[ Article ]

Journal of the Korean Society of Manufacturing Technology Engineers - Vol. 27, No. 3, pp.203-210

ISSN: 2508-5107 (Online)

Print publication date 15 Jun 2018

Received 25 Jan 2018 Revised 26 Mar 2018 Accepted 02 Apr 2018

DOI: https://doi.org/10.7735/ksmte.2018.27.3.203

채터검출을 위한 신경회로망 적용법

유해득^a ; 진도훈^b ; 김종도^c ; 윤문철^a^{, *}

Neural Network Application for Chatter Detection

Hae-Deuk Yu^a ; Do-hun Chin^b ; Jong-Do Kim^c ; Moon-chul Yoon^a^{, *}

aDepartment of Mechanical and Design Engineering, Pukyong National University, 365, Sinseon-ro, Nam-gu, Busan 48547, Korea
bDepartment of Mechanical and Automotive Engineering, Kookje University, 56, Janganut-gil, Pyeongtaek, Gyeonggi-do, 17731, Korea
cCenter of Industrial Cooperation, Jungwon University, 85, Munmu-ro, Goesan-eup, Goesan-gun, Chungbuk-do, 28024, Korea

Correspondence to: ^*Tel.: +82-51-629-6160, Fax: +82-51-629-6150, E-mail address: mcyoon@pknu.ac.kr (Moon Chul Yoon).

Abstract

The end-milling chatter behavior is very complex and is closely related to a non-periodic dynamic property and the end-milling force; therefore, it is very difficult to detect and diagnose chatter using the end-milling force. This paper presents a novel method for detecting chatter in end milling using neural network, such as Generalized regression neural network (GRNN), Radial basis neural network(RBNN) and perceptron regardless of periodic and non-periodic forces. As a pattern criterion variable for target data, stochastic variance and kurtosis are used for the neural network configuration. By comparing the end-milling force histories with stochastic variables in the fundamental end-milling property, the time domain chatter characteristics are well reviewed, and separated and patterned well for chatter detection. These neural network results using stochastic variables show the reliability of chatter detection; furthermore, it can detect the malfunction property in end-milling and can be applied for determining the existence of chatter.

Keywords:

Chatter, GRNN, Kurtosis, Perceptron, RBNN, Variance

Acknowledgments

이 논문은 부경대학교 자율창의학술연구비(2017년) 지원에 의하여 연구되었음.

References

Tlusty, J. and Polacek, M., 1963, The Stability of Machine Tools against Self Excited Vibrations in Machining, Proceedings of the International Research in Production Engineering Conference, Pittsburgh, PA, ASME, New York, 465–474.
Meritt, H. E., 1965, Theory of Self-Excited Machine–Tool Chatter, Transactions of the ASME, Journal of Engineering for Industry 87, 447–454.
Chin, D. H., Son, S. K., Cho, H. D. and Yoon, M. C., 2007, Spectral Analysis of Malfunction Mode in End-Milling, J. of Mechanical Science and Technology, 21, 1637-1643. [https://doi.org/10.1007/BF03177387]
Chin, D. H. and Yoon, M. C., 2006, Time Series Modelling and Spectrum Analysis for Chatter Mode in End-Milling Dynamics, I. J. Advanced Manufacturing Technology, 29, 1125-1133. [https://doi.org/10.1007/s00170-005-0018-9]
Yoon, M. C. and Kim, Y. G., 2004, Cutting Dynamic Force Modelling in End-Milling Operation", J. of Materials Processing Technology, 155, 1383-1389. [https://doi.org/10.1016/j.jmatprotec.2004.04.218]
Yoon, M. C. and Chin D. H., 2005, "Cutting Force Monitoring in the End-Milling Operation for Chatter Detection", Journal of Eng. Manufacturing, 12, 455-466. [https://doi.org/10.1243/095440505X32292]
Ji, Y. H., Kim, J. D., Kim, K. H., Kim, B. T. and Yoon, M. C., 2015, Chatter Detection Using Dynamic Property Variable, Proceedings of the KSMPE Autumn conference, 41.
Yang, J. Y., Kim, B. T. and Yoon, M. C., 2012, Dynamic and Static End-milling Force Analysis According to Workpiece Geometry, J. of KSMPE, 11:4, 13-19.
Ji, Y. H., 2017, The Chatter Detection of End-Milling Force Using Stochastic Variable, Master thesis, Pukyong National University.
Yu, H. D., 2018, Neural Network Application for Chatter Detection, Master thesis, Pukyong National University.
Lee, S. Y., 2016, Simulating Cutting Forces in Milling Machines Using Multi-Layered Neural Networks, J. of KSMTE, 25:4, 271-280. [https://doi.org/10.7735/ksmte.2016.25.4.271]