Comparison of vibration visualization methods for classification of chaos based on CNN

다국어 초록 (Multilingual Abstract)

This study assessed methods for visualizing the vibrations for chaotic systems using a time series, fast Fourier transform (FFT), threshold recurrence plot, and unthresholded recurrence plot. The image classification was then performed using CNN, and the accuracy of each visualization method was compared and analyzed. The nonlinear behavior of chaotic systems was examined using the commonly known Van der pol, Rossler, and Duffing equations. The Lyapunov exponent was calculated for each model parameter change to determine the chaos. The classification accuracy was examined for the chaotic signal in each visualization method of the proposed architecture based on VGG 16 using the determined label and image.
The classification accuracy for the chaos of each visualization method is the result of signals mixed randomly five times. FFT analysis showed the highest evaluation result.

참고문헌 (Reference)

1 C. Dong, "Vibration and noise behaviors during stick-slip friction" 67 (67): 2019

2 K. Simonyan, "Very deep convolutional networks for large-scale image recognition" 2014

3 L. Rabiner, "Theory and Applications of Digital Speech Processing" Prentice Hall Press 2010

4 부석준 ; 문세민 ; 조성배, "Short-time Fourier transform 소음맵을 이용한 컨볼루션기반 BSR (Buzz, Squeak, Rattle) 소음 분류" 한국음향학회 37 (37): 256-261, 2018

5 남재현 ; Jaeyoung Kang, "Semi-analytical approch for brake squeal of a rail pad" 대한기계학회 34 (34): 3147-3153, 2020

6 N. Marwan, "Recurrence plots for the analysis of complex systems" 438 (438): 237-329, 2007

7 T. S. Parker, "Practical Numerical Algorithms for Chaotic Systems" Springer Science & Business Media 2012

8 X. Zheng, "Nonlinear instabilities and control of drill-string stick-slip vibrations with consideration of state-dependent delay" 473 : 115235-, 2020

9 W. Serweta, "Mirror hysteresis and Lyapunov exponents of impact oscillator with symmetrical soft stops" 101 : 89-98, 2015

10 W. Serweta, "Lyapunov exponents of impact oscillators with Hertz’s and Newton’s contact models" 89 : 194-206, 2014

11 강재영, "Lyapunov exponent of friction-induced vibration under smooth friction curve" 대한기계학회 32 (32): 3563-3567, 2018

12 B. Zhou, "Learning deep features for discriminative localization" 2921-2929, 2016

13 J. Nam, "Investigation of friction induced vibration in lead screw system using FE model and its experimental validation" 122 : 98-106, 2017

14 Y. Zou, "Identifying complex periodic windows in continuous-time dynamical systems using recurrence-based methods" 20 (20): 043130-, 2010

15 J. Kang, "Flexible heliogyro solar sail under solar radiation pressure and gravitational force" 179 : 186-196, 2021

16 남재현 ; 백종수 ; 도현철 ; 강재영, "Experimental investigation of friction noise on lubricated contact" 대한기계학회 31 (31): 5751-5760, 2017

17 J. P. Zbilut, "Embeddings and delays as derived from quantification of recurrence plots" 171 (171): 199-203, 2018

18 A. Wolf, "Determining Lyapunov exponents from a time series" 16 (16): 285-317, 1985

19 K. He, "Deep residual learning for image recognition" 770-778, 2016

20 J. Y. Kim, "Deep CNN transferred from VAE and GAN for classifying irritating noise in automobile" 452 : 395-403, 2021

21 J. Nam, "Classification of chaotic squeak and rattle vibrations by CNN using recurrence pattern" 21 (21): 8054-, 2021

22 J. Nam, "Classification of chaotic signals of the recurrence matrix using a convolutional neural network and verification through the lyapunov exponent" 11 (11): 77-, 2021

23 F. C. Moon, "Chaotic and Fractal Dynamics: Introduction for Applied Scientists and Engineers" John Wiley and Sons 2008

24 S. Wallot, "Calculation of average mutual information(ami)and false-nearest neighbors(fnn)for the estimation of embedding parameters of multidimensional time series in matlab" 9 : 1679-, 2018

25 J. Kang, "Calculation of Lyapunov exponents in impacted beam on distributed contact" 431 : 295-303, 2018