Please wait a minute...

Frontiers of Structural and Civil Engineering

Front. Struct. Civ. Eng.    2019, Vol. 13 Issue (6) : 1379-1392     https://doi.org/10.1007/s11709-019-0562-2
RESEARCH ARTICLE
Predicting resilient modulus of recycled concrete and clay masonry blends for pavement applications using soft computing techniques
Mosbeh R. KALOOP1,2,3, Alaa R. GABR3, Sherif M. EL-BADAWY3, Ali ARISHA3, Sayed SHWALLY3, Jong Wan HU1,2()
1. Department of Civil and Environmental Engineering, Incheon National University, Incheon 22012, South Korea
2. Incheon Disaster Prevention Research Center, Incheon National University, Incheon 22012, South Korea
3. Department of Public Works and Civil Engineering, Mansoura University, Mansoura 35516, Egypt
Download: PDF(2891 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

To date, very few researchers employed the Least Square Support Vector Machine (LSSVM) in predicting the resilient modulus (Mr) of Unbound Granular Materials (UGMs). This paper focused on the development of a LSSVM model to predict the Mr of recycled materials for pavement applications and comparison with other different models such as Regression, and Artificial Neural Network (ANN). Blends of Recycled Concrete Aggregate (RCA) with Recycled Clay Masonry (RCM) with proportions of 100/0, 90/10, 80/20, 70/30, 55/45, 40/60, 20/80, and 0/100 by the total aggregate mass were evaluated for use as UGMs. RCA/RCM materials were collected from dumps on the sides of roads around Mansoura city, Egypt. The investigated blends were evaluated experimentally by routine and advanced tests and the Mr values were determined by Repeated Load Triaxial Test (RLTT). Regression, ANN, and LSSVM models were utilized and compared in predicting the Mr of the investigated blends optimizing the best design model. Results showed that the Mr values of the investigated RCA/RCM blends were generally increased with the decrease in RCM proportion. Statistical analyses were utilized for evaluating the performance of the developed models and the inputs sensitivity parameters. Eventually, the results approved that the LSSVM model can be used as a novel tool to estimate the Mr of the investigated RCA/RCM blends.

Keywords Least Square Support Vector Machine      Artificial Neural Network      resilient modulus      Recycled Concrete Aggregate      Recycled Clay Masonry     
Corresponding Authors: Jong Wan HU   
Just Accepted Date: 16 July 2019   Online First Date: 16 September 2019    Issue Date: 21 November 2019
 Cite this article:   
Mosbeh R. KALOOP,Alaa R. GABR,Sherif M. EL-BADAWY, et al. Predicting resilient modulus of recycled concrete and clay masonry blends for pavement applications using soft computing techniques[J]. Front. Struct. Civ. Eng., 2019, 13(6): 1379-1392.
 URL:  
http://journal.hep.com.cn/fsce/EN/10.1007/s11709-019-0562-2
http://journal.hep.com.cn/fsce/EN/Y2019/V13/I6/1379
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Mosbeh R. KALOOP
Alaa R. GABR
Sherif M. EL-BADAWY
Ali ARISHA
Sayed SHWALLY
Jong Wan HU
Fig.1  Crushing of RCA/RCM materials [30]. (a) RCA before crushing; (b) RCM before crushing; (c) RCA after crushing; (d) RCM after crushing.
Fig.2  Particle size distribution for investigated blends. Reprinted from Procedia Engineering, 143, Ali Arisha, Alaa Gabr, Sherif El- Badawy, Sayed Shwally, Using Blends of Construction & Demolition Waste Materials and Recycled Clay Masonry Brick in Pavement, 8, Copyright (2016), with permission from Elsevier.
Fig.3  Training and testing datasets. (a) Training dataset; (b) testing dataset.
data set item RCM (%) θPa τPa Mr (MPa)
training data set max 100.00 6.619 1.170 527.80
min 0.00 0.807 0.088 114.95
mean 43.13 3.283 0.473 296.41
SD 32.86 1.681 0.290 106.95
testing data set max 100.00 6.619 1.170 475.00
min 0.00 0.807 0.088 101.95
mean 43.13 3.072 0.431 285.83
SD 33.209 1.887 0.287 102.849
Tab.1  Statistical analysis for the training and testing data sets
Fig.4  (a) ANN and (b) LSSVM models’ diagram.
Fig.5  Flowchart of stages processing for modeling Mr.
property test result
material (RCA/RCM) 100/0 90/10 80/20 70/30 55/45 40/60 20/80 0/100
OMC 12.7% 14.4% 13.5% 14.3% 11.5% 12.4% 10.1% 10.8%
MDD (t/m3) 1.86 1.84 1.82 1.82 1.84 1.84 1.78 1.75
liquid limit 25% 26%
plasticity index NP* NP*
AASHTO classification A-1-a A-1-a
CBR 152.9% 128.7% 114.5% 114.5% 119.4% 114.5% 69.5% 76.6%
LAA 47.2% 83.8%
pH 9.1 8.8
K (m/s) 1.8E–08 7.7E–09 1.5E–07
water absorption 0.80% 7.20%
specific gravity (Gs) 2.30 2.03
apparent cohesion, c, (kPa) 12.4 25.8 56.8 89.2 80.3 24.0 50.9 43.1
friction Angle, f 58.4 55.6 52.7 48.8 53.2 59.7 50.4 52.7
Mr
(Eq. (1))
K1 2.29±0.270 1.85±0.437 1.62±0.325 1.50±0.033 2.31±0.251 1.34±0.099 1.15±0.090 1.45±0.086
K2 0.49±0.037 0.53±0.163 0.59±0.121 0.57±0.018 0.48±0.027 0.19±0.011 0.37±0.032 0.57±0.007
K3 -0.134±0.004 -0.09±0.031 -0.099±0.019 -0.056±0.001 -0.124±0.028 1.073±0.003 0.548±0.005 -0.194±0.001
R2 0.974 0.981 0.976 0.975 0.975 0.96 0.972 0.981
Tab.2  Summary of the engineering properties of RCA/RCM blends [35]
mineral phase original RCA RCA after mixing original RCM RCM after mixing
Quartz 39% 37.6% 64.8% 55.4%
Dolomite 27.8% 31.2% - -
Calcite 22.3% 14.4% - -
Albite 10.9% - 19.4% 17.6%
Microcline - 16.8% 9.7% 23.4%
Hematite - - 6.1% 3.6%
Tab.3  XRD results for RCA and RCM before and after mixing
Fig.6  XRD analysis for (a) RCA and (b) RCM sample after mixing Reprinted from Ref. [35] with permission from Journal of Materials in Civil Engineering.
Fig.7  Sensitivity analysis of input parameters.
No. of neurons 4 8 10 15 20
R2 0.819 0.839 0.901 0.910 0.915
RMSE (MPa) 45.279 42.646 33.429 31.913 30.951
Tab.4  Statistics measures for the number of ANN hidden neurons
Fig.8  (a) MSE model validation and (b) Input-Hidden and Hidden-output weights values.
Fig.9  LSSVM model design (a) α value, (b) training 95% error band.
model training set testing set
R2 RMSE (MPa) MAE (MPa) E R2 RMSE (MPa) MAE (MPa) E
Reg. 0.817 45.715 31.915 0.644 0.868 38.770 25.988 0.699
ANN 0.901 33.429 24.888 0.722 0.887 34.805 27.297 0.685
LSSVM 0.848 41.473 32.744 0.635 0.982 13.768 10.555 0.878
Tab.5  Statistics measures of the three prediction models for the training and testing data sets
Fig.10  Predicted versus measured Mr for RCA/RCM blends, Regression, ANN, and LSSVM fit for training (left) and testing (right) data sets: (a) Regression; (b) ANN; (c) LSSVM.
