ANN and RSM Modeling Methods for Predicting Material Removal Rate and Surface Roughness during WEDM of Ti50Ni40Co10 Shape Memory Alloy

ANN and RSM Modeling Methods for Predicting Material Removal Rate and Surface Roughness during WEDM of Ti50Ni40Co10 Shape Memory Alloy

Hargovind Soni S. Narendranath M. R. Ramesh 

Department of Mechanical Engineering, National Institute of Technology Karnataka, India

Corresponding Author Email: 
hargovindsoni2002@gmail.com, narenbayalu@gmail.com, ramesdmt@gmail.com
Page: 
435-443
|
DOI: 
https://doi.org/10.18280/ama_a.540304
Received: 
30 December 2017
|
Accepted: 
5 January 2018
|
Published: 
30 September 2017
| Citation

OPEN ACCESS

Abstract: 

Present study exhibits the comparison between experimental and predicted values. Where response surface method (RSM) and artificial neural network (ANN) were used as predictor for the prediction of wire electro discharge machining (WEDM) responses such as the material removal rate (MRR) and surface roughness (SR) during the machining of Ti50Ni40Co10 shape memory alloy. It has been noticed from the literature survey that pulse on time and servo voltage are most important process parameters for the machining of TiNiCo shape memory alloy, hence there are five levels of these process parameters were chosen for the present study. For the present study selected alloy has been developed through vacuum arc melting and L-25 orthogonal array has been created by using Taguchi design of experiment (DOE) for experimental plan. During the present study ANN predicted values have been found to very close to experimental values compare to RSM predicted values, hence it can be say that ANN predictor gives more accurate values compare to RSM predicted values.

Keywords: 

Artificial neural network, Response surface methodology, Wire electric discharge machining, Ti50Ni40Co10 shape memory alloy.

1. Introduction
2. Materials and Methods
3. Results and Discussion
4. Conclusion
Acknowledgment

This work was supported by the Department of Science and Technology (DST) Government of India project reference no. SB/S3/MMER/0067/2013. Authors would like to thank DST for its funding support.

  References

1. S. Dadbakhsh, M. Speirs, J. Van Humbeeck, J.-P. Kruth, Laser additive manufacturing of bulk and porous shape-memory NiTi alloys: From processes to potential biomedical applications, 2016, MRS Bull., vol. 41, no. 10, pp. 765–774.

2. T. Buasri, H. Shim, M. Tahara, T. Inamura, K. Goto, H. Kanetaka, Y. Yamabe-Mitarai, H. Hosoda, Mechanical and Superelastic Properties of Au-51Ti-18Co Biomedical Shape Memory Alloy Heat-Treated at 1173 K to 1373 K, 2016, Adv. Sci. Technol., vol. 97, pp. 141–146.

3. Z. Lekston, D. Stroz, M. J. Drusik-Pawlowska, Preparation and characterization of nitinol bone staples for cranio-maxillofacial surgery, 2012, J. Mater. Eng. Perform., vol. 21, no. 12, pp. 2650–2656.

4. C. Prakash, H. K. Kansal, B. S. Pabla, S. Puri, Experimental investigations in powder mixed electric discharge machining of Ti–35Nb–7Ta–5Zrβ-titanium alloy, 2017 Mater. Manuf. Process., vol. 32, no. 3, pp. 274–285.

5. M. A. Al-Ahmari, M. S. Rasheed, M. K. Mohammed, T. Saleh, A Hybrid Machining Process Combining Micro-EDM and Laser Beam Machining of Nickel–Titanium-Based Shape Memory Alloy, 2015, Mater. Manuf. Process., vol. 31, no. 4, pp. 447–455.

6. H. Soni, N. Sannayellappa, R. Motagondanahalli Rangarasaiah, An experimental study of influence of wire electro discharge machining parameters on surface integrity of TiNiCo shape memory alloy, 2017, J. Mater. Res., Vol. 32, no. 16,  pp. 3200-3208.

7. G. Ugrasen, H. V. Ravindra, G. V. N. Prakash, R. Keshavamurthy, Estimation of Machining Performances Using MRA, GMDH and Artificial Neural Network in Wire EDM of EN-31, 2014, Procedia Mater. Sci., vol. 6, no. Icmpc, pp. 1788–1797.

8. P. Shandilya, P. K. Jain, N. K. Jain, RSM and ANN modeling approaches for predicting average cutting speed during WEDM of SiCp/6061 Al MMC, 2013, Procedia Eng., vol. 64, pp. 767–774. 

9. E. Portillo Perez, M. Marcos, I. Cabanes, A. Zubizarreta, J. A. Sánchez, “ANN for interpolating instability trends in WEDM,” 2008, IFAC Proc. Vol., vol. 17, no. 1 PART 1, pp. 2230–2235.

10. M. Manjaiah, S. Narendranath, S. Basavarajappa, V. N. Gaitonde, Effect of electrode material in wire electro discharge machining characteristics of TiNiCu shape memory alloy, 2015, Precis. Eng., vol. 41, no. April, pp. 68–77.

11. N. Sharma, R. Khanna, R. D. Gupta, R. Sharma, Modeling and multiresponse optimization on WEDM for HSLA by RSM, 2013, Int. J. Adv. Manuf. Technol., vol. 67, no. 9–12, pp. 2269–2281.

12. R. Khanna and H. Singh, Comparison of optimized settings for cryogenic-treated and normal D-3 steel on WEDM using grey relational theory, 2016, Proc. Inst. Mech. Eng. Part L J. Mater. Des. Appl., vol. 230, no. 1, pp. 219–232.