Estimation of flexible pavement structural capacity using machine learning techniques

doi:10.1007/s11709-020-0654-z

Frontiers of Structural and Civil Engineering

2020, Vol. 14

Issue (5): 1083-1096 https://doi.org/10.1007/s11709-020-0654-z

本期目录

Estimation of flexible pavement structural capacity using machine learning techniques

Nader KARBALLAEEZADEH¹, Hosein GHASEMZADEH TEHRANI¹(

), Danial MOHAMMADZADEH SHADMEHRI^2,³, Shahaboddin SHAMSHIRBAND^4,⁵(

)

¹. Civil Engineering Department, Shahrood University of Technology, Shahrood 3619995161, Iran
². Department of Civil Engineering, Ferdowsi University of Mashhad, Mashhad 9177948974, Iran
³. Department of Elite Relations with Industries, Khorasan Construction Engineering Organization, Mashhad 9185816744, Iran
⁴. Department for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, Vietnam
⁵. Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam

全文: PDF(1993 KB) HTML

Abstract：

The most common index for representing structural condition of the pavement is the structural number. The current procedure for determining structural numbers involves utilizing falling weight deflectometer and ground-penetrating radar tests, recording pavement surface deflections, and analyzing recorded deflections by back-calculation manners. This procedure has two drawbacks: falling weight deflectometer and ground-penetrating radar are expensive tests; back-calculation ways has some inherent shortcomings compared to exact methods as they adopt a trial and error approach. In this study, three machine learning methods entitled Gaussian process regression, M5P model tree, and random forest used for the prediction of structural numbers in flexible pavements. Dataset of this paper is related to 759 flexible pavement sections at Semnan and Khuzestan provinces in Iran and includes “structural number” as output and “surface deflections and surface temperature” as inputs. The accuracy of results was examined based on three criteria of R, MAE, and RMSE. Among the methods employed in this paper, random forest is the most accurate as it yields the best values for above criteria (R=0.841, MAE=0.592, and RMSE=0.760). The proposed method does not require to use ground penetrating radar test, which in turn reduce costs and work difficulty. Using machine learning methods instead of back-calculation improves the calculation process quality and accuracy.

Key words： transportation infrastructure flexible pavement structural number prediction Gaussian process regression M5P model tree random forest

收稿日期: 2019-08-27 出版日期: 2020-11-16

Corresponding Author(s): Hosein GHASEMZADEH TEHRANI,Shahaboddin SHAMSHIRBAND

引用本文:

. [J]. Frontiers of Structural and Civil Engineering, 2020, 14(5): 1083-1096.
Nader KARBALLAEEZADEH, Hosein GHASEMZADEH TEHRANI, Danial MOHAMMADZADEH SHADMEHRI, Shahaboddin SHAMSHIRBAND. Estimation of flexible pavement structural capacity using machine learning techniques. Front. Struct. Civ. Eng., 2020, 14(5): 1083-1096.

链接本文:

https://academic.hep.com.cn/fsce/CN/10.1007/s11709-020-0654-z
https://academic.hep.com.cn/fsce/CN/Y2020/V14/I5/1083

model name	mathematical form
AASHTO [¹⁴]	$S N = ∑ i = 1 n h i a g (E i E g) 13$
Noureldin [²³]	$S N eff = 4 (r x) 2 − 36 17.234 r x × D x 3$
Jameson [²⁴]	$S N e f f = 13.5 − 6.5 log ? D 0 + 3.71 log ? D 90$
Rohde [²⁵]	$S N e f f = 0.4728 × S I P − 0.481 × H p 0.7581, S I P = D 0 − D 1.5 H p$
Rohde et al. [²⁶]	$M S N = S N + S N s b g$ $S N s b g = − 1.43 + 3.51 log ? (C B R) − 0.85 (log ? (C B R)) 2$
Asgari [²⁷]	$S N C = a 0 × (D 0) a 1$
COST [²⁸]	$S N e f f = 1.69 + 842.8 D 0 − D 150 − 42.94 D 90$
Modified version of COST’s model [²⁹]	$S N e f f = 1.70 + 813 D 0 − D 150 − 39 D 90$
Romanoschi and Metcalf [³⁰]	$S N = 6.45 − 3.676 × log ? (D 0) + 3.727 × log ? (D 150)$
Hoffman [³¹]	$S N e f f = 0.0182 × E s b g 3 × l 0$
Schnoor and Horak [²⁷]	$S N e f f = e 5.12 × B L I 0.31 × A u p p − 0.78$ $B L I = D 0 − D 30$ $A u p p = 5 D 0 − 2 D 30 − 2 D 60 − D 90 2$
Wimsatt formula [²⁷]	$S N e f f = 0.00045 × D × E P 3$
Abdel-Khalek et al. [³²]	$S N R W D = 23.52 × R W D − 0.24 − 1.39 × ln ? (S D) − 150.69 × R I − 0.81 19.04 + R I − 6.37$ $R I = (average R W D deflection) × (standard deviation of R W D deflection)$
Howard [²⁷]	$S N = 0.971876 + 0.002543 H P + 785.4524 D 0 − D 150 + 69.9904 D 90, S N ≥ 2.5$ $S N = 0.884209 + 0.000866 H P + 866.3272 D 0 − D 150 + 22.6561 D 90, S N < 2.5$
Kim et al. [³³]	$S N e f f = K 1 × S I P k 2 × H P k 3 + (K 4 × (1 + r 0) K 5) + (K 6 × S C I K 7 × B D I K 8)$ $S I P = D 0 − D 1.5 H P$ $S C I = D 0 − D 20$ $B D I = D 20 − D 30$
modified version of Kim et al.’s model [³⁴]	$S N e f f = (1.039 × S I P − 0.412 × H H P 0.76) + (0.22 × (1 + r 0) − 5.541) − (0.0006 × B D I 3.607)$ $S I P = D 0 − D 1.5 H P$ $S C I = D 0 − D 20$ $B D I = D 20 − D 30$
Gedafa et al. [³⁵]	$S N = 0.1438 (log ? (E A L)) 2 − 0.4115 log ? (E A L) − 0.406 R u t + 0.01 D 2 − 0.0091 E F C R + 0.0062 d 02 + 0.0836 E T C R − 0.3364 d 0 + 0.0004 E F C R 2 − 0.0805 D + 6.3763 − 0.0008 (d 0 × D)$
Elbagalati et al. [³⁶]	$S N = 0.29 ln ? (A D T P L N) − 14.27 + 27.55 (A C t h D 0) 0.04695 − 2.426 ln ? (S D)$
Kavussi et al. [³⁷]	$S N e f f = 34.171 × D 0 − 0.638 × D 90 0.330$
Zihan et al. [¹]	$S N T S D = − 24.28 + 0.31 ln ? (A D T) + 0.18 (T t h) + 8.65 (D 48) 0.11 + 18.67 e − 0.013 D 0$

Tab.1

parameter	formula	description
SCI	D₀– D₂₀	asphalt structural evaluation
BDI	D₃₀– D₆₀	base structural evaluation
BCI	D₆₀– D₉₀	subbase and subgrade structural evaluation
AREA	$6 (2 D 30 D 0 + 2 D 60 D 0 + D 90 D 0 + 1)$	pavement and subgrade structural assessment
AUPP	$5 D 0 − 2 D 30 − 2 D 60 − D 90 2$	area under pavement profile; structural evaluation of the pavement upper layers
F₂	$D 30 − D 90 D 60$	shape factor; evaluation of subgrade moduli
F₃	$D 60 − D 120 D 90$	additional shape factor; evaluation of lower layer

