Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Structural and Civil Engineering

ISSN 2095-2430

ISSN 2095-2449(Online)

CN 10-1023/X

Postal Subscription Code 80-968

2018 Impact Factor: 1.272

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Struct. Civ. Eng.    2021, Vol. 15 Issue (3) : 652-664    https://doi.org/10.1007/s11709-021-0719-7
RESEARCH ARTICLE
Prediction of hydro-suction dredging depth using data-driven methods
Amin MAHDAVI-MEYMAND, Mohammad ZOUNEMAT-KERMANI(), Kourosh QADERI
Water Engineering Department, Shahid Bahonar University of Kerman, Kerman 7616913439, Iran
 Download: PDF(1364 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

In this study, data-driven methods (DDMs) including different kinds of group method of data handling (GMDH) hybrid models with particle swarm optimization (PSO) and Henry gas solubility optimization (HGSO) methods, and simple equations methods were applied to simulate the maximum hydro-suction dredging depth (hs). Sixty-seven experiments were conducted under different hydraulic conditions to measure the hs. Also, 33 data samples from three previous studies were used. The model input variables consisted of pipeline diameter (d), the distance between the pipe inlet and sediment level (Z), the velocity of flow passing through the pipeline (u0), the water head (H), and the medium size of particles (D50). Data-driven simulation results indicated that the HGSO algorithm accurately trains the GMDH methods better than the PSO algorithm, whereas the PSO algorithm trained simple simulation equations more precisely. Among all used DDMs, the integrative GMDH-HGSO algorithm provided the highest accuracy (RMSE = 7.086 mm). The results also showed that the integrative GMDHs enhance the accuracy of polynomial GMDHs by ~14.65% (based on the RMSE).
Keywords sedimentation      water resources      dam engineering      machine learning      heuristic     
Corresponding Author(s): Mohammad ZOUNEMAT-KERMANI   
Online First Date: 13 July 2021    Issue Date: 14 July 2021
 Cite this article:   
Amin MAHDAVI-MEYMAND,Mohammad ZOUNEMAT-KERMANI,Kourosh QADERI. Prediction of hydro-suction dredging depth using data-driven methods[J]. Front. Struct. Civ. Eng., 2021, 15(3): 652-664.
 URL:  
https://academic.hep.com.cn/fsce/EN/10.1007/s11709-021-0719-7
https://academic.hep.com.cn/fsce/EN/Y2021/V15/I3/652
Fig.1  Schematic representation of the cross-sectional view of the hydro-suction dredging method. Where hs is the maximum scour depth, d is the pipeline diameter, Z is the distance between pipe inlet and sediment level, and H is the water head.
parameter sources of data set
Ullah et al. [14] Moghbeli [40] Forutan Eghlidi [41] present study
d (mm) 9.7,13.9 11,15,22 30 20,16,13
Z (mm) [1.3,–38.1] 0 [10,–40] [0,–60]
u0 (m/s) [0.99,3.71] [0.93,1.63] 1.13 [0.55,1.84]
H (mm) 400 350,500,650,800 510 700,500,300
D50 (mm) 0.58 0.23 0.51 0.75
hs (mm) [2.66,49.97] [3,45] [24,75] [13.22,94.42]
number of data 11 16 6 67
Tab.1  Summary of the considered data set for modeling the maximum scour depth (hs).
Fig.2  Flowchart of the modeling process of this study.
Fig.3  (a) Geometric overview of the tank and (b) picture of the constructed hydro-suction tank.
Fig.4  Conceptual view of the GMDH network.
