Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network
In this study, some physical and mechanical properties of yellow pine wood (Pinus sylvestris), which is used extensively in furniture industry, were tested after heat treatment. The findings obtained were modelled by artificial neural network (ANN) and interval values related to temperature and time...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Isparta University of Applied Sciences Faculty of Forestry
2021-06-01
|
Series: | Turkish Journal of Forestry |
Subjects: | |
Online Access: | https://dergipark.org.tr/tr/pub/tjf/issue/63166/874681 |
_version_ | 1797909414712180736 |
---|---|
author | Ayşenur Gürgen Sibel Yıldız |
author_facet | Ayşenur Gürgen Sibel Yıldız |
author_sort | Ayşenur Gürgen |
collection | DOAJ |
description | In this study, some physical and mechanical properties of yellow pine wood (Pinus sylvestris), which is used extensively in furniture industry, were tested after heat treatment. The findings obtained were modelled by artificial neural network (ANN) and interval values related to temperature and time variations were tried to be estimated. This study, which makes it easier to reach intermediate values, aims to save the relevant researchers from trial load all of the heating parameters during the furniture design/production stages. In the study scotch pine samples were heat-treated at 150, 160, 170, 180, 190 and 200 °C for 2, 4 and 6 hours, under normal atmosphere conditions. Color changes, weight losses and compression strength parallel to grain values of heat-treated samples were determined. After experimental study, modelling procedure was performed by ANN using two different learning algorithm- Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) algorithm- 15 different hidden neurons. The best model was obtained from 2-7-6 structure using LM learning algorithm. Mean absolute percentage error (MAPE) of the best model was found below 8.0% for estimated color parameters. The weight loss and compression strength parallel to grain were 5.79% and 1.50%, respectively. It was concluded that ANN can be used successfully to predict all studied parameters of heat-treated wood samples. |
first_indexed | 2024-04-10T11:07:50Z |
format | Article |
id | doaj.art-8e9ef96017284a93b4f3f6da32e73e24 |
institution | Directory Open Access Journal |
issn | 2149-3898 |
language | English |
last_indexed | 2024-04-10T11:07:50Z |
publishDate | 2021-06-01 |
publisher | Isparta University of Applied Sciences Faculty of Forestry |
record_format | Article |
series | Turkish Journal of Forestry |
spelling | doaj.art-8e9ef96017284a93b4f3f6da32e73e242023-02-15T16:19:17ZengIsparta University of Applied Sciences Faculty of ForestryTurkish Journal of Forestry2149-38982021-06-0122213514210.18182/tjf.8746811656Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural networkAyşenur Gürgen0Sibel Yıldız1Karadeniz Technical UniversityKaradeniz Technical UniversityIn this study, some physical and mechanical properties of yellow pine wood (Pinus sylvestris), which is used extensively in furniture industry, were tested after heat treatment. The findings obtained were modelled by artificial neural network (ANN) and interval values related to temperature and time variations were tried to be estimated. This study, which makes it easier to reach intermediate values, aims to save the relevant researchers from trial load all of the heating parameters during the furniture design/production stages. In the study scotch pine samples were heat-treated at 150, 160, 170, 180, 190 and 200 °C for 2, 4 and 6 hours, under normal atmosphere conditions. Color changes, weight losses and compression strength parallel to grain values of heat-treated samples were determined. After experimental study, modelling procedure was performed by ANN using two different learning algorithm- Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) algorithm- 15 different hidden neurons. The best model was obtained from 2-7-6 structure using LM learning algorithm. Mean absolute percentage error (MAPE) of the best model was found below 8.0% for estimated color parameters. The weight loss and compression strength parallel to grain were 5.79% and 1.50%, respectively. It was concluded that ANN can be used successfully to predict all studied parameters of heat-treated wood samples.https://dergipark.org.tr/tr/pub/tjf/issue/63166/874681heat-treatmentmodellingscotch pineartificial neural networkisıl işlemmodellemesarıçamyapay sinir ağları |
spellingShingle | Ayşenur Gürgen Sibel Yıldız Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network Turkish Journal of Forestry heat-treatment modelling scotch pine artificial neural network isıl işlem modelleme sarıçam yapay sinir ağları |
title | Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network |
title_full | Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network |
title_fullStr | Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network |
title_full_unstemmed | Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network |
title_short | Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network |
title_sort | modelling some physical and mechanical properties of heat treated scotch pine using artificial neural network |
topic | heat-treatment modelling scotch pine artificial neural network isıl işlem modelleme sarıçam yapay sinir ağları |
url | https://dergipark.org.tr/tr/pub/tjf/issue/63166/874681 |
work_keys_str_mv | AT aysenurgurgen modellingsomephysicalandmechanicalpropertiesofheattreatedscotchpineusingartificialneuralnetwork AT sibelyıldız modellingsomephysicalandmechanicalpropertiesofheattreatedscotchpineusingartificialneuralnetwork |