Neural Network as an Alternative to the Amplitude Spectrum Analysis for Measurement of the Ball Mill Fill Level

Modern intelligent methods for information processing are used to estimate the filling level of the ball mills. This problem has been topical for a long time. Moreover, the increasing number of the used ball mills makes it even more important. The main objective is that the ball mill's functioning mode, which is optimal from the point of view of the energy efficiency, can be reached, if the mill is loaded with the ore as much as possible. In its turn, such a mode may cause an overloading in case of any additional ore supply. This leads to the balls' and ore grain's coarse blowout and, as a result, the mill emergency stopping. As a consequence, the mill downtime results in economic losses. The main aim of this research is to develop a method for processing of the vibration acceleration signal from the ball mill's pin in order to discover the hidden dependencies in it. Such dependencies will allow us to estimate the mills' filling level more effectively, but they cannot be discovered by the classical methods, like spectrum analysis of the signal amplitude. A pilot ball mill is used in the laboratory conditions in order to reach such results. A vibration acceleration sensor is set at its pin. A ball load is changed during experiments. A training set for a neural network is formed as a result of the spectrum analysis of the signal obtained from the sensor. The neural network helped to find a relation between the vibration acceleration spectrum and the ball mill filling level. After the conducted experiments a conclusion can be made that such a network is insensitive to the noise caused by a change of the ball load. This insensitivity is higher in comparison with the methods, which are used as a basis for the conventional vibration-acoustic analyzers.

степень заполнения мельницы, акселерометр, спектральный анализ, шаровая мельница, виброускорение, нейронная сеть, обучение НС, mill fill level, accelerometer, spectrum analysis, ball mill, vibration acceleration, neural network, neural network training process

1. Инструкция по эксплуатации мельниц МШЦУ 5500´6500 № 2615.

2. Андреев С. Е. Дробление, измельчение и грохочение полезных ископаемых. М.: Недра, 1980. 320 с.

3. Улитенко К. Я., Маркин Р. П., Соколов И. В. Виброакустический анализ процессов дробления и измельчения на горно-обогатительных предприятиях // Горный журнал. 2009. № 10. С. 72-76.

4. Jian Tang, Tianyou Chaia, Lijie Zhaoa, etc. Soft sensor for parameters of mill load based on multi-spectral segments PLS submodels and on-line adaptive weighted fusion algorithm // Neurocomputing. 2012. N. 78. P. 38-47.

5. Gugel K., Moon R. M. Automated mill control using vibration signal processing // IEEE Cement Industry Technical Conference, 2007. P. 17-25.

6. Gugel K., Palcios G., Ramirez J., Parra M. Improving ball mill control with modern tools based on digital signal processing technology // IEEE Cement Industry Technical Conference. Dallas, United States. 2003. P. 311-318.

7. Хайкин С. Нейронные сети. М.: ООО И. Д. Вильямс, 2006. 1104 с.

8. Еременко Ю. И., Полещенко Д. А., Глущенко А. И. Синтез системы управления чашевым окомкователем с нейросетевой надстройкой и оценка ее эффективности относительно шаговой системы экстремального управления // Мехатроника. Автоматизация. Управление. 2011. № 10. С. 56-61.

9. Юкио Сато. Без паники! Цифровая обработка сигналов: Пер. с яп. Т. Г. Селиной. М.: Додэка-XXI, 2010. 176 с.

10. Пожарский Ю. М., Полещенко Д. А., Подковыров И. Ю. Определение степени заполнения мельницы мокрого самоизмельчения с применением беспроводных технологий // Горный журнал. 2013. № 2. C. 115-118.

11. Hornick K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximators // Neural Networks. 1989. Vol. 2, № 5. P. 359-366.

12. Cybenko G. Approximation by superposition of a sigmoidal function // Math. Control Systems and Siganls. 1989. № 2. P. 303-314.