Ore grinding process modeling method based on neural network and evolutionary computation

Abstract

The invention provides an ore grinding process modeling method based on a neural network and evolutionary computation, and relates to the technical field of iron ore grinding. The method comprises thesteps that firstly, a case library is established, and the reasonable ore feeding quantity of a ball grinding mill is retrieved from the case library by adopting a case retrieval method; then througha neural network method, a mathematical model is established during the ore grinding of the ball grinding mill, and a relation among the ore feeding quantity, the water feeding quantity and the ore grinding effect is established; the maximum specific productivity of the ball grinding mill and the optimal size distribution of the grinded ore are taken as optimal objects, combined with actual working conditions, constraint conditions are determined, a group of noninferior solution set is obtained by a non-dominated sorting genetic algorithm with an elitist strategy, and an optimal solution is decided by adopting a TOPSIS algorithm. The provided ore grinding process modeling method based on the neural network and the evolutionary computation has the advantages that the reasonable ore feedingquantity and water feeding quantity are calculated, on the basis of ensuring the particle size of ore, the processing efficiency of the ball grinding mill is increased, and the stability, reliabilityand economy during the production of the ore grinding are improved.

Description

technical field [0001] The invention relates to the technical field of iron ore grinding, in particular to a grinding process modeling method based on neural network and evolutionary calculation. Background technique [0002] Grinding operation is a key link in the metal beneficiation process. The quality of the grinding effect directly affects the effect of the beneficiation. At the same time, the grinding operation is also the main energy consumption and material consumption unit in the beneficiation process. How to control the optimal operation of the process It is one of the keys to the whole beneficiation process. There are many factors affecting the grinding process, and the influencing process of each factor is complicated, so it is difficult to determine the mapping relationship between the ore entering the grinding process and the ore coming out of the grinding process. Moreover, there is a certain lag in the grinding operation, and there is a coupling relationship...

AI Technical Summary

Problems solved by technology

There are many factors that affect the grinding process, and the influence process of each factor is complex, so it is difficult to determine the mapping relationship between the ore that enters the grinding process and the ore that is ground out

Moreover, there is a certain lag in the grinding operation, and there is a coupling relationship between the parameters. At present, most of the grinding operations rely on manual experience for tentative adjustments. It is difficult to give timely and accurate information on the parameters of the ball mill according to different ore properties. Adjustment, and then increase the fluctuation of the particle size of the ground ore, increase the difficulty of the subsequent beneficiation process, and affect the beneficiation result

Images