Application of Artificial Neural Networks for Prediction of Mechanical Properties of CNT/CNF Reinforced Concrete

Abstract

Prominence of concrete is characterized by its high mechanical properties and durability, combined with multifunctionality and aesthetic appeal. Development of alternative eco-friendly or multipurpose materials has conditioned improvements in concrete mix design to optimize concrete production speed and price, as well as carbon footprint. Artificial neural networks represent a new and efficient tool in achieving optimal concrete mixtures according to its intended function. This paper addresses concrete mix design and the application of artificial neural networks (ANNs) for self-sensing concrete. The authors review concrete mix design methods and the development of ANNs for prediction of properties for various types of concrete. Furthermore, the authors present developments and applications of ANNs for prediction of compressive strength and flexural strength of carbon nanotubes/carbon nanofibers (CNT/CNF) reinforced concrete using experimental results for the learning process. The goal is to bring the ANN approach closer to a variety of concrete researchers and possibly propose the implementation of ANNs in the civil engineering practice.

Multiple Analytical Models to Evaluate the Impact of Carbon Nanotubes on the Electrical Resistivity and Compressive Strength of the Cement Paste

“…Among the four main models, the ANN model has higher R 2 value and lower RMSE and MAE values relative to the LR, MLR, and NLR models, the previous study also used the ANN model for predicting compressive strength of cement mortar with R 2 value slightly less than achieved from this study and the RMSE and MAE values are greater than this study results [50]. Another research used ANN model to predict the mechanical properties such as compressive strength of concrete modified with carbon nanotube which get R 2 value slightly higher than achieved from this study and this might be due to the high data numbers used in this study [51]. In addition, Figure 13 indicates that the residual error for all models uses dataset preparation, training, and testing.…”

Prediction of Mechanical Properties of Highly Functional Lightweight Fiber-Reinforced Concrete Based on Deep Neural Network and Ensemble Regression Trees Methods

“…The problems, in turn, arising in the enterprises of the construction industry are expressed in manufacturing defects and the imperfection of prescription and technological factors that affect the quality of the resulting concrete, as well as in factors such as the influence of the human factor, errors in the selection of compositions, the production of concrete, and their assessment in terms of the ratio of initial parameters and output parameters. In this regard, it also implies the digitalization of all branches of modern industry, the application of artificial intelligence in the construction industry, and in particular, in concrete technology, which contains many vectors and directions for digitalization and improvement of properties, is seen as a relevant direction [ 10 , 11 , 12 , 13 , 14 , 15 , 16 ]. Currently, one of the relevant areas among artificial intelligence methods in industrial production is neural networks, which allow one to create systems for predicting output parameters, that is, the operational properties of any products, structures, buildings and structures that depend on the characteristics of the initial components and process parameters.…”

“…All the above-mentioned machine learning methods and neural network models have been applied to a wide range of materials, such as heavy concrete without additives [ 9 , 27 , 28 ], concrete with the addition of industrial and agricultural waste ash [ 21 ], slag [ 16 ], eggshell powder [ 12 ], microsilica [ 20 ], recycled concrete aggregate [ 18 , 32 ], ceramic waste [ 11 ], reinforced concrete with the addition of carbon nanotubes/nanofibers, [ 10 ] high-strength concrete [ 23 , 31 ], fiber-reinforced concrete [ 29 ], reinforced concrete (columns, beams, slabs) [ 17 , 19 , 22 , 30 ], and geopolymer concrete [ 13 ], as well as porous cement pastes [ 33 ], soil with cement [ 14 ], and metals [ 15 ].…”

High-Performance Concrete Strength Prediction Based on Machine Learning

“…In recent years, with the rapid development of artificial intelligence technology, various industries are combining new artificial intelligence technologies for self-empowerment, and engineering-based research based on machine learning and deep learning has continued. Many machine learning theories have been applied to concrete-related research, mainly including artificial neural networks [ 3 ], support vector [ 4 ], and integration algorithms [ 5 ]. Erdal et al [ 6 ] predicted the strength of HPC based on wavelet transform neural network model, and the prediction accuracy was good.…”