Sunteți pe pagina 1din 10

Energy 50 (2013) 177e186

Contents lists available at SciVerse ScienceDirect

Energy
journal homepage: www.elsevier.com/locate/energy

Prediction of engine performance and exhaust emissions for gasoline and


methanol using articial neural network
Yusuf ay a, *, Ibrahim Korkmaz b, Adem iek c, Fuat Kara d
a

University of Karabk, Faculty of Engineering, Department of Mechanical Engineering, 78050 Karabk, Turkey
University of Dzce, Dzce Vocational School of Higher Education, 81500 Dzce, Turkey
c
Yldrm Beyazt University, Faculty of Engineering and Natural Sciences, Department of Mechanical Engineering, 06050 Ankara, Turkey
d
University of Dzce, Faculty of Technology, Department of Manufacturing Engineering, 81620 Dzce, Turkey
b

a r t i c l e i n f o

a b s t r a c t

Article history:
Received 26 June 2012
Received in revised form
17 October 2012
Accepted 27 October 2012
Available online 1 December 2012

This study investigates the use of ANN (articial neural networks) modelling to predict BSFC (break
specic fuel consumption), exhaust emissions that are CO (carbon monoxide) and HC (unburned
hydrocarbon), and AFR (airefuel ratio) of a spark ignition engine which operates with methanol and
gasoline. To obtain training and testing data, a number of experiments were performed with a fourcylinder, four-stroke test engine operated at different engine speeds and torques. The experimental
results reveal that the methanol improved the emission characteristics compared with the gasoline. For
the ANN modelling, the standard back-propagation algorithm was found to be the optimum choice for
training the model. In the building of the network structure, four different learning algorithms were used
such as BFGS (Quasi-Newton back propagation), LM (LevenbergeMarquardt learning algorithm). It was
found that the ANN model is able to predict the engine performance and exhaust emissions with
a correlation coefcient of 0.998621, 0.977654, 0.998382 and 0.996075 for the BSFC, CO, HC and AFR for
testing data, respectively. It was obvious that the developed ANN model is fairly powerful for predicting
the brake specic fuel consumption and exhaust emissions of internal combustion engines.
2012 Elsevier Ltd. All rights reserved.

Keywords:
Gasoline
Methanol
ANN
Engine performance
Exhaust emissions

1. Introduction
It is well known that all vehicles in the world are dependent on
fossil fuels such as gasoline, diesel fuel, LPG (liqueed petroleum
gas), LNG (liqueed natural gas) and CNG (compressed natural
gas). The fossil fuel used in vehicles causes factors threatening
human health such as air pollution, acid rains, smog, built up of
carbon dioxide, changes in the heat balance of the earth, and so on.
In addition, world fossil fuel reserves are also limited and will be
consumed away in the near future [1]. Therefore, it seems that the
use of alternative fuels is inevitable. These fuels include alcohols
(such as ethanol and methanol), ethers, vegetable oils, animal fats,
gaseous fuels and bio-diesel [2]. Among the alternative fuels,
methanol is considered to be one of the most favourable fuels for
engines. The reason is that methanol is liquid fuel and similar to
gasoline and diesel in aspects of usage, storage and transportation.
In addition, it can be produced from widely available raw materials
including coal, natural gas and bio-substances. Methanol is a good

* Corresponding author. Tel.: 90 370 4332021; fax: 90 380 5421134.


E-mail address: yusufcay@karabuk.edu.tr (Y. ay).
0360-5442/$ e see front matter 2012 Elsevier Ltd. All rights reserved.
http://dx.doi.org/10.1016/j.energy.2012.10.052

fuel for the spark-ignition engine. Benets such as higher efciency, specic power and lower emissions can be realised with
methanol. Methanol molecule contains 50% oxygen which leads to
combustion speed faster, also its higher laminar ame speed allows
it to be run with rarefaction or more dilute air/fuel mixtures [3].
Methanol fuelled buses had once been introduced to reduce
pollutant emission. However, operational problems have slowed
down the development of methanol-fuelled vehicles, leading to the
phasing out of the methanol-fuelled buses from the market [4].
Due to limitations on the development of methanol-fuelled
engines, lots of studies have been done to improve the engine
performance and to reduce exhaust emissions [5e11]. Yilmaz [12]
performed comparative analysis of biodieseleethanolediesel and
biodieselemethanolediesel blends in a diesel engine. Performance
and emission characteristics of the engine fuelled with biodiesele
methanolediesel and biodieseleethanolediesel were compared to
standard diesel fuel as the baseline. Overall biodieselealcohole
diesel blends showed higher brake specic fuel consumption
than diesel. As alcohol concentrations in blends increase, CO
(carbon monoxide) and HC (unburned hydrocarbon) emissions
increase, while NO (nitrogen oxides) emissions are reduced. Also,
methanol blends were more effective than ethanol blends for

178

Y. ay et al. / Energy 50 (2013) 177e186

Nomenclature
AFR
ANN
BFGS
BSFC
BTE
CNG
CO
f
Ft
HC
i.j
LHV
LM
LNG
LPG
m
MEP
MRE

airefuel ratio
articial neural network
Quasi-Newton back propagation
break specic fuel consumption
brake thermal efciency
compressed natural gas
carbon monoxide
transfer function
fuel type
unburned hydrocarbon
processing elements
lower heating value
LevenbergeMarquardt learning algorithm
liqueed natural gas
liqueed petroleum gas
fuel ow
mean error percentage
mean relative errors

reducing CO and HC emissions, while NO reduction was achieved


by ethanol blends. Yilmaz and Sanchez [13] carried out analysis of
operating a diesel engine on biodieseleethanol and biodiesele
methanol blends. Performance and emission characteristics of
the engine fuelled with biodieseleethanol and biodiesele
methanol blends were compared to neat biodiesel and standard
diesel fuel as the baseline fuels. Overall, biodieselealcohol blends,
as compared to diesel, reduce NO emissions while increasing CO
and HC emissions, at below 70% loads. It was also shown that
biodieseleethanol blend was more effective than biodiesele
methanol for emission reduction and overall engine performance.
Sayin [14] experimentally investigated the effects of methanole
diesel (M5, M10) and ethanolediesel (E5, E10) fuel blends on the
performance and exhaust emissions. The use of methanolediesel
and ethanolediesel blends caused a decrease in the emissions of
smoke opacity, CO and THC (total hydrocarbon). However, NOx
emissions increased with the use of blends. The BSFC (break
specic fuel consumption) with the all fuel blends increased
mainly due to the lower LHV (lower heating value) of methanol
and ethanol. The increase in BSFC with the blend M10 was higher
than that of E10 and M5 was higher than that of E5. All fuel blends
yielded a decrease in BTE (brake thermal efciency) because the
lower LHV of methanol and ethanol. Among the blends, the lowest
BTE was obtained from M10. Anand et al. [15] performed experimental investigations on combustion, performance and emissions
characteristics of neat karanji biodiesel and its methanol blend in
a diesel engine. It was observed that the HC emissions are slightly
higher for biodieselemethanol blend at low load conditions and
with increase in load the differences in HC emissions were insignicant between the two fuels. The differences in CO emissions
were insignicant for the two fuels at lower load conditions
whereas it was signicantly reduced at higher load conditions with
biodieselemethanol blend compared to neat biodiesel. The NO
emissions of biodieselemethanol blend were signicantly lower
compared to neat biodiesel fuel operation at all the tested conditions. Zhu et al. [16], in their study, aimed to investigate the effects
of the blended fuels on reducing NOx and particulate. On the
whole, compared with Euro V diesel fuel, the blended fuels could
lead to reduction of both NOx and PM (particulate matter) of
a diesel engine, with the biodieselemethanol blends being more
effective than the biodieseleethanol blends. The effectiveness of
NOx and particulate reductions was more effective with increase of

N
NETi
n
NOx
o
p
PSI
R2
RMSE
RP
SCG
t
T
THC
wij
wbi
Xj

engine speed
the weighted sum of the input to the ith processing
element
number of processing elements in the previous layer
nitrogen oxides
output value of ANN
number of pattern
pounds per square inch
determination coefcient
root mean square error
resilient back propagation
scaled conjugate gradient learning algorithm
experimental data
torque
total hydrocarbon
the weights of the connections between ith and jth
processing elements
the weights of the biases between layers
the output of the jth processing element

alcohol in the blends. With high percentage of alcohol in the


blends, the HC, CO emissions could increase and the BTE might be
slightly reduced but the use of 5% blends could reduce the HC and
CO emissions as well. Ozsezen and Canakci [17] discussed the
performance and exhaust emissions of a vehicle fuelled with low
content alcohol (ethanol and methanol) blends and pure gasoline.
The test results indicated that when the vehicle was fuelled with
alcoholegasoline blends, the peak wheel power and fuel
consumption slightly increased. And also, in general, alcohole
gasoline blends provided higher combustion efciency compared
to pure gasoline use. Generally, the alcoholegasoline blends at all
vehicle speeds provided slightly higher combustion efciency
relative to pure gasoline. The best combustion efciency was obtained with the use of M5 and E10. In exhaust emission results,
a stable trend was not seen, especially for CO emission. But, on
average, alcoholegasoline blends exhibited decreasing HC
emissions.
Articial neural network is fairly simple and small in size when
compared to the human brain, and has some powerful knowledge
and information processing characteristics due to its similarity to
the human brain [18]. ANN (articial neural network) is one such
effort, and is now progressively utilised as a prognostic tool in the
automotive sector to afford rapid predictions of various engine-out
parameters when new strategies in engine operating conditions are
tested. ANN is more attractive as an engine optimisation tool
because it is robust and less expensive in terms of required time
and resources [19]. In recent years, with the developments in
computer technology, ANN has been applied to many automotive
engineering problems with some degree of success. In automotive
engineering, neural networks have been applied to different engine
investigations such as prediction of exhaust emissions and
modelling of engine performance [20e23]. Naja et al. [24]
developed an ANN model to predict a correlation between brake
power, torque, brake specic fuel consumption, brake thermal
efciency, volumetric efciency, and emission components using
different gasolineeethanol blends and speeds as inputs data. A
standard Back-Propagation algorithm for the engine was used in
this model. It was observed that the ANN model can predict engine
performance and exhaust emissions with R2 (determination coefcient) in the range of 0.97e1. MRE (mean relative errors) values
were in the range of 0.46e5.57%, while RMSE (root mean square
error) were found to be very low. Ghobadian et al. [25] developed

Y. ay et al. / Energy 50 (2013) 177e186

179

2. Material and method

Table 1
Technical specications of the test engine.

