TY - JOUR
T1 - Prediction of Flotation Deinking Performance
T2 - A Comparative Analysis of Machine Learning Techniques
AU - Gavrilović, Tamara
AU - Despotović, Vladimir
AU - Zot, Madalina Ileana
AU - Trumić, Maja S.
N1 - Funding:
This research was partly funded by the Ministry of Education, Science and Technological Development of the Republic of Serbia, within the funding of the scientific research work at the University of Belgrade, Technical Faculty in Bor [grant numbers 451–03-65/2024–03/200131]
Publisher Copyright:
© 2024 by the authors.
PY - 2024/10/6
Y1 - 2024/10/6
N2 - Flotation deinking is one of the most widely used techniques for the separation of ink particles from cellulose fibers during the process of paper recycling. It is a complex process influenced by a variety of factors, and is difficult to represent and usually results in models that are inconvenient to implement and/or interpret. In this paper, a comprehensive study of several machine learning methods for the prediction of flotation deinking performance is carried out, including support vector regression, regression tree ensembles (random forests and boosting) and Gaussian process regression. The prediction relies on the development of a limited dataset that assumes representative data samples obtained under a variety of laboratory conditions, including different reagents, pH values and flotation residence times. The results obtained in this paper confirm that the machine learning methods enable the accurate prediction of flotation deinking performance even when the dataset used for training the model is limited, thus enabling the determination of optimal conditions for the paper recycling process, with only minimal costs and effort. Considering the low complexity of the Gaussian process regression compared to the aforementioned ensemble models, it should be emphasized that the Gaussian process regression gave the best performance in estimating fiber recovery (R2 = 97.77%) and a reasonable performance in estimating the toner recovery (R2 = 86.31%).
AB - Flotation deinking is one of the most widely used techniques for the separation of ink particles from cellulose fibers during the process of paper recycling. It is a complex process influenced by a variety of factors, and is difficult to represent and usually results in models that are inconvenient to implement and/or interpret. In this paper, a comprehensive study of several machine learning methods for the prediction of flotation deinking performance is carried out, including support vector regression, regression tree ensembles (random forests and boosting) and Gaussian process regression. The prediction relies on the development of a limited dataset that assumes representative data samples obtained under a variety of laboratory conditions, including different reagents, pH values and flotation residence times. The results obtained in this paper confirm that the machine learning methods enable the accurate prediction of flotation deinking performance even when the dataset used for training the model is limited, thus enabling the determination of optimal conditions for the paper recycling process, with only minimal costs and effort. Considering the low complexity of the Gaussian process regression compared to the aforementioned ensemble models, it should be emphasized that the Gaussian process regression gave the best performance in estimating fiber recovery (R2 = 97.77%) and a reasonable performance in estimating the toner recovery (R2 = 86.31%).
KW - deinking
KW - flotation
KW - machine learning
KW - paper recycling
KW - support vector regression
UR - http://www.scopus.com/inward/record.url?scp=85206579859&partnerID=8YFLogxK
U2 - 10.3390/app14198990
DO - 10.3390/app14198990
M3 - Article
AN - SCOPUS:85206579859
SN - 2076-3417
VL - 14
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 19
M1 - 8990
ER -