Online particle size analysis on conveyor belts with dense convolutional neural networks

• Published in: Minerals engineering Vol. 193; p. 108019
• Main Authors: Fu, Yihao, Aldrich, Chris
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.03.2023
• Subjects: Bulk solids characterization; Deep learning; Grinding circuits; Image analysis; Particle size analysis; Semantic labeling; Simple linear iterative clustering; Superpixels; U-net; Watershed; Grinding circuits; Deep learning; Bulk solids characterization; Image analysis; Simple linear iterative clustering; Semantic labeling; U-net; Watershed; Superpixels; Particle size analysis
• ISSN: 0892-6875; 1872-9444
• DOI: 10.1016/j.mineng.2023.108019

•Online analysis of particulate feed in mineral processing is not well established.•Segmentation of images of densely packed particles is a challenging task.•Here, particle boundaries were explicitly included in image segmentation.•The results obtained with a U-net neural network were promising.•Segmentation could be further improved with superpixelation of images. Particle size distributions in ore feed systems, as well as the identification of particles in these feed systems can provide important information in the advanced control of unit operations in mineral processing, such as crushing and grinding circuits. Image analysis has long been considered a promising approach to achieve this, as it is an inexpensive, unobtrusive means of acquiring information rich measurements. It typically requires segmentation of images in order to identify individual particles. This is a challenging task to accomplish reliably, as variable lighting, fines adhering to larger particles or contiguous particles, as well as variable particle sizes and shapes can all compromise the accuracy of traditional algorithms. Image segmentation with deep learning methods have recently been investigated to surmount these difficulties. In this investigation, U-net and U-net with superpixel preprocessing with simple linear iterative clustering (SLIC) are proposed and compared with a traditional watershed algorithm. The U-net approaches were markedly more reliable than the watershed algorithm. In addition, preprocessing of the images with SLIC resulted in further improvement of the results.