Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers in Energy

ISSN 2095-1701

ISSN 2095-1698(Online)

CN 11-6017/TK

Postal Subscription Code 80-972

2018 Impact Factor: 1.701

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Energy    2016, Vol. 10 Issue (1) : 114-124    https://doi.org/10.1007/s11708-016-0394-x
RESEARCH ARTICLE
Prediction of performance, combustion and emission characteristics of diesel-thermal cracked cashew nut shell liquid blends using artificial neural network
Arunachalam VELMURUGAN(),Marimuthu LOGANATHAN,E. James GUNASEKARAN
Department of Mechanical Engineering, Annamalai University, Annamalainagar 608002, India
 Download: PDF(1889 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

This paper explores the use of artificial neural networks (ANN) to predict performance, combustion and emissions of a single cylinder, four stroke stationary, diesel engine operated by thermal cracked cashew nut shell liquid (TC-CNSL) as the biodiesel blended with diesel. The tests were performed at three different injection timings (21°, 23°, 25°CA bTDC) by changing the thickness of the advance shim. The ANN was used to predict eight different engine-output responses, namely brake thermal efficiency (BTE), brake specific fuel consumption (BSFC), exhaust gas temperature (EGT), carbon monoxide (CO), oxide of nitrogen (NOx), hydrocarbon (HC), maximum pressure (Pmax) and heat release rate (HRR). Four pertinent engine operating parameters, i.e., injection timing (IT), injection pressure (IP), blend percentage and pecentage load were used as the input parameters for this modeling work. The ANN results show that there is a good correlation between the ANN predicted values and the experimental values for various engine performances, combustion parameters and exhaust emission characteristics. The mean square error value (MSE) is 0.005621 and the regression value of R2 is 0.99316 for training, 0.98812 for validation, 0.9841 for testing while the overall value is 0.99173. Thus the developed ANN model is fairly powerful for predicting the performance, combustion and exhaust emissions of internal combustion engines.
Keywords cashew nut shell liquid (CNSL)      artificial neural networks (ANN)      thermal cracking      mean square error (MSE)     
Corresponding Author(s): Arunachalam VELMURUGAN   
Just Accepted Date: 21 December 2015   Online First Date: 19 January 2016    Issue Date: 29 February 2016
 Cite this article:   
Arunachalam VELMURUGAN,Marimuthu LOGANATHAN,E. James GUNASEKARAN. Prediction of performance, combustion and emission characteristics of diesel-thermal cracked cashew nut shell liquid blends using artificial neural network[J]. Front. Energy, 2016, 10(1): 114-124.
 URL:  
https://academic.hep.com.cn/fie/EN/10.1007/s11708-016-0394-x
https://academic.hep.com.cn/fie/EN/Y2016/V10/I1/114
Properties Measurement standards Diesel CNSL (Cardanol) TC-CNSL
Density at 25°C/(g·cm–3) ASTM D1298 0.8/0.84 0.9326 0.821
Kinematic viscosity at 30°C/(mPa·s) ASTM D 445 2.0 to 4.5 17.2 4.43
Calorific value/(kJ·kg–1) ASTM D 240 42000 39600 41780
Flash point/°C ASTM D 93 80 198 <28
Boiling point/°C ASTM D1160 180–340 225 180–380
Calculated cetane index ASTM D 976 52 28 45
Tab.1  Properties of TC-CNSL and diesel fuel
Fig.1  Schematic diagram of cracking reactor
Parameters Specifications
Type Vertical, water-cooled, four-stroke
Make KIRLOSKAR AV-1
Number of cylinder One
Bore 80 mm
Stroke 110 mm
Displacement volume 560 mL
Compression ratio 17.5:1
Maximum power 3.7 kW
Speed 1500 r·min−1
Dynamometer Eddy current dynamometer
Injection timing 23° bTDC
Injection pressure 20 MPa
Tab.2  Engine specifications
Fig.2  General configuration of proposed ANN
Network type Adaption learning function Performance function Training function Transfer functions Number of neurons
Feed-forward BP LEARNGDM MSE TRAINLM Tansig/Purelin 10
Tab.3  Optimum settings of ANN
S.No. Training function Number of epochs Time taken in seconds for convergence MSE
1 Traingda 117 05 0.12166
2 Traingdx 145 06 0.01548
3 Trainrp 74 04 0.00739
4 Traincgf 71 04 0.12071
5 Trainscg 39 03 0.01505
