Statistical feature extraction based on an ANN approach for estimating the compressive strength of concrete

Gamze Doğan, Musa Hakan Arslan, Murat Ceylan

Abstract


Applications of artificial intelligence in engineering disciplines have become widespread and have provided alternative solutions to engineering problems. Image processing technology (IPT) and artificial neural networks (ANNs) are types of artificial intelligence methods. However, IPT and ANN have been used together in extremely few studies. In this study, these two methods were used to deter- mine the compressive strength of concrete, a complex material whose mechanical features are difficult to predict. Sixty cube-shaped specimens were manufactured, and images of specific features of the specimens were taken before they were tested to determine their compressive strengths. An ANN model was constituted as a result of the process of digitizing the images. In this way, the two different artificial intelligence methods were used together to carry out the analysis. The compressive strength values of the concrete obtained via analytical modeling were compared with the test results. The results of the comparison (R² = 0:9837-0:9961) indicate that the combination of these two artificial intelligence methods is highly capable of predicting the compressive strengths of the specimens. The model's predictive capability was also evaluated in terms of several statistical parameters using a set of statistical methods during the digitization of the images constituting the artificial neural network.

Keywords


strength; concrete; image processing; neural network; nondestructive testing; statistical properties; statistical methods; cross-validation; analytical modelling

Full Text:

PDF

References


AL-MUFTI R.L., FRIED A.N. The early age non-destructive testing of concrete made with recycled concrete aggregate. Construction and Building Materials. 2012, 37, pp. 379-386, doi: 10.1016/j.conbuildmat.2012.07.058.

ARSLAN M.H., CEYLAN M., KALTAKCI M.Y., OZBAY Y., GULAY G. Prediction of force reduction factor R of prefabricated industrial buildings using neural networks. Structural Engineering and Mechanics. 2007, 27(2), pp. 117-34, doi: 10.12989/sem.2007.27.2.117.

ARSLAN M.H. Application of ANN to evaluate effective parameters affecting failure load and displacement of RC buildings. Natural Hazards and Earth System Science Journal. 2009, 9, pp. 967-977, doi: 10.5194/nhess-9-967-2009.

ARSLAN M.H. Prediction of torsional strength of RC beams by using different artificial neural network algorithms and building codes. Advances in Engineering Software. 2010, (41)7-8, pp. 946-955, doi: 10.1016/j.advengsoft.2010.05.009.

ARSLAN M.H. Estimation of Curvature Ductility in Reinforced Concrete Buildings. KSCE Journal. 2012, 16(5), 759-770, doi: 10.1007/s12205-012-0958-1.

ARSLAN M.H., CEYLAN M., KOYUNCU T. An ANN Approaches on Estimating Earthquake Performances of Existing RC Buildings. Neural Network World. 2012, 5(12), pp. 443-458, doi: 10.14311/NNW.2012.22.027.

BASYIGIT C., COMAK B., KILICARSLAN S., UNCU I.S. Assessment of concrete compressive strength by image processing technique. Construction and Building Materials. 2012, 37, pp. 526-532, doi: 10.1016/j.conbuildmat.2012.07.055.

BOGAS J.A., GOMES M.G., GOMES A. Compressive strength evaluation of structural lightweight concrete by non-destructive ultrasonic pulse velocity method. Ultrasonics. 2012, 53(3), pp. 962-972 doi: 10.1016/j.ultras.2012.12.012.

CANKAYA G., ARSLAN M.H., CEYLAN M. Statistical Methods for Processing and Analysis of Digital Images: Determining compressive strength of concrete. International Conference of Applied Statistics. 2012, Bled, Slovenia.

CEYLAN M., ARSLAN M.H., CEYLAN R., KALTAKCI M.Y., OZBAY Y. A New Application Area of ANN and ANFIS: Determination of Earthquake Load Reduction Factor of Prefabricated Industrial Buildings. Civil Engineering and Environmental Systems. 2010, 27(1), pp. 53-69, doi: 10.1080/10286600802506726.

COMAK B., BEYCIOGLU A., BASYIGIT C., KILICARSLAN S. The use of image processing techniques in concrete technology. 6th Intenational Advanced Technologies Symposium 2011 (IATS'11). 2011, Elazig, Turkey.

DOGAROGLU O.K. Utilization opportunities of image processing technology in estimation of live weight and various body sizes of cattles for slaughter. Tekirdag, Turkey, 2006. Master Thesis, Trakya University Institute of Science in Tekirdag, Turkey.

EKICI B.B., AKSOY U.T. Prediction of Building Energy Consumption by Using Artificial Neural Networks. Advances in Engineering Software. 2010, 40(5), pp. 356-362, doi: 10.1016/j.advengsoft.2008.05.003.

ERGUN A., KURKLU G. Determination of concrete strength in current concrete buildings. Earthquake Symposium. 2005, Kocaeli, Turkey.

FRUH C., SCHILDKNECHT T. Object image linking of earth orbiting object in the presence of comics. Advances in Space Research. 2012, 49, pp. 594-602, doi: 10.1016/j.asr.2011.10.021.

GAYDECKI P., SILVA I., FERNANDES B.T., YU Z. Z. A portable inductive scanning system for imaging steel-reinforcing bars embedded within concrete. Sensors and Actuators. 2000, 84, pp. 25-32, doi: 10.1016/S0924-4247(99)00296-4.

