Efficient Optimization of Neural Network using Taguchi-grey Relational Analysis with Signal-to-Noise Ratio Approach for 2.5D End Milling Process
Artificial neural network (ANN) is amongst one of the most popular nonlinear mapping systems in the field of artificial intelligence which has the ability to take care of numerous problems including modelling, predicting, and measuring in experimental knowledge. The execution of ANN relies on few data parameters. Deciding the optimum setting of different parameters till date remains a troublesome assignment. An efficient methodology is needed to obtain the optimum values for various parameters of ANN. In the present study, Grey-Taguchi’s method is used to determine the optimum value of various input parameters of the ANN model trained by different algorithms for multi-objective problem. Optimum values of different ANN parameters have been found by utilizing the Grey-Taguchi analysis in combination with analysis of variance (ANOVA) and S/N ratio analysis. The outcome of conformational experiments clearly demonstrates that the optimum mix of ANN parameters acquired by utilizing the proposed methodology performs better as far as low value of mean square error (MSE) and a low number of iterations needed to perform the investigation are in consideration, which advances results in the lesser calculation effort and time for execution. The methodology suggested in this work can be used for various neural network applications to locate the optimum levels of various parameters.
Optimization, Grey-Taguchi, Neural Networks, Analysis of Variance, End Milling, S/N Ratio
[1]
Alique, A. et al. (2000) ‘A neural network-based model for the prediction of cutting force in milling process: A progress Study on a real case’, Proceedings of the 15th IEEE lntemational Symposium on Intelligent Control (ISIC 2000) Rio, Patras, GREECE.
[2]
Al-Zubaidi, S., Ghani, J. A. and Haron, C. H. C. (2011) ‘Application of NN in Milling Process: A Review Hindawi Publishing Corporation’, Modeling and Simulation in Engineering, Article ID 696275, 7 pages.
[3]
Balasubramanian, S. and Ganapathy, S. (2011) ‘Grey Relational Analysis to determine optimum process parameters for Wire Electro Discharge Machining (WEDM)’, International Journal of Engineering Science and Technology, Vol. 3, No. 1, pp. 95-101.
[4]
Balestrassi, P. P. et al. (2009) ‘Design of experiments on neural network’s training for nonlinear time series forecasting’, Neurocomputing, Vol. 72, pp. 1160–1178.
[5]
Benardos, P. G. and Vosniakos, G. C. (2002) ‘Prediction of surface roughness in CNC face milling using neural networks and Taguchi’s design of experiments’, Robotics and Computer Integrated Manufacturing, Vol. 18, pp. 343–354.
[6]
Benardos, P. G. and Vosniakos, G. C. (2007) ‘Optimizing feedforward artificial neural network architecture’, Engineering Applications of Artificial Intelligence, Vol. 20, pp. 365–382.
[7]
Conde, A., Arriandiaga, A., Sanchez, J. A., Portillo, E., Plaza, S. and Cabanes, I. (2018) ‘High-accuracy wire electrical discharge machining using artificial neural networks and optimization techniques’, Robotics and Computer–Integrated Manufacturing, Vol. 49, pp. 24–38.
[8]
Drouilleta, C., Karandikara, J., Natha, C., Journeauxa, A. C., Mansorib, M. E. and Kurfessa, T. (2016) ‘Tool life predictions in milling using spindle power with the neural network technique’, Journal of Manufacturing Processes, Vol. 22, pp. 161–168.
[9]
Durairaj, M., Sudharsaun, D. and Swamynathan, N. (2013) ‘Analysis of Process Parameters in Wire EDM with Stainless Steel using Single Objective Taguchi Method and Multi Objective Grey Relational Grade’, Procedia Engineering, Vol. 64, pp. 868-877.
[10]
Hamidinejad, S. M., Kolahan, F. and Kokabi A. H. (2012) ‘The modelling and process analysis of resistance spot welding on galvanized steel sheets used in car body manufacturing’, Materials and Design, Vol. 34, pp. 759–767.