1 A Arisha. Evaluation of recycled clay masonry blends in pavement construction. Thesis for the Master’s Degree. Mansoura: Mansoura University, 2017
2 A Arisha, A Gabr, S El-Badawy, S Shwally. Using blends of construction & demolition waste materials and recycled clay masonry brick in pavement. Procedia Engineering, 2016, 143: 1317–1324
3 A Gabr, D Cameron. Properties of recycled concrete aggregate for unbound pavement construction. Journal of Materials in Civil Engineering, 2012, 24(6): 754–764
https://doi.org/10.1061/(ASCE)MT.1943-5533.0000447
4 M Malešev, V Radonjanin, S Marinković. Recycled concrete as aggregate for structural concrete production. Sustainability, 2010, 2(5): 1204–1225
https://doi.org/10.3390/su2051204
5 R Cardoso, R V Silva, J Brito, R Dhir. Use of recycled aggregates from construction and demolition waste in geotechnical applications : A literature review. Waste Management (New York), 2016, 49: 131–145 doi:10.1016/j.wasman.2015.12.021
6 E Mousa, A Azam, M El-Shabrawy, S El-Badawy. Laboratory characterization of reclaimed asphalt pavement for road construction in Egypt. Canadian Journal of Civil Engineering, 2017, 44(6): 417–425
https://doi.org/10.1139/cjce-2016-0435
7 D Andrei, M Witczak, W Houston. Resilient modulus predictive model for unbound pavement materials. In: International Foundation Congress and Equipment Expo 2009, 2009, 401–408
8 R Ji, N Siddiki, T Nantung, D Kim. Evaluation of resilient modulus of subgrade and base materials in Indiana and its implementation in MEPDG. The Scientific World Journal, 2014, 2014: 1–14
9 K George. Prediction of Resilient Modulus from Soils Index Proprieties. 2004
10 F Lekarp, U Isacsson, A Dawson. State of the art. I: Resilient response of unbound aggregates. Journal of Transportation Engineering, 2000, 126(1): 66–75
https://doi.org/10.1061/(ASCE)0733-947X(2000)126:1(66)
11 R Mousa, A Gabr, M Arab, A Azam, S El-Badawy. Resilient modulus for unbound granular materials and subgrade soils in Egypt. In: Proceedings of the International Conference on Advances in Sustainable Construction Materials & Civil Engineering Systems, 2017
12 AASHTO. Mechanistic-Empirical Pavement Design Guide: A Manual of Practice. Interim Edition, American Association of Highways and Transportation Officials. 2008
13 S Kim, J Yang, J Jeong. Prediction of subgrade resilient modulus using artificial neural network. KSCE Journal of Civil Engineering, 2014, 18(5): 1372–1379
https://doi.org/10.1007/s12205-014-0316-6
14 E Sadrossadat, A Heidaripanah, S Osouli. Prediction of the resilient modulus of flexible pavement subgrade soils using adaptive neuro-fuzzy inference systems. Construction & Building Materials, 2016, 123: 235–247
https://doi.org/10.1016/j.conbuildmat.2016.07.008
15 A Reza, M Rahrovan. Application of artifitial neural network to predict the resilient modulus of stabilized base subjected to wet dry cycles. Comput. Mater. Civ. Eng., 2016, 1(1): 37–47
16 M Zaman, P Solanki, A Ebrahimi, L White. Neural network modeling of resilient modulus using routine subgrade soil properties. International Journal of Geomechanics, 2010, 10(1): 1–12
https://doi.org/10.1061/(ASCE)1532-3641(2010)10:1(1)
17 O Elbagalati, M A Elseifi, K Gaspard, Z Zhang. Development of an artificial neural network model to predict subgrade resilient modulus from continuous deflection testing. Canadian Journal of Civil Engineering, 2017, 44(9): 700–706
https://doi.org/10.1139/cjce-2017-0132
18 P Solanki, M Zaman, A. EbrahimiRegression and artificial neural network modeling of resilient modulus of subgrade soils for pavement design applications. Intelligent and Soft Computing in Infrastructure Systems Engineering, 2009, 259: 269–304
19 R Zuo, E Carranza. Support vector machine: A tool for mapping mineral prospectivity. Computers & Geosciences, 2011, 37(12): 1967–1975
https://doi.org/10.1016/j.cageo.2010.09.014
20 T van Gestel, J A K Suykens, B Baesens, S Viaene, J Vanthienen, G Dedene, B de Moor, J Vandewalle. Benchmarking least squares support vector machine classifiers. Machine Learning, 2004, 54(1): 5–32
https://doi.org/10.1023/B:MACH.0000008082.80494.e0
21 P Samui, D Kothari. Utilization of a least square support vector machine (LSSVM) for slope stability analysis. Scientia Iranica, 2011, 18(1): 53–58
https://doi.org/10.1016/j.scient.2011.03.007
22 J Suykens, J Vandewalle. Least squares support vector machine classifiers. Neural Processing Letters, 1999, 9(3): 293–300
https://doi.org/10.1023/A:1018628609742
23 M Kaloop, J Hu. Seismic response prediction of buildings with base isolation using advanced soft computing approaches. Advances in Materials Science and Engineering, 2017, 2017: 7942782
24 P Samui, S Das, T Sitharam. Application of soft computing techniques to expansive soil characterization. In: Intelligent and Soft Computing in Infrastructure Systems Engineering, 2009, 305–306
25 K Fardad, B Najafi, S F Ardabili, A Mosavi, S Shamshirband, T Rabczuk. Biodegradation of medicinal plants waste in an anaerobic digestion reactor for biogas production. Computer, Material and Continua, 2018, 55(3): 318–392
26 K M Hamdia, H Ghasemi, X Zhuang, N Alajlan, T Rabczuk. Sensitivity and uncertainty analysis for flexoelectric nanostructures. Computer Methods in Applied Mechanics and Engineering, 2018, 337: 95–109
https://doi.org/10.1016/j.cma.2018.03.016
27 K M Hamdia, M Silani, X Zhuang, P He, T Rabczuk. Stochastic analysis of the fracture toughness of polymeric nanoparticle composites using polynomial chaos expansions. International Journal of Fracture, 2017, 206(2): 215–227
https://doi.org/10.1007/s10704-017-0210-6
28 M F Badawy, M A Msekh, K M Hamdia, M K Steiner, T Lahmer, T Rabczuk. Hybrid nonlinear surrogate models for fracture behavior of polymeric nanocomposites. Probabilistic Engineering Mechanics, 2017, 50: 64–75
https://doi.org/10.1016/j.probengmech.2017.10.003
29 K Gopalakrishnan, H Ceylan , N. Attoh-OkineIntelligent and Soft Computing in Infrastructure Systems Engineering. 2009
30 ECP. Egyptian Code of Practice for Urban and Rural Roads, Edition 1: Road materials and their tests (part four). The Ministry of Housing, Utilities and Urban Communities, Egypt, 2008
31 T Brey. A multi-parameter artificial neural network model to estimate macrobenthic invertebrate productivity and production. Limnology and Oceanography, Methods, 2012, 10(8): 581–589
https://doi.org/10.4319/lom.2012.10.581
32 M Norgaard, O Ravn, N K Poulsen. NNSYSID-toolbox for system identification with neural networks. Mathematical and Computer Modelling of Dynamical Systems, 2002, 8(1): 1–20
https://doi.org/10.1076/mcmd.8.1.1.8342
33 P Samui, D Kim, B Aiyer. Pullout capacity of small ground anchor: A least square support vector machine approach. Journal of Zhejiang University. Science A, 2015, 16(4): 295–301
https://doi.org/10.1631/jzus.A1200260
34 S Karimi, O Kisi, J Shiri, O, MakarynskyyShiri1 J, Makarynskyy O. A wavelet and neuro-fuzzy conjunction model to forecast air temperature variations at coastal sites. The International Journal of Ocean and Climate Systems, 2015, 6(4): 159–172
https://doi.org/10.1260/1759-3131.6.4.159
35 A Arisha, A Gabr, S El-badawy, S Shwally. Performance evaluation of construction and demolition waste materials for pavement construction in Egypt. Journal of Materials in Civil Engineering,2018, 30(2): 04017270
Related articles from Frontiers Journals
[1] Ali Reza GHANIZADEH, Hakime ABBASLOU, Amir Tavana AMLASHI, Pourya ALIDOUST. Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine[J]. Front. Struct. Civ. Eng., 2019, 13(1): 215-239.
[2] T. Chandra Sekhara REDDY. Predicting the strength properties of slurry infiltrated fibrous concrete using artificial neural network[J]. Front. Struct. Civ. Eng., 2018, 12(4): 490-503.
[3] P. ZAKIAN. An efficient stochastic dynamic analysis of soil media using radial basis function artificial neural network[J]. Front. Struct. Civ. Eng., 2017, 11(4): 470-479.
[4] Faezehossadat KHADEMI,Mahmoud AKBARI,Sayed Mohammadmehdi JAMAL,Mehdi NIKOO. Multiple linear regression, artificial neural network, and fuzzy logic prediction of 28 days compressive strength of concrete[J]. Front. Struct. Civ. Eng., 2017, 11(1): 90-99.
[5] Sadegh REZAEI,Asskar Janalizadeh CHOOBBASTI. Liquefaction assessment using microtremor measurement, conventional method and artificial neural network (Case study: Babol, Iran)[J]. Front. Struct. Civ. Eng., 2014, 8(3): 292-307.
[6] Yasser SHARIFI,Sajjad TOHIDI. Lateral-torsional buckling capacity assessment of web opening steel girders by artificial neural networks – elastic investigation[J]. Front. Struct. Civ. Eng., 2014, 8(2): 167-177.
[7] Pijush Samui, Jagan J. Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach[J]. Front Struc Civil Eng, 2013, 7(2): 133-136.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed