Predicting internal bond strength of particleboard under outdoor exposure based on climate data: comparison of multiple linear regression and artificial neural network

Watanabe, Ken; Korai, Hideaki; Matsushita, Yasuhiro; Hayashi, Tomoyuki

doi:10.1007/s10086-014-1446-7

Cited by 17 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These modeling approaches have been also employed for predicting strength properties of wood and wood products. The applications regarding strength prediction in wood science can be listed as follows: Esteban et al [19]; Esteban et al [10]; Fernandez et al [8]; Eslah et al [20]; Tiryaki and Aydin [21]; Tiryaki et al [22]; and Watanabe et al [23].…”

mentioning

confidence: 99%

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

et al. 2016

View full text Add to dashboard Cite

Ðàçðàáîòàíû íåéðîííàÿ ñåòü è ìíîaeåñòâåííûå ëèíåéíûå ðåãðåññèîííûå ìîäåëè äëÿ îöåíêè àäãåçèîííîé ïðî÷íîñòè äåðåâÿííûõ êîíñòðóêöèé ñ ó÷åòîì èõ âëàaeíîñòè è âðåìåíè ïîëíîé ñáîðêè ýëåìåíòîâ êîíñòðóêöèè äî èõ ïðåññîâàíèÿ. Ðåçóëüòàòû ïðîâåäåííûõ ýêñïåðèìåíòàëüíûõ èññëåäîâàíèé èñïîëüçîâàëè â ðàçðàáîòàííûõ ìîäåëÿõ. Ïîêàçàíî, ÷òî ïðè óâåëè÷åíèè âëàaeíîñòè è âðåìåíè ñáîðêè àäãåçèîííàÿ ïðî÷íîñòü âíà÷àëå ðàñòåò, à çàòåì óìåíüøàåòñÿ. Ñ ïîâûøåíèåì âðåìåíè ïîëíîé ñáîðêè àäãåçèîííàÿ ïðî÷íîñòü ñíèaeàåòñÿ. Ñðàâíåíèå ðàñ÷åòíûõ ðåçóëüòàòîâ, ïîëó÷åííûõ ñ ïîìîùüþ èñêóññòâåííîé íåéðîííîé ñåòè è ìíîaeåñòâåííûõ ëèíåéíûõ ðåãðåññèîííûõ ìîäåëåé, ñâèäåòåëüñòâóåò î ïðåèìóùåñòâå ïåðâîãî ïîäõîäà, ñîãëàñíî êîòîðîìó êîýôôèöèåíò êîððåëÿöèè R 2 = 97,7%, ñðåäíåå îòêëîíåíèå ñîñòàâëÿåò 3,587%. Óñòàíîâëåíî, ÷òî èñêóññòâåííàÿ íåéðîííàÿ ñåòü ÿâëÿåòñÿ ýôôåêòèâíîé äëÿ ïðîãíîçèðîâàíèÿ àäãåçèîííîé ïðî÷íîñòè äåðåâÿííûõ êîíñòðóêöèé, ÷òî ïîçâîëÿåò ñîêðàòèòü êîëè÷åñòâî òðóäîåìêèõ è äîðîãîñòîÿùèõ ýêñïåðèìåíòàëüíûõ èññëåäîâàíèé.Êëþ÷åâûå ñëîâà: èñêóññòâåííàÿ íåéðîííàÿ ñåòü, ïðîãíîçèðîâàíèå, íàïðÿaeåíèå ñöåïëåíèÿ, ìíîaeåñòâåííàÿ ëèíåéíàÿ ðåãðåññèÿ, ñðàâíåíèå ìîäåëåé.Introduction. The adhesive bond of wood is one of the main connection methods used in modern load-bearing constructions [1]. The quality and durability of a wooden product primarily depends on the quality of its adhesive bonding [2]. The moisture content is among the most important factors affecting the final strength and durability of adhesive bonding [3]. The prolonged exposure to high moisture content severely reduces the

show abstract

mentioning

confidence: 99%

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

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The higher the RMSE value, the less accurate the model is. Thus, the β~(β >4 , β 4-3 ) model seems to be slightly inferior, though both can be considered correct [18]. These models confirm that the buffering capacity of chip suspension under the boundary of pH 4 becomes irrelevant for the study.…”

Section: Abc Methodologymentioning

confidence: 69%

“…The tensile strength perpendicular to the surface of a board is considered a measure of the internal bond (IB) of the particleboard that is strongly correlated with the strength of the adhesive bond between the chips in a panel [18][19][20][21][22]. Therefore, the IB was involved in building a correlation with the ABC of the chips used as the raw material in the particleboard preparation.…”

Section: Abc Effectmentioning

confidence: 99%

Comparison of Methodologies for Acid Buffering Capacity Determination—Empirical Verification of Models

2019

View full text Add to dashboard Cite

Raw materials used in particleboard production may have different chemical properties as they have different origins, nature, and storage histories. One of the most important factors is the acidity of the wood which affects the process of bond line formation. Thus, determination of the acid buffering capacity (ABC) of a raw material helps to adjust the optimal amount of hardener in the adhesive. In the present study, three methods for pH-metric ABC determination in the presence of lignocellulosic material were compared. Models that correlate the hardener amount with the internal bonding of particleboards were built from the ABC results. The approach was tested on three materials of different acidity—pine, oak, and ammonia-treated oak. The developed models allowed the prediction of the optimal amount of hardener for the maximized internal bond of the boards. The experimental verification of the models showed a high convergence of the calculated and empirical results.

show abstract

“…The eight sites selected were Asahikawa, Noshiro, Morioka, Tsukuba, Maniwa, Okayama, Shizuoka, and Miyakonojo (Table 1). Recently results have been reported by the authors' research group (Korai et al , 2014aKorai 2012;Korai and Hattori 2013;Korai and Saotome 2014;Watanabe et al 2014;Korai and Watanabe 2015;Kojima et al 2009Kojima et al , 2012Kojima and Suzuki 2011a, b;Sekino et al 2014).…”

Section: Introductionmentioning

confidence: 90%

Comparison between climatic factors and climate deterioration index on strength reduction of particleboards subjected to various climatic conditions in Japan

Korai

Watanabe

2015

Eur. J. Wood Prod.

Self Cite

View full text Add to dashboard Cite

An outdoor test on particleboards subjected to various climatic conditions was conducted in Japan. The significant climatic factors that reduce the particleboard strength (bending strength and internal bond strength) were investigated using multiple regression analysis. The climatic factors that reduce strength were temperature, sunshine duration, and/or precipitation. These three factors were not always significant; the significant climatic factors were different for each exposure time. In addition, the effects of climatic factors on strength reduction were different. Thus, multiple regression analysis using each climatic factor separately was not powerful. Therefore, the three climatic factors were combined into a first principal component using principal component analysis. The principal component score is referred to as the climate deterioration index (CDI). Strength at each exposure time decreased linearly with increasing CDI. The CDI is simpler and more useful as a climate index than individual climatic factors for predicting the strength reduction. In addition, both the relationship between CDI and strength reduction at each exposure time using analysis of covariance and the effects of CDI and exposure time were significant.

show abstract

Predicting internal bond strength of particleboard under outdoor exposure based on climate data: comparison of multiple linear regression and artificial neural network

Cited by 17 publications

References 27 publications

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

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

Comparison of Methodologies for Acid Buffering Capacity Determination—Empirical Verification of Models

Comparison between climatic factors and climate deterioration index on strength reduction of particleboards subjected to various climatic conditions in Japan

Contact Info

Product

Resources

About