Image data extraction and neural network modeling-based platinum flotation grade estimation method

Abstract

The invention relates to an image data extraction and neural network modeling-based platinum flotation grade estimation method. The method comprises the following steps: acquiring the correlation degrees between six variables of aeration rate, pulp density, a collecting agent, an activating agent, a foaming agent and an inhibitor and flotation grade and recovery rate by an variable experiment; carrying out collection and pretreatment on a platinum foam image; extracting five image data of energy, entropy, inertia, homogeneity and gray correlation from four tolerant feature images such as gray level images, histogram equalization, contrast enhancement of images and image binarization obtained by pretreatment; and building a multi-layer perceptron neural network model comprising a three-node input layer, a hidden layer and a dual-node output layer. According to the image data extraction and neural network modeling-based platinum flotation grade estimation method provided by the invention, flotation grade and recovery rate are effectively estimated through the foam image, and the target of monitoring grade and recovery rate in the flotation process in real time is achieved.

Description

technical field [0001] The invention relates to the field of mineral separation, in particular to a platinum flotation grade estimation method based on image data extraction and neural network modeling. Background technique [0002] With the development of science and technology, the requirements for the automatic monitoring technology of various parameters in the beneficiation process are getting higher and higher, and many disadvantages of the traditional method are gradually emerging. Traditional monitoring technologies mainly include: fluorescence analysis and particle size analyzer, which can obtain product grade in a short time. The disadvantages of the traditional method mainly include: the design and development of related equipment is not practical, the error of detection data is large, the service life of the sensor is short due to the poor beneficiation environment, and the maintenance cost of the control system is high. [0003] Artificial neural network (ANN), ...

AI Technical Summary

Problems solved by technology

The disadvantages of the traditional method mainly include: the design and development of related equipment is not practical, the error of detection data is large, the service life of the sensor is short due to the poor beneficiation environment, and the maintenance cost of the control system is high

Images