Professional Documents
Culture Documents
a r t i c l e i n f o a b s t r a c t
Keywords: Aeration is a mass transfer process between the atmosphere and water. Aeration is used for water quality
SVM enhancement in sewage treatment plants and in polluted rivers and lakes. This can be enhanced by cre-
Weir ating turbulence in the water. Plunging overfall jets from weirs are a particular instance of producing
Aeration efficiency such turbulence. In this paper, two intelligent models are realized to predict the air entrainment rate
Air entrainment rate
and aeration efficiency of weirs. Least square support vector machine (LS-SVM) is used as intelligent tool.
Threefold cross validation test method is used to evaluate the performance of LS-SVM models. The cor-
relation between predicted and measured values is found 0.99 for air entrainment rate and 0.98 for aer-
ation efficiency. The test results indicate that the LS-SVM can be used successfully in predicting the air
entrainment rate and aeration efficiency of weirs. Moreover, the performances of the LS-SVM models
are compared with multi nonlinear and linear regression models.
Ó 2008 Elsevier Ltd. All rights reserved.
0957-4174/$ - see front matter Ó 2008 Elsevier Ltd. All rights reserved.
doi:10.1016/j.eswa.2008.10.061
A. Baylar et al. / Expert Systems with Applications 36 (2009) 8368–8374 8369
2. Weir air entrainment is made, Cs is constant with respect to time, and the aeration effi-
ciency (oxygen transfer efficiency), E may be defined as (Gulliver,
Tsang (1987) described four basic air entrainment mechanisms Thene, & Rindels, 1990):
with reference to a free falling jet from a weir. Tsang’s four air Cd Cu
entrainment mechanisms are smooth, rough, oscillating, and disin- E¼ ; ð2Þ
Cs Cu
tegrated. For small drop heights, a water jet with a relatively
smooth surface issues from the weir. The major source of air sup- where u and d are subscripts indicating upstream and downstream
ply is visualized as a thin layer surrounding the jet and carried into locations respectively, Cu the dissolved oxygen concentration at up-
the water upon impact, and therefore the air entrainment capacity stream of hydraulic structure and Cd is the dissolved oxygen con-
is limited. The water surface in the receiving pool is relatively centration at downstream of hydraulic structure.
undisturbed. As the drop height increases, the surface of the jet be- A value of E > 1 means the downstream water has become
comes roughened. The air supply can be considered as coming lar- supersaturated (i.e., Cd > Cs). A transfer efficiency value of 1.0
gely from small air pockets entrapped between the jet surface means that the full transfer up to the saturation value has occurred
roughness and the receiving water. At impact, the jet produces rip- at the structure. No transfer would correspond to E = 0.0. The sat-
ples on the pool surface. Compared with the smooth jet under sim- uration concentration in distilled, deionized water may be ob-
ilar conditions, this mechanism results in shallower bubble tained from charts or equations. This is an approximation
penetration but increased entrainment rate, because the bubbles because the saturation DO concentration for natural waters is often
are more densely packed in the biphasic zone. As the drop height different from that of distilled, deionized water due to the impact
is increased further, the jet begins to oscillate during the fall. The of trace contaminants and salinity.
primary air source originates from large air pockets entrapped be- Oxygen transfer efficiency is sensitive to water temperature,
tween the undulating jet and the pool surface. The pool surface is and investigators have typically employed a temperature correc-
considerably agitated, and air may also be entrained by surface tion factor. For hydraulic structures, Gulliver et al. (1990) devel-
roller action and splashing. Large air pockets are transported from oped a relationship for temperature correction factor:
the surface into the water depth and broken down due to turbu-
E20 ¼ 1 ð1 EÞ1=f ; ð3Þ
lence. With an even larger drop height, the jet breaks up into dis-
crete droplets. The pool surface is intensely agitated, and air is where E is the aeration efficiency at the water temperature of mea-
entrained by the action of surface rollers and by the engulfing of surement, E20 the aeration efficiency at the 20 °C and f is the expo-
air pockets as jet fragments hit the pool surface. The bubbles are nent described by
generally only transported to relatively shallow depths. Disinte-
grated jets have the advantage over solid jets of greater surface f ¼ 1:0 þ 0:02103ðT 20Þ þ 8:261 105 ðT 20Þ2 ; ð4Þ
area; however, air entrainment rate QA and bubble penetration where T is the water temperature.
