Detection of working status during milling process based on vibration - an application of Neural network
Keywords:
Milling status, Vibration, Neural network, Batch training, Genetic AlgorithmAbstract
In this research, a Neural Network was used to defy whether the cutting tool of milling is actually working (i.e., milling) or not (i.e., idling) based on the vibration of 3 axes. Data harvested during experiments were analyzed and used in batch learning. Previous works showed the result of up to 93% classification. Our goal is to investigate the data and reach a higher performance. Therefore, the NN is adopted to recognize the milling status and is implemented by Matlab. Moreover, Genetic Algorithm was used to optimize the NN topology including three parameters: number of tapped delay parameters, number of Fast Fourier Transform (FFT) coefficients, and number of hidden neurons. A preferable recognition rate of 99.6% was achieved.
References
J. V. Abellan-Nebot and F. R. Subirón, "A review of machining monitoring systems based on artificial intelligence process models," The International Journal of Advanced Manufacturing Technology, vol. 47, pp. 237-257, 2010.
P. N. Botsaris and J. A. Tsanakas, "State-of-the-art in methods applied to tool condition monitoring (TCM) in unmanned machining operations: a review," in Proceedings of the International Conference of COMADEM, 2008, pp. 73-87.
C. Lauro, L. Brandão, D. Baldo, R. Reis, and J. Davim, "Monitoring and processing signal applied in machining processes–A review," Measurement, vol. 58, pp. 73-86, 2014.
T.-K. Chung, P.-C. Yeh, H. Lee, C.-M. Lin, C.-Y. Tseng, W.-T. Lo, et al., "An attachable electromagnetic energy harvester driven wireless sensing system demonstrating milling-processes and cutter-wear/breakage-condition monitoring," Sensors, vol. 16, p. 269, 2016.
J. Bishop and R. Mitchell, "Neural networks-an introduction," in IEE Colloquium on Neural Networks for Systems: Principles and Applications, 1991, pp. 1/1-1/3.
N. Ambhore, D. Kamble, S. Chinchanikar, and V. Wayal, "Tool condition monitoring system: A review," Materials Today: Proceedings, vol. 2, pp. 3419-3428, 2015.
G. Zhang, B. E. Patuwo, and M. Y. Hu, "Forecasting with artificial neural networks:: The state of the art," International journal of forecasting, vol. 14, pp. 35-62, 1998.
J. Friedman, T. Hastie, and R. Tibshirani, "The elements of statistical learning" vol. 1: Springer series in statistics New York, 2001.
K. D. Theja, G. H. Gowd, and S. Kareemulla, "Prediction & optimization of end milling process parameters using artificial neural networks," International Journal of Emerging Technology and Advanced Engineering, vol. 3, pp. 117-122, 2013.
C.-X. J. Feng, Z.-G. S. Yu, U. Kingi, and M. P. Baig, "Threefold vs. fivefold cross validation in onehidden-layer and two-hidden-layer predictive neural network modeling of machining surface roughness data," Journal of manufacturing systems, vol. 24, pp. 93-107, 2005.
V. M. Souza, D. F. Silva, and G. E. Batista, "Extracting texture features for time series classification," in 2014 22nd International Conference on Pattern Recognition, 2014, pp. 1425-1430.
C.-C. Chang and C.-J. Lin, "LIBSVM: A library for support vector machines," ACM transactions on intelligent systems and technology (TIST), vol. 2, pp. 1-27, 2011.
S. Karsoliya, "Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture," International Journal of Engineering Trends and Technology, vol. 3, pp. 714-717, 2012.