2.1. Experimental setup and measurements

Item description

Stery

Engine type
Work type
Cylinder number
Total cylinder volume
Idling speed
Cylinder diameter
Piston stroke length
Compression ratio
Maximum torque
Maximum power
Cooling type

Ford-Escort
4-Stroke
4-Cylinder, sequence type
1297 cc
900 rpm
80.978 mm
62.99 mm
8:1
80 Nm (3000 rpm)
40 kW (5500 rpm)
Water cooled

an ANN model to estimate diesel engine performance and exhaust


emission analysis using waste cooking biodiesel fuel. It was
observed that the ANN model can predict the engine performance
and exhaust emissions quite well with correlation coefcients of
0.948, 0.999, 0.929 and 0.999 for the engine torque, BSFC, CO and
HC emissions, respectively. Another study conducted by Deh Kiani
et al. [26] dealt with an ANN modelling of a spark ignition engine to
predict the engine brake power, output torque and exhaust emissions (CO, CO2, NOx and HC) of the engine. Results showed that the
ANN provided the best accuracy in modelling the emission indices
with correlation coefcient equal to 0.98, 0.96, 0.90 and 0.71 for CO,
CO2, HC and NOx, and 0.99 and 0.96 for torque and brake power
respectively.
In this study, the changes in exhaust emissions and engine
performance have been observed by using methanol and gasoline
as fuel without any modications on a spark ignition engine; and
the impact of the fuel on exhaust emissions and break specic fuel
consumption have been examined. An ANN model was also
developed by considering the fuel type, torque, engine speed and
fuel ow in the input layer. By this way, prediction of some
parameters such as CO, HC, BSFC and AFR (airefuel ratio) was
aimed.

The engine used in this experiment was a 4 cylinder, 4 strokes,


and 1.3 L volume Ford-Escort automobile engine. In the hydraulic
brakes, a DPX1A type braking system which has 100 kW power and
750 rpm rates that can rise up to 200 Nm torque maximum was
used. The technical specications of the test engine are given in
Table 1. Electronic mean rotation tachometer was used for
measuring engine rotation. The sensitivity of the device for
measuring number of rotation is 0.04 rpm. During experiments,
the engine inlet and outlet temperatures of engine cooling water,
the temperature of the motor oil in the pan, the insert temperature
for every cylinder, temperature of exhaust gases, the temperature
of fuel at the inlet of carburettor, and the temperature of the testing
environment were measured by three different thermometers,
namely digital, mechanical and mercurial. The measurement
ranges of digital, mechanical and mercurial thermometers
were 230  C O 127  C, 0  C O 100  C and 0  C O 250  C
respectively. The measurement sensitivities of the digital,
mechanical and mercurial thermometers were 0.01  C, 1  C and
1  C, respectively.
SUN SGA-900 Model digital exhaust analysis device was used for
measuring exhaust gas emissions. The technical characteristic of
the exhaust emission device is given in Table 1. Valve adjustments,
point gapping, ignition advance adjustment, plug gapping,
measurements of compression pressures of each cylinder, and
measurement of their ignition voltages were conducted according
to the catalogue values of the engine and tests were initiated. In the
experiments, the rotation value of the engine was kept at 1100 rpm,
and the engine was loaded at 5e70 Nm range by means of hydraulic
dynamometer. Loading was continued at intervals until the engine
reached vibration running limits. The engine rotation was increased
in equal intervals of 300 rpm at 1100e4300 rpm range and loading
operations were repeated at each rotation. Engine test mechanism
can be seen in Fig. 1.

Fig. 1. The schematic layout of the experimental setup.

180

Y. ay et al. / Energy 50 (2013) 177e186

The intervals within which the engine showed regular operation


behaviour, environment, fresh insert, exhaust, motor oil, water
inlet, outlet temperatures, and atmospheric pressure, oil pressure,
mean relative humidity, skewed manometer deviation installed at
the air tank, fuel ow rate, torque value shown by dynamometer,
motor rotation value and exhaust emission values were observed as
test values. All the measurements were collected and recorded. The
test results obtained from the experimental study were used to
train and test the ANN.
2.2. Articial neural networks
ANNs are a logic programming technique developed with the
purpose of automatically performing skills such as learning,
remembering, deciding, and inference, which are features of the
human brain, without receiving any aid. By simply imitating the
operation of the human brain, ANNs have various important
features, such as learning from data, generalisation, working with
an innite number of variables, etc. The smallest units that form the
basis of the operation of ANNs are called articial neural cells. The
articial neural cells consist of mainly ve elements; namely,
inputs, weights, summation functions, activation functions and
outputs (Fig. 2).
ANN has three main layers; namely, the input, hidden and
output layers. The inputs are data from the external world. Neurons
(processing elements) in the input layer transfer data from the
external world to the hidden layer. The data in the input layer is not
processed in the same way as the data in the other layers. The
weights are the values of connections between cells. The outputs
are produced using data from neurons in the input and hidden
layers, and the bias, summation and activation functions. The
summation function is a function which calculates the net input of
the cell. The summation function used in this study is given in Eq.
(1).

NETi

n
X

wij xj wbi

(1)

j1

The activation function provides a curvilinear match between the


input and output layers. In addition, it determines the output of the
cell by processing the net input to the cell. The selection of an
appropriate activation function signicantly affects network
performance. There are many ways to dene the activation function,
such as the threshold function, step activation function, sigmoid
function, and hyperbolic tangent function. The type of activation
function depends on the type of neural network to be designed. A

sigmoid function is widely used for the transfer function. Logistic


transfer function of the ANN model in this study is given in Eq. (2). In
the output layer, the output of network is produced by processing
data from hidden layer and sent to external world.

f NETi

1
1 eNETi

(2)

The signicant advantages of articial neural networks are


learning ability and the use of different learning algorithms. The
most important factor which determines its success in practise,
after the selection of ANN architecture, is the learning algorithm. In
order to obtain the output values closest to the numerical values,
the best learning algorithm and the number of optimum neurons in
the hidden layer must be determined. In the training stage, to
obtain the output precisely, the number of neurons in the hidden
layer was increased step by step (i.e. 5e15).
For this purpose, BFGS (Quasi-Newton back propagation), LM
(LevenbergeMarquardt learning algorithm), RP (resilient back
propagation) and SCG (scaled conjugate gradient learning algorithm) learning algorithms were used in the building of the
network structure. As a result of the conducted trials, the best
learning algorithms for CO, HC, BSFC and AFR were found to be the
LM, RP, SCG and BFGS learning algorithms respectively. The best
network structures for CO, HC, BSFC and AFR were also found to be
4-7-1, 4-14-1, 4-7-1 and 4-11-1 respectively (Table 2). The best ANN
architecture built for the prediction of carbon monoxide is shown
in Fig. 3. The mean prediction accuracy represents validity of
prediction. It is calculated by the formula in Eq. (3). Also, the mean
prediction accuracies of CO, HC, BSFC and AFR for four learning
algorithms are given in Table 2.

