Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete

Deepak Choudhary

doi:doi:10.11648/j.mlr.20190402.11

| Peer-Reviewed

Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete

Deepak Choudhary

Published in Machine Learning Research (Volume 4, Issue 2)

Received: 4 April 2019 Accepted: 23 May 2019 Published: 25 June 2019

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

This paper presents machine learning algorithms based on back-propagation neural network (BPNN) that employs sequential feature selection (SFS) for predicting the compressive strength of Ultra-High Performance Concrete (UHPC). A database, containing 110 points and eight material constituents, was collected from the literature for the development of models using machine learning techniques. The BPNN and SFS were used interchangeably to identify the relevant features that contributed with the response variable. As a result, the BPNN with the selected features was able to interpret more accurate results (r = 0.991) than the model with all the features (r² = 0.816). The utilization of ANN modelling made its way into the prediction of fresh and hardened properties of concrete based on given experimental input parameters, whereby several authors developed AI models to predict the compressive strength of normal weight, light weight and recycled concrete. The steps that were are followed in developing a robust and accurate numerical model using SFS include (1) design and validation of ANN model by manipulating the number of neurons and hidden layers; (2) execution of SFS using ANN as a wrapper; and (3) analysis of selected features using both ANN and nonlinear regression. It is concluded that the usage of ANN with SFS provided an improvement to the prediction model’s accuracy, making it a viable tool for machine learning approaches in civil engineering case studies.

Published in	Machine Learning Research (Volume 4, Issue 2)
DOI	10.11648/j.mlr.20190402.11
Page(s)	27-32
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2019. Published by Science Publishing Group

Keywords

ANN, SFS, UHPC, Compressive Strength, Constituents

References

[1]	S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. Upper Saddle River: Prentice Hall PTR, 1998.
[2]	I. Flood and N. Kartam, Artificial Neural Networks for Civil Engineers: Advanced Features and Applications. New York: American Society of Civil Engineers, 1998.
[3]	J. A. Abdalla, M. F. Attom, and R. Hawileh, “Prediction of minimum factor of safety against slope failure in clayey soils using artificial neural network,” Environ. Earth Sci., vol. 73, no. 9, pp. 5463–5477, 2015.
[4]	J. A. Abdalla, M. Attom, R. Hawileh. “Artificial neural network prediction of factor of safety of slope stability of soils,” The 14th International Conference on Computing in Civil and Building Engineering, Available at Moscow, Russia, 27-29, 2012.
[5]	L. Bal and F. Buyle-Bodin, “Artificial neural network for predicting creep of concrete,” Neural Comput. Appl., vol. 25, no. 6, pp. 1359– 1367, 2014.
[6]	J. A. Abdalla and R. Hawileh, “Modeling and simulation of low-cycle fatigue life of steel reinforcing bars using artificial neural network,” J. Franklin Inst., vol. 348, no. 7, pp. 1393–1403, 2011.
[7]	J. A. Abdalla, RA Hawileh. “Artificial neural network predictions of fatigue life of steel bars based on hysteretic energy.” Journal of Computing in Civil Engineering Vol. 27, no. 5, pp. 489-496, 2013.
[8]	J. Abdalla and R. Hawileh, “Energy-based predictions of number of reversals to fatigue failure of steel bars using artificial neural network,” in The 13th International Conference on Computing in Civil and Building Engineering, 2010.
[9]	J. A. Abdalla, A. Elsanosi, and A. Abdelwahab, “Modeling and simulation of shear resistance of R/C beams using artificial neural network,” J. Franklin Inst., vol. 344, no. 5, pp. 741–756, 2007.
[10]	J. A. Abdalla, A. Abdelwahab, A. Sanousi. “Prediction of shear strength of reinforced concrete beams using artificial neural network,” The First International Conference on Modeling, Simulation and Applied Optimization, Sharjah, U. A. E., 2005.
[11]	H. M. Tanarslan, M. Secer, and A. Kumanlioglu, “An approach for estimating the capacity of RC beams strengthened in shear with FRP reinforcements using artificial neural networks,” Constr. Build. Mater., vol. 30, pp. 556–568, 2012.
[12]	J. A. Abdalla, R. Hawileh, A. Al-Tamimi. “Prediction of FRP-concrete ultimate bond strength using Artificial Neural Network,” International Conference on Modeling, Simulation and Applied Optimization (ICMSAO), Kuala Lumpur, Malaysia, 2011.
[13]	J. A. Abdalla, E. I. Saqan, R. A. Hawileh. “Optimum seismic design of unbonded post-tensioned precast concrete walls using ANN,” Computers and Concrete, Vol. 13, no. 4, pp. 547-567, 2014.
[14]	F. Deng, Y. He, S. Zhou, Y. Yu, H. Cheng, and X. Wu, “Compressive strength prediction of recycled concrete based on deep learning,” Constr. Build. Mater., vol. 175, pp. 562–569, 2018.
[15]	H. Naderpour, A. H. Rafiean, and P. Fakharian, “Compressive strength prediction of environmentally friendly concrete using artificial neural networks,” J. Build. Eng., vol. 16, no. January, pp. 213–219, 2018.
[16]	A. Heidari, M. Hashempour, and D. Tavakoli, “Using of Backpropagation Neural Network in Estimating of Compressive Strength of Waste Concrete,” vol. 1, pp. 54–64, 2017.
[17]	R. Gupta, M. A. Kewalramani, and A. Goel, “Prediction of Concrete Strength Using Neural-Expert System,” J. Mater. Civ. Eng., vol. 18, no. 3, pp. 462–466, 2006.
[18]	S. C. Lee. Prediction of concrete strength using artificial neural networks. Engineering structures; Vo. 25, No. 7:849-857, 2003.
[19]	E. Ghafari, M. Bandarabadi, H. Costa, and E. Júlio, “Prediction of Fresh and Hardened State Properties of UHPC : Comparative Study of Statistical Mixture Design and an Artificial Neural Network Model,” vol. 27, no. 11, pp. 1–11, 2015.
[20]	G. Tayfur, T. K. Erdem, and K. Önder, “Strength Prediction of High-Strength Concrete by Fuzzy Logic and Artificial Neural Networks,” J. Mater. Civ. Eng., vol. 26, no. 11, pp. 1–7, 2014.
[21]	A. Torre, F. Garcia, I. Moromi, P. Espinoza, L. Acuña. Prediction of compression strength of high performance concrete using artificial neural networks. VII International Congress of Engineering Physics, Journal of Physics: Conference Series 582, 2015.
[22]	A. E. N. Kay Wille and Gustavo J. Parra-Montesinos, “Ultra-High Performance Concrete with Compressive Strength Exceeding 150 MPa (22 ksi): A Simpler Way,” Mater. J., vol. 108, no. 1.
[23]	Y. W. W. Zheng, B. Luo, “Compressive and tensile properties of reactive powder concrete with steel fibres at elevated temperatures,”Constr. Build. Mater., vol. 41, pp. 844–851, 2013.
[24]	K.-Q. Yu, J.-T. Yu, J.-G. Dai, Z.-D. Lu, and S. P. Shah, “Development of ultra-high performance engineered cementitious composites using polyethylene (PE) fibers,” Constr. Build. Mater., vol. 158, pp. 217–227, 2018.
[25]	S. Abbas, M. L. Nehdi, and M. A. Saleem, “Ultra-High Performance Concrete: Mechanical Performance, Durability, Sustainability and Implementation Challenges,” Int. J. Concr. Struct. Mater., vol. 10, no. 3, pp. 271–295, 2016.
[26]	N. Soliman and A. Tagnit-Hamou, Using glass sand as an alternative for quartz sand in UHPC, vol. 145. 2017.
[27]	N. Gu, M. Fan, L. Du, and D. Ren, “Efficient sequential feature selection based on adaptive eigenspace model,” Neurocomputing, vol. 161, pp. 199–209, 2015.
[28]	R. Kohavi and G. H. John, “Wrappers for feature subset selection,” Artif. Intell., vol. 97, no. 1–2, pp. 273–324, 1997.
[29]	H. Zhou, M. You, L. Liu, and C. Zhuang, “Sequential data feature selection for human motion recognition via Markov blanket,” Pattern Recognit. Lett., vol. 86, pp. 18–25, 2017.
[30]	V. F. Rodriguez-Galiano, J. A. Luque-Espinar, M. Chica-Olmo, and M. P. Mendes, “Feature selection approaches for predictive modelling of groundwater nitrate pollution: An evaluation of filters, embedded and wrapper methods,” Sci. Total Environ., vol. 624, pp. 661–672, 2018. S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. Upper Saddle River: Prentice Hall PTR, 1998.

Cite This Article

Plain Text BibTeX RIS

APA Style

Deepak Choudhary. (2019). Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete. Machine Learning Research, 4(2), 27-32. https://doi.org/10.11648/j.mlr.20190402.11

Copy | Download

ACS Style

Deepak Choudhary. Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete. Mach. Learn. Res. 2019, 4(2), 27-32. doi: 10.11648/j.mlr.20190402.11

Copy | Download

AMA Style

Deepak Choudhary. Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete. Mach Learn Res. 2019;4(2):27-32. doi: 10.11648/j.mlr.20190402.11

Copy | Download

@article{10.11648/j.mlr.20190402.11,
  author = {Deepak Choudhary},
  title = {Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete},
  journal = {Machine Learning Research},
  volume = {4},
  number = {2},
  pages = {27-32},
  doi = {10.11648/j.mlr.20190402.11},
  url = {https://doi.org/10.11648/j.mlr.20190402.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mlr.20190402.11},
  abstract = {This paper presents machine learning algorithms based on back-propagation neural network (BPNN) that employs sequential feature selection (SFS) for predicting the compressive strength of Ultra-High Performance Concrete (UHPC). A database, containing 110 points and eight material constituents, was collected from the literature for the development of models using machine learning techniques. The BPNN and SFS were used interchangeably to identify the relevant features that contributed with the response variable. As a result, the BPNN with the selected features was able to interpret more accurate results (r = 0.991) than the model with all the features (r2 = 0.816). The utilization of ANN modelling made its way into the prediction of fresh and hardened properties of concrete based on given experimental input parameters, whereby several authors developed AI models to predict the compressive strength of normal weight, light weight and recycled concrete. The steps that were are followed in developing a robust and accurate numerical model using SFS include (1) design and validation of ANN model by manipulating the number of neurons and hidden layers; (2) execution of SFS using ANN as a wrapper; and (3) analysis of selected features using both ANN and nonlinear regression. It is concluded that the usage of ANN with SFS provided an improvement to the prediction model’s accuracy, making it a viable tool for machine learning approaches in civil engineering case studies.},
 year = {2019}
}

Copy | Download

TY  - JOUR
T1  - Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete
AU  - Deepak Choudhary
Y1  - 2019/06/25
PY  - 2019
N1  - https://doi.org/10.11648/j.mlr.20190402.11
DO  - 10.11648/j.mlr.20190402.11
T2  - Machine Learning Research
JF  - Machine Learning Research
JO  - Machine Learning Research
SP  - 27
EP  - 32
PB  - Science Publishing Group
SN  - 2637-5680
UR  - https://doi.org/10.11648/j.mlr.20190402.11
AB  - This paper presents machine learning algorithms based on back-propagation neural network (BPNN) that employs sequential feature selection (SFS) for predicting the compressive strength of Ultra-High Performance Concrete (UHPC). A database, containing 110 points and eight material constituents, was collected from the literature for the development of models using machine learning techniques. The BPNN and SFS were used interchangeably to identify the relevant features that contributed with the response variable. As a result, the BPNN with the selected features was able to interpret more accurate results (r = 0.991) than the model with all the features (r2 = 0.816). The utilization of ANN modelling made its way into the prediction of fresh and hardened properties of concrete based on given experimental input parameters, whereby several authors developed AI models to predict the compressive strength of normal weight, light weight and recycled concrete. The steps that were are followed in developing a robust and accurate numerical model using SFS include (1) design and validation of ANN model by manipulating the number of neurons and hidden layers; (2) execution of SFS using ANN as a wrapper; and (3) analysis of selected features using both ANN and nonlinear regression. It is concluded that the usage of ANN with SFS provided an improvement to the prediction model’s accuracy, making it a viable tool for machine learning approaches in civil engineering case studies.
VL  - 4
IS  - 2
ER  -

Copy | Download

Author Information

Deepak Choudhary

Electronics & Communication Department, ABES Engineering College, Ghaziabad, India

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Deepak Choudhary. (2019). Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete. Machine Learning Research, 4(2), 27-32. https://doi.org/10.11648/j.mlr.20190402.11

Copy | Download

ACS Style

Deepak Choudhary. Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete. Mach. Learn. Res. 2019, 4(2), 27-32. doi: 10.11648/j.mlr.20190402.11

Copy | Download

AMA Style

Deepak Choudhary. Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete. Mach Learn Res. 2019;4(2):27-32. doi: 10.11648/j.mlr.20190402.11

Copy | Download

@article{10.11648/j.mlr.20190402.11,
  author = {Deepak Choudhary},
  title = {Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete},
  journal = {Machine Learning Research},
  volume = {4},
  number = {2},
  pages = {27-32},
  doi = {10.11648/j.mlr.20190402.11},
  url = {https://doi.org/10.11648/j.mlr.20190402.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mlr.20190402.11},
  abstract = {This paper presents machine learning algorithms based on back-propagation neural network (BPNN) that employs sequential feature selection (SFS) for predicting the compressive strength of Ultra-High Performance Concrete (UHPC). A database, containing 110 points and eight material constituents, was collected from the literature for the development of models using machine learning techniques. The BPNN and SFS were used interchangeably to identify the relevant features that contributed with the response variable. As a result, the BPNN with the selected features was able to interpret more accurate results (r = 0.991) than the model with all the features (r2 = 0.816). The utilization of ANN modelling made its way into the prediction of fresh and hardened properties of concrete based on given experimental input parameters, whereby several authors developed AI models to predict the compressive strength of normal weight, light weight and recycled concrete. The steps that were are followed in developing a robust and accurate numerical model using SFS include (1) design and validation of ANN model by manipulating the number of neurons and hidden layers; (2) execution of SFS using ANN as a wrapper; and (3) analysis of selected features using both ANN and nonlinear regression. It is concluded that the usage of ANN with SFS provided an improvement to the prediction model’s accuracy, making it a viable tool for machine learning approaches in civil engineering case studies.},
 year = {2019}
}

Copy | Download

TY  - JOUR
T1  - Learning Algorithms Using BPNN & SFS for Prediction of Compressive Strength of Ultra-High Performance Concrete
AU  - Deepak Choudhary
Y1  - 2019/06/25
PY  - 2019
N1  - https://doi.org/10.11648/j.mlr.20190402.11
DO  - 10.11648/j.mlr.20190402.11
T2  - Machine Learning Research
JF  - Machine Learning Research
JO  - Machine Learning Research
SP  - 27
EP  - 32
PB  - Science Publishing Group
SN  - 2637-5680
UR  - https://doi.org/10.11648/j.mlr.20190402.11
AB  - This paper presents machine learning algorithms based on back-propagation neural network (BPNN) that employs sequential feature selection (SFS) for predicting the compressive strength of Ultra-High Performance Concrete (UHPC). A database, containing 110 points and eight material constituents, was collected from the literature for the development of models using machine learning techniques. The BPNN and SFS were used interchangeably to identify the relevant features that contributed with the response variable. As a result, the BPNN with the selected features was able to interpret more accurate results (r = 0.991) than the model with all the features (r2 = 0.816). The utilization of ANN modelling made its way into the prediction of fresh and hardened properties of concrete based on given experimental input parameters, whereby several authors developed AI models to predict the compressive strength of normal weight, light weight and recycled concrete. The steps that were are followed in developing a robust and accurate numerical model using SFS include (1) design and validation of ANN model by manipulating the number of neurons and hidden layers; (2) execution of SFS using ANN as a wrapper; and (3) analysis of selected features using both ANN and nonlinear regression. It is concluded that the usage of ANN with SFS provided an improvement to the prediction model’s accuracy, making it a viable tool for machine learning approaches in civil engineering case studies.
VL  - 4
IS  - 2
ER  -

Copy | Download