Comparative Assessment of the Hybrid Genetic Algorithm–Artificial Neural Network and Genetic Programming Methods for the Prediction of Longitudinal Velocity Field around a Single Straight Groyne
Graphical abstract
Introduction
Groyne or spur dike is a transverse river structure built from the riverbank toward the center to disrupt the approaching flow and divert it away from the side of the river on which the groyne is installed. It is used to control bank erosion [1], provide the fairway of sufficient depth and width [2], as habitat for various species [3], and as a countermeasure against local scour around a bridge abutment [4]. Baisically, groynes are protective structures, but, on the contrary, they may induce local strong flow around the head zone and it’s downstream as a result of the river constriction. The most important flow structures around a single groyne are as follows: (1) the vertical downflow immediately at the leading face of the groyne [5], (2) horseshoe vortex (HSV) and three dimensional necklace vortex around and next to the the groyne tip Koken and Constantinescu [6], (3) recirculating and reattachment zones at the wake of the groyne, and (4) a turbulent mixing layer (TML) bounding the separation zone Koken and Constantinescu [6]. More detailes about the three dimensional flow features around a single straight groyne are reported by Koken and Constantinescu [6], Koken and Constantinescu [7] and [8].
The accelerated flow around the groyne head, the HSV, the vertical downflow, and TML may induce local bed erosion around the groyne Koken and Constantinescu 2008a[6], and as a result of undermining of the foundation, these flow features can affect the stability of the structure. Consequently, it is of great importance to enhance our understanding about the flow physics and its interaction with the river structures. The current knowledge about the flow around the groynes is based on the previous experimental and numerical studies [5], [6], [7], [8], [9], [10], [11], [12].
Experimental studies are costly and they are time consuming. This is why nowadays most of the flow field studies appear more in the form of numerical models, which provide predictions in a cheap and versatile way. Despite performing advanced numerical simulations in the literature (e.g., [13], [14], [15], [16], [17], [18], [19] comprehensive numerical model is not provided to predict all the aspects of the complex 3D flow fields around groynes. This problem is partly related to the assumptions made in turbulence modeling. Advanced eddy-resolving techniques such as Large Eddy Simulation (LES) and Detached Eddy Simulations (DES) have been developed; however, they still remain computationally prohibitive for hydraulic engineers requiring routine calculations of highly turbulent flows around river structures. In addition, implementation of advanced numerical models requires high-performance computer resources.
On the contrary, soft computing methods such as Artificial Neural Network (ANN), Genetic Algorithms (GA), and Fuzzy logics are becoming an important class of efficient tools for developing intelligent systems and providing solutions to complicated engineering problems with less computational costs compared to the advanced numerical methods.
ANN nowadays is recognized as a very efficient tool for relating input data to output data that is representing arbitrarily complex non-linear processes. Consequently, they have been widely utilized in various fields. In water resource management, the ANN are used to forecast the rainfall intensity [20], River flood forecasting [21], forecasting the quality of water for the North Saskatchewan River [22], estimation of maximum local scour depth around river structures [23], [24], prediction of the friction coefficient in open channels [25], prediction of backwater through arched bridge constrictions [26], and discharge prediction in straight compound open channels [27]. Multi-layer feed-forward neural network was used to simulate the onset of river breakup considering the relationship among the streamflow hydraulics, meteorological conditions, and ice mechanics [28]. Assessment of the tranquility of Trabzon Yacht Harbor was performed using ANN [29]. They tested the capability of the ANN for the input values of different wave and breakwater conditions. Length of hydraulic jumps in a rectangular channel was determined using ANN [30]. Capability of wavelet-based data preprocessing method was investigated for improving the performance of the ANN method in hydrologic field non-stationary time series forecasting [31].
Genetic Programing (GP) is one of the new and efficient techniques to solve a wide range of problems in hydraulic engineering field such as velocity prediction in compound open channels [32], rainfall-runoff modeling [33], [34], [31], [35], sediment modeling [36], [37], [38], [39], [40], and open channel characteristics [41]. GP is a technique that automatically solves the problems without needing the user to specify the form of the solution.