Fig.5  Boxplots of inputs (d, Z0, u0, H, and D50) and output (hs) data sets.
statistical parameter inputs
R2 Mallows’ Cp d Z u0 H D50
29.4 ?809.6 ✓ – – – –
67.6 ?319.6 – ✓ – – –
?5.4 1116.9 – – ✓ – –
12.8 1022.3 – – – ✓ –
18.2 ?953.0 – – – – ✓
84.4 ?105.9 ✓ ✓ – – –
71.1 ?277.2 – ✓ ✓ – –
87.3 ??70.9 ✓ ✓ ✓ – –
86.8 ??76.9 ✓ ✓ – – ✓
90.7 ??28.9 ✓ ✓ ✓ – ✓
89.2 ??48.2 ✓ ✓ – ✓ ✓
92.7 ???6.0 ✓ ✓ ✓ ✓ ✓
Tab.2  Results of the best subsets regression (BSR) method for determining the most effective independent parameters on the maximum scour depth (hs).
parameter whole data set training data set
range		 validation data set
range		 testing data set
range
range SCC vs hs
H (mm) 300–800 0.358 300–800 300–800 300–800
Z (mm) −60–10 −0.822 −60–10 −45–0 −40–5.1
d (mm) 9.7–30 0.542 9.7–30 11–30 13–30
D50 (mm) 0.23–0.73 0.427 0.23–0.73 0.23–0.73 0.23–0.73
u0 (m/s) 0.55–3.71 0.233 0.55–3.71 0.74–1.84 0.74–2.42
hs (mm) 2.66–94.42 1 2.66–94.42 8.5–78.7 5.54–71.72
Tab.3  Range of training, validation, and testing data sets.
method parameter value
PSO initial inertia weight
cognitive acceleration (C1)
social acceleration (C2)
inertia weight damping ratio
population size
search range
GMDH-iteration
equations-iteration		 1
1
2
0.99
100
[−10,10]
100
1000
HGSO l1 (is a constant value)
l2 (is a constant value)
l3 (is a constant value)
a (is a constant value)
β (is a constant value)
K (is a constant value)
B1 (is a constant value)
B2 (is a constant value)
ε (is a constant value)
number of gases
cluster number
search range
GMDH-iteration
equations-iteration		 0.005
100
0.01
1
1
1
0.5
0.5
0.05
100
5
[−10,10]
100
1000
Tab.4  Initial structural and tuning parameters of the applied PSO and HGSO algorithms in this study.
Fig.6  Hydro-suction sediment transport phases for d = 16 mm, H = 50 cm, and Z = 0.
method layer neuron train validation
RMSE (mm) R2 IA RMSE (mm) R2 IA
GMDH I-PSO ?3 ?5 7.911 0.866 0.968 4.806 0.927 0.985
GMDH I-PSO ?5 ?5 5.043 0.944 0.979 2.931 0.971 0.987
GMDH I-PSO ?5 10 5.922 0.923 0.976 3.376 0.962 0.991
GMDH I-PSO ?5 15 6.343 0.912 0.981 3.358 0.948 0.995
GMDH I-PSO 10 ?5 5.645 0.93? 0.988 1.814 0.989 0.997
GMDH I-PSO 10 10 5.531 0.933 0.977 2.161 0.982 0.996
GMDH I-PSO 10 15 5.202 0.941 0.985 0.894 0.997 0.997
GMDH II-PSO ?3 ?5 7.221 0.886 0.964 3.881 0.937 0.982
GMDH II-PSO ?5 ?5 6.011 0.922 0.985 3.816 0.951 0.993
GMDH II-PSO ?5 10 6.454 0.908 0.98? 2.746 0.967 0.99?
GMDH II-PSO ?5 15 5.774 0.929 0.977 2.185 0.981 0.986
GMDH II-PSO 10 ?5 4.626 0.953 0.982 1.992 0.987 0.997
GMDH II-PSO 10 10 6.528 0.929 0.982 1.917 0.984 0.995
GMDH II-PSO 10 15 5.105 0.943 0.984 1.667 0.989 0.999
GMDH I-HGSO ?3 ?5 9.249 0.825 0.966 6.659 0.854 0.979
GMDH I-HGSO ?5 ?5 7.7?? 0.887 0.979 3.792 0.95? 0.985
GMDH I-HGSO ?5 10 5.874 0.928 0.985 2.087 0.985 0.992
GMDH I-HGSO ?5 15 5.803 0.929 0.974 4.162 0.933 0.992
GMDH I-HGSO 10 ?5 5.611 0.931 0.959 2.908 0.974 0.994
GMDH I-HGSO 10 10 6.517 0.926 0.971 2.298 0.981 0.997
GMDH I-HGSO 10 15 6.654 0.903 0.977 2.287 0.97? 0.997
GMDH II-HGSO ?3 ?5 7.516 0.885 0.941 4.882 0.914 0.966
GMDH II-HGSO ?5 ?5 5.847 0.928 0.963 4.376 0.932 0.987
GMDH II-HGSO ?5 10 5.115 0.944 0.979 3.095 0.966 0.996
GMDH II-HGSO ?5 15 6.7?? 0.903 0.979 2.595 0.97? 0.986
GMDH II-HGSO 10 ?5 8.45? 0.893 0.982 3.093 0.98? 0.994
GMDH II-HGSO 10 10 6.978 0.925 0.972 1.686 0.989 0.995
GMDH II-HGSO 10 15 6.248 0.917 0.974 1.781 0.987 0.993
LE(g)-PSO – – 7.209 0.887 0.97? 6.375 0.913 0.976
NLE-PSO(h) – – 6.24? 0.915 0.978 5.37? 0.937 0.983
LE- HGSO – – 7.618 0.88? 0.966 6.757 0.901 0.971
NLE- HGSO – – 7.896 0.882 0.961 4.792 0.948 0.985
Tab.5  Results of the GMDH and regression methods in the training and validation data sets.
method layer neuron RMSE (mm) R2 MAE (mm) IA
GMDH I-PSO ?3 ?5 13.552 0.822 11.923 0.866
GMDH I-PSO ?5 ?5 12.65? 0.752 ?9.634 0.883
GMDH I-PSO ?5 10 11.861 0.856 10.015 0.899
GMDH I-PSO ?5 15 ?9.167 0.871 ?7.915 0.929
GMDH I-PSO 10 ?5 12.668 0.855 10.593 0.856
GMDH I-PSO 10 10 ?9.421 0.841 ?7.511 0.929
GMDH I-PSO 10 15 ?9.627 0.83? ?6.856 0.926
GMDH II-PSO ?3 ?5 11.089 0.754 ?7.861 0.902
GMDH II-PSO ?5 ?5 10.846 0.768 ?8.236 0.903
GMDH II-PSO ?5 10 10.964 0.731 ?7.855 0.884
GMDH II-PSO ?5 15 ?8.927 0.831 ?6.098 0.932
GMDH II-PSO 10 ?5 10.012 0.768 ?8.139 0.924
GMDH II-PSO 10 10 ?8.081 0.895 ?6.488 0.947
GMDH II-PSO 10 15 ?8.835 0.905 ?7.111 0.935
GMDH I-HGSO ?3 ?5 12.217 0.613 9.52 0.883
GMDH I-HGSO ?5 ?5 11.998 0.844 10.511 0.889
GMDH I-HGSO ?5 10 ?8.435 0.923 ?7.261 0.943
GMDH I-HGSO ?5 15 ?8.615 0.858 ?7.022 0.948
GMDH I-HGSO 10 ?5 ?9.854 0.883 ?8.511 0.922
GMDH I-HGSO 10 10 ?8.286 0.891 ?7.211 0.94?
GMDH I-HGSO 10 15 ?8.936 0.853 ?6.545 0.938
GMDH II-HGSO ?3 ?5 12.123 0.775 10.066 0.892
GMDH II-HGSO ?5 ?5 10.767 0.813 ?8.835 0.909
GMDH II-HGSO ?5 10 7.235 0.919 ?5.774 0.959
GMDH II-HGSO ?5 15 8.899 0.864 ?7.057 0.932
GMDH II-HGSO 10 ?5 8.605 0.856 ?7.156 0.937
GMDH II-HGSO 10 10 7.086 0.922 ?5.683 0.956
GMDH II-HGSO 10 15 7.3?? 0.873 ?5.322 0.956
LE(h)-PSO – – 9.122 0.829 ?7.781 0.936
NLE(i)-PSO – – 8.829 0.827 ?6.199 0.946
LE- HGSO – – 10.41?? 0.815 ?9.129 0.914
NLE- HGSO – – 10.39?? 0.888 8.68 0.91?
Tab.6  Results of the GMDH and regression methods in the testing data set.
Fig.7  Scatter plots of the predicted (simulated) hs in the testing phase (networks with 10 layers and a maximum of 10 neurons in each layer). (a) GMDH I-PSO; (b) GMDH II-PSO; (c) GMDH I-HGSO; (d) GMDH II-HGSO
Fig.8  Taylor diagram of the applied methods (testing data).
1 M M Alemu. Integrated watershed management and sedimentation. Journal of Environmental Protection, 2016, 7(4): 490–494
https://doi.org/10.4236/jep.2016.74043
2 N Jiang, L Fu. Problems of reservoir sedimentation in China. Chinese Geographical Science, 1998, 8(2): 117–125
https://doi.org/10.1007/s11769-997-0025-x
3 R Pishgar, S A Ayyoubzadeh, M Ghodsian, M Saneie. The influence of burrowing-type suction pipe geometrical and mechanical specifications on the hydro-suction method performance. ISH Journal of Hydraulic Engineering, 2021, 27(2): 170–179
https://doi.org/10.1080/09715010.2018.1531732
4 W T Ke, Y W Chen, H C Hsu, K Toigo, W C Weng, H Capart. Influence of sediment consolidation on hydrosuction performance. Journal of Hydraulic Engineering (New York, N.Y.), 2016, 142(10): 04016037
https://doi.org/10.1061/(ASCE)HY.1943-7900.0001143
5 ICOLD. Sedimentation and sustainable use of reservoirs and river systems. In: ICOLD Bulletin. Paris: International Comittee on Large Dams, 2009
6 A J Schleiss, M J Franca, C Juez, G De Cesare. Reservoir sedimentation. Journal of Hydraulic Research, 2016, 54(16): 1–21
7 G Rehbinder. Sediment removal with a siphon at critical flux. Journal of Hydraulic Research, 1994, 32(6): 845–860
https://doi.org/10.1080/00221689409498694
8 R H Hotchkiss, X Huang. Hydrosuction sediment-removal systems (HSRS): Principles and field test. Journal of Hydraulic Engineering (New York, N.Y.), 1995, 121(6): 479–489
https://doi.org/10.1061/(ASCE)0733-9429(1995)121:6(479)
9 C B Brown. The Control of Reservoir Silting. Washington, D.C.: United States Department of Agriculture, Miscellaneous Publication, No. 521, 1943
10 J Evrard. Considerations on sedimentation in the hydraulic installations of electricite de France (French electricity Authority). In: International Seminar of Experts on Reservoir Desiltation. Tunisia, 1980
11 S Bruk. Methods of Computing Sedimentation in Lakes and Reservoirs. Paris: UNESCO, 1985
12 University of Nebraska. Water current newsletter. Water current, 1993, 25(3): 3–8
13 S B Brahme, J B Herbich. Hydraulic model studies for suction cutterheads. Journal of Waterway, Port, Coastal, and Ocean Engineering, 1986, 112(5): 591–606
https://doi.org/10.1061/(ASCE)0733-950X(1986)112:5(591)
14 S M Ullah, K A Mazurek, N Rajaratnam, S Reitsma. Siphon removal of cohesionless materials. Journal of Waterway, Port, Coastal, and Ocean Engineering, 2005, 131(3): 115–122
https://doi.org/10.1061/(ASCE)0733-950X(2005)131:3(115)
15 S C Chen, S C Wang, C H Wu. Sediment removal efficiency of siphon dredging with wedge-type suction head and float tank. International Journal of Sediment Research, 2010, 25(2): 149–160
https://doi.org/10.1016/S1001-6279(10)60034-0
16 Y Tao, C Li, X Min, Z Min. Siphon pipeline resistance characteristic research. Procedia Engineering, 2012, 28(12): 99–104.
17 A Parsaie, A H Haghiabi, M Saneie, H Torabi. Predication of discharge coefficient of cylindrical weir-gate using adaptive neuro fuzzy inference systems (ANFIS). Frontiers of Structural and Civil Engineering, 2017, 11(1): 111–122
https://doi.org/10.1007/s11709-016-0354-x
18 G Chen, S Zhao, W Huai, G Gu. General model for stage–discharge prediction inmulti-stage compound channels. Journal of Hydraulic Research, 2018, 57(4): 1–17
19 A Mahdavi-Meymand, M Scholz, M Zounemat-Kermani. Challenging soft computing optimization approaches in modeling complex hydraulicphenomenon of aeration process. ISH Journal of Hydraulic Engineering, 2019: 1–12
https://doi.org/10.1080/09715010.2019.1574619
20 S Sayari, A Mahdavi-Meymand, M Zounemat-Kermani. Prediction of critical velocity in pipeline flow of slurries using TLBO Algorithm: A Comprehensive Study. Journal of Pipeline Systems Engineering and Practice, 2020, 11(2): 04019057
https://doi.org/10.1061/(ASCE)PS.1949-1204.0000439
21 K Roushangar, R Ghasempour, S Biukaghazadeh. Evaluation of the parameters affecting the roughness coefficient of sewer pipes with rigid and loose boundary conditions via kernel based approaches. International Journal of Sediment Research, 2020, 35(2): 171–179
https://doi.org/10.1016/j.ijsrc.2019.08.004
22 P K Singh, X Tang. Estimation of apparent shear stress of asymmetric compound channels using neuro-fuzzy inference system. Journal of Hydro-environment Research, 2020, 29: 96–108
https://doi.org/10.1016/j.jher.2020.01.007
23 M Zounemat-Kermani, D Stephan, M Barjenbruch, R Hinkelmann. Ensemble data mining modeling in corrosion of concrete sewer: A comparative study of network-based (MLPNN & RBFNN) and tree-based (RF, CHAID, & CART) models. Advanced Engineering Informatics, 2020, 43: 101030
https://doi.org/10.1016/j.aei.2019.101030
24 K M Hamdia, X Zhuang, T Rabczuk. An efficient optimization approach for designing machine learning models based on genetic algorithm. Neural Computing & Applications, 2021, 33(6): 1923–1933
https://doi.org/10.1007/s00521-020-05035-x
25 H Guo, X Zhuang, T Rabczuk. A deep collocation method for the bending analysis of Kirchhoff plate. Materials & Continua, 2019, 59(2): 433–456
https://doi.org/10.32604/cmc.2019.06660
26 E Samaniego, C Anitescu, S Goswami, V M Nguyen-Thanh, H Guo, K Hamdia, X Zhuang, T Rabczuk. partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications. Computer Methods in Applied Mechanics and Engineering, 2020, 362: 112790
https://doi.org/10.1016/j.cma.2019.112790
27 T Kondo, J Ueno, S Takao. Medical image diagnosis of lung cancer by multi-layered GMDH-type neural network self-selecting functions. Artificial Life and Robotics, 2013, 18(1-2): 20–26
https://doi.org/10.1007/s10015-013-0094-0
28 X Song, W Li, D Ma, D Wang, L Qu, Y Wang. A match-then-predict method for daily traffic flow forecasting based on group method of data handling. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(11): 982–998
https://doi.org/10.1111/mice.12381
29 L Mo, L Xie, X Jiang, G Teng, L Xu, L Xiao. GMDH-based hybrid model for container throughput forecasting: Selective combination forecasting in nonlinear subseries. Applied Soft Computing, 2018, 62: 478–490
https://doi.org/10.1016/j.asoc.2017.10.033
30 M A Sattari, G H Roshani, R Hanus. Improving the structure of two-phase flow meter using feature extraction and GMDH neural network. Radiation Physics and Chemistry, 2020, 171: 108725
https://doi.org/10.1016/j.radphyschem.2020.108725
31 M A Lashteh Neshaei, M A Mehrdad, N Abedimahzoon, N Asadollahi. Predicting beach profile evolution with group method data handling-type neural networks on beaches with seawalls. Frontiers of Structural and Civil Engineering, 2013, 7(2): 117–126
https://doi.org/10.1007/s11709-013-0205-y
32 M Masoumi Shahr-Babak, M J Khanjani, K Qaderi. Uplift capacity prediction of suction caisson in clay using a hybrid intelligence method (GMDH-HS). Applied Ocean Research, 2016, 59: 408–416
https://doi.org/10.1016/j.apor.2016.07.005
33 A Parsaie, H M Azamathulla, A H Haghiabi. Prediction of discharge coefficient of cylindrical weir–gate using GMDH-PSO. ISH Journal of Hydraulic Engineering, 2018, 24(2): 116–123
https://doi.org/10.1080/09715010.2017.1372226
34 A Mahdavi-Meymand, M Zounemat-Kermani. A new integrated model of the group method of data handling and the firefly algorithm (GMDH-FA): Application to aeration modelling on spillways. Artificial Intelligence Review, 2020, 53(4): 2549–2569
https://doi.org/10.1007/s10462-019-09741-4
35 K Qaderi, F Javadi, M R Madadi, M M Ahmadi. A comparative study of solo and hybrid data driven models for predicting bridge pier scour depth. Marine Georesources and Geotechnology, 2021, 39(5): 589–599
https://doi.org/10.1080/1064119X.2020.1735589
36 A G Ivakhnenko. The group method of data handling—A rival of the method of stochastic approximation. Soviet Automatic Control, 1968, 1(3): 43–55
37 S J Farlow. Self-Organizing Method in Modeling: GMDH Type Algorithm. New York: Marcel Dekker Inc, 1984.
38 R C Eberhart, J Kennedy. New optimizer using particle swarm theory. In: Proceedings of the sixth international symposium. Nagoya: IEEE, 1995, 39–43
39 F A Hashim, E H Houssein, M S Mabrouk, W Al-Atabany, S Mirjalili. Henry gas solubility optimization: A novel physics-based algorithm. Future Generation Computer Systems, 2019, 101: 646–667
https://doi.org/10.1016/j.future.2019.07.015
40 A. Moghbeli Experimental and numerical study of different methods of sediment desilting from dam reservoir. Thesis for the Master’s Degree. Kerman: Shahid Bahonar University of Kerman, 2019 (in Persian)
41 M Forutan Eghlidi. Experimental study of hydrosuction system function for Cohesionless and adhesive sediment. Thesis for the Master’s Degree. Kerman: Shahid Bahonar University of Kerman, 2016 (in Persian)
42 K E Taylor. Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research—Atmospheres, 2001, 106(D7): 7183–7192
https://doi.org/10.1029/2000JD900719
[1] Zohreh SHEIKH KHOZANI, Khabat KHOSRAVI, Mohammadamin TORABI, Amir MOSAVI, Bahram REZAEI, Timon RABCZUK. Shear stress distribution prediction in symmetric compound channels using data mining and machine learning models[J]. Front. Struct. Civ. Eng., 2020, 14(5): 1097-1109.
[2] Walid Khalid MBARAK, Esma Nur CINICIOGLU, Ozer CINICIOGLU. SPT based determination of undrained shear strength: Regression models and machine learning[J]. Front. Struct. Civ. Eng., 2020, 14(1): 185-198.
[3] Renpeng CHEN, Pin ZHANG, Huaina WU, Zhiteng WANG, Zhiquan ZHONG. Prediction of shield tunneling-induced ground settlement using machine learning techniques[J]. Front. Struct. Civ. Eng., 2019, 13(6): 1363-1378.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed