destructive manner, i.e. without compromising the structure. Modern rebound hammer test methods seem to be a suitable instrument with which it is possible to reduce the length of technological breaks associated with concrete ageing to a minimum, and consequently, reduce the total cost of the construction. However, the use of these methods presents a number of challenges. As many conducted experiments have shown, there is no single conversion relationship (regression model) between non-destructive rebound hammer test methods and compressive strength. It is therefore advisable to always create a unique conversion relationship for each individual concrete. In addition, it must be noted that conventional regression analysis methods operate with 50% reliability. In construction testing, however, the most common is the so-called characteristic value, which is defined as a 5% quantile. This value is therefore determined with 95% reliability. This paper describes the construction of a so-called "characteristic curve", which can be used to estimate the compressive strength of concrete in a structure using rebound hammer test methods with 95% reliability. Consequently, the values obtained from the characteristic curve can be easily used for practical applications.

scholarly journals Development and Evaluation of the Combined Machine Learning Models for the Prediction of Dam Inflow

Water ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 2927
Author(s):  
Jiyeong Hong ◽  
Seoro Lee ◽  
Joo Hyun Bae ◽  
Jimin Lee ◽  
Woon Ji Park ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Random Forest ◽  
Multilayer Perceptron ◽  
Short Term Memory ◽  
Learning Algorithms ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Dam Inflow

Predicting dam inflow is necessary for effective water management. This study created machine learning algorithms to predict the amount of inflow into the Soyang River Dam in South Korea, using weather and dam inflow data for 40 years. A total of six algorithms were used, as follows: decision tree (DT), multilayer perceptron (MLP), random forest (RF), gradient boosting (GB), recurrent neural network–long short-term memory (RNN–LSTM), and convolutional neural network–LSTM (CNN–LSTM). Among these models, the multilayer perceptron model showed the best results in predicting dam inflow, with the Nash–Sutcliffe efficiency (NSE) value of 0.812, root mean squared errors (RMSE) of 77.218 m3/s, mean absolute error (MAE) of 29.034 m3/s, correlation coefficient (R) of 0.924, and determination coefficient (R2) of 0.817. However, when the amount of dam inflow is below 100 m3/s, the ensemble models (random forest and gradient boosting models) performed better than MLP for the prediction of dam inflow. Therefore, two combined machine learning (CombML) models (RF_MLP and GB_MLP) were developed for the prediction of the dam inflow using the ensemble methods (RF and GB) at precipitation below 16 mm, and the MLP at precipitation above 16 mm. The precipitation of 16 mm is the average daily precipitation at the inflow of 100 m3/s or more. The results show the accuracy verification results of NSE 0.857, RMSE 68.417 m3/s, MAE 18.063 m3/s, R 0.927, and R2 0.859 in RF_MLP, and NSE 0.829, RMSE 73.918 m3/s, MAE 18.093 m3/s, R 0.912, and R2 0.831 in GB_MLP, which infers that the combination of the models predicts the dam inflow the most accurately. CombML algorithms showed that it is possible to predict inflow through inflow learning, considering flow characteristics such as flow regimes, by combining several machine learning algorithms.

scholarly journals Utilization of tailings in cement and concrete: A review

2019 ◽  
Vol 26 (1) ◽  
pp. 449-464 ◽  
Author(s):  
Mifeng Gou ◽  
Longfei Zhou ◽  
Nathalene Wei Ying Then
Keyword(s):  
Compressive Strength ◽  
Cementitious Materials ◽  
Solid Wastes ◽  
Supplementary Cementitious Materials ◽  
Cement Clinker ◽  
Fine Aggregate ◽  
Granulated Blast Furnace Slag ◽  
Fine Aggregates ◽  
Compressive Strength Of Concrete ◽  
Cement And Concrete

