Sebahattin Tiryaki

Application of Artificial Neural Networks for predicting tensile index and brightness in bleaching pulp

The purpose of this study was to develop artificial neural network (ANN) models for predicting the effects of wood species, sodium perborate tetrahydrate (SPBTH) ratio, time, and beating degree on tensile index and brightness in bleaching pulp. Unbleached kraft-AQ bamboo and poplar pulps were exposed to first stage oxygen delignification for bleaching under 0,5 MPa, 3% NaOH and 12% consistency conditions. SPBTH bleaching was then carried out as the final stage. SPBTH bleached pulp was next beaten using two different degrees (55 SR° and 65 SR°). Tensile index and brightness data for training, validation and testing of the models were elicited from these experimental investigations. The models were established using the resulting data. The lowest R2 value was 0,98 among training, testing and validation data sets in the prediction of both tensile index and brightness. The networks therefore explain at least 98% of the experimental data for all data sets. The results indicate that ANN is a useful and effective tool for predicting tensile index and brightness. This study thus describes a novel and alternative approach to predicting tensile index and brightness in bleaching pulp compared to the literature.

Experimental investigation and prediction of bonding strength of Oriental beech (Fagus orientalis Lipsky) bonded with polyvinyl acetate adhesive

Adhesive bond strength of solid wood plays a key role in the efficient use of wood in a large number of engineering applications. In this study, the effects of amount of adhesive, pressing pressure, and pressing time on bonding strength of beech wood bonded with polyvinyl acetate adhesive were investigated and predicted by developing an artificial neural network (ANN) model. Experimental results have showed that bonding strength of wood samples increased generally by increasing amount of adhesive, pressing pressure, and pressing time. Besides, ANN analysis has yielded highly satisfactory results. The designed neural network model allows predicting the bonding strength of wood samples with mean absolute percentage error of 2.454% and correlation coefficient of 97.8% for testing phase. It is clear from the results that the model has a good learning and generalization ability. This model therefore can be used to predict bonding strength of beech samples bonded with polyvinyl acetate adhesive under given conditions. Consequently, this study provides beneficial insights for practitioners in terms of the safe and efficient use of wood as an engineering material in applications related to the strength of the bond between wood and adhesive.

Evaluation of process parameters for lower surface roughness in wood machining by using Taguchi design methodology

This paper presents a study of the Taguchi design method for obtaining lower surface roughness values in terms of process parameters in wood machining. The process parameters considered were feed rate, cutting depth, number of knives, annual ring (earlywood–latewood) and grit number of abrasive. The settings of the process parameters were determined by using Taguchi experimental design method. Orthogonal arrays of Taguchi and the signal-to-noise (S/N) ratio were employed to find the optimal levels and to analyze the effect of process parameters on surface roughness. In addition, the Pareto ANOVA analysis was used in order to measure the influence of each process parameter on surface roughness. The results of Taguchi analysis revealed that the most significant variable on surface roughness of both beech and spruce woods by S/N ratio analysis and Pareto ANOVA analysis is the grit number of abrasive. It was also understood that the Taguchi design technique is very suitable to solve the surface quality problem regarding machining of wood species.

Predictive Performance of Artificial Neural Network and Multiple Linear Regression Models in Predicting Adhesive Bonding Strength of Wood

The purpose of this study was to develop artificial neural network (ANN) and multiple linear regression (MLR) models that are capable of predicting the bonding strength of wood based on moisture content, open assembly time and closed assembly time of the joints prior to pressing process. For this purpose, the experimental studies were conducted and the models based on the experimental results were set up. As a result of the experiments conducted, it was observed that bonding strength first increased and then decreased with increasing the wood moisture content and adhesive open assembly time. In addition, the increased closed assembly time caused a decrease in bonding strength of wood. The ANN results were compared with the results obtained from the MLR model to evaluate the models’ predictive performance. It was found that the ANN model with the R2 value of 97.7% and the mean absolute percentage error of 3.587% in test phase exhibits higher prediction accuracy than the MLR model. The comparison results confirm the feasibility of ANN model in terms of predictive performance. Consequently, it can be said that ANN is an effective tool in predicting wood bonding strength, and quite useful instead of costly and time-consuming experimental investigations.