6 Trainbfg 45 03 0.00984
7 Trainlm 30 02 0.00565
Tab.4  Performance of the network using various training algorithms for the performance, combustion and emission model
Fig.3  Performance of tested ANN model of injection timing of 21°bTDC, 23°bTDC and 25°bTDC
Injection timings/°bTDC Injection pressure/MPa Blend/% Cal load/(N·m)
22 18 20 4.71
22 18 40 9.42
22 18 60 14.13
22 18 80 18.84
22 18 100 23.55
22 20 0 0
22 20 20 4.71
22 20 40 9.42
22 20 60 14.13
22 20 80 18.84
23 20 0 0
23 20 20 4.71
23 20 40 9.42
23 20 60 14.13
23 20 80 18.84
23 20 100 23.55
23 22 80 18.84
23 22 60 14.13
23 22 40 9.42
23 22 20 4.71
24 18 20 4.71
24 20 40 9.42
24 20 60 14.13
24 20 80 18.84
24 20 100 23.55
24 22 80 18.84
24 22 60 14.13
24 22 40 9.42
24 22 20 4.71
24 22 0 0
Tab.5  Random 30 ‘unknown’ data points
Engine parameters Ranges
Engine control parameters (ANN-input) Injection timings/°CA 21, 23, 25
Injection pressure/MPa 18, 20, 22
Blend/% 0, 20, 40, 60, 80, 100
Calculate load/(N·m) 0, 4.71, 9.42, 14.13, 18.84, 23.55
Fuel type Thermal cracked cashew nut shell liquid (TC-CNSL)
Engine-out responses (ANN-output) BTE/% 0–35
BSFC/(g·kWh–1) 0–906
EGT/°C 157–436
HC/(g·kWh–1) 0.04–0.11
CO/(g·kWh–1) 0.26–1.05
NOx/(g·kWh–1) 0.517–8.40
Pmax/MPa 5.223–7.104
HRR/(J·°CA–1) 26.98–52.96
Tab.6  Engine parameters and their ranges
Fig.4  Overall correlation coefficient R of selected network architecture
Fig.5  Comparison of ANN prediction of BTE with measured data for the 30 data points
Fig.6  Comparison of ANN prediction of BSFC with measured data for the 30 data points
Fig.7  Comparison of ANN prediction of EGT with measured data for the 30 data points
Fig.8  Comparison of ANN prediction of CO with measured data for the 30 data points
Fig.9  Comparison of ANN prediction of HC with measured data for the 30 data points
Fig.10  Comparison of ANN prediction of NOx with measured data for the 30 data points
Fig.11  Comparison of ANN prediction of Pmax with measured data for the 30 data points
Fig.12  Comparison of ANN prediction of HRR with measured data for the 30 data points
1 Vedharaj  S, Vallinayagam  R, Yang  W M, Chou  S K, Chua  K J E, Lee  P S. Performance emission and economic analysis of preheated CNSL biodiesel as an alternate fuel for a diesel engine. International Journal of Green Energy, 2015, 12(4): 359–367
https://doi.org/10.1080/15435075.2013.841162 
2 Vedharaj  S, Vallinayagam  R, Yang  W M, Chou  S K, Chua  K J E, Lee  P S. Experimental and finite element analysis of a coated diesel engine fuelled by cashew nut shell liquid biodiesel. Experimental Thermal and Fluid Science, 2014, 53: 259–268
https://doi.org/10.1016/j.expthermflusci.2013.12.018
3 Vallinayagam  R, Vedharaj  S, Yang  W M, Saravanan  C G, Lee  P S, Chua  K J E, Chou  S K. Impact of ignition promoting additives on the characteristics of a diesel engine powered by pine oil-diesel blend. Fuel, 2014, 117: 278–285
https://doi.org/10.1016/j.fuel.2013.09.076
4 Shivakumar,  Srinivasa Pai  P, Shrinivasa Rao  B R.  Artificial neural network based prediction of performance and emission characteristics of a variable compression ratio CI engine using WCO as a biodiesel at different injection timings. Applied Energy, 2011, 88(7): 2344–2354  
https://doi.org/10.1016/j.apenergy.2010.12.030
5 Çay  Y, Korkmaz  I, Çiçek  A, Kara  F. Prediction of engine performance and exhaust emissions for gasoline and methanol using artificial neural network. Energy, 2013, 50: 177–186  
https://doi.org/10.1016/j.energy.2012.10.052
6 Mohamed Ismail  H, Ng  H K, Queck  C W, Gan  S. Artificial neural networks modelling of engine-out responses for a light-duty diesel engine fuelled with biodiesel blends. Applied Energy, 2012, 92: 769–777
https://doi.org/10.1016/j.apenergy.2011.08.027
7 Betiku  E, Omilakin  O R, Ajala  S O, Okeleye  A A, Taiwo  A E, Solomon  B O. Mathematical modeling and process parameters optimization studies by artificial neural network and response surface methodology: a case of non-edible neem (Azadirachta indica) seed oil biodiesel synthesis. Energy, 2014, 72: 266–273
https://doi.org/10.1016/j.energy.2014.05.033