Tab.2

Tab.3

Fig.1

Tab.4

Tab.5

category no.	inputs	target
1	D₀, D₂₀, D₃₀, D₄₅, D₆₀, D₉₀, D₁₂₀, D₁₅₀, D₁₈₀, and Surface temp.	SN_eff
2	AUPP, SCI, BDI, F₂, F₃, and Surface temp.
3	AUPP, SCI, BDI, Surface temp., and D₀
4	AUPP, SCI, D₀×Surface temp., D₀– D₆₀, and D₂₀– D₃₀
5	AUPP, SCI, BDI, D₀×Surface temp., F₂, and F₃
6	D₀– D₆₀, D₀– D₄₅, D₂₀– D₃₀, and $s u r f a c e t e m p . A U P P$
7	AUPP, D₀– D₄₅, $S u r f a c e t e m p . (D 0 − D 60) × (D 20 − D 30)$ , and $1 B D I × S C I × A U P P × (D 0 − D 60) × (D 20 − D 30)$

Tab.6

Tab.7

Fig.2

Fig.3

Fig.4

1	Z Uddin Ahmed Zihan, M A Elseifi, K Gaspard, Z Zhang. Development of a structural capacity prediction model based on traffic speed deflectometer measurements. Transportation Research Record: Journal of the Transportation Research Board, 2018, 2672(40): 315–325 https://doi.org/10.1177/0361198118758058
2	M Onyango, S A Merabti, J Owino, I Fomunung, W Wu. Analysis of cost effective pavement treatment and budget optimization for arterial roads in the city of Chattanooga. Frontiers of Structural and Civil Engineering, 2018, 12(3): 291–299 https://doi.org/10.1007/s11709-017-0419-5
3	C M Kuo, T Y Tsai. Significance of subgrade damping on structural evaluation of pavements. Road Materials and Pavement Design, 2014, 15(2): 455–464 https://doi.org/10.1080/14680629.2014.884016
4	R L Lytton. Concepts of pavement performance prediction and modeling. In: Proceeddings of the 2nd North American Conference on Managing Pavements. Toronto, Ontario: Ministry of Transportation, 1987
5	N Kargah-Ostadi, Y Zhou, T Rahman. Developing performance prediction models for pavement management systems in local governments in absence of age data. Transportation Research Record: Journal of the Transportation Research Board, 2019, 2673(3): 0361198119833680 https://doi.org/10.1177/0361198119833680
6	O Elbagalati, M Elseifi, K Gaspard, Z Zhang. Development of the pavement structural health index based on falling weight deflectometer testing. International Journal of Pavement Engineering, 2018, 19(1): 1–8 https://doi.org/10.1080/10298436.2016.1149838
7	H S Abd El-Raof, R T Abd El-Hakim, S M El-Badawy, H A Afify. Simplified closed-form procedure for network-level determination of pavement layer moduli from falling weight deflectometer data. Journal of Transportation Engineering, Part B: Pavements, 2018, 144(4): 04018052 https://doi.org/10.1061/JPEODX.0000080
8	F Moghadas Nejad , F Zare Motekhases, H Zakeri, A Mehrabi. An image processing approach to asphalt concrete feature extraction. Journal of Industrial and Intelligent Information, 2015, 3(1): 54–60 https://doi.org/10.12720/jiii.3.1.54-60
9	Y Deng, Q Yang. Rapid evaluation of a transverse crack on a semi-rigid pavement utilising deflection basin data. Road Materials and Pavement Design, 2019, 20(4): 929–942 https://doi.org/10.1080/14680629.2018.1424026
10	N Karballaeezadeh, D Mohammadzadeh S, S Shamshirband, P Hajikhodaverdikhan, A Mosavi, K Chau. Prediction of remaining service life of pavement using an optimized support vector machine (case study of Semnan-Firuzkuh road). Engineering Applications of Computational Fluid Mechanics, 2019, 13(1): 188–198 https://doi.org/10.1080/19942060.2018.1563829
11	L Pinkofsky, D Jansen. Structural pavement assessment in Germany. Frontiers of Structural and Civil Engineering, 2018, 12(2): 183–191 https://doi.org/10.1007/s11709-017-0412-z
12	P Liu, D Wang, F Otto, M Oeser. Application of semi-analytical finite element method to analyze the bearing capacity of asphalt pavements under moving loads. Frontiers of Structural and Civil Engineering, 2018, 12(2): 215–221 https://doi.org/10.1007/s11709-017-0401-2
