Near Infrared Spectroscopy Identification Method of Wood Surface Defects Based on SA-PBT-SVM
YU Hui-ling1, MEN Hong-sheng2, LIANG Hao2, ZHANG Yi-zhuo2*
1. Northeast Forestry University, Information and Computer Engineering College, Harbin 150040, China
2. Northeast Forestry University, College of Mechanical and Electrical Engineering, Harbin 150040, China
Abstract：In this paper, near infrared spectroscopy was applied to build an identification model to predict four types of defects on the surface of wood boards. A calibration set and a prediction set made of 50 and 30 samples were built randomly and respectively. In addition, a near infrared spectrometer, ranging from 900 to 1 700 nm was used to collect the spectra of the surface of the boards. The original spectra were pre-treated by SNV algorithm to eliminate the influence of solid particle size, surface scattering, and the change of optical path of diffused reflectance spectra. Afterwards, a training model was built by partial binary tree of support vector machine (PBT-SVM), and parameters were optimized by simulated annealing (SA) algorithm to find the optimal parameters and band characteristics. Then an identification model was built based on optimal parameters, band characteristics, and the identification of prediction set. The results showed that the performance of polynomial kernel function was obtained with the parameters setting as γ=28.63, coef=18.69, d=1 and, C=12.03. The recognition rate of crack and live knot was 100%, while the recognition rate of dead knot and wormhole was 93.33%. The mean accuracy of identification reached 96.65% with an average recognition time of 0.002 s. The approach was feasible to classify the four types of defects on the surface of solid wood effectively.
Key words：Solid wood plate; Defect identification; Near infrared spectroscopy; Partial two tree double support vector machine; Simulated annealing
[1] Zhang Yizhuo, Xu Chao, Li Chao. Journal of Forestry Research, 2015, 26(3): 745.
[2] Zhang Yizhuo, Liu Sijia, Cao Jun. Wood Sci. Technol., 2016, 50(3): 297.
[3] Zhang Yizhuo, Liu Sijia, Tu Wenjun. Optical Engineering, 2015, 54(10): 103102(1).
[4] Sundaram J, Mani S, Kandala C V K. American Journal of Analytical Chemistry, 2015, 6(12): 923.
[5] Jones P D, Schimleck L R, Peter G F, et al. Wood Sci. Technol., 2006, 40(8): 709.
[6] YANG Zhong, CHEN Ling, FU Yue-jin(杨 忠, 陈 玲, 付跃进). Journal of Northeast Forestry University(东北林业大学学报), 2012, 40(8): 70.
[7] Miranda Angela，Lavrador Rui，Julio Filipal, et al. Behavior Research Methods, 2016, 48(4): 1667.
[8] Cogill S, Wang L. Bioinformatics, 2016, 32(23): 3611.
[9] Xu Yitian, Chen Mei, Li Guohui. International Journal of Systems Science, 2016, 47(15): 3637.
[10] Zhai Shijun, Pan Juan, Luo Hongwei, et al. Measurement, 2016, 80: 58.
