机械故障与润滑油的性状具有紧密关系。因此,研究一种能够快速、无损对润滑油品牌识别方法至关重要。该研究应用近红外光谱分析法结合偏最小二乘判别分析(Partial Least Squares-Discriminant Analysis,PLS-DA)模式识别方法对7种润滑油...机械故障与润滑油的性状具有紧密关系。因此,研究一种能够快速、无损对润滑油品牌识别方法至关重要。该研究应用近红外光谱分析法结合偏最小二乘判别分析(Partial Least Squares-Discriminant Analysis,PLS-DA)模式识别方法对7种润滑油品牌进行识别。研究结果表明,采用近红外光谱结合PLS-DA方法对校正样本建立判别模型,模型的校正相关系数均大于0.980,校正集均方根误差(RMSEC)和预测集均方根误差(RMSEP)都小于0.062,对7种润滑油品牌识别率均为100%。结合遗传算法对变量进行筛选,选出62个波数点代替全波段进行建模,模型对未知样本的识别率均为98.1%,大大缩减建模的计算量,为在润滑油判别分析仪器开发方面提供一定的理论指导。展开更多
采集四川省筠连县春、夏、秋三季共15份早白尖红茶样品,采用顶空固相萃取-气相色谱-质谱技术对红茶样品的香气成分进行测定,运用偏最小二乘-判别分析(partial least square-discriminant analysis,PLS-DA)建立不同季节茶叶判别模型,绘...采集四川省筠连县春、夏、秋三季共15份早白尖红茶样品,采用顶空固相萃取-气相色谱-质谱技术对红茶样品的香气成分进行测定,运用偏最小二乘-判别分析(partial least square-discriminant analysis,PLS-DA)建立不同季节茶叶判别模型,绘制层次聚类的树状热图确定关键香气成分在不同季节样品中的分布规律。结果表明,春季样品醇类(113.05μg/g)和酯类物质(34.92μg/g)含量明显高于夏秋两季样品,而醛类物质(23.85μg/g)明显低于夏秋两季样品,且所建PLS-DA模型可将春和夏秋两季样品明显区分。进一步分析后的分层聚类的树状热图显示,苯乙醛、橙花醇和香叶醇是春季样品区别于其它两季茶样的特征香气化合物,在此基础上可通过芳樟醇、芳樟醇氧化物Ⅰ和Ⅱ对夏、秋两季样品进行进一步区分。该研究为解析不同季节早白尖红茶香气物质提供基础研究数据,也为进一步探究筠连早白尖红茶关键香气形成机制奠定基础。展开更多
Laser-induced breakdown spectroscopy （LIBS） has become a powerful technology in geological applications. The correct identification of rocks and soils is critical to many geological projects. In this study, LIBS dat...Laser-induced breakdown spectroscopy （LIBS） has become a powerful technology in geological applications. The correct identification of rocks and soils is critical to many geological projects. In this study, LIBS database software with a user-friendly and intuitive interface is developed based on Windows, consisting of a database module and a sample identification module. The database module includes a basic database containing LIBS persistent lines for elements and a dedicated geological database containing LIBS emission lines for several rock and soil reference standards. The module allows easy use of the data. A sample identification module based on partial least squares discriminant analysis （PLS-DA） or support vector machine （SVM） algorithms enables users to classify groups of unknown spectra. The developed system was used to classify rock and soil data sets in a dedicated database and the results demonstrate that the system is capable of fast and accurate classification of rocks and soils, and is thus useful for the detection of geological materials.展开更多
文摘机械故障与润滑油的性状具有紧密关系。因此,研究一种能够快速、无损对润滑油品牌识别方法至关重要。该研究应用近红外光谱分析法结合偏最小二乘判别分析(Partial Least Squares-Discriminant Analysis,PLS-DA)模式识别方法对7种润滑油品牌进行识别。研究结果表明,采用近红外光谱结合PLS-DA方法对校正样本建立判别模型,模型的校正相关系数均大于0.980,校正集均方根误差(RMSEC)和预测集均方根误差(RMSEP)都小于0.062,对7种润滑油品牌识别率均为100%。结合遗传算法对变量进行筛选,选出62个波数点代替全波段进行建模,模型对未知样本的识别率均为98.1%,大大缩减建模的计算量,为在润滑油判别分析仪器开发方面提供一定的理论指导。
文摘采集四川省筠连县春、夏、秋三季共15份早白尖红茶样品,采用顶空固相萃取-气相色谱-质谱技术对红茶样品的香气成分进行测定,运用偏最小二乘-判别分析(partial least square-discriminant analysis,PLS-DA)建立不同季节茶叶判别模型,绘制层次聚类的树状热图确定关键香气成分在不同季节样品中的分布规律。结果表明,春季样品醇类(113.05μg/g)和酯类物质(34.92μg/g)含量明显高于夏秋两季样品,而醛类物质(23.85μg/g)明显低于夏秋两季样品,且所建PLS-DA模型可将春和夏秋两季样品明显区分。进一步分析后的分层聚类的树状热图显示,苯乙醛、橙花醇和香叶醇是春季样品区别于其它两季茶样的特征香气化合物,在此基础上可通过芳樟醇、芳樟醇氧化物Ⅰ和Ⅱ对夏、秋两季样品进行进一步区分。该研究为解析不同季节早白尖红茶香气物质提供基础研究数据,也为进一步探究筠连早白尖红茶关键香气形成机制奠定基础。
基金supported by National Major Scientific Instruments and Equipment Development Special Funds,China(No.2011YQ030113)
文摘Laser-induced breakdown spectroscopy （LIBS） has become a powerful technology in geological applications. The correct identification of rocks and soils is critical to many geological projects. In this study, LIBS database software with a user-friendly and intuitive interface is developed based on Windows, consisting of a database module and a sample identification module. The database module includes a basic database containing LIBS persistent lines for elements and a dedicated geological database containing LIBS emission lines for several rock and soil reference standards. The module allows easy use of the data. A sample identification module based on partial least squares discriminant analysis （PLS-DA） or support vector machine （SVM） algorithms enables users to classify groups of unknown spectra. The developed system was used to classify rock and soil data sets in a dedicated database and the results demonstrate that the system is capable of fast and accurate classification of rocks and soils, and is thus useful for the detection of geological materials.
