Please wait a minute...

Frontiers of Mechanical Engineering

Front Mech Eng    2013, Vol. 8 Issue (3) : 319-332     https://doi.org/10.1007/s11465-013-0269-3
RESEARCH ARTICLE
Multi-objective optimization of process parameters in Electro-Discharge Diamond Face Grinding based on ANN-NSGA-II hybrid technique
Ravindra Nath YADAV1(), Vinod YADAVA1, G.K. SINGH1,2
1. Department of Mechanical Engineering, Motilal Nehru National Institute of Technology, Allahabad-211004, India; 2. Department of Mechanical Engineering, Galgotias University, Gr. Noida, India
Download: PDF(518 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

The effective study of hybrid machining processes (HMPs), in terms of modeling and optimization has always been a challenge to the researchers. The combined approach of Artificial Neural Network (ANN) and Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) has attracted attention of researchers for modeling and optimization of the complex machining processes. In this paper, a hybrid machining process of Electrical Discharge Face Grinding (EDFG) and Diamond Face Grinding (DFG) named as Electrical Discharge Diamond face Grinding (EDDFG) have been studied using a hybrid methodology of ANN-NSGA-II. In this study, ANN has been used for modeling while NSGA-II is used to optimize the control parameters of the EDDFG process. For observations of input-output relations, the experiments were conducted on a self developed face grinding setup, which is attached with the ram of EDM machine. During experimentation, the wheel speed, pulse current, pulse on-time and duty factor are taken as input parameters while output parameters are material removal rate (MRR) and average surface roughness (Ra). The results have shown that the developed ANN model is capable to predict the output responses within the acceptable limit for a given set of input parameters. It has also been found that hybrid approach of ANN-NSGA-II gives a set of optimal solutions for getting appropriate value of outputs with multiple objectives.

Keywords hybrid machining processes (HMPs)      electrical discharge diamond grinding (EDDG)      artificial neural network (ANN)      genetic algorithm      modeling and optimization     
Corresponding Author(s): YADAV Ravindra Nath,Email:rnymnnit@yahoo.com   
Issue Date: 05 September 2013
 Cite this article:   
Ravindra Nath YADAV,Vinod YADAVA,G.K. SINGH. Multi-objective optimization of process parameters in Electro-Discharge Diamond Face Grinding based on ANN-NSGA-II hybrid technique[J]. Front Mech Eng, 2013, 8(3): 319-332.
 URL:  
http://journal.hep.com.cn/fme/EN/10.1007/s11465-013-0269-3
http://journal.hep.com.cn/fme/EN/Y2013/V8/I3/319
Fig.1  Different configurations of EDDG process
Fig.2  EDDFG as combination of EDFG and DFG
Fig.3  Photographic view of EDDFG setup
Fig.4  Schematic diagram of EDDFG process
Type of abrasiveDiamond
Grit number80/100
GradeM (Medium)
Concentration75
Bonding materialBronze
Depth of abrasive5 mm
Wheel diameter30 mm
Tab.1  Detail of metal bonded grinding wheel
SymbolInput parametersValues
SWheel speed (RPM)700875105012251400
CPulse current (A)4681012
TPulse on-time (μs)4070100130160
DDuty factor0.470.550.630.710.79
Tab.2  Input parameters and their values
Experimental runsInput parameters and their valuesMRR (mm3/min)Ra (μm)
SCTD
1105081000.630.9753.54
28756700.550.3273.01
312256700.550.6842.90
487510700.550.6793.26
5125010700.551.3793.18
6105081000.631.0423.49
787561300.550.2202.69
8122561300.550.9092.86
9875101300.550.4683.07
101225101300.550.9663.48
11105081000.631.0923.23
128756700.710.8683.24
1312256700.711.6683.39
1487510700.711.2453.35
15122510700.711.7413.64
16105081000.630.9753.89
1787561300.710.8133.59
18122561300.711.6483.75
19875101300.711.2123.73
201225101300.711.7613.82
21105081000.631.1743.59
2270081000.630.8023.94
23140081000.632.1723.96
24105041000.630.7072.62
251050121000.631.8133.45
26105081000.631.2363.57
2710508400.631.0133.22
28105081600.631.0373.80
29105081000.470.8033.07
30105081000.791.3833.94
31105081000.631.1093.30
Tab.3  Experimental results at corresponding inputs
Experimental runsInput parameters and their valuesMRR (mm3/min)Ra (μm)
SCTD
170061000.630.9354.21
270081500.71.3074.59
387541000.70.7294.48
487561500.571.7084.31
58758500.631.3663.93
6105041500.630.8133.97
710506500.71.2683.85
8105081000.571.2794.41
Tab.4  Experimental results with corresponding inputs for testing the network
Fig.5  Performance of single layer network with varying neurons
Fig.6  ANN (4-8-2) architecture
Fig.7  Training performance of (4-8-2) ANN architecture
Experimental runsExperimentalPredicted% Absolute error
MRR (mm3/min)Ra (μm)MRR (mm3/min)Ra (μm)MRRRa
10.9354.211.0644.0613.813.59
21.3074.591.4234.368.895.10
30.7294.480.8444.2815.714.55
41.7084.311.5424.069.735.78
51.3663.931.3593.870.481.50
60.8133.970.9123.9812.200.15
71.2683.851.4573.9314.902.10
81.2794.411.3614.266.413.34
Tab.5  Experimental and predicted values of MRR and
Fig.8  Comparison between experimental and predicted MRR
Fig.9  Comparison between experimental and predicted
Fig.10  Flow chart of ANN-NSGA-II approach
Fig.11  Effect of wheel speed on MRR and
Fig.12  Effect of pulse current on MRR and
Fig.13  Effect of pulse on-time on MRR and
Fig.14  Effect of duty factor on MRR and
Fig.15  Pareto optimal front
Sl. No.Wheel speed (RPM)Current (A)Pulse on-time (μm)Duty factorMRR (mm3/min)Ra (μm)
114008.22121.410.622.1753.92
211204.00150.430.771.1312.54
313774.74159.730.652.1242.89
414008.60160.000.572.1603.75
513977.38160.000.512.1383.03
611344.00153.280.771.2152.54
713998.21146.550.622.1603.86
814008.52160.000.572.1603.69
911194.00152.970.781.4742.54
1014008.46158.700.572.1603.66
1114008.40159.960.572.1603.56
1211214.00143.640.761.6012.54
1310864.00160.000.791.5562.54
1413958.08160.000.552.1573.23
1513655.00129.340.692.0802.69
1614008.01160.000.562.1563.18
1713978.18160.000.562.1583.31
1814008.35160.000.562.1603.51
1911114.00151.880.791.9062.54
2010844.00160.000.791.5132.54
2113764.83137.930.702.0742.66
2210824.00156.070.791.8142.54
2311244.00160.000.791.3342.54
2411184.00160.000.791.3882.54
2514008.44160.000.562.1603.61
2611284.00160.000.791.3662.54
2711064.00155.920.781.4372.54
2813977.90159.160.552.1543.14
2913704.75156.980.652.1212.87
3014007.73160.000.562.1493.06
Tab.6  Optimal solution set and corresponding inputs-outputs
1 Konig W, Cronjager L, Spur G, Tonshoff H K, Vigneau M, Zdeblick W J. Machining of new materials. CIRP Annals- Manufacturing Technology , 1990, 39(2): 673–681
doi: 10.1016/S0007-8506(07)63004-2
2 Rajurkar K P, Gu L. Resent research and developments in hybrid machining processes, Proc. 3rd Int. 24th AIMTDR Conf . Vishakhapatnam. 2010, 39–44
3 Kozak J, Oczos K E. Selected problems of abrasive hybrid machining. Journal of Materials Processing Technology , 2001, 109(3): 360–366
doi: 10.1016/S0924-0136(00)00824-4
4 Aoyama T, Inasaki I. Hybrid machining-combination of electrical discharge machining and grinding, Proc. 14th N. Am. Manuf. Res. Conf. Annu . Meeting, Minnesota. 1986, 654–661
5 Wei B, Rajurkar K P. Abrasive electro discharge grinding of super alloys and ceramics, Proc. 1st Int. Mach. Grind. Conf . Dearborn, Michigan. 1995, 188–196
6 Kozak J. Abrasive electrodischarge grinding (AEDG) of advanced materials. Archives of Civil and Mechanical Engineering , 2002, 2: 83–101
7 Koshy P, Jain V K, Lal G K. Mechanism of material removal in electrical discharge diamond grinding. International Journal of Machine Tools & Manufacture , 1996, 36(10): 1173–1185
doi: 10.1016/0890-6955(95)00103-4
