Two-Dimensional Convolutional Neural Networks for Wood Quality Assessment

Abstract

Different materials, including wood, have been tested using the contact Ultrasonic Testing (UT) technique. The time and velocity of the ultrasonic wave in a wood section have traditionally been monitored and correlated with wood quality. This practice, however, has not yielded satisfactory results, prompting researchers to develop new strategies to address the issue. In this study, the primary objective is to employ convolutional neural networks (CNN) to assess wood quality using the results of contact ultrasonic testing. To this end, 2D CNN models are employed to train on labeled ultrasonic signals as the training set. The developed models are thus set to solve supervised classification problems based on data gathered from testing specimens with various health conditions. The tested specimens are two types of wood with and without natural imperfections. Therefore, the size and shape of damage are different across specimens-billets harvested from trees at two sites in NSW and WA, Australia. This study aims to visualize and investigate the properties of the features extracted by the inner layers of the developed CNN models. This way, an unsupervised strategy can be devised to solve the clustering problem of woods based on their health condition.