Abstract:Spectral analysis has been widely used in wood physical feature parameter detection such as wood species, density, strength, surface roughness and humidity. However, the current wood detection is used to predict the single wood parameter. If the multiple wood parameter detections are required, the single wood detection needs to be performed some times. In order to improve the wood parameter detection’s efficacy, we propose a simultaneous prediction scheme for wood species and wood density parameters with only one prediction. First, the K/S algorithm is used to divide the training and prediction sets to make them representative. Then, two dimensionality-reduction methods of principal component analysis and wavelet transform are combined with BP neural network and least squares support vector machine to establish four prediction models that can predict both wood species and density. In experiments, a small fiber spectrometer of USA Ocean Optics USB2000-VIS-NIR is used to acquire the visible/near infrared spectral curves with a spectral interval of 350~1 100 nm. The results show that all four models can achieve simultaneous prediction of wood species and density, and the model established by wavelet transform dimensionality-reduction method combined with least squares support vector machine is relatively better. The correct recognition rate of wood species based on the combination of wavelet transform and partial least squares support vector machine is 100%, the density correlation coefficient of training set is 0.973 4, the density correlation coefficient of prediction set is 0.940 8, the density training root mean square error is 0.026 13, and the prediction root mean square error is 0.038 46. It lays a theoretical foundation for the development of portable real-time on-line detection instruments that can simultaneously predict several parameters of wood physical feature. Moreover, another spectrometer of FLAME-NIR with a spectral interval of 900~1 650 nm is also used to perform the same prediction experiments. By comparisons, we find that the prediction results with the FLAME-NIR model are slightly superior to those with the USB2000-VIS-NIR model. Therefore, our simultaneous prediction of wood species and wood density is practical with a definite stability, accuracy, and a low instrumentation cost.
赵 鹏,李 悦. 可见光/近红外光谱分析的木材树种与密度同时预测[J]. 光谱学与光谱分析, 2019, 39(11): 3525-3532.
ZHAO Peng, LI Yue. Simultaneous Prediction of Wood Density and Wood Species Based on Visible/Near Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(11): 3525-3532.
[1] Mendoza F A, Cichy K, Lu R, et al. Food and Bioprocess Technology, 2014, 7(9):2666.
[2] Li J, Huang W, Zhao C, et al. Journal of Food Engineering, 2013, 116(2):324.
[3] Li X L, Yi S L, He S L, et al. Precision Agriculture, 2016, 17(3):365.
[4] Wang J X, Fan L F, Wang H H, et al. Biosystems Engineering, 2017, 162:40.
[5] Hauksson J B, Bergqvist G, Bergsten U, et al. Wood Science and Technology, 2001, 35(6):475.
[6] Nisgoski S, Oliveira A A, Muñiz G I B. Wood Science and Technology, 2017, 51(4):929.
[7] ZHAO Rong-jun, XING Xin-ting, LÜ Jian-xiong, et al(赵荣军,邢新婷,吕建雄,等). Scientia Silvae Sinicae(林业科学),2012,48(6): 106.
[8] CHEN Zhen-ning(陈振宁). Chinese Journal of Analytical Chemistry(分析化学),2001,25(11): 1322.
[9] Tao Z H, Yuan Z, Ping C. Journal of Mathematical Chemistry, 2009, 46(4):1050.
[10] ZHANG Yao, LI Min-zan, ZHENG Li-hua, et al(张 瑶,李民赞,郑立华,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2015,31(9): 121.
[11] SUN Xu-dong, DONG Xiao-ling(孙旭东,董小玲). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2013,29(14): 262.
[12] WANG Jing, JIANG Gang, CHEN Zhong-jie(王 静,蒋 刚,陈中杰). Application Research of Computers(计算机应用研究),2013,30(12): 3597.
[13] JIN Ye, YANG Kai, WU Yong-jiang, et al(金 叶,杨 凯,吴永江,等). Chinese Journal of Analytical Chemistry(分析化学),2012,40(6): 925.
[14] GUO Wen-chuan, LIU Da-yang(郭文川,刘大洋). Transactions of the Chinese Society of Agricultural Mechinery(农业机械学报),2014,45(9): 230.