Online measurement of particle size distribution in the crushing process is critical to reduce particle obstruction and to reduce energy consumption. Nevertheless, commercial systems to determine size distribution do not accurately identify large particles (20–250 mm), leading to particle obstruction, increasing energy consumption, and reducing equipment availability. To solve this problem, an online sensor prototype was designed, implemented, and validated in a copper ore plant. The sensor is based on 2D images and specific detection algorithms. The system consists of a camera (1024p) mounted on the conveyor belt and image processing software, which improves the detection of large particle edges. The algorithms determine the geometry of each particle, from a sequence of digital photographs. For the development of the software, noise reduction algorithms were evaluated and selected, and a routine was designed to incorporate morphological mathematics (erosion, dilation, opening, lock) and segmentation algorithms (Roberts, Prewitt, Sobel, Laplacian–Gaussian, Canny, watershed, geodesic transform). The software was implemented (in MatLab Image Processing Toolbox) based on the 3D equivalent diameter (using major and minor axes, assuming an oblate spheroid). The size distribution adjusted to the Rosin Rammler function in the major axis. To test the sensor capabilities, laboratory images were used, where the results show a precision of 5% in Rosin Rambler model fitting. To validate the large particle detection algorithms, a pilot test was implemented in a large mining company in Chile. The accuracy of large particle detection was 60% to 67% depending on the crushing stage. In conclusion, it is shown that the prototype and software allow online measurement of large particle sizes, which provides useful information for screening equipment maintenance and control of crushers’ open size setting, reducing the obstruction risk and increasing operational availability.
Automatic Hologram Acquisition of Pt Catalyst Nanoparticles on TiO2 Using Particle Detection with Image Processing and AI Classification
