Study on Neural Networks Usage to Analyse Correlation between Spectrum of Vibration Acceleration Signal from Pin of Ball Mill and its Filling Level

Abstract:

The question about modern intelligent information processing methods usage for a ball mill filling level evaluation is considered. Vibration acceleration signal has been measured on a mill laboratory model for that purpose. It is made with accelerometer attached to a mill pin. The conclusion is made that mill filling level can not be measured with the help of such signal amplitude only. So this signal spectrum processed by a neural network is used. A training set for the neural network is formed with the help of spectral analysis methods. Trained neural network is able to find the correlation between mill pin vibration acceleration signal and mill filling level. Test set is formed from the data which is not included into the training set. This set is used in order to evaluate the network ability to evaluate the mill filling degree. The neural network guarantees no more than 7% error in the evaluation of mill filling level.

• Periodical: Applied Mechanics and Materials (Volume 770)
• Pages: 540-546
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.770.540
• Online since: June 2015
• Authors: Yuri Eremenko*, Dmitry Poleshchenko, Anton Glushchenko
• Keywords: Acceleration Gage, Mill Feeling Degree, Neural Network, Spectral Analysis, Vibration Acceleration Signal, Wet Self-Grinding Mill

References

[1] V.K. Gupta, S. Sharma, Analysis of ball mill grinding operation using mill power specific kinetic parameters, J. Advanced Powder Technology. 78 (2014) 33–36.

DOI: 10.1016/j.apt.2013.10.003

[2] M.H. Wang, R.Y. Yang, A.B. Yu, DEM investigation of energy distribution and particle breakage in tumbling ball mills, J. Powder Technology. 223 (2012) 83–91.

DOI: 10.1016/j.powtec.2011.07.024

[3] Y. Zhang, Coal level control for coal pulverizer using power current method, J. East China Electric Power. 29(7) (2001) 48–49.

[4] D. Dorzhdamba, I.T. Kimyaev, K. Ya. Ulitenko, Principles of building of the automatic control system of the technological process for comminution of raw materials on the base of vibrating acoustic analyzer for charging VAZM-1 mill, J. Tsvetnye Metally. 10 (2003).

[5] S. Omatu, K. Maruzuki, Y. Rubiayh, Neuro-Control and Its Applications, Springer, London, (1996).

[6] Yu.I. Eremenko, D.A. Poleshchenko, A.I. Glushchenko, et. al., On Estimating the Efficiency of a Neural Optimizer for the Parameters of a PID Controller for Heating Objects Control, J. Automation and Remote Control. 75(6) (2014) 1137-1144.

DOI: 10.1134/s0005117914060137

[7] Yu.I. Eremenko, D.A. Poleshchenko, A.I. Glushchenko, About Heating Plants Control System Developing on Basis of Neural Network Usage for PID-Regulator Parameters Optimization, J. Applied mechanics and materials. 682 (2014) 80-86.

DOI: 10.4028/www.scientific.net/amm.682.80

[8] K. Gugel, R.M. Moon, Automated mill control using vibration signal processing, in: Proceedings of the IEEE Cement Industry Technical Conference, Charleston, 2007, p.17–25.

DOI: 10.1109/citcon.2007.358983

[9] K. Gugel, G. Palacios, J. Ramirez, M. Parra, Improving ball mill control with modern tools based on digital signal processing (DSP) technology, in: Proceedings of the IEEE-IAS/PCA 2003 Cement Industry Technical Conference, Dallas, 2003, p.311–318.

DOI: 10.1109/citcon.2003.1204732

[10] J.W. Cooley, J.W. Tukey, An algorithm for the machine calculation of complex Fourier series, J. Math. Comput. 19 (90) (1965) 297–301.

DOI: 10.1090/s0025-5718-1965-0178586-1

[11] K. Hornik, M. Stinchcombe, H. White, Multilayer feed-forward networks are universal approximators, J. Neural networks. 2(5) (1989) 359-366.

DOI: 10.1016/0893-6080(89)90020-8

[12] Yu.M. Pozharskiy, D.A. Poleshchenko, I. Yu. Podkovyrov, Definition of the filling degree of wet autogenous mill, using the wireless technologies, J. Gorny Zhurnal. 2 (2013) 115-118.