Machine learning-based model for predicting concrete compressive strength (original) (raw)

USING THE ARTIFICIAL NEURAL NETWORKS FOR PREDICTING COMPRESSIVE STRENGTH OF NORMALLY CONCRETES

IAEME PUBLICATION, 2020

In this study Artificial Neural Networks (ANNs) models were developed for predicting the compressive strength, at the age of 28 days, of normally concretes. The experimental results used to construct the models were gathered from laboratory of Isra University - Amman in 2019. Total of 15 experimental design used for modeling ANN models. 80% in the training set, and 10% in the testing set, and 10% in the validation set. To construct the model, three input parameters were used to achieve one output parameter, referred to as the compressive strength of normally concrete. The results obtained in both, the training and testing phases strongly show the potential use of ANN to predict 28 days' compressive strength of normally concretes with average accuracy 90% and correlation coefficient 95%

Artificial Neural Network Model for Predicting Compressive Strength of Concrete

Tikrit Journal of Engineering Sciences

Compressive strength of concrete is a commonly used criterion in evaluating concrete. Although testing of the compressive strength of concrete specimens is done routinely, it is performed on the 28th day after concrete placement. Therefore, strength estimation of concrete at early time is highly desirable. This study presents the effort in applying neural network-based system identification techniques to predict the compressive strength of concrete based on concrete mix proportions, maximum aggregate size (MAS), and slump of fresh concrete. Back-propagation neural networks model is successively developed, trained, and tested using actual data sets of concrete mix proportions gathered from literature. The test of the model by un-used data within the range of input parameters shows that the maximum absolute error for model is about 20% and 88% of the output results has absolute errors less than 10%. The parametric study shows that water/cement ratio (w/c) is the most significant facto...

Prediction of Compressive Strength of Concrete by Artificial Neural Network

In the competitive nature of construction, concrete has a versatile use in the construction practice. The compressive strength of concrete is mostly used criterion in producing concrete. However testing for compressive strength of concrete specimens is a complicated and time consuming task, more importantly it would be too late to alter if the test result does not satisfy the required strength, since the test is usually performed at the 28 day after the placement of concrete at the construction site, therefore accurate and realistic strength estimation before the placement of concrete is highly desirable. In our project we aim at predicting the compressive strength of concrete by artificial neural network technique (ANN). ANN is one among the artificial intelligence and also strong potential has a feasible tool for prediction. The basic methodology of neural network consists of three processes Network training, Testing, Implementation. In this network training is nothing but the learning method, there are many such learning methods. But here in our project we are using back propagation method for the prediction of compressive strength of concrete. This back propagation consists of input layer, hidden layer and output layer. The results were obtained for 1000, 10000 and 1 lakh epochs and minimum error was obtained for 10000 epochs with 10 numbers of neurons, hence the developed model could be proposed for decision making to analyze appropriate turnovers for a project using artificial neural network.

Research Review and Modeling of Concrete Compressive Strength Using Artificial Neural Networks

2016

As the construction industry is flourishing day by day, modelling techniques are becoming more and more important in making predictions. Artificial neural network is one of the techniques through which these predictions can be made with limited errors. This research paper deals with the prediction of the compressive strength of concrete using artificial neural network (ANN). The parameters under consideration were different grades of concrete (M-20 and M-30), different curing techniques that are commonly used during the construction of a building (sprinkling, ponding etc.), duration of curing and ageing of the concrete block samples (cubes and cylinders). These parameters were given as input to train the network for the output compressive strength obtained experimentally. Different weights were obtained for the network layer which were used for getting the target value. The network formed was validated for the compressive strength of concrete for the required sample by giving inputs...

Estimated of Concrete Compressive Strength by Using Neural Network and Machine Learning

2021

Abstract: The most fundamental input of the construction sector is concrete, which would be a massively complicated element. Concrete is among the most common structural construction materials due to its strength. Since some manufacturers manufacture out of reach and low quality, there is a growing demand for earthquake-resistant design in the fully prepared concrete industry. Concrete's strength-gaining properties are influenced by a variety of factors. This research aims to use the results of early compressive strength tests to predict strength properties at various ages. The ability to estimate the determination and strength of normal concrete using the early day strength properties result has been examined. Including both concrete and regional concrete mixes, a basic numerical equation forecast the concrete strength at any age is proposed. The goal of this article is to show how artificial neural networks (ANN) and machine learning can be used to forecast the compressive str...

Prediction of Concrete Properties Using Multiple Linear Regression and Artificial Neural Network

2018

The selection of appropriate type and grade of concrete for a particular application is the critical step in any construction project. Workability & compressive strength are the two significant parameters that need special attention. The aim of this study is to predict the slump along with 7-days & 28-days compressive strength based on the data collected from various RMC plants. There are many studies reported in general to address this issue time to time over a long period. However, considering the worldwide use of a huge quantity of concrete for various infrastructure projects, there is a scope for the study that leads to most accurate estimate. Here, data from various concrete mixing plants and ongoing construction sites was collected for M20, M25, M30, M35, M40, M45, M50, M55, M60 and M70 grade of concrete. Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models were built to predict slump as well as 7-days and 28-days compressive strength. A variety of exper...

Prediction of Concrete Compressive Strength & Slump using Artificial Neural Networks (ANN)

2021

Concrete is the most used building material in the world, due to its high compressive strength and durability. Those properties are measured and assessed in fresh and hardened states of concrete, with standard methods which are time and cost consuming. In the present study, the compressive strength and slump of concrete has been predicted using Artificial Neural Network (ANN), which is constructed using different input parameters involving concrete mix design (i.e. coarse & fine aggregates properties, cement content, water/cement (W/C) ratio, admixtures type and dosage …etc.).The predicted strength was compared with the experimentally obtained actual compressive strength and slump data collected in many years for different materials and mix designs in the Sudan. An ANN model has been developed by using MATLAB neural network toolbox. A good co-relationships with regression values of 0.915 and 0.931 for strength and slump respectively have been obtained between the predicted and exper...