GridSort: Image-based Optical Bulk Material Sorting Using Convolutional LSTMs

Medientyp: Sonstige Veröffentlichung; E-Artikel

Titel: GridSort: Image-based Optical Bulk Material Sorting Using Convolutional LSTMs

Beteiligte: Reith-Braun, Marcel [Verfasser:in]; Bauer, Albert [Verfasser:in]; Staab, Maximilian [Verfasser:in]; Pfaff, Florian [Verfasser:in]; Maier, Georg [Verfasser:in]; Gruna, Robin [Verfasser:in]; Längle, Thomas [Verfasser:in]; Beyerer, Jürgen [Verfasser:in]; Kruggel-Emden, Harald [Verfasser:in]; Hanebeck, Uwe D. [Verfasser:in]

Erschienen: International Federation of Automatic Control, 2024-02-21

Sprache: Englisch

DOI: https://doi.org/10.5445/IR/1000168675; https://doi.org/10.1016/j.ifacol.2023.10.971

ISSN: 2405-8963

Schlagwörter: Monitoring of product quality and control performance ; DATA processing & computer science ; Neural networks in process control ; Machine learning methods and applications ; Artificial intelligence in mining ; minerals and metals ; Process monitoring and fault diagnosis

Entstehung:

Anmerkungen: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.

Beschreibung: Optical sorters separate particles of different classes by first detecting them while they are transported, e.g., on a conveyor belt, and subsequently bursting out particles of undesired classes using compressed air nozzles. Currently, the most promising results are achieved by predictive tracking, a multitarget tracking approach based on extracted midpoints from area-scan camera images that analyzes the particles’ motion and activates the nozzles accordingly. However, predictive tracking requires expert knowledge for setup and preceding object detection. Moreover, particle shapes are only considered implicitly, and the need to solve an association problem rises the computational complexity of the algorithm. In this paper, we present GridSort, an image-based approach that forecasts the scene at the nozzle array using a convolutional long short-term memory neural network and subsequently extracts nozzle activations, thus circumventing the aforementioned weaknesses. We show how GridSort can be trained in an unsupervised fashion and evaluate it using a coupled discrete element–computational fluid dynamics simulation of an optical sorter. We compare our method with predictive tracking in terms of sorting accuracy and demonstrate that it is an easy-to-apply alternative while achieving state-of-the-art results.

Zugangsstatus: Freier Zugang

Nur in Feld suchen:

Zuletzt gesuchte Begriffe: