Application of fuzzy cluster analysis on diagnosing the locations of the hole defects in Acer mono wood using acoustic testing

Abstract

In order to detect the locations of timber holes defect, a new method based on fuzzy clustering analysis and acoustic non-destructive testing of wood was proposed. There were three kinds of timber samples were taken in the research, and one with a hole at a certain end of it, one with a hole at the middle of it and the other one without a hole. Acoustic signals were collected with hammering method, and time-frequency feature vectors were extracted as the sample data. Cluster analysis was made on the training samples using fuzzy similar matrix based on the transitive closure, after which different classes of fuzzy patterns were created. The test samples were then identified by maximum membership degree principle. The results showed that the method was able to detect the position of hole defects in Acer mono wood effectively and accurately. The detection accuracy for samples with an end hole was 84%, for samples with a middle hole was 92% and for samples without a hole was 94%.