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

Using Neural Networks to Prediction of compressive strength of heavy concrete

E3S Web of Conferences

The article is devoted to the study of the process of predicting the compressive strength of concrete. Fully connected neural networks are used as a forecasting tool. The need for research is caused by the fact that concrete is one of the materials widely used in construction, and the existing automated tools have insufficient accuracy. The paper investigates the structure of a neural network: select of the number of layers, the number of neurons in layers, the activation function, the optimization method, the number of epochs, and the technique to prevent overfitting. Comparison of the obtained results with the results of laboratory tests showed that neural networks could achieve acceptable prediction accuracy. The coefficient of determination refers to the main indicators of the quality of forecasting. Now, the coefficient of determination is approximately equal to 0.889. In the future, the started research can be continued and the value of the coefficient of determination can be ...

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...

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...

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...