8 Arumugam  S, Sriram  G, Shankara Subramanian  P R. Application of artificial to predict the performance and exhaust emissions of diesel engine using rapeseed oil methyl ester. Procedia Engineering, 2012, 38: 853–860 
https://doi.org/10.1016/j.proeng.2012.06.107
9 Ghobadian  B, Rahimi  H, Nikbakht  A M, Najafi  G, Yusaf  T F. Diesel engine performance and exhaust emission analysis using waste cooking biodiesel fuel with an artificial neural network. Renewable Energy, 2009, 34(4): 976–982
https://doi.org/10.1016/j.renene.2008.08.008
10 Moradi  G R, Dehghani  S, Khosravian  F, Arjmandzadeh  A. The optimized operational conditions for biodiesel production from soybean oiland application of artificial neural networks for estimation of the biodiesel yield. Renewable Energy, 2013, 50: 915–920
https://doi.org/10.1016/j.renene.2012.08.070
11 Najafi  G, Ghobadian  B, Tavakoli  T, Buttsworth  D R, Yusaf  T F, Faizollahnejad  M. Performance and exhaust emissions of a gasoline engine with ethanol blended gasoline fuels using artificial neural network. Applied Energy, 2009, 86(5): 630–639
https://doi.org/10.1016/j.apenergy.2008.09.017
12 Çelikten I, Mutlu  E, Solmaz  H. Variation of performance and emission characteristics of a diesel engine fueled with diesel, rapeseed oil and hazelnut oil methyl ester blends. Renewable Energy, 2012, 48: 122–126 
https://doi.org/10.1016/j.renene.2012.04.040
13 Parlak  A, Islamoglu  Y, Yasar  H, Egrisogut  A. Application of artificial neural network to predict specific fuel consumption and exhaust temperature for a diesel engine. Applied Thermal Engineering, 2006, 26(8-9): 824–828  
https://doi.org/10.1016/j.applthermaleng.2005.10.006
14 Sayin  C, Ertunc  H M, Hosoz  M, Kilicaslan  I, Canakci  M. Performance and exhaust emissions of a gasoline engine using artificial neural network. Applied Thermal Engineering, 2007, 27(1): 46–54
https://doi.org/10.1016/j.applthermaleng.2006.05.016
15 Canakci  M, Erdil  A, Arcaklioglu  E. Performance and exhaust emissions of a biodiesel engine. Applied Energy, 2006, 83(6): 594–605
https://doi.org/10.1016/j.apenergy.2005.05.003
16 Çelik  V, Arcaklioglu  E. Performance maps of a diesel engine. Applied Energy, 2005, 81(3): 247–259 
https://doi.org/10.1016/j.apenergy.2004.08.003
17 Can  O, Celikten  I, Usta  N. Effects of ethanol addition on performance and emissions of a turbocharged indirect injection diesel engine running at different injection pressures. Energy Conversion and Management, 2004, 45(15-16): 2429–2440 
https://doi.org/10.1016/j.enconman.2003.11.024
18 Yusaf  T F, Buttsworth  D R, Saleh  K H, Yousif  B F. CNG-diesel engine performance and exhaust emission analysis with the aid of artificial neural network. Applied Energy, 2010, 87(5): 1661–1669
https://doi.org/10.1016/j.apenergy.2009.10.009
19 Oğuz H, Saritas  I, Baydan H E. Prediction of diesel engine performance using biofuels with artificial neural network. Expert Systems with Applications, 2010, 37(9): 6579–6586  
https://doi.org/10.1016/j.eswa.2010.02.128
20 Kiani Deh Kiani  M, Ghobadian  B,  Tavakoli  T,  Nikbakht  A M, Najafi G. Application of artificial neural networks for the prediction of performance and exhaust emissions in SI engine using ethanol-gasoline blends. Energy, 2010, 35(1): 65–69  
https://doi.org/10.1016/j.energy.2009.08.034
21 Sayin  C, Ertunc  H M, Hosoz  M, Kilicaslan  I, Canakci  M. Performance and exhaust emissions from a gasoline engine using artificial neural network. Applied Thermal Engineering, 2007, 27(1): 46–54
https://doi.org/10.1016/j.applthermaleng.2006.05.016
22 Canakci  M, Ozsezan  A N, Arcaklioglu  E, Erdil  A. Predication of performance and exhaust emissions of a diesel engine fuelled with biodiesel produced from waste frying palm oil. Expert Systems with Applications, 2009, 86: 630–639
23 Velmurugan  A, Loganathan  M, James Gunasekran  E. Experimental investigations on combustion, performance and emission characteristics of thermal cracked cashew nut shell liquid (TC-CNSL)-diesel blends in a diesel engine. Fuel, 2014, 132: 236–245 
https://doi.org/10.1016/j.fuel.2014.04.060
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed