基于近红外光谱技术的含节子木材抗弯性能研究  

Research on the Bending Resistance of Wood Containing Knots Based on Near-infrared Spectroscopy Technology

作　　者：宋闯 孙丽萍[2] 王鹏鲲 杨杨 SONG Chuang;SUN Liping;WANG Pengkun;YANG Yang(The 723 Institute of CSSC,Yangzhou 225000,China;College of Mechanical and Electrical Engineering,Northeast Forestry University,Harbin 150040,China;Harbin University,Harbin 150076,China)

机构地区：[1]中国船舶集团有限公司第七二三研究所,江苏扬州225000 [2]东北林业大学,机电工程学院,哈尔滨150040 [3]哈尔滨学院,哈尔滨150076

出　　处：《森林工程》2024年第4期168-174,共7页Forest Engineering

基　　金：中国博士后科学基金项目(2019M651240)。

摘　　要：针对含节子木材力学特性不确定,不易判断其是否可用的现状,提出一种通过检测含节子木材的抗弯性能来对含有节子的木材是否可用进行评判的方法。选取在东北地区占到总森林面积15%~20%的常见树木蒙古栎为试验对象,首先采用目标检测算法对木材表面含节子区域进行识别;然后对识别的区域进行光谱提取,并构建定量预测模型;最后通过深度学习对含节子木材的力学性能进行分析。试验结果表明,提出的基于连续投影的支持向量机算法(Successive Projections AlgorithmSupport Vector Machine,SPA-SVM)预测模型对木材抗弯性能具有优秀的预测能力,其试验结果指标决定系数R2=0.96,均方根误差RMSE=0.58,相对分析误差RPD=5.09。该预测模型能非常准确地对含节子木材的抗弯性能进行预测,预测结果与真实数值误差较小,符合试验要求标准,预测结果可以为木材是否使用提供依据。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.

关 键 词：近红外光谱 抗弯性能 力学样本制备 光谱数据处理 特征值提取 支持向量机 预测模型 

分 类 号：S784[农业科学—林学]