A study on a new algorithm to optimize ball mill system based on modeling and GA

作者：Wang Heng^*; Jia Min ping; Huang Peng; Chen Zuo liang

来源：Energy Conversion and Management, 2010, 51(4): 846-850.

DOI：10.1016/j.enconman.2009.11.020

• Ball mill
• Neural network
• Genetic algorithm
• Electric energy

Aiming at the disadvantage of conventional optimization method for ball mill pulverizing system, a novel approach based on RBF neural network and genetic algorithm was proposed in the present paper. Firstly, the experiments and measurement for fill level based on vibration signals of mill shell was introduced. Then, main factors which affected the power consumption of ball mill pulverizing system were analyzed, and the input variables of RBF neural network were determined. RBF neural network was used to map the complex non-linear relationship between the electric consumption and process parameters and the non-linear model of power consumption was built. Finally, the model was optimized by genetic algorithm and the optimal work conditions of ball mill pulverizing system were determined. The results demonstrate that the method is reliable and practical. and can reduce the electric consumption obviously and effectively.

• 出版日期2010-4
• 单位东南大学