POLİVİNİLASETAT TUTKALI İLE YAPIŞTIRILMIŞ DOĞU KAYINI (Fagus orientalis Lipsky) VE DOĞU LADİNİ (Picea orientalis (L.) Link.) ODUNLARININ YAPIŞMA PERFORMANSI ÜZERİNE SUDA BEKLETME FAKTÖRLERİNİN ETKİLERİNİN ARAŞTIRILMASI

Odunun yapistirici bagi odun kaynaklarinin etkili kullaniminda anahtar bir faktordur. Bu nedenle, bir yapistirici ile birlestirilen odun urunlerinin performansinin farkli sartlar altinda degerlendirilmesi oldukca onemlidir. Bu calismada, PVAc ile yapistirilan odun ornekleri farkli sicakliktaki suya (20, 40, 60 ve 80oC) farkli sureler (10, 20, 30 ve 40 dakika) icin maruz birakilmistir. Deneysel sonuclar incelendiginde, PVAc ile yapistirilmis odun orneklerinin suya maruz birakilmasi ile orneklerin yapisma direncinde onemli derecede bir dusus oldugu gozlemlenmistir. Direnc degerlerinde gozlemlenen bu dususler ozellikle 60 °C ve uzerindeki sicakliktaki su ile muamelede daha ciddi oranlara ulasmistir. Ayrica, direnc degerlerindeki dususler maruz birakilan surenin artisi ile genellikle artmistir.

THE INFLUENCE OF RAW MATERIAL GROWTH REGION, ANATOMICAL STRUCTURE AND CHEMICAL COMPOSITION OF WOOD ON THE QUALITY PROPERTIES OF PARTICLEBOARDS

In the present study, the impact of raw material grown region on the physical, mechanical, surface properties and formaldehyde emission of the particleboard was investigated. Ailanthus altissima wood grown in Trabzon had longer fiber length and thicker fiber and trachea cell wall than those of the wood grown in Artvin. The highest amounts of lignin, ash, condensed tannin and solubility values were found in wood grown in Artvin. Ailanthus altissima wood grown in Trabzon had higher amounts of cellulose and hemicellulose than those of the wood grown in Artvin. Particleboards made from wood grown in Artvin had worse surface quality and mechanical strength properties than those of panels made from wood grown in Trabzon. On the other hand, the results showed that particleboards produced from wood grown in Artvin had lower thickness swelling and formaldehyde emision values than those of the panels produced from wood grown in Trabzon.

Investigation of Performance on Forest Products Industry with Performance Appraisal System

Ozet Calismanin amaci: Bu calisma ile Turkiye genelinde orman urunleri sanayi sektorlerinde (mobilya, levha urunleri, kagit ve kagit urunleri) yer alan 14 orman urunleri isletmesinde calisan 432 kisiye ulasilarak isletmelerde uygulanan performans degerlendirme sistemlerinin verimlilik ve motivasyonel etkileri ile performans degerlendirme uygulamalarinin alt sektorler duzeyinde ve katilimcilarin demografik ozelliklerine bagli olarak farklilik gosterip gostermedigi arastirilmistir. Materyal ve Yontem: Bu amacla hazirlanan anket formu, isletmelerdeki calisanlara yuz yuze gorusme teknigi ile uygulanmistir. Toplanan anketler, SPSS paket programina islenerek aciklayici istatistikler, faktor analizi ve varyans analizi ile test edilmistir. Sonuclar: Sonuclar incelendiginde, performans degerlendirme uygulamalarin alti tane faktore (performans degerlendirmenin; amaci, kriterleri, gorusmeleri, uygulamalari, verimlilik etkisi ve motivasyonel etkisi) ayrilabilecegi belirlenmistir. Performans degerlendirme sistemleri alt faktorleri bakimindan orman urunleri sanayi alt sektorleri bazinda anlamli bir farkin olmadigi belirlenmistir. Ayrica demografik ozelliklere gore yapilan varyans analizi sonuclarina gore yas gruplari bakimindan anlamli bir farklilik olmamakla beraber, egitim durumu, cinsiyet, medeni durum, calisilan pozisyon ve toplam calisma suresine gore performans degerlendirme alt faktorleri duzeyinde anlamli farkliliklar belirlenmistir. Arastirma vurgulari: Isletmeler acisindan performans degerlendirme calismalari calisanlarin verimliligine yonelik gostergeler icerdiginden isletmeler icin cok onemli uygulamalardir.