are significantly reduced because of energy loss to the surrounding
atmosphere during the fall (Wormleaton & Tsang, 2000). 4. Experiments
The mass balance equation relating the instantaneous rate of The data used in this study were taken from study conducted by
change in DO concentration (dC/dt) to the rate of oxygen mass Baylar and Bagatur (2006) on a large model. Schematic representa-
transfer between air and water is tion of the experimental setup is shown on Fig. 1. The experimental
channel was 3.40 m long, 0.60 m wide, and 0.50 m deep with a
dC A maximum water flow rate of 4 L/s. The water was pumped from
¼ K L ðC s CÞ; ð1Þ
dt V a pump to the stilling tank. The water jet from the test weir
where C is the DO concentration, KL the liquid film coefficient for plunged into a downstream water pool, whose height could be ad-
oxygen, A the surface area associated with the volume V, over which justed using a pulley arrangement. The water depth in the down-
transfer occurs, Cs the saturation concentration and t is the time. Eq. stream water pool was controlled by an adjustable weir. The
(1) does not consider sources and sinks of oxygen in the water body plan-view dimensions of the downstream water pool were
because their rates are relatively slow compared to the oxygen 1.20 1.20 m. An air flow meter installed on the air-hood was
transfer that occurs at most hydraulic structures due to the increase used to measure air entrainment rate QA. The plan-view dimen-
in free-surface turbulence and the large quantity of air that is nor- sions of the air-hood were 0.75 0.60 m. The test weir featured
mally entrained into the flow. three exchangeable weir elements: 45° triangular sharp-crested
The predictive relations assume that Cs is constant and deter- weir, 90° triangular sharp-crested weir and 135° triangular
mined by the water–atmosphere partitioning. If that assumption sharp-crested weir.
60 60
o
θ = 45
o θ = 135
Q = 1 L/s Q = 1 L/s
50 50
Q = 2 L/s Q = 2 L/s
Q = 3 L/s Q = 3 L/s
40 40
(m 3 /s )
Q = 4 L/s Q = 4 L/s
Q Ax 10 - 4 (m 3 /s )
-4
30 30
Q Ax 10
20 20
10 10
0 0
0.00 0.15 0.30 0.45 0.60 0.75 0.90 1.05 0.00 0. 15 0.30 0.45 0.60 0.75 0.90 1.05
h (m) h(m)
Fig. 2. Variation in air entrainment rate with drop height for h = 45°. Fig. 4. Variation in air entrainment rate with drop height for h = 135°.
60 0.6
o o
θ = 90 θ = 45
Q = 1 L/s Q = 1 L/s
50 0.5
Q = 2 L/s Q = 2 L/s
Q = 3 L/s Q = 3 L/s
40 0.4
Q = 4 L/s Q = 4 L/s
Q Ax 10 - 4 (m 3 /s )
E 20
30 0.3
20 0.2
10 0.1
0 0.0
0.00 0.15 0.30 0.45 0.60 0.75 0.90 1.05 0.00 0.15 0.30 0.45 0.60 0.75 0.90 1.05
h (m) h (m)
Fig. 3. Variation in air entrainment rate with drop height for h = 90°. Fig. 5. Variation in aeration efficiency with drop height for h = 45°.
A. Baylar et al. / Expert Systems with Applications 36 (2009) 8368–8374 8371
wT xk þ b P þ1; if yk ¼ þ1
E
0.3
: ð8Þ
wT xk þ b 6 1; if yk ¼ 1
These two sets of inequalities can be combined into one single
0.2
set as follows:
yk ½wT xk þ b P 1 k ¼ 1; . . . ; N: ð9Þ
0.1 SVM formulations are done with in a context of convex optimi-
zation theory. The general methodology is to start formulating the
problem as a constrained optimization problem, next formulate
0.0 the Lagrangian and then take the conditions for optimality, finally
0.00 0.15 0.30 0.45 0.60 0.75 0.90 1.05 solve the problem in the dual space of Lagrange multipliers. With
resulting classifier
h (m)
" #
XN
Fig. 6. Variation in aeration efficiency with drop height for h = 90°. yðxÞ ¼ sign ak yk xtk x þ b : ð10Þ
k¼1
" 0:172 #4:598 This linear SVM classifier was extended to non-separable case
0:293 h
Q A ¼ 0:171h Q 0:158 cos ; ð5Þ by Cortes and Vapnik (1995). It is done by taking additional slack
2 variable in the problem formulation. One modifies the set of
" 0:206 #1 inequalities into
1:341 0:280 h
E20 ¼ 1 1 þ 0:149h Q sin ; ð6Þ
2 yk wT xk þ b P 1 nk ; k ¼ 1; . . . ; N: ð11Þ
where h is the drop height (m), Q the discharge (m3/s), and h is the The SVM has been used for linear and nonlinear function esti-
angle in triangular sharp-crested weir (deg.). mation too. The details of them can be found in literature. The least
square version of the SVM classifier was described by Suykens and
5. Least square support vector machine (LS-SVM) Vandewalle (1999). The LS-SVM considers equality type con-
straints instead of inequalities as in the classic SVM approach. This
The SVM is a supervised learning technique which is developed reformulation greatly simplifies a problem such that the LS-SVM
by Vladimir Vapnik and co-workers at AT&T Bell Laboratories in solution follows directly from solving a set of linear equations
rather than from a convex quadratic program. For a LS-SVM classi-
fier, in the primal space it takes the form,
When radial basic function (RBF) kernels are used, two tuning
parameters (c, r) are added. Where c is the regularization constant
0.1
and r the width of RBF kernel.