HASSAN A.M.T., JONES S.W. Non-destructive testing of ultra-high performance fibre reinforced concrete (UHPFRC): A feasibility study for using ultrasonic and resonant frequency testing techniques. Construction and Building Materials. 2012, 35, pp. 361-367, doi: 10.1016/j.conbuildmat.2012.04.047.

HAYKIN S. Neural Networks: A comprehensive foundation. 2nd ed. New York: Prentice-Hall, 1998.

HOBBS B., KEBIR M.T. Non-destructive testing techniques for the forensic engineering investigation of reinforced concrete buildings. Forensic Science International. 2007, 167(2,3), pp. 167-172, doi: 10.1016/j.forsciint.2006.06.065.

MATLAB. Matlab Reference Guide [online]. The MathWorks, Inc. Natick, MA, 1996 [viewed 2015-02-02]. Available from: http://www.mathworks.com/matlabcentral.

KOROGLU M.A, CEYLAN M., ARSLAN M.H., ILKI A. Estimation of Fslexural Capacity of Quadrilateral FRP-Confined RC Columns Using Combined Artificial Neural Network. Engineering Structures. 2012, 42, pp. 23-32, doi: 10.1016/j.engstruct.2012.04.013.

KOSE M.M., Parameters affecting the fundamental period of RC buildings with infill walls. Engineering Structure. 2009, 31(1), pp. 93-102, doi: 10.1016/j.engstruct.2008.07.017.

KUCUK O.F. Ultrasonic surface waves - finding concrete strength with the help of Schmidt method. Sanliurfa, Turkey, 2006. Master Thesis, Harran University Institute of Science in Sanliurfa, Turkey.

MIDDLETON L., SIVASWAMY J. Edge detection in a hexagonal- image processing framework. Image and Vision Computing. 2001, 19(14), pp. 1071-1081, doi: 10.1016/S0262-8856(01)00067-1.

NAGATAKI S., GOKCE A., SAEKI T., HISADA M. Assessment of recycling process induced damage sensitivity of recycled concrete aggregates. Cement and Concrete Research. 2004, 34(6), pp. 965{971, doi: 10.1016/j.cemconres.2003.11.008.

NAMBIAR E.K.K., RAMAMURTHY, K. Air-void characterization of foam concrete. Cement and Concrete Research. 2007, 37(2), pp. 221-230, doi: 10.1016/j.cemconres.2006.10.009.

OKUYAN M.N. The fact that compressive strength of high resistant concrete including silica fume is non-damaged, Master Thesis 2007, Harran University Institute of Science in Sanliurfa, Turkey.

OZBAY Y., CEYLAN R., KARLIK B.A. A fuzzy clustering neural network architecture for classification of ECG arrhythmias. Computers in Biology and Medicine. 2006, 36(4), pp. 376-388, doi: 10.1016/j.compbiomed.2005.01.006.

OZEN M. Investigation of relationship between aggregate shape parameters and concrete strength using imaging techniques. Ankara, Turkey, 2007. Master Thesis, Graduate School of Natural and Applied Sciences of Middle East Technical University in Ankara.

SCHUTTER G.D. Advanced monitoring of cracked structures using video microscope and automated image analysis. NDT&E International. 2002, 35(4), pp. 209-212, doi: 10.1016/S0963-8695(01)00042-1.

SPYROU S., DAVISON J.B. Displacement measurement in studies of steel T-stub connections. Journal of Constructional Steel Research. 2001, 57(6), pp. 647-659, doi: 10.1016/S0143-974X(01)00003-7.

STEVENS R., IKEDA J., CASILLAS A., PALACIO J., CLYMAN S. Artificial Neural Network-Based Performance Assessments. Computers in Human Behavior. 1999, 15(3-4), pp. 295-313, doi: 10.1016/S0747-5632(99)00025-4.

Turkish Standards, TS EN 13791. Assessment of in-situ compressive strength in structures and precast concrete components. Turkish Standards Institute 2010, Ankara.

Turkish Standards, TS 500. Design and Construction Rules of Concrete. Turkish Standards Institute 2000, Ankara.

VERIM V. Finding tissue boundaries by using image processing methods. Ankara, Turkey, 2005. Master Thesis, Gazi University Institute of Science in Ankara, Turkey.

WINDER R.J., MORROW P.J., MCRITCHIE I.N., BAILIE J.R., HART P.M. Algorithms for digital image processing in diabetic retinopathy. Computerized Medical Imaging and Graphics. 2009, 33(8), pp. 608-622, doi: 10.1016/j.compmedimag.2009.06.003.

YUKSEL S.B., ARSLAN M.H. Design Forces for Groups of Six Cylindrical Silos by ANN. Structures & Buildings Journal. 2012, 165(10), pp. 567-580, doi: 10.1680/stbu.10.00049.




DOI: http://dx.doi.org/10.14311/NNW.2015.%25x

Refbacks

  • There are currently no refbacks.


Should you encounter an error (non-functional link, missing or misleading information, application crash), please let us know at nnw.ojs@fd.cvut.cz.
Please, do not use the above address for non-OJS-related queries (manuscript status, etc.).
For your convenience we maintain a list of frequently asked questions here. General queries to items not covered by this FAQ shall be directed to the journal editoral office at nnw@fd.cvut.cz.