In view of the uncertain mechanical properties of knot-bearing wood and the difficulty of judging whether it is usable, this article proposes a method to evaluate the usability of wood containing knots by detecting the bending properties of wood containing knots. The common tree Quercus mongolica, which accounts for 15%-20% of the total forest area in Northeast China, is selected as the experimental object. Firstly, the object detection algorithm is used to identify the areas containing knots on the suface of wood, followed by spectral extraction of the identified area and the construction of a quantitative prediction model. Finally, the mechanical properties of wood containing knots are analyzed through deep learning. The experimental results indicate that the SPA-SVM prediction model proposed in this article has excellent predictive ability for the bending properties of wood, with experimental results indicators of R2=0.96, RMSE=0.58, and RPD=5.09. The prediction model proposed in this article can accurately predict the bending properties of wood containing knots. The predicted results have a small error with the actual values, which meets the experimental requirements and standards. The predicted results can provide a basis for whether the wood can be used.
Horvath等[3]利用近红外光谱技术建立了针对山杨木树种抗弯强度和弹性模量的偏最小二乘预测模型;Schimleck等[4]应用BP神经网络,通过近红外光谱数据对无瑕疵蒙达利松的弹性模量(Modulus of elasticity,MOE)进行了预测;Kothiyal等[5]在不对木材含水率进行统一处理的情况下,对细叶桉的近红外光谱数据与力学性能之间的关系进行了研究,发现在此条件下随机森林模型的测定系数较高;Xu等[6]研究发现了木材力学性能试件中水分含量的不同会影响静曲强度(Modulus of Rapture,MOR)预测模型的精确度;Liang等[7]通过基于遗传算法优化的偏最小二乘法进行光谱优选,构建了蒙古栎的近红外光谱值与其MOR对应关系的模型。
根据国家《无疵小试样木材物理力学性质试验方法第2部分:取样方法和一般要求》(GB/T 1927.2—2021)要求,将木材切片制成粗条,选取粗条中含节子的部分,制备尺寸为300 mm mm70 mm的含节子木材力学试样共计150个。对这些试样按照编号QX1—QX150的顺序进行标记,之后将所有试样放入干燥箱中干燥,以确保试样水分含量均为12%左右,最后将每个试样分别放入单个密封袋中,以防止存放时试验室内的水蒸气对试样造成影响。
ZHANGP P.Analysis of the development status and trends of forest resources in china[J].Green Technology,2019(17):204-206.
[3]
初伟杰.探析木材检验工作的重要性[J].农村实用科技信息,2015(7):32.
[4]
CHUW J.Exploring the importance of wood inspection work[J].Practical Scientific and Technological Information in Rural Areas,2015(7):32.
[5]
HORVATHL, PESZLENI, PERALTAP,et al.Use of transmittance near-infrared spectroscopy to predict the mechanical properties of 1- and 2-year-old transgenic aspen[J].Wood Science and Technology,2011,45(2):303-314.
[6]
SCHIMLECKL R, DEMATOS, OILVEIRAJIM,et al.Non-destructive estimation of pernambuco(Caesalpinia echinata) clear wood properties using near infrared spectroscopy[J].Journal of Near Infrared Spectorscopy,2011,19(5):411-419.
[7]
KOTHIYALV, RATURIA.Estimating mechanical properties and specific gravity for five-year-old Eucalyptus tereticornis having broad moisture content range by NIR spectroscopy[J].Holzforschung,2011,65(5):757-762.
[8]
XUQ H, XUM H, NIY H,et al.Progresses and perspectives of near infrared spectroscopy analytical technology[J].Canadian Journal of Forest Research,2011,41(2):352-358.
[9]
LIANGH, CAOJ, TUW J,et al.Nondestructive determination of the compressive strength of wood using near-infrared spectroscopy[J].Bioresources,2016,11(3):7205-7213.
CHUX L, CHENP, LIJ Y,et al.The latest progress and prospects of near-infrared spectroscopy analysis technology[J].Journal of Analysis and Testing,2020,39(10):1181-1188.
[12]
FUJIMOTOT, KOBORIH, TSUCHIKAWAS.Prediction of wood density independently of moisture conditions using near infrared spectroscopy[J].Journal of Near Infrared Spectorscopy,2012,20(3):353-359.
XIEF, ZHUD J.Overview of deep learning object detection methods[J].Application of Computer Systems,2022,31(2):1-12.DOI:10.15888/j.cnki.csa.008303 .
[15]
LISBETHG T.Determination of dry matter content and basic density of norway spruce by near infrared reflectance and transmittance spectroscopy[J].Journal of Near Infrared Spectroscopy,1994,2(3).
LIM Y, CHEND S, WANGX Y,et al.Nature of the knot and its impact on wood properties[J].Journal of Northwest Forestry University,2020,35(4):197-204.
[18]
YUNS, HAND, OHS J,et al.CutMix: regularization strategy to train strong classifiers with localizable features[C].2019 IEEE/CVF International Conference on Computer Vision(ICCV),Seoul,Korea,2019:33-42.
ZHANGS L, WANGW D, GUY H,et al.Principal component analysis of near infrared spectroscopy-Markov distance clustering discrimination for authenticity identification of cigarettes[J].Spectroscopy and Spectral Analysis,2011,31(5):1254-1257.
[21]
CHENJ H, YUH L, JIANGD P,et al.A novel NIRS modelling method with OPLS-SPA and MIX-PLS for timber evaluation[J].Journal of Forestry Research,2022,33(1):369-376.
[22]
YANGY, WANGF H, JIANGD P.PSO-SVR model for ecology property of indoor decoration surface materials[J].Journal of Northeast Forestry University,2019,47(4):81-85.
[23]
SCHIMLECKL R, EVANSR, MATHESONA C,et al.Estimation of Pinus radiata D.Don clear wood properties by near-infrared spectroscopy[J].Journal of Wood Science,2002,48(2):132-137
XIAOX L, CHENC M.Establishment and validation of a multiple linear regression model for predicting ethanol concentration[J].Infrared Technology,2021,43(12):1228-1233.
[26]
SCHIMLECKL R, EVANSR, MATHESONA C.Estimation of Pinus radiata D.Don clear wood properties by near-infrared spectroscopy[J].Journal of Wood Science,2002,48(2):132-137.
[27]
WUS Y.Information system establishment and prediction analysis for SVM model of RBF kernel function[J].Journal of Physics:Conference Series,2021,1982(1):81-93.