中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 均匀设计-PLS-NIR法预测卷烟配方烟丝中梗丝及薄片丝含量 中国烟草学报 2010,16 (2) 26-30
Position: Home > Articles > Estimation of cut stem and reconstituted tobacco content in different cigarette blends by uniform design-PLS-NIR Acta Tabacaria Sinica 2010,16 (2) 26-30

均匀设计-PLS-NIR法预测卷烟配方烟丝中梗丝及薄片丝含量

作  者：
胡立中;张胜军;余小平;张灵辉
单  位：
安徽中烟工业公司技术中心
关键词：
均匀设计;梗丝;薄片丝;结构;近红外模型
摘  要：
利用均匀试验设计方法,确立预测的样品集111组。依据梗丝、薄片丝和烟丝不同的光谱特性,使用近红外光谱检测仪收集样品集的光谱信息,采用偏最小二乘法,建立梗丝、薄片丝在烟支中比例的近红外测试模型。结果表明:梗丝、薄片丝与叶丝配方模型具有较好的预测准确性,梗丝均方差为0.500,平均相对误差在6.44%以下;薄片丝均方差为0.487,其平均相对误差在6.88%。
译  名：
Estimation of cut stem and reconstituted tobacco content in different cigarette blends by uniform design-PLS-NIR
作  者：
HU Li-zhong,ZHANG Sheng-jun,YU Xiao-ping,ZHANGg Ling-huiTechnology Center of China Tobacco Anhui Industrial Corporation,Hefei 230081,China
关键词：
uniform design;cut stem;reconstituted tobacco;blend make-up;NIR model
摘  要：
111 predicted sample sets were ascertained by employing method of uniform experimental design.Due to different spectral properties of cut stem,reconstituted tobacco,and cut tobacco,the spectral information was collected by near-infrared spectrometer.Based on spectral differences,a near-infrared spectrum model of the samples,obtained through blending different proportion of cut stem and reconstituted tobacco,was established using partial least squares(PLS)method.Result showed that the model had a high predictive capability.The mean square deviation of cut stem was 0.500,and its average relative error was below 6.44%;while in the case of the reconstituted tobacco,the corresponding values were 0.487 and about 6.88%,respectively.

相似文章

导出引用
计量
文章访问数: 16
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46