Journal
MINERALS ENGINEERING
Volume 23, Issue 9, Pages 720-730Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.mineng.2010.05.001
Keywords
Comminution; Grinding; Artificial intelligence; Modeling
Funding
- National High Technology Research and Development Program of China [2006AA060202]
- National Science Foundation of China [60534010]
- Ministry of Education of China [B08015]
- Research Foundation of Ministry of Education of China [308007]
Ask authors/readers for more resources
Real-time measurement of the mill load is the key to improve the production capacity and energy efficiency for the grinding process. In this paper, experimental analysis of the wet mill load based on the vibration signals of the laboratory-scale ball mill shell is presented. A series of experiments are conducted to investigate the vibration characteristics corresponding to different grinding conditions such as dry grinding, wet grinding and water grinding. The power spectral density of the vibration signals is systematically interpreted. Experimental results show that the rheological properties of the pulp affect the amplitude and frequency of the vibration signal. The most important conclusion is that the frequency range of the shell vibration of the laboratory wet mill can be divided into three parts, namely natural frequency band, main impact frequency band and secondary impact frequency band. Finally, soft-sensor models between vibration signal and mill operating parameters of mill load are established using genetic algorithm-partial least square (GA-PLS) technology. After more work on industry scale ball mill is done, the soft-sensor modeling based on the mill shell vibration for operating parameters of mill load will improve the performance of the ball mill in the grinding process. (C) 2010 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available