AbstractOne of the advantages of cement and the cement concrete industry in sustainability is the ability to utilize large amounts of industrial solid wastes such as fly ash and ground granulated blast furnace slag. Tailings are solid wastes of the ore beneficiation process in the extractive industry and are available in huge amounts in some countries. This paper reviews the potential utilization of tailings as a replacement for fine aggregates, as supplementary cementitious materials (SCMs) in mortar or concrete, and in the production of cement clinker. It was shown in previous research that while tailings had been used as a replacement for both fine aggregate and cement, the workability of mortar or concrete reduced. Also, at a constant water to cement ratio, the compressive strength of concrete increased with the tailings as fine aggregate. However, the compressive strength of concrete decreased as the replacement content of the tailings as SCMs increased, even whentailings were ground into smaller particles. Not much research has been dedicated to the durability of concrete with tailings, but it is beneficial for heavy metals in tailings to stabilize/solidify in concrete. The clinker can be produced by using the tailings, even if the tailings have a low SiO2 content. As a result, the utilization of tailings in cement and concrete will be good for the environment both in the solid waste processing and virgin materials using in the construction industry.

scholarly journals Effect of Tile Powder Used as a Cementitious Material on the Mechanical Properties of Concrete

2019 ◽  
Vol 9 (5) ◽  
pp. 4596-4599 ◽  
Author(s):  
N. Bheel ◽  
R. A. Abbasi ◽  
S. Sohu ◽  
S. A. Abbasi ◽  
A. W. Abro ◽  
...  
Keyword(s):  
Tensile Strength ◽  
Compressive Strength ◽  
Fresh Concrete ◽  
Cementitious Material ◽  
Splitting Tensile Strength ◽  
Hardened Concrete ◽  
Compressive Strength Of Concrete ◽  
Powder Content ◽  
Cylindrical Samples

This study was undertaken to reduce the usage of cement in concrete where different proportions of tile powder as cement replacement were used. Since in the manufacture of cement an exuberant amount of carbon dioxide is disposed of in the environment, this research aims to curtail the dependence on cement and its production. The objective of this work is to investigate the properties of fresh mix concrete (workability) and hardened concrete (compressive and splitting tensile strength) in concrete with different proportions of 0%, 10%, 20%, 30%, and 40% of tile powder as a cement substitute. In this study, a total of 90 concrete samples were cast with mix proportions of 1:1.5:3, 0.5 water-cement ratio, cured for 7, 14 and 28 days. For determining the compressive strength, cubical samples, with dimensions of 100mm×100mm×100mm, were cast, while for the determination of the splitting tensile strength, cylindrical samples with dimensions of 200mm diameter and 100mm height, were tested after 7, 14, and 28 days. The highest compressive strength of concrete achieved for tile powder concrete was 7.50% at 10% replacement after 28days of curing. The splitting tensile strength got to 10.2% when concrete was replaced with 10% of tile powder and cured for 28 days. It was also shown that with increasing percentage of the tile powder content, the workability of the fresh concrete increases.

scholarly journals Prediction of Compressive Strength Using Support Vector Regression

MENDEL ◽  
2019 ◽  
Vol 25 (1) ◽  
pp. 51-56
Author(s):  
Goutham J Sai ◽  
Vijay Pal Singh
Keyword(s):  
Compressive Strength ◽  
Support Vector Regression ◽  
Design Stage ◽  
Support Vector ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Study Support ◽  
Compressive Strength Of Concrete ◽  
Non Destructive

At the design stage of a structure, the members of adequate dimension and strength is provided. But with passage of time, the strength of the members reduces gradually due to exposure to environmental conditions and unexpected loadings other than for which the structure is designed. Non Destructive Testing (NDT) method provides a convenient and rapid method of determination of existing strength of concrete without subjecting the member to any damage.  In the present study, Support Vector Regression (SVR) in Python has been used for the prediction of compressive strength of concrete. Three different NDT techniques have been used as input for the SVR model. A good co-relation between predicted strength and strength determined after crushing the concrete cubes has been achieved. It has also been observed that accuracy in the predicted strength is more in case of inputs from more than one NDT technique is used.

Sign in / Sign up

Export Citation Format

Share Document