Artificial Neural Network Approach to Predict Compressive Strength of Concrete through Ultrasonic Pulse Velocity

Bilgehan, Mahmut; Turğut, Paki

doi:10.1080/09349840903122042

Cited by 55 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leshchinsky (1991) identified several advantages of this method, the most important being the possibility to conduct in situ strength tests where appropriate sized cores are unavailable. The sound velocity tests are also regularly used to characterize dynamic and static properties of the rock masses (Singh and Kotiyal 2013;Bilgehan and Turgut 2010;Moradian and Behnia 2009). However, sound velocity tests can be sensitive to micro-cracks, mineral constituents, porosity, temperature, weathering and others factors (Yasar and Erdogan 2004).…”

Section: Introductionmentioning

confidence: 99%

Prediction of Strength Parameters of Himalayan Rocks: A Statistical and ANFIS Approach

et al. 2015

View full text Add to dashboard Cite

The knowledge of geomechanical properties of rocks is essential for planning and design of structures in civil, mining, and other allied industries. Direct assessment of these properties is quite expensive and time consuming. It also requires fine precision in sample preparation and high-end testing instruments. To overcome these problems, 597 rock samples of four different Himalayan rock types have been tested for their strength attributes in a laboratory. The test results were correlated with their P-wave velocity using linear regression analysis for estimation of compressive, tensile, cohesive strengths and angle of internal friction. Subsequently, an adaptive neurofuzzy inference system (ANFIS) technique was applied to find its efficiency as a predictor against normal regression system. The results indicated that the ANFIS is comparatively better at prediction of geotechnical strength parameters when pitted against regression techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Strength Parameters of Himalayan Rocks: A Statistical and ANFIS Approach

et al. 2015

View full text Add to dashboard Cite

show abstract

“…The research by Carcano and Moreno [9] was focused on studying pulses passing through concrete specimens to propose a model for assessing the quality of concrete made with limestone aggregates. Through arti cial neural networks and using ultrasonic pulse velocity, Kewalramani and Gupta [10] and also Bilgehan and Turgut [11] predicted concrete compressive strength. Trtnik et al [4] used MATLAB software to provide a model for prediction of concrete compressive strength based on neural networks and ultrasonic pulse velocity.…”

Section: Introductionmentioning

confidence: 99%

Strength and elastic moduli of a concrete bridge using advanced nondestructive techniques

2017

View full text Add to dashboard Cite

In this research, Non-Destructive Test (NDT) wave tomography techniques are used to estimate the strength and elastic moduli and to assess the health condition of the piers of an existing concrete bridge. There are various empirical relationships to evaluate concrete characteristics based on NDT techniques. However, it is not clear which empirical relationship matches the desired concrete better. Therefore, using only one empirical model can lead to inaccurate results. In the current investigation, the mean value of several appropriate relationships is considered as the desired value. Also, the use of only one NDT technique causes some errors. In order to accurately estimate the concrete characteristics, the combination of two or more nondestructive methods is very e cient. In this research, data of Ultrasonic Pulse Velocity (UPV) and shear wave velocity tests are used simultaneously. The results show that the combination of the two criteria of strength and elasticity and using an average value of several empirical models give a relatively accurate scale for assessment of the concrete condition. The results show the ability and e ciency of the combination of two di erent NDT methods to estimate the strength, elastic moduli, and health condition of the concrete structure.

show abstract

“…The applicability of neural networks for the prediction of workability and slump of concrete was investigated by [16][17][18][19]. Hardened properties of concrete such as concrete strength, ultrasonic pulse velocity, elastic modulus, mechanical behavior at high temperature were predicted by [20][21][22][23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

Comparison of artificial neural networks and general linear model approaches for the analysis of abrasive wear of concrete

Gençel¹,

Kocabaş²,

Gök³

et al. 2011

Construction and Building Materials

View full text Add to dashboard Cite

Artificial Neural Network Approach to Predict Compressive Strength of Concrete through Ultrasonic Pulse Velocity

Cited by 55 publications

References 15 publications

Prediction of Strength Parameters of Himalayan Rocks: A Statistical and ANFIS Approach

Prediction of Strength Parameters of Himalayan Rocks: A Statistical and ANFIS Approach

Strength and elastic moduli of a concrete bridge using advanced nondestructive techniques

Comparison of artificial neural networks and general linear model approaches for the analysis of abrasive wear of concrete

Contact Info

Product

Resources

About