Üniversite öğrencilerinin kaygı düzeylerini etkileyen faktörleri belirlemeye yönelik bir çalışma (KTÜ örneği)

Calismanin amaci: Bu calisma kapsaminda Karadeniz Teknik Universitesi, Orman Fakultesi, Orman Endustri Muhendisligi Bolumu ogrencilerine durumluk-surekli kaygi olcegi uygulanarak, kaygi duzeyleri ve bu kaygi duzeylerini etkileyen faktorler tespit edilmeye calisilmistir. Materyal ve Yontem: Calismada 40 sorudan olusan Durumluk-Surekli Kaygi Olcegi kullanilmistir. Olcek degerlendirilirken Mann-Whitney U testi ve Kruskal Wallis testi uygulanmistir. Sonuclar: Calisma neticesinde durumluk ve surekli kaygi duzeyleri sirasiyla 46.50 ve 43.97 olarak bulunmustur. Ayrica, bu kaygi duzeylerinin cinsiyet, sinif, akademik basari duzeyi, aile aylik ortalama gelir, is deneyimi ve bolumu isteyerek tercih etme durumuna gore farklilik gostermedigi belirlenmistir. Arastirma vurgulari: Durumluk ve surekli kaygi duzeyleri ogrencilerin egitim hayatlari ve is hayatlarindaki basarilarini etkileyen onemli kavramlardir.

Predictive Models for Modulus of Rupture and Modulus of Elasticity of Particleboard Manufactured in Different Pressing Conditions

Abstract Determining the mechanical properties of particleboard has gained a great importance due to its increasing usage as a building material in recent years. This study aims to develop artificial neural network (ANN) and multiple linear regression (MLR) models for predicting modulus of rupture (MOR) and modulus of elasticity (MOE) of particleboard depending on different pressing temperature, pressing time, pressing pressure and resin type. Experimental results indicated that the increased pressing temperature, time and pressure in manufacturing process generally improved the mechanical properties of particleboard. It was also seen that ANN and MLR models were highly successful in predicting the MOR and MOE of particleboard under given conditions. On the other hand, a comparison between ANN and MLR revealed that the ANN was superior compared to the MLR in predicting the MOR and MOE. Finally, the findings of this study are expected to provide beneficial insights for practitioners to better understand usability of such composite materials for engineering applications and to better assess the effects of pressing conditions on the MOR and MOE of particleboard.

Analysis of volumetric swelling and shrinkage of heat treated woods: Experimental and artificial neural network modeling approach

Shrinkage and swelling characteristics of wood as a hygroscopic material affect negatively its effective utilization for a variety of applications. Heat treatment is widely used for minimizing the negative effects of volumetric swelling and shrinkage of wood. The present study aims to develop artificial neural network (ANN) models for predicting volumetric swelling and shrinkage of heat treated woods. For this purpose, wood samples were subjected to heat treatment at varying temperatures (130, 150, 170 and 190 oC) for varying durations (2, 4, 6 and 8 h). Experimental results have showed that volumetric swelling and shrinkage of wood decreased by heat treatment. Then, neural networks models capable of predicting the swelling and shrinkage of the treated woods were developed based on the resulting data. It was seen that ANN models allowed volumetric swelling and shrinkage of such woods to predict successfully with a limited set of experimental data. This approach was able to predict volumetric swelling and shrinkage of wood with a mean absolute percentage error equal to 2,599% and 2,647% in test phase, respectively. The developed models might thus serve as a robust tool to predict volumetric swelling and shrinkage with less number of experiments.