This paper presents a machine vision method for detection and classification of copper ore grains. We proposed a new method that combines both seeded regions growing segmentation and edge detection, where region growing is limited only to grain boundaries. First, a 2D Fast Fourier Transform (2DFFT) and Gray-Level Co-occurrence Matrix (GLCM) are calculated to improve the detection results and processing time by eliminating poor quality samples. Next, detection of copper ore grains is performed, based on region growing, improved by the first and second derivatives with a modified Niblack’s theory and a threshold selection method. Finally, all the detected grains are characterized by a set of shape features, which are used to classify the grains into separate fractions. The efficiency of the algorithm was evaluated with real copper ore samples of known granularity. The proposed method generates information on different granularity fractions at a time with a number of grain shape features.
Moisture of bulk material has a significant impact on energetic efficiency of dry grinding, resultant particle size distribution and particle shape, and conditions of powder transport. As a consequence, moisture needs to be measured or estimated (modelled) in many points. This research investigates mutual relations between material moisture and particle classification process in a grinding installation. The experimental setup involves an inertial-impingement classifier and cyclone being part of dry grinding circuit with electromagnetic mill and recycle of coarse particles. The tested granular material is copper ore of particle size 0–1.25 mm and relative moisture content 0.5–5%, fed to the installation at various rates. Higher moisture of input material is found to change the operation of the classifier. Computed correlation coefficients show increased content of fine particles in lower product of classification. Additionally, drying of lower and upper classification products with respect to moisture of input material is modelled. Straight line models with and without saturation are estimated with recursive least squares method accounting for measurement errors in both predictor and response variables. These simple models are intended for use in automatic control system of the grinding installation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.