Ore granularity grading method and system based on image and deep neural network

Abstract

The invention relates to an ore granularity grading method and a system based on an image and a deep neural network, and the system comprises a crusher, a belt conveyor and a control system, and is characterized in that a camera electrically connected with the control system is arranged above the belt conveyor; the method comprises the following steps: 1) collecting ore image data by the camera and transmitting the data to a control system, and constructing an ore granularity training sample set by a computer; 2) performing image preprocessing on the training sample set to enhance the image and reduce the noise; 3) optimizing the training sample set to obtain a model; 4) performing ore granularity segmentation on the ore image by applying the obtained optimized U-NET network model; and 5)performing granularity statistical calculation on the image segmentation result to obtain ore diameter and granularity distribution. The method has the advantages that the ore granularity can be detected and displayed on line in real time, and a foundation is laid for efficient production of an automatic control crusher.

Description

technical field [0001] The invention belongs to the technical field of mineral processing and detection, and in particular relates to an ore particle size classification method and system based on images and deep neural networks. Background technique [0002] The particle size of the broken product is an important parameter to evaluate the crushing effect of the crusher. It is usually determined by the sieve size of a certain sieve through which 95% of the broken product (80% in foreign countries) passes through. At present, the particle size of crushed products is mostly determined by inefficient, off-line manual screening methods. The biggest shortcoming of this detection method is that it is not synchronized with the production, and it is difficult to control and adjust the production of the crusher online in time according to the particle size of the crushed product, so that the automatic control of the production of the crusher cannot be realized. In recent years, digi...

AI Technical Summary

Problems solved by technology

The utility model patent "A Conveyor Belt Ore Granularity Image Acquisition Equipment" proposes a hardware system, but does not involve software algorithms; the invention patent "An Ore Granularity Detection Technology Based on Multivariate and Multi-Scale Entropy" proposes an image processing algorithm. However, complex feature extraction processes such as region extraction, boundary extraction, and image segmentation are required

Images