MPA 100  MEP

(3)

In this study, 70 experimental data sets were prepared for the


training and testing data for the ANN. The ratio for training and
testing data was selected as 85%:15%, i.e. 10 and 60 sets of the
experimental data were randomly selected for the testing data and
training data, respectively. In the back propagation model, the
scaling of inputs and outputs dramatically affects the performance
of an ANN. As mentioned above, the logistic sigmoid transfer
function was used in this study. One of the characteristics of this
function is that only a value between 0 and 1 can be produced.
The input and output data sets were normalised before the
training and testing process. In this study, the input and output
values were normalised between 0 and 1 to obtain the optimal
predictions. Fuel type, engine speed, torque, fuel ow, carbon

Fig. 2. The structure of an articial neural cell.

Y. ay et al. / Energy 50 (2013) 177e186

181

Table 2
Prediction accuracy values for CO, HC, BSFC and AFR using four different learning algorithms.
Learning algorithm

Network structure

Prediction accuracy (%)


CO

SCG
SCG
SCG
SCG
SCG
SCG
SCG
SCG
SCG
SCG
SCG
LM
LM
LM
LM
LM
LM
LM
LM
LM
LM
LM
BFGS
BFGS
BFGS
BFGS
BFGS
BFGS
BFGS
BFGS
BFGS
BFGS
BFGS
RP
RP
RP
RP
RP
RP
RP
RP
RP
RP
RP

4-5-1
4-6-1
4-7-1
4-8-1
4-9-1
4-10-1
4-11-1
4-12-1
4-13-1
4-14-1
4-15-1
4-5-1
4-6-1
4-7-1
4-8-1
4-9-1
4-10-1
4-11-1
4-12-1
4-13-1
4-14-1
4-15-1
4-5-1
4-6-1
4-7-1
4-8-1
4-9-1
4-10-1
4-11-1
4-12-1
4-13-1
4-14-1
4-15-1
4-5-1
4-6-1
4-7-1
4-8-1
4-9-1
4-10-1
4-11-1
4-12-1
4-13-1
4-14-1
4-15-1

HC

BSFC

AFR

Training set

Testing set

Training set

Testing set

Training set

Testing set

Training set

Testing set

90.89
93.09
91.97
93.44
92.52
96.06
95.59
94.51
97.24
95.69
96.96
93.86
92.76
95.08
96.33
97.02
98.98
97.56
98.54
98.80
98.59
98.69
92.13
93.24
93.05
93.62
97.13
97.71
95.39
97.05
98.13
98.51
98.69
90.78
91.76
90.11
91.86
91.25
92.05
93.08
93.04
93.01
94.00
92.89

84.50
84.37
89.37
86.13
87.88
85.59
90.06
83.32
87.13
84.93
86.56
87.97
84.26
91.44
85.98
83.96
82.57
85.02
83.10
81.60
84.38
82.85
88.93
88.45
90.66
88.17
86.92
86.18
84.56
77.84
76.58
74.92
75.07
87.59
90.47
89.67
87.37
88.05
89.00
89.07
85.46
87.71
84.82
86.28

94.63
96.16
97.23
96.37
97.82
97.71
97.85
97.57
98.90
99.20
98.90
95.69
97.73
98.07
98.41
98.74
99.37
99.38
99.45
99.27
99.37
99.34
96.29
96.12
97.52
97.22
97.87
97.89
98.29
98.88
99.32
99.20
99.30
95.50
95.29
96.11
96.91
96.44
97.13
96.99
97.02
96.72
98.02
97.41

93.20
94.53
93.66
94.89
93.48
94.43
96.26
91.59
93.37
92.16
91.87
94.15
95.05
95.14
92.11
90.33
89.47
87.07
86.62
89.82
83.99
88.24
91.97
92.00
92.78
94.52
91.89
92.38
92.73
91.66
91.43
88.80
90.26
94.33
94.45
93.76
93.08
95.13
94.46
94.08
95.85
94.99
96.48
93.90

97.34
98.06
98.59
98.48
98.63
99.03
98.68
98.48
99.01
99.02
98.57
98.05
98.49
98.57
98.74
98.77
98.78
98.95
98.97
99.08
99.12
98.91
95.04
98.02
97.84
98.69
98.56
98.76
98.83
98.95
99.01
98.99
98.83
96.14
96.90
98.02
98.18
97.74
97.80
97.99
98.26
98.29
98.67
98.05

97.03
96.91
97.40
96.08
94.75
96.38
96.14
95.41
95.60
94.21
94.03
96.05
96.79
96.11
95.37
94.71
94.56
95.88
95.35
95.58
93.62
94.83
95.12
96.56
96.45
94.58
96.13
96.72
96.87
95.22
94.44
95.63
95.63
94.02
95.74
95.57
95.71
95.57
96.51
96.66
96.68
96.27
95.54
95.21

97.22
97.29
98.42
98.59
98.40
98.35
98.43
98.67
99.11
98.90
99.19
98.37
98.49
99.22
99.09
98.81
99.24
99.40
99.22
99.29
99.25
99.26
98.17
98.09
98.45
98.71
98.77
99.17
98.93
99.21
99.31
99.31
99.35
96.88
96.84
97.71
97.61
98.18
98.27
98.27
98.17
98.49
98.19
98.30

