Abstract
Machine learning (ML)-based models, decision tree and ANFIS, were used to predict the degree of surface checking and bending properties of 30-month weathered thermally modified timber. The results showed that the investigated initial board properties did not allow accurate predictions of surface checks. ML regression and clustering analysis confirmed important variables for accurate predictions of bending properties were dynamic stiffness, acoustic velocity, density and lowest local bending modulus. ML models performed better than conventional regression models used for timber grading, and a prediction accuracy of 80–90% for bending stiffness and 50–70% for bending strength could be achieved.
Highlights
Modified timber (TMT) is recommended for use in out door above-ground situations, where it is directly exposed to weather [1,2,3,4]
After 30 months of weathering, surface checks were present in both thermally modified (TM) and control boards
Cmax of unmodified Norway spruce boards was normally distributed (Fig. 3b). Both the total number and maximum depth of surface checks were significantly higher for TM boards compared to the control, as discussed earlier in detail by van Blokland et al [24]
Summary
Modified timber (TMT) is recommended for use in out door above-ground situations, where it is directly exposed to weather [1,2,3,4]. Deep surface checks (i.e. equal or greater than 50% of the timber’s thickness) were found in Norway spruce TMT after a 30-month weath ering [24]. These checks are longer and more frequent in TMT than unmodified timber, especially on the pith side of timbers, where checks develop predominantly along growth rings. Previous studies on unmodified Norway spruce clear wood showed a positive correlation between size of surface checks after weathering and density that was explained by differences in wood’s moisture uptake and sorption [27,28].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have