摘要
以柞木为研究对象,以900~1 700 nm的近红外光谱仪获取木材表面近红外光谱数据,对89个柞木样本进行检测,其中58个组成校正集,31个为预测集。首先,采集样本径切面光谱数据,并利用SG平滑对光谱数据进行预处理;然后,利用反向区间偏最小二乘（Bi PLS）选出均方根误差最小的波长区间组合;再利用连续投影算法（SPA）进一步选择出波长特征;最后,以优选出的波长特征作为输入,建立偏最小二乘法回归模型,确定出木材基本密度与近红外光谱之间的联系。Bi PLS算法将光谱划分区间划分为10时,均方根误差最小,其最佳区间组合为[3 5 6 7 9],变量个数由全光谱117个降至59个;应用SPA算法二次降维,变量个数降至6个,降低变量信息的冗余,减少了变量个数,提高了建模的速度和效率。Bi PLS-SPA模型较PLS、i PLS、Bi PLS、SPA-PLS具有更高的相关系数,更小的均方根误差,柞木基本密度预测相关系数为0.925,预测均方根误差为0.010 4,相对分析误差为2.83。
With Xylosma racemosum as the research object,900-1 700 nm near-infrared spectrometer was used to obtain wood surface spectral data. The 89 X. racemosum samples were detected,of which 58 composed the calibration set,and 31 were used for the prediction set. Firstly,the diameter section spectral data was acquired and preprocessed by SG smoothing method; Secondly,backward interval partial least squares（ BiP LS） was implemented to divide the spectrum into several wavelength interval,and intervals with the smallest RMSE were selected as a data combination; thirdly,successive projections algorithm（ SPA） was chosen to select the wavelength characteristics from the data combination; Then,using optimized characteristics as the input variable,partial least squares regression model can be established and finally the correlation between the near infrared spectrum and wood basic density was built. The RMSECV had minimum value when the spectrum was divided into 10 intervals,and the optimum interval combination was [3 5 6 7 9],and the number of variables dropped from 117 to 6. Consequently,the number of variables were reduced and the modeling speed was increased.BiP LS-SPA model has a higher correlation coefficient than the PLS,iP LS,BiP LS,SPA-PLS method. The prediction correlation coefficient of X. racemosum basic density is 0.925,with the RMSEP of 0.010 4,and the RPD of 2.83.
出处
《东北林业大学学报》
CAS
CSCD
北大核心
2016年第10期79-83,共5页
Journal of Northeast Forestry University
基金
国家林业局"948"项目(2015-4-52)
