| 基于近红外光谱技术建立沉香含油量预测模型 |
| |
| 引用本文： | 林艳,何紫迪,毛积鹏,蒋开彬,刘天颐,黄少伟.基于近红外光谱技术建立沉香含油量预测模型[J].热带作物学报,2018,39(1):182-188. |
| |
| 作者姓名： | 林艳 何紫迪 毛积鹏 蒋开彬 刘天颐 黄少伟 |
| |
| 作者单位： | 1华南农业大学林学与风景园林学院
2广东省森林植物种质资源创新与利用重点实验室 |
| |
| 摘 要： | 为建立沉香(Aquilaria sp.)含油量的近红外光谱预测模型,在950~1 650 nm的光谱范围内,使用DA7200 NIRS分析仪收集了64个沉香样本的光谱数据,采用偏最小二乘法(PLS)建立回归模型,并选择最佳预处理方法和最佳主成分数,建立沉香含油量近红外光谱模型。结果表明,采用卷积平滑法(S-G)对光谱进行预处理且当最佳主成分数为7时,可达到最优模型,其校正集相关系数(RC)和校正集均方根误差(RMSEC)分别为0.980 9和0.958 9,交互验证集相关系数(RV)和交互验证集均方根误差(RMSEV)分别为0.697 4、1.029 0。说明预测值与测量值具有显著的相关性,该模型的预测准确度较高,可以满足对沉香结香品质进行快速预测的要求。
|
| 关 键 词： | 近红外 沉香 含油量 预测模型 |
Prediction Models of Oil Content of Agarwood Based on Near Infrared Spectroscopy |
| |
| LIN Yan,HE Zidi,MAO Jipeng,JIANG Kaibin,LIU Tianyi,HUANG Shaowei.Prediction Models of Oil Content of Agarwood Based on Near Infrared Spectroscopy[J].Chinese Journal of Tropical Crops,2018,39(1):182-188. |
| |
| Authors: | LIN Yan HE Zidi MAO Jipeng JIANG Kaibin LIU Tianyi HUANG Shaowei |
| |
| Institution: | 1College of Forestry and Landscape Architecture, South China Agricultural University
2 Guangdong Key Laboratory for Innovative Development and Utilization of Forest Plant Germplasm, Guangzhou, Guangdong 510642, China |
| |
| Abstract: | The spectral data of 64 agarwood samples between the spectrum of 950 nm to 1 650 nm were collected using DA7200 NIRS analyzer to estabilish a prediction model of near infrared spectroscopy of agarwood oil content. A regression model was established using the partial least squares (PLS) method, and selecting the best pretreatment method and the optimal number of principal components to set up a model of the near infrared spectra of the oil content. Results showed that the smoothing ( S-G) method was best for spectral preprocessing, and when the best optimum principal component number was 7 can achieve the optimal mode. The related coefficient of calibration (RC) and root mean square error of calibration (RMSEC) was 0.980 9, 0.958 9; the related coefficient of validation ( RV) and root mean square error of validation ( RMSEV) was 0.697 4, 1.029 0. The prediction value has a significant correlation with the measured value, and the prediction accuracy of the model is high, which can meet the requirement of rapid prediction of agarwood quality. |
| |
| Keywords: | near infrared spectroscopy Aquilaria sinensis oil content prediction models |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《热带作物学报》浏览原始摘要信息 |
| 点击此处可从《热带作物学报》下载免费的PDF全文 |
|
