Sign up Log in
rjees logo



Effect of Moisture Content and Grain Orientation on Timber Beam Shear Strength Prediction Models

Authors: *Faluyi, F., Adetayo, O.A. And Omolayo, O.

DOI Info: http://doi.org/10.5281/zenodo.15778057

ABSTRACT

The shear strength of timber beams is significantly influenced by various factors, including moisture content and grain orientation. Accurate prediction of timber’s shear strength is crucial for ensuring the structural integrity and reliability of timber-based constructions. This research focused on developing two predictive models for determining the shear strength of timber under wet and oven-dried conditions and grain orientation in parallel and perpendicular direction. Linear regression (LR) and Extreme Gradient Boosting (XGBoost) models were developed using experimental data obtained from shear strength tests on four selected timber species from southwestern Nigeria namely: Anogeissus leiocarpa (Ayin), Pterocarpus erinaceus (Eru), Funtumia elastica (Ayere), and Albizia adianthifolia (Alakiriti). The models’ accuracy was evaluated by various metrics by comparing the predicted outcome with experimental results. It was observed that with reduction in the moisture content, coefficient of determination (R2) increased. This implied that shear strength predictability is more robust when the moisture content is lower. Also, judging by the R2 values, it could be summarized that the prediction is less prone to error when the grain orientation was parallel compared to when perpendicular. XGBoost has the highest R2 score of 0.9845 while the R2 score of LR was 0.8023, indicating that XGBoost performed better than LR. These results underscore the models’ effectiveness in predicting the shear strength of timber across the two conditions considered, providing a reliable tool for engineers and researchers.


Affiliations: Department of Civil Engineering, Federal University, Oye-Ekiti, Nigeria.
Keywords: Grain Orientation, Moisture Content, Predictive Model, Shear Strength, Extreme Gradient Boosting, Linear Regression
Published date: 2025/06/30

Download Full Text

SUBMIT A MANUSCRIPT

ISSN: 2635-3342 (Print)

ISSN: 2635-3350 (Online)

DOI: In progress

ISI Impact Factor: In progress

Indexing & Abstracting
AR Index google scholar Directory of research journal indexing JIFactor Info base index scientific journal impact factor

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License



(+234) 806 927 5563

Chemical Engineering Department, Faculty of Engineering, University of Benin, PMB 1154, Ugbowo, Benin City, Edo State, Nigeria.