• PDF / 1,007,229 Bytes
• 11 Pages / 595.276 x 790.866 pts Page_size
• 90 Downloads / 176 Views

DOWNLOAD

REPORT

Concrete Compressive Strength Prediction Using Neural Networks Based on Non-destructive Tests and a Self-calibrated Response Surface Methodology Ali Poorarbabi1 · Mohammadreza Ghasemi1 · Mehdi Azhdary Moghaddam1 Received: 16 May 2020 / Accepted: 28 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020

Abstract An artificial neural network (ANN) model and response surface methodology (RSM) were established to estimate the compressive strength of concrete by using the combination of three non-destructive tests (NDT); rebound number, pulse velocity tests and resistance surface. These techniques are utilized in an attempt to increase the reliability of the non-destructive tests in detecting the strength of concrete. These methods were trained using a set of different mixes and at different ages of concrete specimens. In this case, 180 experimental specimens were conducted and their data are published. Then, different neural network topologies and algorithms besides RSM were examined using the given data. The published models are for two combination including the combination of UPV and RN and the combination UPV, RN and SR. The results show that the accuracy of the published models are increased by aging. In addition, it is showed that RSM don’t need calibration process, while its accuracy is enough. Hence, RSM is a promising method to conduct on NDTs and compressive strength prediction, while ANN needs to perform many times to find the best accuracy. Keywords Non-destructive tests · Compressive strength · Concrete structures · Response surface methodology · Artificial neural network

1 Introduction Concrete structures are most widely spread structures in all around the world which its compressive strength is widely accepted the principal indicator of the level of quality of such structures [1–3]. Concrete is prepared by mixing different materials including cement, water, fine aggregates and coarse aggregates in certain proportions which lead to a specific and desirable compressive strength (FC ). Generally, concrete’s compressive strength is assessed using destructive procedures in which gradually increasing compressive stress is applied to concrete specimens in the laboratory until the sample is failed [4–7]. In the case of the aged concrete struc-

B

Mohammadreza Ghasemi [email protected] Ali Poorarbabi [email protected] Mehdi Azhdary Moghaddam [email protected]

1

Civil Engineering Department, University of Sistan and Baluchestan, P.O. Box 9816745563-161, Zahedan, Iran

tures, destructive tests demand high cost and also decrease the capability of existent structures [8–10]. Hence, nowadays non-destructive tests (NDT) are used widely to assess the specifications of concrete structures especially in terms of compressive strength [8–10]. NDTs lead to reduction in the labour consumption of testing, lower damages to structure and low-cost testing equipment in comparison with core testing as the common destructive test [11]. These benefits are valuable when the results f

Recommend Documents

Prediction of uniaxial compressive strength of carbonate rocks from nondestructive tests using multivariate regression a

147 75 9MB

Recurrent neural network-based prediction of compressive and flexural strength of steel slag mixed concrete

212 105 2MB

Retraction Note to: Prediction compressive strength of Portland cement-based geopolymers by artificial neural networks

220 77 153KB

Prediction of Compressive Strength of Concrete Using Recycled Materials from Fly Ash Based on Ultrasonic Pulse Velocity

149 71 86MB

Retraction Note to: Artificial neural networks for prediction compressive strength of geopolymers with seeded waste ashe

170 33 152KB

Functional Link Neural Network-Based Prediction of Compressive and Flexural Strengths of Jarosite Mixed Cement Concrete

111 102 44MB

Mechanical and Physical Based Artificial Neural Network Models for the Prediction of the Unconfined Compressive Strength

212 74 2MB

Estimating Model Parameters of Concrete Materials Based on Neural Networks

175 83 24MB

Bitcoin Cost Prediction Using Neural Networks

222 49 22MB

A comparative study of various hybrid neural networks and regression analysis to predict unconfined compressive strength

223 14 1MB

A novel deep neural networks based path prediction

167 95 704KB

Machine learning approaches for estimation of compressive strength of concrete

180 88 1MB