Identification of Tool Wear Condition Based on Generalized Fractal Dimensions and BP Neural Network Optimized with Genetic Algorithm

Abstract:

Based on multi-fractal theory, the generalized fractal dimensions of acoustic emission (AE) signals during cutting process were calculated using improved box-counting method. The generalized dimension spectrums of AE signals for different tool wear condition were gained, and the relation between tool wear condition and generalized dimensions was analyzed. Together with cutting process parameters, the generalized fractal dimensions were taken as the input vectors of BP neural network after normalization. The initial weight and bias values of BP neural network which was used to classify the tool wear condition were optimized with Genetic Algorithm. The test results showed that the method can be used effectively for the identification of tool wear condition.

• Periodical: Applied Mechanics and Materials (Volume 318)
• Pages: 71-75
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.318.71
• Online since: May 2013
• Authors: Kai Feng Zhang, Hui Qun Yuan, Peng Nie
• Keywords: BP Neural Network (BPNN), Condition Identification, Generalized Fractal Dimension, Genetic Algorithm (GA), Tool Wear

References

[1] A.G. Rehorn, J. Jin , P.E. Orban, State-of-the-art methods and results in tool condition monitoring: a review, Int J Adv Manuf Technol. 26 (2005) 693-710.

DOI: 10.1007/s00170-004-2038-2

[2] A.A. Kassim, M. Zhu, M.A. Mannan, Tool condition classification using hidden markov model basedon fractal analysis of machined surface textures, Machine Vision and Applications. 17 (2006) 327-336.

DOI: 10.1007/s00138-006-0038-y

[3] B.B. Mandelbrot, Multifractal Measures, Especially for the Geophysicist, PAGEOPH. 131 (1989) 5-42.

DOI: 10.1007/bf00874478

[4] B. Li, P.L. Zhang, Z.J. Wang, et al, Morphological covering based generalized dimension for gear fault diagnosis, Nonlinear Dyn. 67 (2012) 2561-2571.

DOI: 10.1007/s11071-011-0169-1

[5] V. Pitsikalis, P. Maragos, Analysis and classification of speech signals by generalized fractal dimension features, Speech Communication. 51 (2009) 1206-1223.

DOI: 10.1016/j.specom.2009.06.005

[6] R.H. Osuri, S.Chatterjee, S.Chandrashekhar. On-line condition monitoring of tool wear in end milling using acoustic emission, International Journal of Production Research. 29 (1991) 1339 -1353.

DOI: 10.1080/00207549108948014

[7] J. Bhaskaran, M. Murugan, N. Balashanmugam, M. Chellamalai, Monitoring of hard turning using acoustic emission signal, Journal of Mechanical Science and Technology. 26 (2012) 609-615.

DOI: 10.1007/s12206-011-1036-1

[8] L. Olsen, Mixed generalized dimensions of self-similar measures, J. Math. Anal. Appl. 306 (2005) 516-539.

[9] D. Russel, J. Hanson, E. Ott, Dimension of strange attractors, Physical Review Letters. 45 (1980) 175-1178.