基于近红外光谱和稀疏偏最小二乘回归的生物质工业分析

林木生物质能源作为一种新型可再生能源，具有非常广阔的发展前景。基于近红外光谱技术，首次引入稀疏偏最小二乘回归建立木屑生物质的工业分析模型，用于生物质燃料特性的快速分析测定。工业分析总共测定了80种木屑的水分、灰分、挥发分和固定碳含量百分比;按照样品种类和产地将其划分为训练集和测试集，利用近红外光谱仪采集光谱数据并进行小波滤波处理;再利用稀疏偏最小二乘回归建立木屑生物质的定量分析模型，并与主成分回归、偏最小二乘回归、最小绝对收敛及变量筛选方法的建模效果进行比较。结果证明，相对于以上三种建模方法，稀疏偏最小二乘回归能够挑选出有重要影响的波长群组，降低非目标波段的噪声干扰，从而增强数学模型的解释能力并提高定量分析的准确度。利用稀疏偏最小二乘回归算法挑选的波长区间基本覆盖了工业分析中水分的吸收峰，而对于灰分、挥发分和固定碳的吸收峰波段尚无准确定位，需要继续探讨。总体而言，稀疏偏最小二乘回归能够减少无关信息的干扰，提高模型定量分析的准确度，增强模型的解释能力，将会在近红外光谱技术应用领域内起到重要作用。

Biomass Compositional Analysis Using Sparse Partial Least Squares Regression and Near Infrared Spectrum Technique

Forest bio-fuel, a new type renewable energy, has attracted increasing attention as a promising alternative. In this study, a new method called Sparse Partial Least Squares Regression(SPLS) is used to construct the proximate analysis model to analyze the fuel characteristics of sawdust combining Near Infrared Spectrum Technique. Moisture, Ash, Volatile and Fixed Carbon percentage of 80 samples have been measured by traditional proximate analysis. Spectroscopic data were collected by Nicolet NIR spectrometer. After being filtered by wavelet transform, all of the samples are divided into training set and validation set according to sample category and producing area. SPLS, Principle Component Regression (PCR), Partial Least Squares Regression (PLS) and Least Absolute Shrinkage and Selection Operator (LASSO) are presented to construct prediction model. The result advocated that SPLS can select grouped wavelengths and improve the prediction performance. The absorption peaks of the Moisture is covered in the selected wavelengths, well other compositions have not been confirmed yet. In a word, SPLS can reduce the dimensionality of complex data sets and interpret the relationship between spectroscopic data and composition concentration, which will play an increasingly important role in the field of NIR application.