93.12
94.00
95.95
95.25
95.08
94.97
96.31
93.43
94.68
94.53
94.06
95.03
96.00
94.77
95.51
93.46
94.01
94.81
93.48
94.30
93.77
93.97
94.62
94.93
95.44
94.58
94.56
94.35
96.72
95.28
93.29
93.59
92.87
94.73
94.56
94.76
94.59
95.87
94.80
94.11
95.09
95.08
94.97
92.52

monoxide, unburned hydrocarbon, break specic fuel consumption and airefuel ratio were normalised dividing by 5, 5000, 35,
26, 8, 1500, 4600 and 20, respectively. The digits for the fuel type
to be entered into the articial neural networks were determined

as methanol 1 and gasoline 2, because they do not have


numerical values.
Exhaust emissions and engine performance values predicted
after ANN training were compared with the values obtained from
the experimental study. The RMSE, MEP (mean error percentage)
and R2 values were used for comparison. RMSE, MEP and R2 are
represented in Eqs. (4)e(6).

0
11=2
 X

2
1


@
tj  oj A
RMSE
p
j
 
P 
 
j tj  oj tj  100
MEP %
p

R2 1 
Fig. 3. ANN architecture with a single hidden layer for carbon monoxide.

2 !
P
j tj  oj
P  2
j oj

(4)

(5)

(6)

182

Y. ay et al. / Energy 50 (2013) 177e186

3. Results and discussion


3.1. Experimental evaluation of CO, HC, BSFC and AFR
As can be seen in Fig. 4, performance values obtained when
methanol was used as fuel were lower than gasoline. According to
the engine performance curves, brake specic fuel consumption is
more than the values where rotation values are low and high,
whereas it is less in medium rotations such as 3000 rpm. This case
shows the same feature for both gasoline and methanol fuels. When
the engine is operated with gasoline, brake specic fuel consumption is minimum at 1800 and 3000 rpm interval, which are
approximately 900 g/kWh. On the other hand, when it is operated
with methanol, specic consumption is minimum at 1800e
3000 rpm intervals, which are 1800 g/kWh. As it can be seen from
these values, motor performance values obtained when methanol
was used as fuel became lower than gasoline for the same situation.
This case is caused by the fact that evaporation heat of methanol is
3.28 times higher than the evaporation heat of gasoline, and that its

lower heating value is 2.24 times less than the lower heating value
of gasoline. Therefore, when the engine is operated on methanol, its
brake specic fuel consumption will be approximately two times
higher than gasoline. As no modication was applied to the engine,
engine performance was negatively affected as higher octane value
of methanol was not beneted. Moreover, in case of insufcient
intake manifold heating the fuel enters the cylinders as liquid. The
negative aspects appearing can easily be seen when looking at the
performance characteristic curves.
Because the lower heating value of methanol is lower than the
lower heating value of gasoline, if the same power and rotation
value are aimed, the ow rate of the methanol sent to cylinders has
to be increased. This case serves as one of the basic reasons of
excessive increase in brake specic fuel consumption. With it is
a high evaporation temperature, methanol is heated with the preheat process applied on suction manifold and an attempt is made to
partially meet the energy needed. Although the manifold was
heated from outside, it can be clearly seen from engine performance that this temperature was less than sufcient. Therefore, the

Fig. 4. Comparison of CO, HC, BSFC, and AFR values for gasoline and methanol engine.

Y. ay et al. / Energy 50 (2013) 177e186

183

Table 3
Statistical data for CO, HC, BSFC and AFR using four different algorithms.
Goal

Sequence

Learning algorithm

Network structure

Training set

Testing set

RMSE

R2

MEP

RMSE

R2

MEP

CO
1
2
3
4

LM
BFGS
RP
SCG

4-7-1
4-7-1
4-6-1
4-11-1

0.020667
0.027081
0.035288
0.014658

0.996902
0.994665
0.990877
0.998443

4.922218
6.950387
8.239697
4.414095

0.049213
0.050708
0.046600
0.051715

0.977654
0.976326
0.979911
0.977706

8.564867
9.343023
9.531393
9.944888

1
2
3
4

RP
SCG
LM
BFGS

4-14-1
4-11-1
4-7-1
4-8-1

0.012874
0.010802
0.011896
0.015316

0.999332
0.999529
0.999430
0.999054

1.975396
2.146407
1.927521
2.775601

0.018734
0.021846
0.027593
0.037676

0.998382
0.997842
0.996507
0.993543

3.515423
3.735359
4.855570
5.481618

1
2
3
4

SCG
BFGS
LM
RP

4-7-1
4-11-1
4-6-1
4-12-1

0.007156
0.004075
0.006477
0.007890

0.999634
0.999881
0.999700
0.999555

1.413558
1.170858
1.505776
1.744768

0.010976
0.012582
0.013977
0.010183

0.998621
0.998207
0.997738
0.998841

2.595133
3.126220
3.210128
3.321998

1
2
3
4

BFGS
SCG
RP
LM

4-11-1
4-11-1
4-9-1
4-8-1

0.006147
0.011275
0.012429
0.005067

0.999872
0.999569
0.999477
0.999913

1.073933
1.568444
1.819480
0.911500

0.032479
0.037634
0.028903
0.038115

0.996075
0.994873
0.997047
0.995011

3.277073
3.694142
4.130722
4.486403

HC

BSFC

AFR

fact that methanol which enters cylinders in liquid form cannot be


burned completely and acts as the second reason for the decrease in
motor performance. This case does not only lower performance, it
also deteriorates the exhaust emissions.
In Fig. 4, the change in exhaust CO emission values with engine
rotation values can be seen. If the engine is operated with gasoline,
CO emission varies between 2 and 5%, whereas when methanol is
used as fuel, this rate varies between 1 and 2%. When CO emissions
compared to gasoline and methanol fuels, there is a decrease by
half. The BSFC and the CO values for both gasoline and methanol
increase with increasing engine speed. Because of the lack of

combustion time, in these conditions, airefuel mixture combustion


instabilities are the main reasons.
The most prominent example of the fact that methanol enters
cylinders mostly in liquid phase can be seen from HC emissions. In
the case that engine runs with methanol, a signicant increase is
observed in HC emissions, which is one of the results of this situation. When gasoline is used as fuel, HC emissions occur at higher
values such as 1300 ppm at lower speed; as the engine rotation and
load increases, it reduces to the level of 700 ppm. When methanol
is used as fuel, HC emissions vary between 800 ppm and 400 ppm.
If sufcient pre-heating was conducted, the fuel would enter

Fig. 5. Matching of the experimental and ANN values for testing sets of CO, HC, BSFC and AFR.

184

Y. ay et al. / Energy 50 (2013) 177e186

cylinders in vapour form, and HC emission values would be lower


(Fig. 4).
In Fig. 4, the change in AFR values with engine rotation values
can be seen. If the engine is operated with gasoline, AFR varies
between 13 and 15, whereas when methanol is used as fuel, this
rate varies between 6 and 15. AFR compared to gasoline and
methanol fuels, AFR values of gasoline are higher than methanol
fuel values. Both gasoline and methanol fuels values are rst
decreasing but then they are nearly constant with engine speed. A
stoichiometric mixture is the working point that modern engine
management systems employing fuel injection attempt to achieve
in light load cruise situations. For gasoline fuel, the stoichiometric
airefuel mixture is approximately 14.7. The approximate mass of
air is 14.7 mass of fuel. Any mixture less than 14.7 to 1 is considered
to be a rich mixture; any more than 14.7 to 1 is a lean mixture.
Whereas the methanol fuel stoichiometric air-to-fuel ratio is 6:1.
3.2. Prediction of engine performance and exhaust emissions using
articial neural network
Articial neural networks are an information-processing
system which was inspired by biological neural networks and

CO

HC

In addition to the information given in Table 3, the R2 values


were close to 1 for both the training and testing set. Similarly,
RMSE and MEP were fairly low. In the training period, for BSFC,
CO, HC and AFR, the mean relative error was found to be less than
5%. Other MEP results for the training and testing data were within
acceptable error limits (5%), whereas MEP results for the carbon
monoxide was about 8% for the testing data. Comparisons of the
ANN predictions and experimental results for testing sets of
output parameters are demonstrated in Fig. 5. It is seen that the
test patterns consist of the results of 10 tests. The most striking
point here is that the prediction values are very close to the
experimental values. As shown in Fig. 5, the predictive ability of
the network for BSFC, CO, HC and AFR was found to be satisfactory.
This means that the selection of four input parameters as inuencing factors for predictions of engine performance and exhaust
emissions provides satisfactory results. The equations of the break
specic fuel consumption, carbon monoxide, unburned hydrocarbon and airefuel ratio are given in Eqs. (7)e(10). Also, BSFC, CO,
HC and AFR of the spark ignition engine which operates with
methanol and gasoline fuels can be accurately calculated by these
formulae.

1
1 e0:47$F126:5857$F20:6243$F30:3029$F40:1169$F530:1875$F62:5677$F71:3785

(7)

1
1 e1:6669$F10:7857$F22:3483$F32:3565$F41:8671$F50:9765$F63:7981$F71:2198$F80:7510$F91:9372$F101:2220$F112:5052$F121:9013$F131:8961$F143:6045
(8)

BSFC

AFR

1
1 e1:3444$F114:2160$F21:051$F33:7197$F412:3523$F52:5808$F610:3370$F71:3444

(9)

1
1 e5:5227$F16:3870$F211:4906$F33:1129$F48:8843$F50:8038$F61:7763$F73:9820$F84:6401$F914:6868$F109:6594$F110:4704
(10)

which includes some performance features comparable to biological neural networks. The use of an ANN model is considered as
a practical and reliable approach for non-linear problems is to test
the prediction ability of specic fuel consumption, air fuel ratio
and exhaust emissions for a gasoline/methanol engine. The input
parameters of the network are fuel type, engine speed, torque and
fuel ow and its output parameters are also carbon monoxide,
unburned hydrocarbon, break specic fuel consumption and aire
fuel ratio. In this study, a computer program has been developed
in MATLAB platform to predict CO, HC, BSFC and AFR of the engine.
The optimum network structures and statistical parameters of
ANN models for four learning algorithms were given in Table 3. It
is apparent from Table 3, the prediction performances for both
training and testing sets of HC, BSFC and AFR showed that all the
approaches provide a quite satisfactory accuracy. Their R2 values
are more than 0.99. R2 value of testing set of CO is only about 0.97
while R2 value of training set of CO is only more than 0.99. The
best prediction results were obtained by LM, RP, SCG and BFGS
learning algorithms for CO, HC, BSFC and AFR respectively. But, in
general, SCG learning algorithm gave optimal or near optimal
results for all engine values. The LM learning algorithm had the
highest speed compared with the other learning algorithms and it
reached to optimal solutions with small number of neurons in
hidden layer.

where Fi (i 1, 2, 3, ..., 6 or 7) can be calculated according to Eq.


(11).

Fi

1
1 eEi

(11)

where Ei is the weighted sum of the inputs, and is calculated via the
equations in Tables 4e7 respectively. The data ow was completed
with the weights between the layers. The weight values of the input
and hidden layers are given in the Tables 4e7. Here, the effect of the
parameters that are at the input layer (fuel type, engine speed,
torque, and fuel ow) on the BSFC, CO, HC and AFR can be observed.
Table 4
Weights between input layer and hidden layer for carbon monoxide.
Ei w1 x Ft w2 x N w3 x T w4 x m qi
i

w1

w2

w3

w4

qi

1
2
3
4
5
6
7

20.5567
3.2179
8.8508
7.4488
2.3375
2.3561
3.0032

18.8115
2.6905
1.6973
5.2651
16.5006
2.5278
4.2582

43.5460
0.6381
1.6597
0.1136
34.2741
0.6399
0.9201

137.1448
2.1837
9.6879
10.3693
0.3408
2.0305
0.4256

64.8508
2.3224
1.5509
1.0095
16.1222
1.9868
0.9356

Y. ay et al. / Energy 50 (2013) 177e186


Table 5
Weights between input layer and hidden layer for unburned hydrocarbon.
Ei w1 x Ft w2 x N w3 x T w4 x m qi
i

w1

w2

w3

w4

qi

1
2
3
4
5
6
7
8
9
10
11
12
13
14

2.3233
20.7017
37.6477
5.4834
20.8279
0.6687
3.1090
5.7232
2.1559
15.8216
9.5964
2.0175
5.1409
2.1905

14.8439
6.4541
1.1580
9.3051
3.4757
0.7165
0.1522
4.0079
50.9460
0.2831
1.2197
7.6085
11.3877
6.5494

8.8019
37.3731
0.5470
4.8038
12.8066
3.3239
8.3508
16.6259
1.9872
12.6757
3.8456
9.4049
0.1544
12.0538

2.0713
13.3634
10.9087
3.8739
53.1614
27.3673
2.5015
2.5595
39.0036
7.5211
5.6979
1.0777
1.7356
2.4864

7.9305
13.1148
28.9961
1.2853
0.3983
3.3342
4.3130
5.8816
12.8126
9.0443
1.9857
2.8794
9.4755
4.1366

Table 6
Weights between input layer and hidden layer for break specic fuel consumption.
Ei w1 x Ft w2 x N w3 x T w4 x m qi
i

w1

w2

w3

w4

qi

1
2
3
4
5
6
7

6.1367
0.9215
6.2304
8.2761
13.3334
2.0337
10.8711

8.6065
6.1443
7.5374
4.2407
9.6042
0.4886
0.8904

2.7542
9.7505
5.2516
2.2491
21.8834
0.1355
0.2756

1.1512
3.2887
2.1166
0.5642
11.6602
8.3803
2.6254

11.4027
4.3706
0.8362
1.4162
5.6802
0.3306
1.6316

185

is a good alternative to other conventional modelling techniques in


the prediction of the break specic fuel consumption and exhaust
emissions.
According to the ndings of this study, engine performance
values when operated with methanol are lower than those obtained when operated with gasoline. As the higher octane values of
methanol were not taken into consideration and engines
compression rate was not modied as per this value, it affected the
engine performance negatively. Nevertheless, as the heating of
suction manifold is less than sufcient, methanol enters cylinders
mostly in liquid phase. When the engine was operated with
methanol, signicant decrease was observed in the emissions
compared to the gasoline case. It has been found out that the more
than expected values of emission was caused by the fact that
methanol entered cylinders in liquid phase due to its high evaporation heat. During experiments, methanol suction manifold was
treated with pre-heat but it became obvious that this was not
sufcient for the examination of performance and emission curves.
That the evaporation temperature of methanol is high requires
heating of methanol at suction manifold. The insufcient heating at
suction manifold causes vibrated operation of the engine especially
at higher rotations. When methanol is used as fuel in the spark
ignition engine, sufcient heating of suction manifold is necessary
in terms of motor performance and exhaust emission. In particular,
during intercity travels, during when motor vehicles reach higher
power rates, heating of suction manifold is even more necessary.

References

Table 7
Weights between input layer and hidden layer for air-fuel ratio.
Ei w1 x Ft w2 x N w3 x T w4 x m qi
i

w1

w2

w3

w4

qi

1
2
3
4
5
6
7
8
9
10
11

3.4724
0.6950
13.9449
7.6819
5.2721
0.6250
1.6734
16.8867
7.3617
0.4572
6.7352

6.0658
9.5892
8.1972
24.1519
12.4115
5.7735
21.6636
22.9654
5.8099
8.6139
4.9454

5.4282
7.2658
1.6756
0.0617
1.1646
16.3744
16.0527
1.7804
1.5742
0.7837
3.2717

4.9926
9.2055
9.9349
7.9679
7.2202
18.6978
18.8932
11.1511
6.1791
2.9229
3.8012

4.3480
24.3873
1.5099
5.4471
8.8788
16.5786
19.4814
14.2951
2.0851
4.8989
0.7176

4. Conclusions
In this study, an ANN modelling was used for the prediction of
the BSFC, CO, HC and AFR of a spark ignition engine which operates
with methanol and gasoline fuels. For training period, different
training algorithms such as BFGS, LM, RP and SCG back propagation
were used. The best results in the prediction of BSFC, CO, HC and
AFR were obtained by network architecture of 4-7-1, 4-7-1, 4-14-1
and 4-11-1 and the SCG, LM, RP and BFGS learning algorithms,
respectively. In the ANN model, the coefcients of determination of
the BSFC, CO, HC and AFR for both the training and the testing set
were notably close to 1. It was determined that the ANN results
obtained for the BSFC, CO, HC and AFR were within acceptable error
limits (5%). These results show that the learning capacity of the
ANN is quite powerful in the prediction of the BSFC, CO, HC and
AFR. Therefore, the use of ANN is highly recommended for the
prediction of break specic fuel consumption and exhaust emissions without conducting complicated, expensive, and timeconsuming experimental studies. This study shows that an ANN

[1] Cay Y, Cicek A, Kara F, Sagiroglu S. Prediction of engine performance for an


alternative fuel using articial neural network. Appl Therm Eng 2012;37:
217e25.
[2] Lenin AH, Azhagesan N, Berlin Selva Rex CR, Thyagarajan K. Performance of
diesel engine operating with pongamia methyl esters as biodiesel. Asian J Sci
Res 2012;5:153e61.
[3] Xie FX, Li XP, Wang XC, Su Y, Hong W. Research on using EGR and ignition
timing to control load of a spark-ignition engine fuelled with methanol. Appl
Therm Eng 2013;50:1084e91.
[4] Cheng CH, Cheung CS, Chan TL, Lee SC, Yao CD. Experimental investigation on
the performance, gaseous and particulate emissions of a methanol fumigated
diesel engine. Sci Total Environ 2008;389:115e24.
[5] Korkmaz I, Cay Y. The impact of methanol fuelled spark ignition engines on
engine performance and exhaust emissions. Energ Educ Sci Technol Part A:
Energ Sci Res 2012;28(1):301e10.
[6] Adnan R, Masjuki HH, Mahlia TMI. Performance and emission analysis of
hydrogen fuelled compression ignition engine with variable water injection
timing. Energy 2012;43:416e26.
[7] Mohammadi P, Nikbakh AM, Tabatabaei M, Farhadi K, Mohebbi A, Khatami M.
Experimental investigation of performance and emission characteristics of DI
diesel engine fuelled with polymer waste dissolved in biodiesel-blended
diesel fuel. Energy 2012;46(1):596e605.
[8] Gong CM, Huang K, Jia JL, Su Y, Gao Q, Liu XJ. Regulated emissions from
a direct-injection spark-ignition methanol engine. Energy 2011;36:3379e87.
[9] Masi M. Experimental analysis on a spark ignition petrol engine fuelled with
LPG (liqueed petroleum gas). Energy 2012;41:252e60.
[10] Rakopoulos DC, Rakopoulos CD, Giakoumis EG, Dimaratos AM. Characteristics
of performance and emissions in high-speed direct injection diesel engine
fuelled with diethyl ether/diesel fuel blends. Energy 2012;43:214e24.
[11] Chauhan BS, Kumar N, Cho HM. A study on the performance and emission of
a diesel engine fuelled with Jatropha biodiesel oil and its blends. Energy 2012;
37:616e22.
[12] Yilmaz N. Comparative analysis of biodiesel-ethanol-diesel and biodieselmethanol-diesel blends in a diesel engine. Energy 2012;40:210e3.
[13] Yilmaz N, Sanchez TM. Analysis of operating a diesel engine on biodieselethanol and biodiesel-methanolblends. Energy 2012;46(1):126e9.
[14] Sayin C. Engine performance and exhaust gas emissions of methanol and
ethanolediesel blends. Fuel 2010;89:3410e5.
[15] Anand K, Sharma RP, Mehta PS. Experimental investigations on combustion,
performance and emissions characteristics of neat karanji biodiesel and its
methanol blend in a diesel engine. Biomass Bioenerg 2011;35:533e41.
[16] Zhu L, Cheung CS, Zhang WG, Huang Z. Emissions characteristics of a diesel
engine operating on biodiesel and biodiesel blended with ethanol and
methanol. Sci Total Environ 2010;408:914e21.
[17] Ozsezen AN, Canakci M. Performance and combustion characteristics of
alcohol-gasoline blends at wide-open throttle. Energy 2011;36:2747e52.

186

Y. ay et al. / Energy 50 (2013) 177e186

[18] Topcu IB, Saridemir M. Prediction of compressive strength of concrete containing y ash using articial neural networks and fuzzy logic. Comput Mater
Sci 2008;41:305e11.
[19] Ismail HM, Ng HK, Queck CW, Gan S. Articial neural networks modelling of
engine-out responses for a light-duty diesel engine fuelled with biodiesel
blends. Appl Energy 2012;92:769e77.
[20] Tinaut FV, Melgar A, Gimenez B, Reyes M. Prediction of performance and
emissions of an engine fuelled with natural gas/hydrogen blends. Int J Hydrog
Energy 2011;36:947e56.
[21] Yusaf TF, Yousif BF, Elawad MM. Crude palm oil fuel for diesel-engines:
experimental and ANN simulation approaches. Energy 2011;36:4871e8.
[22] Sharon H, Jayaprakash R, Karthigai Selvan M, Soban Kumar DR, Sundaresan A,
Karuppasamy K. Biodiesel production and prediction of engine performance
using SIMULINK model of trained neural network. Fuel 2012;99:197e203.

[23] Yap WK, HoT Karri V. Exhaust emissions control and engine parameters
optimization using articial neural network virtual sensors for a hydrogenpowered vehicle. Int J Hydrog Energy 2012;37:8704e15.
[24] Naja G, Ghobadian B, Tavakoli T, Buttsworth DR, Yusaf TF, Faizollahnejad M.
Performance and exhaust emissions of a gasoline engine with ethanol
blended gasoline fuels using articial neural network. Appl Energ 2009;86:
630e9.
[25] Ghobadian B, Rahimi H, Nikbakht AM, Naja G, Yusaf TF. Diesel engine
performance and exhaust emission analysis using waste cooking biodiesel
fuel with an articial neural network. Renew Energ 2009;34:976e82.
[26] Deh Kiani MK, Ghobadian B, Tavakoli T, Nikbakht AM, Naja G. Application of articial neural networks for the prediction of performance and
exhaust emissions in SI engine using ethanol- gasoline blends. Energy
2010;35:65e9.

S-ar putea să vă placă și