Recently, some attempts have been made to use intelligent methods for studying the open channel hydrodynamics. There are two major advantages of modelling the complex velocity field by using the soft computing methods. First, soft computing methods have a high performance in modelling the complex problems. Therefore, the results of these methods could be used efficiently in the practical situations or researches. Second, soft computing methods reconstruct the discrete laboratory velocity measurements into analytical relationships, and thus continuous velocity field description could be developed. The power of the ANN for modeling the velocity profiles and contours and simulating the discharges in 90-degree combined open channels was evaluated by [42]. A 3D flow field in 90-degree curved channel was predicted using CFD, ANN, and GA methods by [43]. The applicability of ANN models for modeling the velocity distribution of combined open channel flows was investigated by [44]. They used CFD data for construction and test of the ANN models. Recently, ANN and GP models are used for modeling the distribution of the longitudinal velocity in open channel junction [45].
Literature review shows that no attempt has been made to predict the 3D complex flow field around groyne structure using intelligent methods. In this research, performance of an innovative hybrid Genetic Algorithm structure recognition–Artificial neural network (GAA) and GP methods are evaluated for simulating the mean flow field around single straight groynes based on highly accurate and large experimental datasets.
The following section of the paper gives details of the experimental study for data generation. Then structures of the soft computing methods are presented and in subsequent sections step by step implementation of the GAA and GP methods for prediction of the longitudinal flow around single straight groyne is given. Finally, we will apply the developed GAA and GP to plot the velocity contours at various cross sections around the groynes to assess their capability in prediction of the important flow features.
Section snippets
Experimental setup and data generation
Highly accurate experimental measurements were performed for generation of the flow field data around single straight groynes. Laboratory experiments in a flatbed straight rectangular flume, 11 m long and 1 m wide were carried out to examine the three dimensional flow fields (Fig. 1). The flume was connected to a head box 2 m wide and 1 m long following with 2.35 m length streamlined bed and side transitions to provide a smooth flow conditions. Three guide vanes were installed on the bed transition
Soft computing methods and materials
In the present study, soft computing GAA and GP methods are used for simulating the longitudinal velocity field around a single straight groyne. Details of the methods are described in the sequence parts of this section. The input parameters of the present models are the non-dimensional coordinates of each velocity measuring point and the length of the groyne (L). The coordinates of each point and the groyne length are normalized by using the channel width (B); X* = X/B, Y* = Y/B, Z* = Z/B, and L* = L/B
Results and discussion
In this section, some investigations are performed in order to find the optimum GAA and GP. Then the performances of the methods are compared with each other. In order to find the appropriate GAA model, in the first part of this section, the GAA models were compared by using various transfer functions. The second part aims to determine the most appropriate mathematical functions of the GP models. The GAA and GP models that are modeled until now use the entire input variables of X*, Y*, Z*, and
Conclusion
In this paper longitudinal velocity field around single straight groyne with various lengths is modeled by using two powerful soft computing methods of auto hidden neuron number adjustable genetic algorithm-based artificial neural network (GAA) and the genetic programming (GP) as two applications of the GA. Data set has been generated using highly accurate experimental measurements of 3D turbulent flow fields.
In order to find the optimum GAA, different transfer functions were examined and the
References (57)
- et al.
Mean Flow and Turbulence around an Experimental Spur dike
Advances in Water Resources
(2009) - et al.
Finite Element Surface Model for Flow around Vertical Wall Abutments
Journal of Fluids and Structures
(2000) - et al.
Rainfall forecasting in space and time using a neural network
Journal of hydrology
(1992) - et al.
Forecasting raw-water quality parameters for the North Saskatchewan River by neural network modeling
Water Research
(1997) - et al.
Neural network modelling for estimation of scour depth around bridges piers
Journal of hydrodynamics
(2007) A multi-output descriptive neural network for estimation of scour geometry downstream from hydraulic structures
Advances in engineering softwares
(2011)- et al.
Application of artificial neural network to predict the friction factor of open channel flow
Communications in Nonlinear Science and Numerical Simulation.
(2009) - et al.
Artificial neural network approaches for prediction of backwater through arched bridge constrictions
Advances in Engineering Software
(2010) - et al.
A neural network approach for prediction of discharge in straight compound open channel flow
Flow Measurement and Instrumentation
(2011) - et al.
Applicability of multilayer feed-forward neural networks to model the onset of river breakup
Cold Regions Science and Technology
(2012)
Artificial neural network approach for assessing harbor tranquility: The case of Trabzon Yacht Harbor, Turkey
Applied Ocean Research
Determination of the length of hydraulic jumps using artificial neural networks
Advances in Engineering Software
Streamflow prediction using linear genetic programming in comparison with a neuro-wavelet technique
Journal of Hydrology
Modelling rainfall-runoff using genetic programming
Mathematical and Computer Modelling
A genetic programming approach to suspended sediment modelling
Journal of Hydrology
Suspended sediment modeling using genetic programming and soft computing techniques
Journal of Hydrology
Neural networks for estimation of discharge capacity of triangular labyrinth side-weir located on a straight channel
Expert Systems with Applictions
Missouri River Design Study, Laboratory Investigation of L-head Channel Control Structures
Sediment exchange between a river and its groyne fields: mobile-bed experiment
Journal of Hydraulic Engineering
Streambank Erosion and Channel Scour Manipulation using Rockfill Dikes and Gabions. WRRI Report for Project No.373909
Parallel Walls as an Abutment Scour Countermeasure
Journal of Hydraulic Engineering.
On Scour Around Spur Dike. Proc., 12th congr
of the IAHR, Delft, The Netherlands
An Investigation of the Flow and Scour Mechanisms around Isolated Spur dikes in a Shallow Open Channel. Part I. Conditions Corresponding to the Initiation of the Erosion and Deposition Process
Water Resources Research
An Investigation of the Flow and Scour Mechanisms around Isolated Spur dikes in a Shallow Open Channel. Part II. Conditions Corresponding to the Final Stages of the Erosion and Deposition Process
Water Resources Research
An Investigation of the Dynamics of Coherent Structures in a Turbulent Channel Flow with a Vertical Sidewall Obstruction
Physics of Fluids
Coherent Structure Dynamics Upstream of a Long Rectangular Block at the Side of a Large Aspect Ratio Channel
Physics of Fluids
Turbulent Burst around Experimental Spur dike
International Journal of Sediment Research.
Scale Effects in Flume Experiments on Flow around a Spur dike in Flat Bed Channel
Journal of Hydraulic Engineering
Cited by (10)
Artificial intelligence models for prediction of the aeration efficiency of the stepped weir
2019, Flow Measurement and InstrumentationCitation Excerpt :Many variants of the artificial intelligence data mining models have emerged, such as artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), and support vector machine (SVM). These methods have been used to predict aeration efficiency under different flow conditions, e.g., [3,8,9,16,17,22,43]). The main drawback for the application of these methods is that the code itself is un-accessible for practitioners.
A two-stage gene selection method for biomarker discovery from microarray data for cancer classification
2018, Chemometrics and Intelligent Laboratory SystemsCitation Excerpt :Moradi et al. [34] studied the subset of the salient and less correlated characteristics using the HPSO-LS method to integrate the local research strategy and the optimisation of the particle swarm. Safarzadeh et al. [35] modeled the longitudinal velocity field using a new hybrid method of artificial neural network based on genetic algorithm (GAA) that can automatically regulate the number of hidden neurons. Ghamisi and Benediktsson [36] have incorporated particle swarm optimisation (PSO) and Genetic Algorithm (GA) to identify discrimination between path, contextual pixels and behave better than other conventional approaches regarding performance measurements.
Splicing process inspired cuckoo search algorithm based ENNs for modeling FCCU reactor-regenerator system
2018, Chemical Engineering JournalCitation Excerpt :However, there are few articles about intelligent modeling methods for the reactor-regenerator system. Since 1990s, rising again artificial neural networks (ANNs) have been widely studied owing to the ability of expressing arbitrary nonlinear mapping [7,12–15]. ANNs can be divided into two types, the feedforward and the recurrent.
Novel approach for dam break flow modeling using computational intelligence
2018, Journal of HydrologyCitation Excerpt :This had led to the computational intelligence (CI) approaches, which have been also used in hydraulic and hydrology engineering (Govindaraju, 2000; Kişi, 2004; Malekmohamadi et al., 2008). These include: support vector machine (SVM) (Batt and Stevens, 2013; Yu et al., 2004), artificial neural networks (ANN) (Babovic et al., 2001; Kazeminezhad et al., 2010), and its direct extensions, time-delay neural network (Sun et al., 2010), radial basis function (RBF) (Vojinovic et al., 2003), gene expression programming (GEP) (Elhakeem and Sattar, 2015), and the combination of these techniques (Ebtehaj et al., 2018; Safarzadeh et al., 2017). For example, Babovic et al. (2001) proposed a mathematical scheme to combine observations and numerical results in the framework of an ANN system for accurate predictions.
Experimental and Numerical Investigation of Hydrodynamic Performance of a Sloping Floating Breakwater with and Without Chain-Net
2022, Iranian Journal of Science and Technology - Transactions of Civil Engineering