A Method Of Wood Defect Identification Based On Multiple Characteristics And Its Influencing Factors

At present, the stress wave nondestructive testing technology and micro-drilling resistance testing technology have been widely used to detect the internal defects of wood. However, the existing stress wave testing can only determine the existence of defects in the wood, but can not identify the type of wood defect. In this paper, the stress wave wood nondestructive testing technology and micro-drilling resistance wood testing technology are studied. The data sets of stress wave propagation velocity in different wood species, different moisture content and different types of defects are collected, and the data sets of resistance data in different densities, different detection directions and different moisture content and different types of defects are collected. This paper analyzes experimental data and studies the impact of various factors on the stress wave velocity and resistance data. In addition, this paper presents a method which combines stress wave and micro-drilling resistance to identify wood defects. This method measures stress wave velocity and resistance data in the wood firstly, and then classifies the internal conditions of wood using support vector machine(SVM) with the stress wave velocity as the classification feature. In order to demonstrate the effectiveness of the proposed method, 31 samples with different conditions from pecan wood and 28 samples with different conditions from pine wood were selected as experimental samples. The Arbotom detector from Rinntech Company in German was used to collect 117 groups data of stress wave velocity from pecan wood and 80 groups data of stress wave velocity from pine wood. The Resistograph detector from Rinntech Company in German was used to collect 117 groups data of resistance data from pecan wood and 80 groups data of resistance data from pine wood. The classification accuracy of pecan wood and pine wood are 93.75% and 95% respectively. The different internal conditions(e.g. voids, cracks, decay) in pecan wood and pine wood were classified respectively by SVM.