Laboratoř integrace procesů

Browse

Now showing 1 - 5 of 16

A waste separation system based on sensor technology and deep learning: A simple approach applied to a case study of plastic packaging waste
(ELSEVIER SCI LTD, 2024-04-15) Pučnik, Rok; Dokl, Monika; Fan, Yee Van; Vujanović, Annamaria; Novak Pintarič, Zorka; Aviso, Kathleen B.; Tan, Raymond R; Pahor, Bojan; Kravanja, Zdravko; Čuček, Lidija
Plastic waste pollution is a challenging and complex issue caused mainly by high consumption of single-use plastics and the linear economy of "extract-make-use-throw". Improvements in recycling efficiency, behaviour changes, circular business models, and a more precise waste management system are essential to reduce the volume of plastic waste. This paper proposes a simplified conceptual model for a smart plastic waste separation system based on sensor technology and deep learning (DL) to facilitate recovery and recycling. The proposed system could be applied either at the source (in a smart waste bins) or in a centralised sorting facility. Two smart separation systems have been investigated: i) the one utilising 6 sensors (near-infrared (NIR), humidity, temperature, CO2, CH4, and a laser profile sensor) and ii) the one with an RGB camera to separate packaging materials based on their composition, size, cleanliness, and appearance. Simulations with a case study showed that for a camera-based sorting, Inception-v3, a DL model based on convolution neural networks (CNN), achieved the best overall accuracy (78%) compared to ResNet-50, MobileNet-v2, and DenseNet-201. In addition, the separation resulted in a higher number of misclassified items in bins, as it focused solely on appearance rather than material composition. Sensor-based sorting faced limitations, particularly with dark colouration and organic matter entrapment. Combining the information from sensors and cameras could potentially mitigate the limitations of each individual method, thus resulting in higher purity of the separated fractions.
Application of Machine Learning and Neural Networks to Predict the Yield of Cereals, Legumes, Oilseeds and Forage Crops in Kazakhstan
(MDPI, 2023-06-01) Sadenova, Marzhan; Beisekenov, Nail; Varbanov, Petar Sabev; Pan, Ting
The article provides an overview of the accuracy of various yield forecasting algorithms and offers a detailed explanation of the models and machine learning algorithms that are required for crop yield forecasting. A unified crop yield forecasting methodology is developed, which can be adjusted by adding new indicators and extensions. The proposed methodology is based on remote sensing data taken from free sources. Experiments were carried out on crops of cereals, legumes, oilseeds and forage crops in eastern Kazakhstan. Data on agricultural lands of the experimental farms were obtained using processed images from Sentinel-2 and Landsat-8 satellites (EO Browser) for the period of 2017-2022. In total, a dataset of 1600 indicators was collected with NDVI and MSAVI indices recorded at a frequency of once a week. Based on the results of this work, it is found that yields can be predicted from NDVI vegetation index data and meteorological data on average temperature, surface soil moisture and wind speed. A machine learning programming language can calculate the relationship between these indicators and build a neural network that predicts yield. The neural network produces predictions based on the constructed data weights, which are corrected using activation function algorithms. As a result of the research, the functions with the highest prediction accuracy during vegetative development for all crops presented in this paper are multi-layer perceptron, with a prediction accuracy of 66% to 99% (85% on average), and polynomial regression, with a prediction accuracy of 63% to 98% (82% on average). Thus, it is shown that the use of machine learning and neural networks for crop yield prediction has advantages over other mathematical modelling techniques. The use of machine learning (neural network) technologies makes it possible to predict crop yields on the basis of relevant data. The individual approach of machine learning to each crop allows for the determination of the optimal learning algorithms to obtain accurate predictions.
Decomposition and fragmentation of conventional and biobased plastic wastes in simulated and real aquatic systems
(Springer Nature, 2024-07-16) Plohl, Olivija; Fras Zemljič, Lidija; Erjavec, Alen; Sep, Noemi; Čolnik, Maja; Fan, Yee Van; Škerget, Mojca; Vujanović, Annamaria; Čuček, Lidija; Volmajer Valh, Julija
Plastics play a crucial role in our daily lives. The challenge, however, is that they become waste and contribute to a global environmental problem, increasing concerns about pollution and the urgent need to protect the environment. The accumulation and fragmentation of plastic waste, especially micro- and nanoplastics in aquatic systems, poses a significant threat to ecosystems and human health. In this study, the decomposition and fragmentation processes of conventional and biobased plastic waste in simulated water bodies (waters with different pH values) and in real water systems (tap water and seawater) are investigated over a period of one and six months. Three types of plastic were examined: thermoplastic polyethylene terephthalate and thermoset melamine etherified resin in the form of nonwovens and biobased polylactic acid (PLA) in the form of foils. Such a comprehensive study involving these three types of plastics and the methodology for tracking degradation in water bodies has not been conducted before, which underlines the novelty of the present work. After aging of the plastics, both the solid fraction and the leachate in the liquid phase were carefully examined. The parameters studied include mass loss, structural changes and alterations in functional groups observed in the aged plastics. Post-exposure assessment of the fragmented pieces includes quantification of the microplastic, microscopic observations and confirmation of composition by in situ Attenuated Total Reflectance Fourier Transform Infrared Spectroscopy. The leachate analysis includes pH, conductivity, turbidity, total carbon and microplastic size distribution. The results highlight the importance of plastic waste morphology and the minor degradation of biobased PLA and show that microfibers contribute to increased fragmentation in all aquatic systems and leave a significant ecological footprint. This study underlines the crucial importance of post-consumer plastic waste management and provides valuable insights into strategies for environmental protection. It also addresses the pressing issue of plastic pollution and provides evidence-based measures to mitigate its environmental impact.
Review of Developments in Plate Heat Exchanger Heat Transfer Enhancement for Single-Phase Applications in Process Industries
(MDPI, 2023-07-30) Arsenyeva, Olga; Tovazhnyansky, Leonid; Kapustenko, Petro; Klemeš, Jiří; Varbanov, Petar Sabev
A plate heat exchanger (PHE) is a modern, effective type of heat transfer equipment capable of increasing heat recuperation and energy efficiency. For PHEs, enhanced methods of heat transfer intensification can be further applied using the analysis and knowledge already available in the literature. A review of the main developments in the construction and exploration of PHEs and in the methods of heat transfer intensification is presented in this paper with an analysis of the main construction modifications, such as plate-and-frame, brazed and welded PHEs. The differences between these construction modifications and their influences on the thermal and hydraulic performance of PHEs are discussed. Most modern PHEs have plates with inclined corrugations on their surface that create a strong, rigid construction with multiple contact points between the plates. The methods of PHE exploration are mostly experimental studies and/or CFD modelling. The main corrugation parameters influencing PHE performance are the corrugation inclination angle in relation to the main flow direction and the corrugation aspect ratio. Optimisation of these parameters is one way to enhance PHE performance. Other methods of heat transfer enhancement, including improving the form of the plate corrugations, use of nanofluids and active methods, are considered. Future research directions are proposed, such as improving fundamental understanding, developing new corrugation shapes and optimisation methods and area and cost estimations.
Oxyfuel Combustion Makes Carbon Capture More Efficient
(AMER CHEMICAL SOC, 2024-01-10) Fózer, Dániel; Mizsey, Peter; Varbanov, Petar Sabev; Szanyi, Ágnes; Talei, Saeed
Fossil energy carriers cannot be totally replaced, especially if nuclear power stations are stopped and renewable energy is not available. To fulfill emission regulations, however, points such as emission sources should be addressed. Besides desulfurization, carbon capture and utilization have become increasingly important engineering activities. Oxyfuel technologies offer new options to reduce greenhouse gas emissions; however, the use of clean oxygen instead of air can be dangerous in the case of certain existing technologies. To replace the inert effect of nitrogen, carbon dioxide is mixed with oxygen gas in the case of such air combustion processes. In this work, the features of carbon capture in five different flue gases of air combustion and such oxyfuel combustion where additional carbon dioxide is mixed with clean oxygen are studied and compared. The five different flue gases originate from the gas-fired power plant, coal-fired power plant, coal-fired combined heat and power plant, the aluminum production industry, and the cement manufacturing industry. Monoethanolamine, which is an industrially preferred solvent for carbon dioxide capture from gas streams at low pressures, is selected as an absorbent, and the same amount of carbon dioxide is captured; that is, always that amount of carbon dioxide is captured, which is the result of the fossil combustion process. ASPEN Plus is used for mathematical modeling. The results show that the oxyfuel combustion cases need significantly less energy, especially at high carbon dioxide removal rates, e.g., higher than 90%, than that of the air combustion cases. The savings can even be as high as 84%. Moreover, 100% carbon capture was also be completed. This finding can be due to the fact that in the oxyfuel combustion cases, the carbon dioxide concentration is much higher than that of the air combustion cases because of the inert carbon dioxide and that higher carbon dioxide concentration results in a higher driving force for the mass transfer. The oxyfuel combustion processes also show another advantage over the air combustion processes since no nitrogen oxides are produced in the combustion process.

Browse

Recent Submissions