Artificial Neural Network-based Prediction Model to Minimize Dust Emission in the Machining Process

Basit Öğe Kaydı
dc.contributor.authorSinger, Hilal
dc.contributor.authorIlce, Abdullah C.
dc.contributor.authorSenel, Yunus E.
dc.contributor.authorBurdurlu, Erol
dc.date.accessioned2024-09-25T19:56:22Z
dc.date.available2024-09-25T19:56:22Z
dc.date.issued2024
dc.departmentAbant İzzet Baysal Üniversitesien_US
dc.description.abstractBackground: Dust generated during various wood-related activities, such as cutting, sanding, or processing wood materials, can pose significant health and environmental risks due to its potential to cause respiratory problems and contribute to air pollution. Understanding the factors influencing dust emission is important for devising effective mitigation strategies, ensuring a safer working environment, and minimizing environmental impact. This study focuses on developing an artificial neural network (ANN) model to predict dust emission values in the machining of black poplar ( Populus nigra L.), oriental beech ( Fagus orientalis L.), and medium-density fiberboards. Methods: The multilayer feed-forward ANN model is developed using a customized application built with MATLAB code. The inputs to the ANN model include material type, cutting width, number of blades, and cutting depth, whereas the output is the dust emission. Model performance is assessed through graphical and statistical comparisons. Results: The results reveal that the developed ANN model can provide adequate predictions for dust emission with an acceptable level of accuracy. Through the implementation of the ANN model, the study predicts intermediate dust emission values for different cutting widths and cutting depths, which are not considered in the experimental work. It is observed that dust emission tends to decrease with reductions in cutting width and cutting depth. Conclusion: This study introduces an alternative approach to optimize machining-process conditions for minimizing dust emissions. The findings of this research will assist industries in obtaining dust emission values without the need for additional experimental activities, thereby reducing experimental time and costs. (c) 2024 Occupational Safety and Health Research Institute. Published by Elsevier B.V. on behalf of Institute, Occupational Safety and Health Research Institute, Korea Occupational Safety and Health Agency. This is an open access article under the CC BY-NC-ND licenseen_US
dc.description.sponsorshipScientific Research Unit of Gazi University [07/2011-35]en_US
dc.description.sponsorshipThe authors are grateful for the support of the Scientific Research Unit of Gazi University [07/2011-35] .en_US
dc.identifier.endpage326en_US
dc.identifier.issn2093-7911
dc.identifier.issn2093-7997
dc.identifier.issue3en_US
dc.identifier.startpage317en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12491/13258
dc.identifier.volume15en_US
dc.identifier.wosWOS:001308364300001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.ispartofSafety And Health At Worken_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmzYK_20240925en_US
dc.subjectArtificial neural networken_US
dc.subjectDust emissionen_US
dc.subjectErgonomicsen_US
dc.subjectForest industryen_US
dc.subjectMaterial processingen_US
dc.titleArtificial Neural Network-based Prediction Model to Minimize Dust Emission in the Machining Processen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu