Using Particle Swarm Optimization Based Neural Network for Modeling of Thrust Force Drilling of PA-6/Nanoclay Nanocomposites

Abstract:

This paper presents a newly approach for modeling thrust force in drilling of PA-6/ Nanoclay Nanocomposites materials, by using Particle Swarm Optimization based Neural Network (PSONN). In this regard, advantages of statistical experimental algorithm technique, experimental measurements, particle swarm optimization and artificial neural network are exploited in an integrated manner. For this purpose, numerous experiments for PA-6 and PA-6/ Nanoclay Nanocomposites are conducted to obtain thrust force values by using drill of high speed steel with point angles and 2mm in diameter. Then, a predictive model for thrust force is created by using PSONN algorithm. Also, the training capacity of PSONN is compared to that of the conventional neural network. The results indicate that nanoclay content on PA-6 polyamide significantly decrease the thrust force. Also, the obtained results for modeling of thrust force have shown very good training capacity of the proposed PSONN algorithm with compared to that of a conventional neural network (BPNN).

• Periodical: Applied Mechanics and Materials (Volumes 34-35)
• Pages: 722-726
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.34-35.722
• Online since: October 2010
• Authors: M. Reza, Soleymani Yazdi, M. Reza Razfar, M. Asadnia
• Keywords: Artificial Neural Network (ANN), Drilling, Modeling, Nanocomposite, Particle Swarm Optimization Algorithm (PSO), Poly Amid 6-Nanoclay

References

[1] J-J. Luo, I. M. Daniel, Characterization and modeling of mechanical behavior of polymer/clay nanocomposites , Composites Science and Technology, Vol. 63 (2003), P. 1607-1616.

DOI: 10.1016/s0266-3538(03)00060-5

[2] FZ. Fang, YC. Liu, On minimum exit-burr in micro cutting, J Micromech Microeng, Vol. 4 (2004), P. 984-988.

DOI: 10.1088/0960-1317/14/7/020

[3] J. Davim, J. Paulo, R. Leonardo, Ant َ◌nio. Festas, A M. Abr, Machinability study on precision turning of PA66 polyamide with and without glass fiber reinforcing, Materials and Design, Vol. 30 (2009), P. 228-234.

DOI: 10.1016/j.matdes.2008.05.003

[4] V G. Dhokia, S. Kumar, P. Vichare, S. T. Newman, R. D. Allen, Surface roughness prediction model for CNC machining of polypropylene. Proc. IMechE Part B: J. Engineering Manufacture, Vol. 222 (2008), P. 137-157.

DOI: 10.1243/09544054jem884

[5] Vimal G. Dhokia, Sanjeev. Kumar, Parag. Vichare, Stephen T. Newman, An intelligent approach for the prediction of surface roughness in ball-end machining of polypropylene, Robotics and Computer-Integrated Manufacturing, Vol. 24 (2008).

DOI: 10.1016/j.rcim.2008.03.019

[6] PG. Benardos, GC. Vosniakos, Prediction of surface roughness in CNC face milling using neural networks and Taguchi's design of experiments. Robot Comput Integr Manuf, Vol. 18 (2002), P. 343-354.

DOI: 10.1016/s0736-5845(02)00005-4

[7] Yu. Jianbo, Wang. Shijin, Xi. Lifeng, Evolving artificial neural networks using an improved PSO and DPSO, Neurocomputing, Vol. 71 (2008), P. 1054-1060.

DOI: 10.1016/j.neucom.2007.10.013

[8] Leandro dos Santos Coelho, Chu-Sheng Lee, Solving economic load dispatch problems in power systems using chaotic and Gaussian particle swarm optimization approaches, Int J Elec Power, Vol. 30 (2008), P. 297-307.

DOI: 10.1016/j.ijepes.2007.08.001

[9] Du. Weilin, Li. Bin, Multi-strategy ensemble particle swarm optimization for dynamic optimization, Inform Sciences, Vol. 178(2008), P. 3096-3109.

DOI: 10.1016/j.ins.2008.01.020

[10] Y.W. Guo, A.R. Mileham, G.W. Owen, P.G. Maropoulos, W. D Li, Operation sequencing optimazation for five-axis prismatic parts using a particle swarm optimization approach, proc. IMechE, Part B: J. Eng-ineering Manufacture, Vol. 223 (2008).

DOI: 10.1243/09544054jem1224

[11] K.W. Chau, Application of a PSO-based neural network in analysis of outcomes of construction claims, Automat Constr, Vol. 16 (2007), P. 642-646.

DOI: 10.1016/j.autcon.2006.11.008

[12] J. Salerno, Using the particle swarm optimization technique to train a recurrent neural model, in: Ninth International Conference on Tools with Artificial Intelligence (ICTAI'97), IEEE Press, (1997).

DOI: 10.1109/tai.1997.632235

[13] C.F. Juang, A hybrid genetic algorithm and particle swarm optimization for recurrent network design, IEEE Trans. Syst. Man Cybernet, Vol. 34 (2004), P. 997-1006.

DOI: 10.1109/tsmcb.2003.818557

[14] A. Guerra. Fábio, Leandro dos S, Coelho. Multi-step ahead nonlinear identification of Lorenz's chaotic system using radial basis neural network with learning by clustering and particle swarm optimization, Chaos, Solitons & Fractals, Vol. 35 (2008).

DOI: 10.1016/j.chaos.2006.05.077

[15] Qing-liang, CHANG., Hua-qiang, ZHOU., and Chao-jiong, HOU. Using particle swarm optimization algorithm in an artificial neural network to forecast the strength of paste filling material, J China Univ Mining & Technol, Vol. 18 (2008), P. 551-555.

DOI: 10.1016/s1006-1266(08)60292-8

[16] v. Kiranyaz, Ince. Turker, Yildirim. Alper, Gabbouj. Moncef, Evolutionary artificial neural networks by multi-dimensional particle swarm optimization Neural Networks, In Press, Corrected Proof, (2009).

DOI: 10.1016/j.neunet.2009.05.013