13	S Dai, Q Yan. Pavement evaluation using ground penetrating radar. In: Pavement Materials, Structures, and Performance. American Society of Civil Engineers, 2014, 222–230
14	AASHTO. Guide for Design of Pavement Structures. Washington, D.C.: American Association of State Highway and Transportation Officials, 1993
15	R Chen, P Zhang, H Wu, Z Wang, Z Zhong. Prediction of shield tunneling-induced ground settlement using machine learning techniques. Frontiers of Structural and Civil Engineering, 2019, 13(6): 1363–1378 https://doi.org/10.1007/s11709-019-0561-3
16	A Abed, N Thom, L Neves. Probabilistic prediction of asphalt pavement performance. Road Materials and Pavement Design, 2019, 20(Sup 1): 1–18 https://doi.org/10.1080/14680629.2019.1593229
17	K A Abaza. Deterministic performance prediction model for rehabilitation and management of flexible pavement. International Journal of Pavement Engineering, 2004, 5(2): 111–121 https://doi.org/10.1080/10298430412331286977
18	P Dalla Valle. Reliability in Pavement Design. Nottingham: University of Nottingham, 2015
19	Y H. Huang Pavement Analysis and Design. Englewood Cliffs, NJ: Prentice-Hall, 1993
20	N Kargah-Ostadi, S M Stoffels, N Tabatabaee. Network-level pavement roughness prediction model for rehabilitation recommendations. Transportation Research Record: Journal of the Transportation Research Board, 2010, 2155(1): 124–133 https://doi.org/10.3141/2155-14
21	J Yang, J J Lu, M Gunaratne, Q Xiang. Forecasting overall pavement condition with neural networks: Application on Florida highway network. Transportation Research Record: Journal of the Transportation Research Board, 2003, 1853(1): 3–12 https://doi.org/10.3141/1853-01
22	N Kargah-Ostadi, S M Stoffels. Framework for development and comprehensive comparison of empirical pavement performance models. Journal of Transportation Engineering, 2015, 141(8): 04015012 https://doi.org/10.1061/(ASCE)TE.1943-5436.0000779
23	A S. Noureldin New scenario for backcalculation of layer moduli of flexible pavements. Transportation Research Record, 1993, 1384: 23–28
24	G Jameson. Development of Procedures to Predict Structural Number and Subgrade Strength from Falling Weight Deflectometer Deflections. Vermont South, Victoria: ARRB Transport Research, 1993
25	G T. Rohde Determining pavement structural number from FWD testing. Transportation Research Record, 1994, 1(1448): 61–68
26	G T Rohde, F Jooste, E Sadzik, T Henning. The calibration and use of HDM-IV performance models in a pavement management system. In: The Fourth International Conference on Managing Pavements. Durban, South Africa: Pretoria, 1998
27	H Schnoor, E Horak. Possible method of determining structural number for flexible pavements with the falling weight deflectometer. In: Abstracts of the 31st Southern African Transport Conference (SATC 2012). Pretoria, South Africa: Minister of Transport, 2012
28	European Cooperation in Science and Technology (COST). Information gathering work of Task Group 2, in Falling Weight Deflectometer (COST 336). 1998
29	A L Crook, S R Montgomery, W S Guthrie. Use of falling weight deflectometer data for network-level flexible pavement management. Transportation Research Record: Journal of the Transportation Research Board, 2012, 2304(1): 75–85 https://doi.org/10.3141/2304-09
30	K V. DasariDeflection based condition assessment for Rolling Wheel Deflectometer at network level. Thesis for the Master’s Degree. Louisiana: Louisiana State University, 2013
