A Modeling Method of Grinding Process Based on Neural Network and Evolutionary Computation
A neural network and modeling method technology, applied in the field of iron ore grinding, can solve the problems of complex impact process, increased fluctuation of the particle size of the ground ore, and increased difficulty in the beneficiation process, so as to reduce the adjustment time, improve the real-time performance, The effect of improving the efficiency of grinding production
Active Publication Date: 2020-09-29
NORTHEASTERN UNIV LIAONING
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
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
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.
[0021] A modeling method of grinding process based on neural network and evolutionary computation, such as figure 1 shown, including the following steps:
[0022] Step 1: Collect historical production data during the grinding process, including ball mill time, ball mill water supply and overflow particle size;
[0023] In this embodiment, some historical data of ball mill table hours, ball mill water supply and overflow particle size are shown in Table 1:
[0024] Table 1 Partial historical production data table of the grinding process
[0025]
[0026] Step 2: collect the historical data of ore properties and the most preferred ore particle size; the historical data...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More 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...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05B19/418
CPCG05B19/41885G05B2219/32339Y02P90/02
Inventor 高宪文郝得智王明顺佟俊霖张鼎森刘博健
Owner NORTHEASTERN UNIV LIAONING