8 Koshy P, Jain V K, Lal G K. Grinding of cemented carbide with electrical spark assistance. Journal of Materials Processing Technology , 1997, 72(1): 61–68
doi: 10.1016/S0924-0136(97)00130-1
9 Choudhury S K, Jain V K, Gupta M. Electrical discharge diamond grinding of high speed steel. Machining Science and Technology , 1999, 3(1): 91–105
doi: 10.1080/10940349908945685
10 Jain V K, Mote R G. On the temperature and specific energy during electrodischarge diamond grinding (EDDG). International Journal of Advanced Manufacturing Technology , 2005, 26(1-2): 56–67
doi: 10.1007/s00170-003-1983-5
11 Yadav S K S, Yadava V, Narayana V L. Experimental study and parameter design of electro-discharge diamond grinding. International Journal of Advanced Manufacturing Technology , 2008, 36(1-2): 34–42
doi: 10.1007/s00170-006-0820-z
12 Yadav S K S, Yadava V. Multi-objective optimization of electrical discharge diamond cutoff grinding (EDDCG) using Taguchi method. Int. J. Manuf. Technol. Ind. Eng. , 2010, 1: 193–198
13 Singh G K, Yadava V, Kumar R. Robust parameter design and multi-objective optimization of electro-discharge diamond face grinding process of HSS. Int. J. Mach. Mach. Mater. , 2012, 11: 1–19
14 Singh G K, Yadava V, Kumar R. Diamond face grinding of WC-Co composite with spark assistance: Experimental study and parameter optimization. Int. J. Precis. Eng. Manuf. , 2010, 11(4): 509–518
doi: 10.1007/s12541-010-0059-3
15 Singh G K, Yadava V, Kumar R. Experimental study and parameter optimization of electro-discharge diamond face grinding. Int. J. Abras. Technol. , 2011, 4: 14–40
16 Agrawal S S, Yadava V. Artificial neural network modeling of electrical discharge diamond surface grinding (EDDSG), Proc. 7th Int. Conf. Precis . Meso, Micro and Nano Eng. Pune. 2011,265–269
17 Joshi S N, Pande S S. Development of an intelligent process model for EDM. International Journal of Advanced Manufacturing Technology , 2009, 45(3-4): 300–317
doi: 10.1007/s00170-009-1972-4
18 Jain R K, Jain V K, Kalra P K. Modelling of abrasive flow machining process: A neural network approach. Wear , 1999, 231(2): 242–248
doi: 10.1016/S0043-1648(99)00129-5
19 Yousef B F, Knopf G K, Bordatchev E V, Nikumb S K. Neural network modeling and analysis of the material removal process during laser machining. International Journal of Advanced Manufacturing Technology , 2003, 22(1-2): 41–53
doi: 10.1007/s00170-002-1441-9
20 Briceno J F, Mounayri H E, Mukhopadhyay S. Selecting an artificial neural network for efficient modeling and accurate simulation of the milling process. International Journal of Machine Tools & Manufacture , 2002, 42(6): 663–674
doi: 10.1016/S0890-6955(02)00008-1
21 Sanjay C, Neema M L, Chin C W. Modeling of tool wear in drilling by statistical analysis and artificial neural network. Journal of Materials Processing Technology , 2005, 170(3): 494–500
doi: 10.1016/j.jmatprotec.2005.04.072
22 Markopoulos A P, Manolakos D E, Vaxevanidis N M. Artificial neural network models for the prediction of surface roughness in electrical discharge machining. Journal of Intelligent Manufacturing , 2008, 19(3): 283–292
doi: 10.1007/s10845-008-0081-9
23 Kumar S, Choudhury S K. Prediction of wear and surface roughness in electro-discharge diamond grinding. Journal of Materials Processing Technology , 2007, 191(1-3): 206–209
doi: 10.1016/j.jmatprotec.2007.03.032
24 Yadav S K S, Yadava V. Artificial neural network modeling of electrical discharge diamond cut-off grinding (EDDCG), Proc. 3rd Int. 24th AIMTDR Conf . Vishakhapatnam. 2010, 271–275
25 Sharma V, Yadava V, Rao R. Yadava, R. Rao, Optimization of kerf quality characteristics during Nd: YAG laser cutting of nickel based superalloy sheet for straight and curved cut profiles. Optics and Lasers in Engineering , 2010, 48(9): 915–925
doi: 10.1016/j.optlaseng.2010.03.005
26 Tosun N. Determination of optimum parameters for multi-performance characteristics in drilling by using grey relational analysis. International Journal of Advanced Manufacturing Technology , 2006, 28(5-6): 450–455
doi: 10.1007/s00170-004-2386-y
27 Mahapatra S S, Patnaik A. Optimization of wire electrical discharge machining (WEDM) process parameters using Taguchi method. International Journal of Advanced Manufacturing Technology , 2007, 34(9-10): 911–925
doi: 10.1007/s00170-006-0672-6
28 Jung J H, Kwon W T. Optimization of EDM process for multiple performance characteristics using Taguchi method and Grey relational analysis. Journal of Mechanical Science and Technology , 2010, 24(5): 1083–1090
doi: 10.1007/s12206-010-0305-8
29 Kansal H K, Singh S, Kumar P. Parametric optimization of powder mixed electrical discharge machining by response surface methodology. Journal of Materials Processing Technology , 2005, 169(3): 427–436
doi: 10.1016/j.jmatprotec.2005.03.028
30 Siddiquee A N, Khan Z A, Mallick Z. Grey relational analysis coupled with principal component analysis for optimisation design of the process parameters in in-feed centreless cylindrical grinding. International Journal of Advanced Manufacturing Technology , 2010, 46(9-12): 983–992
doi: 10.1007/s00170-009-2159-8
31 Rajasekaran S, Pai G A V. Neural Networks, Fuzzy Logic and Genetic Algorithms: Synthesis and Applications. PHI Learning Pvt. Ltd . New Delhi, 2004
32 Deb K, Pratap A, Agarwal S, Meyarivan T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation , 2002, 6(2): 182–197
doi: 10.1109/4235.996017
33 Mitra K, Gopinath R. Multiobjective optimization of an industrial grinding operation using elitist nondominated sorting genetic algorithm. Chemical Engineering Science , 2004, 59(2): 385–396
doi: 10.1016/j.ces.2003.09.036
34 Tavoli M A, Zadeh N N, Khakhali A, Mehran M. Multi-objective optimization of abrasive flow machining processes using polynomial neural networks and genetic algorithms. Machining Science and Technology , 2006, 10(4): 491–510
doi: 10.1080/10910340600996126
35 Su J C, Kao J Y, Tarng J Y S. Optimisation of the electrical discharge machining process using a GA-based neural network. International Journal of Advanced Manufacturing Technology , 2004, 24: 81–90
36 Kanagarajan D, Karthikeyan R, Palanikumar K, Davim J P. Optimization of electrical discharge machining characteristics of WC/Co composites using non-dominated sorting genetic algorithm (NSGA-II). International Journal of Advanced Manufacturing Technology , 2008, 36(11-12): 1124–1132
doi: 10.1007/s00170-006-0921-8
37 Joshi S N, Pande S S. Intelligent process modeling and optimization of die-sinking electric discharge machining. Applied Soft Computing , 2011, 11(2): 2743–2755
doi: 10.1016/j.asoc.2010.11.005
38 Mandal D, Pal S K, Saha P. Modeling of electrical discharge machining process using back propagation neural network and multi-objective optimization using non-dominating sorting genetic algorithm-II. Journal of Materials Processing Technology , 2007, 186(1-3): 154–162
doi: 10.1016/j.jmatprotec.2006.12.030
39 Rao G K M, Janardhana G R, Rao D H, Rao M S. Development of hybrid model and optimization of surface roughness in electric discharge machining using artificial neural networks and genetic algorithm. Journal of Materials Processing Technology , 2009, 209(3): 1512–1520
doi: 10.1016/j.jmatprotec.2008.04.003
40 AliR, NejadM. Modeling and optimization of electrical discharge machining of SiCparameters using neural network and non-dominating sorting genetic algorithm (NSGA-II). Materials Sciences and Applications , 2011, 2: 669–675
41 Wang K, Gelgele H L, Wang Y, Yuan Q, Fang M. A hybrid intelligent method for modelling the EDM process. International Journal of Machine Tools & Manufacture , 2003, 43(10): 995–999
doi: 10.1016/S0890-6955(03)00102-0
42 Cochran W G, Cox G M. Experimental Designs, Asia Publishing House, Bombay, 1959.
43 Moller M F. A scale conjugate gradient algorithm for fast supervised learning. Neural Networks , 1993, 6(4): 525–533
doi: 10.1016/S0893-6080(05)80056-5
44 Deb K. Multi-Objective Optimization using Evolutionary Algorithm, First ed., John Wiley and Sons, Ltd, West Sussex, 2002
45 Song L. NGPS-A NSGA-II Program in Matlab, Version 1.4, Coll. Astronaut . Northwestern Polytech. Univ. China, [on line], 2011, Available from: http://www.mathworks.com/matlabcentral/fileexchange (Accessed 20 April, 2012)
Related articles from Frontiers Journals
[1] Jiali ZHAO, Shitong PENG, Tao LI, Shengping LV, Mengyun LI, Hongchao ZHANG. Energy-aware fuzzy job-shop scheduling for engine remanufacturing at the multi-machine level[J]. Front. Mech. Eng., 2019, 14(4): 474-488.
[2] Weiwei ZHANG,Xiaosong WANG,Zhongren WANG,Shijian YUAN. Enhancing fatigue life of cylinder-crown integrated structure by optimizing dimension[J]. Front. Mech. Eng., 2015, 10(1): 102-110.
[3] Pengxing YI,Lijian DONG,Tielin SHI. Multi-objective genetic algorithms based structural optimization and experimental investigation of the planet carrier in wind turbine gearbox[J]. Front. Mech. Eng., 2014, 9(4): 354-367.
[4] Sunil Dhingra,Gian Bhushan,Kashyap Kumar Dubey. Multi-objective optimization of combustion, performance and emission parameters in a jatropha biodiesel engine using Non-dominated sorting genetic algorithm-II[J]. Front. Mech. Eng., 2014, 9(1): 81-94.
[5] Christopher John NASSAU, N. Scott LITOFSKY, Yuyi LIN. Analysis of spinal lumbar interbody fusion cage subsidence using Taguchi method, finite element analysis, and artificial neural network[J]. Front Mech Eng, 2012, 7(3): 247-255.
[6] Abdelbadia CHAKER, Abdelfattah MLIKA, Med Amine LARIBI, Lotfi ROMDHANE, Sa?d ZEGHLOUL. Synthesis of spherical parallel manipulator for dexterous medical task[J]. Front Mech Eng, 2012, 7(2): 150-162.
[7] T. ESSOMBA, M. A. LARIBI, J. P. GAZEAU, S. ZEGHLOUL, G. POISSON. Contribution to the design of robotized tele-echography system[J]. Front Mech Eng, 2012, 7(2): 135-149.
[8] XIA Junyong, HU Youmin, WU Bo, SHI Tielin. Theory analysis and system identification methods on thermal dynamics characteristics of ballscrews[J]. Front. Mech. Eng., 2008, 3(4): 408-415.
[9] LIU Xiong, CHEN Yan, YE Zhiquan. Optimization model for rotor blades of horizontal axis wind turbines[J]. Front. Mech. Eng., 2007, 2(4): 483-488.
[10] JIANG Kai, CHEN Hai-xia, YUAN Sen-miao. Multiobjective image recognition algorithm in the fully automatic die bonder[J]. Front. Mech. Eng., 2006, 1(3): 313-316.
[11] CHANG Jian-feng, ZHONG Yue-xian, HAN Zan-dong. Optimal Method of Capacitated Lot-Sizing Planning in Manufacturing Systems[J]. Front. Mech. Eng., 2006, 1(1): 67-70.
Viewed
Full text


Abstract

Cited

  Shared   0
  Discussed