Fuzzy forecasting model based method for detecting pulp concentration in ore grinding process of dressing plant

Abstract

The present invention discloses a fuzzy forecasting model based method for detecting pulp concentration in an ore grinding process of a dressing plant. The ore grinding concentration and overflow concentration are predicted and estimated online by using a fuzzy model construction method based on soft computing, a characteristic variable set in a forecasting model is established based on applying an attribute set evaluation metric based on neighborhood decision resolution and a characteristic set selection method on field record data, a fuzzy scheme is established based on applying the fuzzy scheme construction method based on an effective information rate on the field record data, and a prediction rule is obtained by performing fuzzy prediction rule extraction on the field data. By means of the method provided by the present invention, the subjectivity and limitation of a conventional fuzzy modeling method are avoided, a stable and reliable prediction result can be provided for the detection of a key parameter in the ore grinding process of the dressing plant, and a basis is established for the optimization control and process monitoring of the ore grinding process.

Description

【Technical field】 [0001] The invention belongs to the technical field of pulp concentration detection, and relates to online detection of pulp concentration in a grinding and grading system of a concentrator, in particular to a method for detecting the pulp concentration in the grinding process of a concentrator based on a fuzzy prediction model. 【Background technique】 [0002] The wet ball mill closed-circuit grinding classification system is widely used in large-scale mineral processing plants in my country. As the pulp concentration (including grinding concentration and overflow concentration) that represents the key state information of the production process, most of them still pass manual experiments and offline analysis. However, it cannot be directly applied to the optimization control of the grinding process, so that the phenomenon of underload and belly swelling of the grinding mill occurs from time to time during the operation of the grinding and grading system, whi...

AI Technical Summary

Problems solved by technology

Some use the gray relational analysis method to select the auxiliary variables of the pulp concentration prediction model, and build a neural network-based grinding pulp concentration prediction model. In the process of model learning, the numericalization of the characteristics of the problem will inevitably lead to the loss of process variable information, which makes the actual promotion and application of the neural network subject to many restrictions.

Fuzzy modeling uses easy-to-understand language rules and the resulting fuzzy model has good stability and robustness, but in fuzzy modeling, auxiliary variable selection, fuzzy scheme determination and rule set construction are usually based on operator and expert knowledge and experience, which will inevitably produce certain limitations and subjectivity, which will affect the accuracy and generalization ability of the fuzzy prediction model

Moreover, for this kind of multi-dimensional fuzzy model, the rule explosion problem will be encountered, which makes the design and application of the fuzzy model very difficult.

Images