Identification of wood species and duration of exposure in weathered wood using guided wave propagation

Abstract

ABSTRACT Nondestructive health monitoring of weathered timber structures in outdoor applications is a critical safety and quality control task. This study proposes a guided Lamb wave propagation approach for identifying the type of wood and estimating the duration of exposure in different wood species under artificial weathering. Accordingly, alder, fir, oak, and poplar wood specimens underwent accelerated weathering conditions. The intact and degraded wood specimens were assessed via the Lamb wave propagation experiments, and different sensory features were extracted and used to train machine learning models. The decision tree and random forest classification were performed to identify the type of wood and the duration of exposure to weathering. The results of the decision tree classification indicated that the extracted wave-based features could identify the type of wood species with an accuracy of 82.5%. The wave features could also classify the duration of exposure to weathering with a maximum accuracy of 75%. Higher classification performance was obtained using the random forest model where the wood species and exposure duration were classified with an accuracy of 85% and 81.25%, respectively. Overall, the guided Lamb wave propagation exhibited the potential for in-situ assessment and species identification of weathered wood in outdoor conditions.