60 0.6
Measured
Predicted
50 0.5
40 0.4
-4
Q A x 10
E 20
30 0.3
20 0.2
10 0.1
Measured
Predicted
0 0.0
0 5 10 15 20 25 0 5 10 15 20 25
Sample Sample
h, angle in triangular sharp-crested weir h, air entrainment rate QA used for determining the optimal values of RBF kernel parameters.
and aeration efficiency E20. The parameters, Q, h, and h were used For QA, the determined optimal c value is 511.35 and optimal r va-
as inputs to the LS-SVM models to predict QA and E20, respectively. lue is 1.9914. The test performance of LS-SVM model is graphically
72 experimental data sets were used for the SVM model. Before presented in Fig. 8. As seen in Fig. 8, LS-SVM model predicts the
training and testing of LS-SVM model for QA and E20, the data set measured values at high accuracy rate. Threefold cross validation
was normalized by using method is applied to the 72 experimental data sets for computing
the validation of LS-SVM models. The correlation between mea-
xi xmin
xi ¼ þ b; ð15Þ sured QA and predicted by LS-SVM model is 0.99.
xmax xmin
Moreover, the measured air entrainment rates QA are compared
where xmin and xmax are the minimum and maximum of the input with the LS-SVM model, the nonlinear regression (NLR) technique
data and b is the bias value (b = 0.1). and the linear regression (LR) technique results. It can be obviously
In the first part of this study, the LS-SVM model with RBF kernel seen from Table 1 that the LS-SVM model approximates the mea-
is trained for air entrainment rates QA. Grid search algorithm is sured QA values with a quite high accuracy. The LS-SVM model
Table 1
Absolute relative error (ARE) statistics for computed QA using LS-SVM, NLR and LR models.
Table 2
Absolute relative error (ARE) statistics for computed E20 using LS-SVM, NLR and LR models.
seems to have similar performance to multi nonlinear regression Baylar, A. (2003). An investigation on the use of venturi weirs as an aerator. Water
Quality Research Journal of Canada, 38(4), 753–767.
model. The accuracy of the linear regression model is lower than
Baylar, A., & Bagatur, T. (2000). Aeration performance of weirs. Water SA, 26(4),
the LS-SVM and multi nonlinear regression models. 521–526.
In the second part of this study, the LS-SVM model with RBF Baylar, A., & Bagatur, T. (2001a). Aeration performance of weirs. Water Engineering &
kernel is trained for aeration efficiencies E20. Grid search algorithm Management Part 1, 148(3), 33–36.
Baylar, A., & Bagatur, T. (2001b). Aeration performance of weirs. Water Engineering
is used for determining the optimal values of RBF kernel parame- & Management, Part 2, 148(4), 14–16.
ters. For E20, the determined optimal c value is 76.517 and optimal Baylar, A., & Bagatur, T. (2006). Experimental studies on air entrainment and oxygen
r value is 3.0647. The test performance of LS-SVM model for E20 is content downstream of sharp-crested weirs. Water and Environment Journal,
20(4), 210–216.
graphically presented in Fig. 9. As it can be seen from Fig. 9, LS- Baylar, A., & Emiroglu, M. E. (2002). The effect of sharp-crested weir shape on air
SVM model predicts the measured values at high accuracy. Three- entrainment. Canadian Journal of Civil Engineering, 29(3), 375–383.
fold cross validation method is applied to the 72 experimental data Baylar, A., & Ozkan, F. (2006). Applications of venturi principle to water aeration
systems. Environmental Fluid Mechanics, 6(4), 341–357.
sets for computing the validation of LS-SVM models. The correla- Baylar, A., Bagatur, T., & Tuna, A. (2001a). Aeration performance of triangular notch
tion between measured E20 and predicted by LS-SVM model is 0.98. weirs at recirculating system. Water Quality Research Journal of Canada, 36(1),
The measured aeration efficiencies E20 are compared with the 121–132.