31	M S Hoffman. Direct method for evaluating structural needs of flexible pavements with falling-weight deflectometer deflections. Transportation Research Record: Journal of the Transportation Research Board, 2003, 1860(1): 41–47 https://doi.org/10.3141/1860-05
32	A M Abdel-Khalek, M A Elseifi, K Gaspard, Z Zhang, K Dasari. Model to estimate pavement structural number at network level with rolling wheel deflectometer data. Transportation Research Record: Journal of the Transportation Research Board, 2012, 2304(1): 142–149 https://doi.org/10.3141/2304-16
33	M Y Kim, D Y Kim, M R Murphy. Improved method for evaluating the pavement structural number with falling weight deflectometer deflections. Transportation Research Record: Journal of the Transportation Research Board, 2013, 2366(1): 120–126 https://doi.org/10.3141/2366-14
34	H S Abd El-Raof, R T Abd El-Hakim, S M El-Badawy, H Afify. Structural number prediction for flexible pavements based on falling weight deflectometer data. In: Transportation Research Board 97th Annual Meeting. Washington D.C.: Transportation Research Board, 2018
35	D S Gedafa, M Hossain, R Miller, T Van. Network-level flexible pavement structural evaluation. International Journal of Pavement Engineering, 2014, 15(4): 309–322 https://doi.org/10.1080/10298436.2013.784766
36	O Elbagalati, M A Elseifi, K Gaspard, Z Zhang. Prediction of in-service pavement structural capacity based on traffic-speed deflection measurements. Journal of Transportation Engineering, 2016, 142(11): 04016058 https://doi.org/10.1061/(ASCE)TE.1943-5436.0000891
37	A Kavussi, M Abbasghorbani, F Moghadas Nejad, A Bamdad Ziksari. A new method to determine maintenance and repair activities at network-level pavement management using falling weight deflectometer. Journal of Civil Engineering and Management, 2017, 23(3): 338–346 https://doi.org/10.3846/13923730.2015.1073173
38	R Salvi, A Ramdasi, Y A Kolekar, L V Bhandarkar. Use of Ground-Penetrating Radar (GPR) as An Effective Tool in Assessing Pavements—A Review. Geotechnics for Transportation Infrastructure, Singapore: Springer, 2019, 85–95 https://doi.org/10.1007/978-981-13-6713-7_7
39	A Benedetto, F Tosti, L Bianchini Ciampoli, F D’Amico. An overview of ground-penetrating radar signal processing techniques for road inspections. Signal Processing, 2017, 132: 201–209 https://doi.org/10.1016/j.sigpro.2016.05.016
40	E Horak, J W Maina, I Van Wijk, A Hefer, G Jordaan, P Olivier, P W de Bruin. Revision of the South African Pavement Design Method. Draft Contract Report, No. SANRAL/SAPDM/B-2/2009-01. 2009
41	H Guo, X Zhuang, T Rabczuk. A deep collocation method for the bending analysis of Kirchhoff Plate. Computers, Materials & Continua, 2019, 59(2): 433–456 https://doi.org/10.32604/cmc.2019.06660
42	C Anitescu, E Atroshchenko, N Alajlan, T Rabczuk. Artificial neural network methods for the solution of second order boundary value problems. Computers, Materials & Continua, 2019, 59(1): 345–359 https://doi.org/10.32604/cmc.2019.06641
43	K M Hamdia, H Ghasemi, X Zhuang, N Alajlan, T. Rabczuk Computational machine learning representation for the flexoelectricity effect in truncated pyramid structures. Computers, Materials & Continua, 2019, 59(1): 79–87
44	K M Hamdia, H Ghasemi, Y Bazi, H AlHichri, N Alajlan, T Rabczuk. A novel deep learning based method for the computational material design of flexoelectric nanostructures with topology optimization. Finite Elements in Analysis and Design, 2019, 165: 21–30 https://doi.org/10.1016/j.finel.2019.07.001
45	A Y Sun, D Wang, X Xu. Monthly streamflow forecasting using Gaussian process regression. Journal of Hydrology (Amsterdam), 2014, 511: 72–81 https://doi.org/10.1016/j.jhydrol.2014.01.023
