Application of Artificial Neural Network to Nondestructive Testing of Internal Wood Defects Based on the Intrinsic Frequencies

Abstract

The location and size of internal wood defects are nondestructively determined using experimental modal analysis and artificial neural network in this study. The different defect sizes and locations were simulated by removing mass from intact wood specimens. At room temperature in the laboratory, free vibration testing was conducted to generate the frequency response functions (FRF) of intact and defective Korean Pine (Pinus koraiensis) wood specimens using fast Fourier transform analysis system. The first three orders intrinsic frequencies were captured by picking up the location of each order peak of FRF curves. Then, two identification indexes developed by previous research were constructed based on these intrinsic frequencies, and they were used as input parameters to build the networks for localization and size determination of wood defects respectively. These two artificial neural networks were trained and tested for wood defects recognition. The research results showed that: (1) the intrinsic frequencies of defective wood were lower than those of intact wood; and (2) the constructed two identification indexes were capable to effectively detect the location and size of wood defects, which were more sensitive to large size defects than small size defects.