Baylar, A., Bagatur, T., & Tuna, A. (2001b). Aeration performance of triangular-notch
LS-SVM model, the nonlinear regression (NLR) technique and the weirs. Journal of the Chartered Institution of Water and Environmental
linear regression (LR) technique results. It can be obviously seen Management, 15(3), 203–206.
from Table 2 that the LS-SVM model approximates the measured Baylar, A., Hanbay, D., & Ozpolat, E. (2007). Modeling aeration efficiency of stepped
cascades by using ANFIS. CLEAN – Soil, Air, Water, 35(2), 186–192.
E20 values with a quite high accuracy. The LS-SVM model seems
Baylar, A., Hanbay, D., & Ozpolat, E. (2008). An expert system for predicting aeration
to have similar performance to multi nonlinear and linear regres- performance of weirs by Using ANFIS. Expert Systems with Applications, 35(3),
sion models. 1214–1222.
Baylar, A., & Emiroglu, M. E. (2007). The role of weir types in entrainment of air
bubbles. International Journal of Science and Technology, 2(2), 143–154.
7. Conclusions Chanson, H. (1995). Predicting oxygen content downstream of weirs, spillways and
waterways. Proceedings of the Institution of Civil Engineers – Water, Maritime and
Energy, 112(1), 20–30.
The dominant aeration mechanism in free overfall jet from a weir Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3),
is that of air bubbles being carried into the biphasic zone when the jet 273–297.
plunges into the receiving pool. The degree of aeration will depend Emiroglu, M. E., & Baylar, A. (2003a). Experimental study of the influence of
different weir types on the rate of air entrainment. Water Quality Research
upon the amount of air entrained. In this study, LS-SVM models were
Journal of Canada, 38(4), 769–783.
developed to determine the air entrainment rate and aeration effi- Emiroglu, M. E., & Baylar, A. (2003b). The effect of broad-crested weir shape on air
ciency of weirs. It was found from the test results that LS-SVM mod- entrainment. Journal of Hydraulic Research, 41(6), 649–655.
Emiroglu, M. E., & Baylar, A. (2005). The influence of included angle and sill slope on
els can be used successfully in predicting the air entrainment rate
air entrainment of triangular planform labyrinth weirs. Journal of Hydraulic
and aeration efficiency of weirs. The most important aspect of the Engineering, ASCE, 131(3), 184–189.
intelligent modeling is the ability of self-organization without Emiroglu, M. E., & Baylar, A. (2006). Closure of ‘the influence of included angle and
requirements of programming and the immediate response of a sill slope on air entrainment of triangular planform labyrinth weirs’. Journal of
Hydraulic Engineering, ASCE, 132(7), 748.
trained net during real-time applications. These features make the Ervine, D. A. (1998). Air entrainment in hydraulic structures: A review. Proceedings
intelligent models suitable for complex systems modeling. of the Institution of Civil Engineers – Water, Maritime and Energy, 130(3),
142–153.
Gulliver, J. S., Thene, J. R., & Rindels, A. J. (1990). Indexing gas transfer in self-aerated
References flows. Journal of Environmental Engineering, ASCE, 116(3), 503–523.
Gulliver, J. S., Wilhelms, S. C., & Parkhill, K. L. (1998). Predictive capabilities in
Baylar, A. (2002). Study on the effect of type selection of weir aerators on oxygen oxygen transfer at hydraulics structures. Journal of Hydraulic Engineering, ASCE,
transfer, PhD thesis. Firat University, Elazig, Turkey (in Turkish). 124(7), 664–671.
8374 A. Baylar et al. / Expert Systems with Applications 36 (2009) 8368–8374
Hanbay, D., Turkoglu, I., & Demir, Y. (2007). Predicting chemical oxygen demand Wilhelms, S. C., Gulliver, J. S., & Parkhill, K. (1992). Reaeration at Low-Head
(COD) based on wavelet decomposition and neural networks. CLEAN – Soil, Air, Hydraulic Structures. Tech. Rep. Hl-91, US Army Engineer Waterways
Water, 35(3), 250–254. Experiment Station, Vicksburg, Miss.
Suykens, J. A. K., & Vandewalle, J. (1999). Least squares support vector machine Wormleaton, P. R., & Tsang, C. C. (2000). Aeration performance of rectangular
classifiers. Neural Processing Letters, 9(3), 293–300. planform labyrinth weirs. Journal of Environmental Engineering, ASCE, 126(5),
Tsang, C. C. (1987). Hydraulic and aeration performance of labyrinth weirs, PhD Thesis. 456–465. <http://www.esat.kuleuven.ac.be/sista/lssvmlab>.
University of London, London.