Modeling and Multi-Objective Optimization of Operating Parameters in Semi Autogenous Grinding Mill

Mill optimization has many economic benefits. Semi autogenous grinding mills are complex multi-input and multi-output systems that are difficult to optimize. The purpose of this study is to examine the functions of the wear of lifters, power draw and product size distribution. The design variables are mill speed, ball filling, slurry concentration and slurry filling. To achieve this aim, a pilot mill was carried out. The experimental results used to create training cases for the artificial neural network and then the optimization of the design variables is conducted by multi-objective genetic algorithm. Level diagrams are then used to select the best solution from the Pareto front. Finally, the response surface methodology has been used to study the interaction between the design parameters. The results showed that the best grinding occurs at 70-80% of the critical speed and ball filling of 15-20%. Optimized grinding was observed when the slurry volume was 1-1.5 times of the ball bed voidage volume and the slurry concentration was 60-70%. Additionally, variables with the largest effect on the process are mill speed and ball filling.