A Study on the Prediction and Comparison of Processing Using the Artificial Neural Network in Nitinol Electrochemical Machining

Abstract:

Nitinol consists of nickel and titanium. Nitinol is one of the shape memory alloys, which changes the crystal structure at a certain temperature and is restored to a memorized form. Because of these unique features, it is used in medical devices, high precision sensors, and aerospace industries. However, Nitinol is a traditional method of processing, resulting in thermal deformation and residual stress after processing. Therefore, the electrochemical machining (ECM), which does not produce residual stress and thermal deformation, has emerged as an alternative processing technique. This study used artificial neural network (ANN), which are the basis of AI, to replace conventional design of experiments (DOE). This method was shown to be more useful than conventional method of design of experiments (RSM, Taguchi) by applying artificial neural network to electrochamical machining (ECM) and comparing root mean square errors (RMSE).

• Periodical: Key Engineering Materials (Volume 793)
• Pages: 23-28
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.793.23
• Online since: January 2019
• Authors: Woo Jae Song, Eun Sang Lee*
• Keywords: Artificial Neural Network, Electrochemical Machining, Machining Prediction, Nitinol (SMA)

References

[1] Min-Jung Shin, Seung-Yub Baek and Eun-Sang Lee, 2007, A Study for Improving Surface Roughness and Micro-deburring Effect of Nitinol Shape Memory Alloy by Electropolishing,, Journal of the Korean Society of Manufacturing Technology Engineers, Vol. 16, No. 6, p.49~54.

[2] Tae-Hee Shin, Baek-Kyoum Kim, Seung-Yub Baek and Eun-Sang Lee, 2009, The Machining Characteristics of Groove Patterning for Nitinol Shape Memory Alloy Using Electrochemical Machining,, Journal of the Korean Society of Manufacturing Technology Engineers, Vol. 18, No. 6, p.551~557.

[3] Himadri Majumder, Kalipada Maity, 2018, Prediction and optimization of surface roughness and micro-hardness using grnn and MOORA-fuzzy-a MCDM approach for nitinol in WEDM,, Measurement, Vol. 119, p.1~13.

DOI: 10.1016/j.measurement.2018.01.003

[4] Woo-Jae Song and Eun-Sang Lee, 2017, A Study on the Optimal Conditions of Hole Machining of Microplate by Application of Response Surface Methodology in Wire-Pulse Electrochemical Machining,, Journal of the Korean Society of Manufacturing Process Engineers, Vol. 16, No. 5, p.141~149.

DOI: 10.14775/ksmpe.2017.16.5.141

[5] Da-som JIN, Kwang-ho CHUN, Eun-sang LEE, 2017, Analysis of the current density characteristics in through-mask electrochemical micromachining (TMEMM) for fabrication of micro-hole arrays on invar alloy film, ,Chinese Journal of Aeronautics, Volume 30, No. 3, pp.1231-1241.

DOI: 10.1016/j.cja.2016.10.021

[6] H.R. Gurupavan, T.M. Devegowda, H.V. Ravindra, G. Ugrasen, 2017, Estimation of Machining Performances in WEDM of Aluminium based Metal Matrix Composite Material using ANN, ,Materials Today: Proceedings, Volume 4, Issue 9, pp.10035-10038.

DOI: 10.1016/j.matpr.2017.06.316

[7] Jae-Kyum Kim, Byeoung-Do Kim, Dong-Weon Yoon and Jun-Won Choi, 2016, Deep Neural Network-based Automatic Modulation Classification Technique,, The Journal of Korean Institute of Information Technology, Vol. 14, No. 12, p.107~115.

DOI: 10.14801/jkiit.2016.14.12.107