Department of Chemistry and Applied Biosciences, ETH Zurich, Switzerland.
Anal Chim Acta. 2011 Mar 18;689(2):190-7. doi: 10.1016/j.aca.2011.01.041. Epub 2011 Jan 26.
The use of biofuels, such as bioethanol or biodiesel, has rapidly increased in the last few years. Near infrared (near-IR, NIR, or NIRS) spectroscopy (>4000cm(-1)) has previously been reported as a cheap and fast alternative for biodiesel quality control when compared with infrared, Raman, or nuclear magnetic resonance (NMR) methods; in addition, NIR can easily be done in real time (on-line). In this proof-of-principle paper, we attempt to find a correlation between the near infrared spectrum of a biodiesel sample and its base stock. This correlation is used to classify fuel samples into 10 groups according to their origin (vegetable oil): sunflower, coconut, palm, soy/soya, cottonseed, castor, Jatropha, etc. Principal component analysis (PCA) is used for outlier detection and dimensionality reduction of the NIR spectral data. Four different multivariate data analysis techniques are used to solve the classification problem, including regularized discriminant analysis (RDA), partial least squares method/projection on latent structures (PLS-DA), K-nearest neighbors (KNN) technique, and support vector machines (SVMs). Classifying biodiesel by feedstock (base stock) type can be successfully solved with modern machine learning techniques and NIR spectroscopy data. KNN and SVM methods were found to be highly effective for biodiesel classification by feedstock oil type. A classification error (E) of less than 5% can be reached using an SVM-based approach. If computational time is an important consideration, the KNN technique (E=6.2%) can be recommended for practical (industrial) implementation. Comparison with gasoline and motor oil data shows the relative simplicity of this methodology for biodiesel classification.
在过去的几年中，生物燃料的使用（如生物乙醇或生物柴油）迅速增加。与红外、拉曼或核磁共振（NMR）方法相比，近红外（近红外，NIR，或 NIRS）光谱（>4000cm（-1））以前被报道为生物柴油质量控制的一种廉价和快速替代方法；此外，NIR 可以很容易地实时进行（在线）。在这篇原理验证论文中，我们试图找到生物柴油样品的近红外光谱与其基础油之间的相关性。该相关性用于根据其来源（植物油）将燃料样品分类为 10 组：向日葵、椰子、棕榈、大豆/大豆、棉籽油、蓖麻、麻疯树等。主成分分析（PCA）用于异常值检测和 NIR 光谱数据的降维。使用了四种不同的多元数据分析技术来解决分类问题，包括正则判别分析（RDA）、偏最小二乘法/潜在结构投影（PLS-DA）、K-最近邻（KNN）技术和支持向量机（SVMs）。使用现代机器学习技术和 NIR 光谱数据可以成功地按原料（基础油）类型对生物柴油进行分类。发现 KNN 和 SVM 方法非常适合基于原料油类型的生物柴油分类。使用基于 SVM 的方法可以达到小于 5%的分类错误（E）。如果计算时间是一个重要的考虑因素，那么 KNN 技术（E=6.2%）可以推荐用于实际（工业）实施。与汽油和机油数据的比较表明，该方法对于生物柴油分类相对简单。