46	C K Williams, C E Rasmussen. Gaussian processes for machine learning. International Journal of Neural Systems, 2004, 14(2): 69–106
47	C K Arthur, V A Temeng, Y Y Ziggah. Novel approach to predicting blast-induced ground vibration using Gaussian process regression. Engineering with Computers, 2020, 36: 29–42
48	J J Li, A Jutzeler, B. Faltings Estimating urban ultrafine particle distributions with gaussian process models. In: CEUR Workshop Proceedings. Canberra, 2014, 145–153
49	W Chu, Z Ghahramani. Gaussian processes for ordinal regression. Journal of Machine Learning Research, 2005, 6: 1019–1041
50	P Samui. Utilization of Gaussian process regression for determination of soil electrical resistivity. Geotechnical and Geological Engineering, 2014, 32(1): 191–195 https://doi.org/10.1007/s10706-013-9705-8
51	P Samui, J Jagan. Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach. Frontiers of Structural and Civil Engineering, 2013, 7(2): 133–136 https://doi.org/10.1007/s11709-013-0202-1
52	J R Quinlan. Learning with continuous classes. In: The 5th Australian joint conference on artificial intelligence. Hobart, Tasmania: World Scientific, 1992
53	Y, Wang I H. Witten Induction of model trees for predicting continuous classes. Hamilton: University of Waikato, 1996
54	T Singh, M Pal, V Arora. Modeling oblique load carrying capacity of batter pile groups using neural network, random forest regression and M5 model tree. Frontiers of Structural and Civil Engineering, 2019, 13(3): 674–685 https://doi.org/10.1007/s11709-018-0505-3
55	A Behnood, V Behnood, M Modiri Gharehveran, K E Alyamac. Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm. Construction & Building Materials, 2017, 142: 199–207 https://doi.org/10.1016/j.conbuildmat.2017.03.061
56	I H Witten, E Frank, M A Hall. Data Mining: Practical Machine Learning Tools and Techniques. 3rd ed. Burlington, MA: Morgan Kauffman, 2011
57	S Blaifi, S Moulahoum, R Benkercha, B Taghezouit, A Saim. M5P model tree based fast fuzzy maximum power point tracker. Solar Energy, 2018, 163: 405–424 https://doi.org/10.1016/j.solener.2018.01.071
58	L Breiman, J, Friedman R Olshen, C. Stone Classification and regression trees. Wadsworth Int. Group, 1984, 37(15): 237–251
59	L Breiman. Random forests. Machine Learning, 2001, 45(1): 5–32 https://doi.org/10.1023/A:1010933404324
60	W Y Loh. Classification and regression trees. Wiley Interdisciplinary Reviews, Data Mining and Knowledge Discovery, 2011, 1(1): 14–23 https://doi.org/10.1002/widm.8
61	J Sadler, J L Goodall, M M Morsy, K Spencer. Modeling urban coastal flood severity from crowd-sourced flood reports using Poisson regression and Random Forest. Journal of Hydrology (Amsterdam), 2018, 559: 43–55 https://doi.org/10.1016/j.jhydrol.2018.01.044
62	H Sun, D Gui, B Yan, Y Liu, W Liao, Y Zhu, C Lu, N Zhao. Assessing the potential of random forest method for estimating solar radiation using air pollution index. Energy Conversion and Management, 2016, 119: 121–129 https://doi.org/10.1016/j.enconman.2016.04.051
63	T Xu, A J Valocchi, M Ye, F Liang. Quantifying model structural error: Efficient Bayesian calibration of a regional groundwater flow model using surrogates and a data-driven error model. Water Resources Research, 2017, 53(5): 4084–4105 https://doi.org/10.1002/2016WR019831
64	K E Taylor. Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research, D, Atmospheres, 2001, 106(D7): 7183–7192 https://doi.org/10.1029/2000JD900719

Viewed

Full text

Abstract

Cited

Shared

Discussed