Predicting the Impacts of Various Factors on Failure Load of Screw Joints for Particleboard Using Artificial Neural Networks

Basit Öğe Kaydı
dc.authoridBARDAK, selahattin/0000-0001-9724-4762
dc.contributor.authorBardak, Selahattin
dc.date.accessioned2025-03-23T19:30:10Z
dc.date.available2025-03-23T19:30:10Z
dc.date.issued2018
dc.departmentSinop Üniversitesi
dc.description.abstractInnovations in the furniture industry have an important place in the global competitive environment. The use of mechanical joining techniques is rapidly increasing in the furniture industry. One of the most common mechanical joining techniques is screwing. This study investigated the impacts of screw diameter, screw length, and the distance between the screws on the failure load of screw joints in particleboard. Additionally, a model was developed on an artificial neural network model (ANN), based on experimental data, to predict the failure load of joints. The results indicated that the highest tension and compression strengths of joints were achieved when the distance is 140 mm between the screws. Joint strengths of all specimens were improved when the screw length and diameter were increased. It is necessary to estimate the effect of various factors to improve furniture joint performance. Coefficients of determination at 0.98 (tension strength test) and 0.96 (compression strength test) were predicted for the testing phase by the ANN model. All these findings established that the prediction was compatible with experimental data of tension and compression strengths. The results of the analysis showed that the neural network approach was effective in predicting the failure load of screw joints and showed that the ANN model has great potential in the design optimization of furniture assemblies.
dc.identifier.doi10.15376/biores.13.2.3868-3879
dc.identifier.endpage3879
dc.identifier.issn1930-2126
dc.identifier.issue2
dc.identifier.scopus2-s2.0-85074228606
dc.identifier.scopusqualityQ3
dc.identifier.startpage3868
dc.identifier.urihttps://doi.org/10.15376/biores.13.2.3868-3879
dc.identifier.urihttps://hdl.handle.net/11486/5034
dc.identifier.volume13
dc.identifier.wosWOS:000440518000008
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorBardak, Selahattin
dc.language.isoen
dc.publisherNorth Carolina State Univ Dept Wood & Paper Sci
dc.relation.ispartofBioresources
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250323
dc.subjectScrew
dc.subjectJoint
dc.subjectFurniture
dc.subjectArtificial neural networks
dc.titlePredicting the Impacts of Various Factors on Failure Load of Screw Joints for Particleboard Using Artificial Neural Networks
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu