Implementation and evaluation of a real-time capable approach to sensor-based sorting using CNNs© Lehrstuhl für Abfallverwertungstechnik und Abfallwirtschaft der Montanuniversität Leoben (12/2024)
In state-of-the-art optical sorting, engineered image processing algorithms are commonly used to identify materials. However, for complex material textures and high- ensity material streams, these approaches are often unable to maintain the desired sorting quality. Convolutional neural networks (CNNs) have been proven to outperform such approaches in their ability to classify objects in images.
I-STEP – A Case Study: Machine Learning Powered Condition Monitoring of a Linear Motion Industrial Vibrating Screen© Lehrstuhl für Abfallverwertungstechnik und Abfallwirtschaft der Montanuniversität Leoben (12/2024)
Vibrating Screens, crucial in mineral and waste processing industries, usually lack adequate condition monitoring to assess condition states or predict machine errors. Addressing this issue, IFE Aufbereitungstechnik GmbH and its partners are developing "i-STEP," a digitalization solution potentially integrating any market-available sensor for a customizable, plant- wide monitoring platform. Thus far, a vibration sensor, "SES" has been developed to specifically measure oscillation patterns of vibrating screens, which is the main focus of this research.
The Allegory of Stupidity and Waste© Lehrstuhl für Abfallverwertungstechnik und Abfallwirtschaft der Montanuniversität Leoben (12/2024)
This paper on the allegory of stupidity and waste is a more or less daring view on tomorrow’s capabilities in global waste management. A society facing seemingly unresolvable ecological challenges seems to be immune to its own overconsumption.
Polymer Differentiation with Computed Tomography: Opportunities and Limitations© Lehrstuhl für Abfallverwertungstechnik und Abfallwirtschaft der Montanuniversität Leoben (12/2024)
In the context of polymer recycling, differentiation and analysis of various polymer types are crucial for effective material separation and reuse. This study explores the effectiveness of computed tomography (CT) in distinguishing between different types of polymers based on their density and elemental composition, facilitating more efficient recycling processes.
De-oiling of grinding sludge: What is the potential of mechanical de-oiling
by a centrifuge?© Lehrstuhl für Abfallverwertungstechnik und Abfallwirtschaft der Montanuniversität Leoben (12/2024)
Grinding sludge is a waste flow emerging from semi-finished products brought to their near-net-shape dimensions by grinding. In the grinding process, up to 50 wt% of the workpiece can be grinded off (Hagedorn et al. 2022). A lubricant is constantly sprayed onto the contact point between grinding tool and workpiece to reduce heat development, to remove the emerging metal chips and to reduce friction (Klocke 2018).
Value Chain Optimization for Metal Recycling Processes through Probabilistic Modeling© Lehrstuhl für Abfallverwertungstechnik und Abfallwirtschaft der Montanuniversität Leoben (12/2024)
Optimizing the value chain in metal recycling processes presents significant challenges due to the complex nature of defining processes and the limited availability of sensor technologies capable of continuous monitoring (Golev & Corder 2016). Metal recycling remains at the forefront of industries advancing through expert knowledge and process simulation (Reuter et al. 2013).