为实现掺混汽油快速无损鉴别，提出一种利用t 分布邻域嵌入结合深度置信网络的鉴别方法，以解决机器学习中高维特征向量间的非线性关系。以92#、95#、98#及定比混合汽油为研究对象，采用多元散射校正算法对原始红外波段投射光谱测量数据进行预处理，利用t-SNE非线性方法进行光谱数据降维处理，分别采用深度置信网络和极限学习机建立汽油种类光谱鉴别模型并对比分析两种方法识别精度。研究表明：该文所选择方法构建的汽油鉴别模型性能更优，对汽油种类预测精准度高达92.5%，从而验证了该方法在汽油鉴别中的有效性。研究结果可为掺混成品油鉴别及溯源研究提供技术支持。
Abstract
In order to realize the fast nondestructive identification of blended gasoline, an identification method based on t-distributed stochastic neighborhood embedding(t-SNT) combined with deep belief networks was proposed to solve the nonlinear relationship between high-dimensional feature vectors in machine learning. Taking 92#, 95#, 98# and fixed ratio blended gasoline as the research objects, the projection spectrum measurement data in original infrared band was preprocessed by multivariate scattering correction algorithm, and the dimension reduction of spectral data was carried out by using t-SNE nonlinear method. The spectral identification model of gasoline types was established by using deep belief networks and extreme learning machine respectively, and the identification accuracy of the two methods was compared and analyzed. The research shows that the gasoline identification model constructed by this method has better performance, and the prediction accuracy of gasoline types is as high as 92.5%, which verifies the effectiveness of this method in gasoline identification. The results of this research can provide technical support for the identification and traceability of blending refined oil products.
关键词
深度置信网络 /
鉴别 /
掺混 /
红外光谱
{{custom_keyword}} /
Key words
deep belief networks /
infrared spectrum /
blending /
identification
{{custom_keyword}} /
基金
中国石油科技创新基金研究项目（2018D-5007-0608）；东北石油大学优秀中青年创新团队基金（KYCXTD201901）；大庆市指导性科技项目（zd-2019-04）
{{custom_fund}}
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
陈玥洋, 高志山, 郁晓晖, 等. 基于区间组合移动窗口法筛选近红外光谱信息[J]. 应用光学,2017,38(1):99-105.
谈爱玲, 毕卫红. 基于近红外光谱法的多组分复杂溢油源定量建模分析[J]. 光谱学与光谱分析,2019,43(5):86-90.
姜黎, 张军, 陈哲, 等. 基于不同波段对成品汽油的模式识别分析[J]. 光谱实验室,2010,27(3):1208-1212.
王丽, 卓林, 何鹰, 等. 近红外光谱技术鉴别海面溢油[J]. 光谱学与光谱分析,2009,24(12):1537-1539.
郝勇, 陈斌. 近红外光谱预处理中几种小波消噪方法的分析[J]. 光谱学与光谱分析,2006,26(10):1838-1841.
沈永, 郭天太, 孔明, 等. 基于D-ELM的矿井气体FTIR光谱定量分析[J]. 应用光学,2016,37(5):725-729.
王振浩, 杜虹锦, 李国庆, 等. 基于t-分布邻域嵌入的同调机群无监督识别[J]. 电力系统保护与控制,2018,46(22):64-71.
董骏. 面向数据集的ST-SNE算法高维数据降维研究[J]. 计算技术与
CHEN Yueyang, GAO Zhishan, YU Xiaohui, et al. Screening near infrared spectral information based on interval combination moving window method[J]. Applied Optics,2017,38(1):99-105.
TAN Ailing, BI Weihong. Quantitative modeling analysis of multi-component complex oil spill sources based on near infrared spectroscopy[J]. Spectroscopy and Spectral Analysis,2019,43(5):86-90.
VERAS G, GOMES A, DASILVA A. Classification of biodiesel sing NIR spectrometry and multivariate techniques[J]. Talanta,2009,83(2):565-568.
JIANG Li, ZHANG Jun, CHEN Zhe, et al. Pattern recognition analysis of finished gasoline based on different bands[J]. Spectroscopy Laboratory,2010,27(3):1208-1212.
WANG Li, ZHUO Lin, HE Ying, et al. Identification of oil spills by near infrared spectroscopy[J]. Spectroscopy and Spectral Analysis,2009,24(12):1537-1539.
VAN DER MAATEN L, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learing Research,2008,9:2579-2605.
HINTON G E, OSINDERO S, THE Y W. A fast learning algor
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