[11]
Hoskins, J. C. and Himmelblau, D. M. (1988) ‘Artificial neural network models of knowledge representation in chemical engineering’, Computers & Chemical Engineering, Vol. 12, No. 9, 10, pp. 881-890.
[12]
Inohira, E. And Yokoi, H. (2007) ‘An Optimal design method for Artificial Neural Networks by using the Design of Experiments’, Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol. 11, No. 6, pp. 593-599.
[13]
Jung, J. H. and Kwon, W. T. (2010) ‘Optimization of EDM process for multiple performance characteristics using Taguchi method and Grey relational analysis’, Journal of Mechanical Science and Technology, Vol. 24, No. 5, pp. 1083-1090.
[14]
Karkalos, N. E., Galanis, N. I. and Markopoulos, A. P. (2016) ‘Surface roughness prediction for the milling of Ti–6Al–4V ELI alloy with the use of statistical and soft computing techniques’, Measurement, Vol. 90, pp. 25–35.
[15]
Kasdekara, D. K., Parasharb, V. and Aryac, C. (2018) ‘Artificial neural network models for the prediction of MRR in Electro-chemical machining’, Materials Today: Proceedings’, Vol. 5, pp. 772–779.
[16]
Kasman, S. (2013) ‘Multi-response optimization using the Taguchi-based grey relational analysis: a case study for dissimilar friction stir butt welding of AA6082-T6/AA5754-H111’, Int J AdvManufTechnol, Vol. 68, pp. 795–804.
[17]
Kayabasi, E., Ozturk, S., Celik, E. and Kurt, H. (2017) ‘Determination of cutting parameters for silicon wafer with a Diamond Wire Saw using an artificial neural network’, Solar Energy, Vol. 149, pp. 285–293.
[18]
Kopac, J. and Krajnik, P. (2007) ‘Robust Design of flank milling parameters based on grey-Taguchi method’, Journal of Materials Processing Technology, Vol. 191, pp. 400-403.
[19]
Korkut, I., Acır, A. and Boy, M. (2011) ‘Application of regression and artificial neural network analysis in modeling of tool–chip interface temperature in machining’, Expert Systems with Applications, Vol. 38, pp. 11651–11656.
[20]
Kumar, D., Gupta, A. K., Chandna, P. and Pal, M. (2015) ‘Optimization of neural network parameters using Grey–Taguchi methodology for manufacturing process applications’, ProcIMechE Part C: J Mechanical Engineering Science, Vol. 229, No. 14, pp. 2651–2664.
[21]
Kumar, S. A. et al. (2013) ‘Prediction of fretting wear behavior of surface mechanical attrition treated Ti–6Al–4V using artificial neural network’, Materials and Design, Vol. 49, pp. 992–999.
[22]
Kumari, N., Gohel, J. V., Kumar, S. and Patel, R. (2017) ‘Multi-response optimization of ZnO thin films using Grey-Taguchi technique and development of a model using ANN’, Optik, Vol. 144, pp. 422–435.
[23]
Kuram, E. and Ozcelik, B. (2013) ‘Multi-objective optimization using Taguchi based grey relational analysis for micro-milling of Al 7075 material with ball nose end mill’, Measurement, Vol. 46, pp. 1849–1864.
[24]
Laosiritaworn, W. and Chotchaithanakorn, N. (2009) ‘Artificial Neural Networks parameters optimization with Design of Experiments: An Application in Ferromagnetic Materials Modeling’, Chiang Mai J. Sci., Vol. 36, No. 1, pp. 83-91.
[25]
Lin, H. L. (2013) ‘Optimization of Inconel 718 alloy welds in an activated GTA welding via Taguchi method, grey relational analysis, and a neural network’, Int J AdvManufTechnol, Vol. 67, pp. 939–950.
[26]
Lin, J. L. et al. (2000) ‘Optimization of the electrical discharge machining process based on the Taguchi method with fuzzy logics’, J Mater Process Technol, Vol. 102, pp. 48–55.
[27]
Lin, T. Y., Ping, H. C. and Hsu, T. H. (2011) ‘A Systematic approach to the Optimization of Artificial Neural Networks’, IEEE, Vol. 6, pp. 76-79.
[28]
Maiyara, L. M. et al. (2013) ‘Optimization of Machining Parameters for End Milling of Inconel 718 Super Alloy Using Taguchi Based Grey Relational Analysis’, Procedia Engineering, Vol. 64, pp. 1276– 1282.
[29]
Mikołajczyk, T., Nowicki, K., Bustillo, A. and Yu Pimenov, D. (2018) ‘Predicting tool life in turning operations using neural networks and image processing’, Mechanical Systems and Signal Processing, Vol. 104, pp. 503–513.
[30]
Milos, J., Madic, M. and Radovanovic, R. (2011) ‘Optimal selection of NN Training and Architectural Parameters using Taguchi Method: A Case Study’, FME Transactions, Vol. 39, pp. 79-86.
[31]
Mondal, S. et al. (2013) ‘Application of Taguchi-based grey relational analysis for evaluating the optimal laser cladding parameters for AISI1040 steel plane surface’, Int J AdvManufTechnol, Vol. 66, pp. 91–96.
[32]
Moshat, S. et al. (2010) ‘Parametric optimization of CNC end milling using entropy measurement technique combined with grey-Taguchi method’, International Journal of Engineering, Science and Technology, Vol. 2, No. 2, pp. 1-12.
[33]
Mukherjee, I. and Routroy, S. (2012) ‘Comparing the Performance of Neural Networks Developed by using Levenberg–Marquardt and Quasi-Newton with the Gradient Descent Algorithm for Modelling a Multiple Response Grinding Process’, Expert Systems with Applications, Vol. 39, pp. 2397–2407.
[34]
Öktem, H. (2009) ‘An integrated study of surface roughness for modeling and optimization of cutting parameters during end milling operation’, Int J AdvManufTechnol, Vol. 43, pp. 852–861.
[35]
Ortiz-Rodríguez, J. M., Martínez-Blanco, M. R. and Vega-Carrillo, H. R. (2006) ‘Robust design of Artificial Neural Networks applying the Taguchi methodology and DoE’, Proceedings of the Electronics. Robotics and Automotive Mechanics Conference (CERMA'06) 5 IEEE.
[36]
Ozcelik, B., Oktem, H. and Kurtaran, H. (2005) ‘Optimum surface roughness in end milling Inconel 718 by coupling neural network model and genetic algorithm’, Int J AdvManufTechnol, Vol. 27, pp. 234–241.
[37]
Packianather, M. S., Drake, P. R. and Rowlands, H. (2000) ‘Optimizing the parameters of Multilayered Feed forward neural networks through Taguchi design of experiments’, Qual. Reliab. Engg. Int, Vol. 16, pp. 461–473.
[38]
Peterson, G. E. and Clair, D. C. S. (1995) ‘Using Taguchi’s Method of Experimental Design to Control Errors in Layered Perceptrons’, IEEE Transactions On Neural Networks, Vol. 6, No. 4, pp. 949-961.
[39]
Pillai, J. U., Sanghrajka, I., Shunmugavel, M., Thangaraj, M., Goldberg, M. and Littlefair, G. (2018) ‘Optimisation of multiple response characteristics on end milling of Aluminium alloy using Taguchi-Grey relational approach’, Measurement, Vol. 124, pp. 291-298.
[40]
Radhakrishnan, T. and Nandan, U. (2005) ‘Milling force prediction using Regression and Neural Networks’, Journal of Intelligent Manufacturing, Vol. 16, pp. 93–102.
[41]
Rajyalakshmi, G. and Ramaiah, P. V. (2013) ‘Multiple process parameter optimization of wire electrical discharge machining on Inconel 825 using Taguchi grey relational analysis’, Int J AdvManufTechnol, Vol. 69, pp. 1249–1262.
[42]
Rojek, I. (2017) ‘Technological process planning by the use of neural networks Artificial Intelligence for Engineering Design’, Analysis and Manufacturing, Vol. 31, pp. 1–15.
[43]
Sahu, P. K., Kumari, K. and Pal, S. (2016) ‘Hybrid fuzzy-grey-Taguchi based multi weld quality optimization of Al/Cu dissimilar friction stir welded joints’, Advances in Manufacturing, Vol. 4, No. 3, pp. 237-247.
[44]
Santos, M. S. and Ludermir, T. B. (1999) ‘Using Factorial Design to Optimize Neural Networks’, IEEE, Vol. 6, pp. 857-861.
[45]
Sathiya, P., Panneerselvam, K. and Jaleel, M. Y. A. (2012) ‘Optimization of laser welding process parameters for super austenitic stainless steel using artificial neural networks and genetic algorithm’, Materials and Design, Vol. 36, pp. 490–498.
[46]
Shie, J. R. (2006) ‘Optimization of Dry Machining Parameters for High-Purity Graphite in End-Milling Process by Artificial Neural Networks: A Case Study’, Materials and Manufacturing Processes, Vol. 21, No. 8, pp. 838-845.
[47]
Singla, A. M., Sharma, S., Kaul, A. and Rajyalakshmi, G. (2018) ‘Optimization of WEDM process during machining of Al-Al2O3 composite using Taguchi based Grey Relational Analysis’, MATEC Web of Conferences Vol. 172, No. 04008, ICDAMS 2018.
[48]
Sreenivasulu, R. and Rao, C. S. (2012) ‘Application of Gray Relational Analysis for Surface Roughness error in drilling of Al 6061 alloy’, International Journal of Lean Thinking, Vol. 3, No. 2, pp. 67-78.
[49]
Sukthomya, W. and Tnnock, J. (2005) ‘The optimization of neural network parameters using Taguchi’s design of experiments approach: An application in manufacturing process modeling’, Neural Comput&Applic, Vol. 14, pp. 337–344.
[50]
Talasila, S. R., Valusa, R. and Anne, V. (2012) ‘Taguchi based Grey Relational Analysis to Optimize Face Milling Process with Multiple Performance Characteristics’, International Conference on Trends in Industrial and Mechanical Engineering (ICTIME’2012), March 24-25, Dubai
[51]
Tamiloli, N., Venkatesan, J. and Ramnath, B. V. (2016) ‘A grey-fuzzy modeling for evaluating surface roughness and material removal rate of coated end milling insert’, Measurement, Vol. 84, pp. 68-82.
[52]
Tamrin, K. F. et al. (2014) ‘Determination of optimum parameters using grey relational analysis for multi-performance characteristics in CO2 laser joining of dissimilar materials’, Optics and Lasers in Engineering, Vol. 57, pp. 40–47.
[53]
Tripathy, S. and Tripathy, D. K. (2016) ‘Multi-attribute optimization of machining process parameters in powder mixed electro-discharge machining using TOPSIS and grey relational analysis’, Engineering Science and Technology, an International Journal. Vol. 19, pp. 62–70.
[54]
Tsao, C. C. (2009) ‘Grey–Taguchi method to optimize the milling parameters of aluminum alloy’, Int J AdvManufTechnol, Vol. 40, pp. 41–48.
[55]
Tzenga, C. J. et al. (2009) ‘Optimization of turning operations with multiple performance characteristics using the Taguchi method and Grey relational analysis’, Journal of materials processing technology, Vol. 209, pp. 2753–2759.
[56]
Wang, Q., Stockton, D. J. and Baguley, P. (2000) ‘Process cost modeling using neural networks’, International Journal of Production Research, Vol. 38, No. 16, pp. 3811-3821.
[57]
Zain, A. M., Haron, H. and Sharif, S. (2011) ‘Estimation of the minimum machining performance in the abrasive water jet machining using integrated NN-SA’, Expert Systems with Applications, Vol. 38, pp. 8316–8326.
