不同光照下的近红外光谱模型传递研究 张文君袁 唐 红袁 蒋巧勇 (中国计量学院,测试计量学院,浙江杭州 310018 ) 摘 要院针对室外光照对近红外光谱检测带来误差的问题袁提出基于模型传递来减少检测误差的方法遥 以圆黄梨为 样品袁分析样品在室内尧室外阴影下的近红外光谱袁 建立室内光谱的偏最小二乘渊PLS冤 模型遥 采用直接校正渊direct standardization袁DS冤算法袁减小室内外光谱差距袁使得室内 PLS 模型能预测室外光谱遥 结果表明院在室内建立的模型能 预测经 DS 算法传递后的室外光谱袁预测决定系数渊r 2 p 冤和预测均方根误差渊root mean square error of prediction袁RMSEP冤 分别为 0.71 和 0.374袁能有效解决室外光照对光谱检测的影响遥 关键词院近红外光谱曰直接校正曰光照影响曰模型传递曰糖度 文献标志码院A 文章编号院1674-5124渊2015冤12-0070-04 Research on model transfer of near infrared spectroscopy at different illumination ZHANG Wenjun,TANG Hong,JIANG Qiaoyong ( College of Metrological Technology and Engineering, China Jiliang University, Hangzhou 310018, China ) Abstract: To minimize the error in sample detection by near infrared spectrometers outdoor, a method using model transfer to lower the measurement error has been proposed in this paper. The near infrared spectroscopy ( NIRS ) was used to detect the sample-Wonhuwang pear under outdoor and indoor shadows and the results were analyzed to establish a Partial Least Squares ( PLS ) model for indoor spectrum. The detection errors between the near infrared spectrums under indoor and outdoor shadows were reduced through Direct Standardization ( DS ) algorithm to enable the model to predict the near infrared spectrum outdoor. Experimental results show the determination coefficient and root mean square error of prediction are 0.71 and 0.374 respectively. It can lower the effect of outdoor light on spectrum detection. Keywords: NIRS;DS;illumination;model transfer;sugar 收稿日期院2015-06-10曰收到修改稿日期院2015-08-14 基金项目院浙江省自然科学基金渊Y14F020161冤 作者简介: 张文君渊1990-冤袁女袁江苏南通市人袁硕士研究生袁 专业方向为近红外检测技术遥 0 引 言 室内恒定条件下袁近红外光谱技术广泛应用于水 果品质检测遥 但在水果摊尧果园等有光照的环境下进 行检测时袁光照会影响光谱的检测结果遥 关于室外光 照对近红外光谱检测影响的研究很少遥 Saranwong [1] 研 究芒果在室内和室外不同光照条件下的可溶性固形 物袁得出用黑色袋子套在芒果上可以消除部分光照 影响袁 但应用范围有限曰吴方龙 [2] 在室内通过台灯数 量来模拟不同光照强度对贡梨光谱检测的影响袁但 灯光并不等同于室外光照袁 实验结果也不能准确反 映室外光照的影响遥 国内学者将模型传递的方法应用于不同环境下 检测遥 胡润文 [3] 将脐橙总糖光谱建立在不同仪器上传 递袁对比了斜率截距校正法和 DS 算法的传递效果曰 中国测试 CHINA MEASUREMENT & TEST Vol.41 No.12 December, 2015 第 41 卷第 12 期 2015 年 12 月 doi院10.11857/j.issn.1674-5124.2015.12.018
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
预测经 DS 算法传递后的室外光谱袁预测决定系数渊r2p冤和预测均方根误差渊root mean square error of prediction袁RMSEP冤分别为 0.71 和 0.374袁能有效解决室外光照对光谱检测的影响遥关键词院近红外光谱曰直接校正曰光照影响曰模型传递曰糖度
文献标志码院A 文章编号院1674-5124渊2015冤12-0070-04
Research on model transfer of near infrared spectroscopy at different illumination
ZHANG Wenjun,TANG Hong,JIANG Qiaoyong(College of Metrological Technology and Engineering,China Jiliang University,Hangzhou 310018,China)
Abstract: To minimize the error in sample detection by near infrared spectrometers outdoor, amethod using model transfer to lower the measurement error has been proposed in this paper. Thenear infrared spectroscopy (NIRS)was used to detect the sample-Wonhuwang pear under outdoorand indoor shadows and the results were analyzed to establish a Partial Least Squares (PLS)model for indoor spectrum. The detection errors between the near infrared spectrums under indoorand outdoor shadows were reduced through Direct Standardization (DS) algorithm to enable themodel to predict the near infrared spectrum outdoor. Experimental results show the determinationcoefficient and root mean square error of prediction are 0.71 and 0.374 respectively. It can lowerthe effect of outdoor light on spectrum detection.Keywords: NIRS;DS;illumination;model transfer;sugar
[1] Saranwong S袁 Sornsrivichai J袁 Kawano S. On-tree eval鄄uation of harvesting quality of mango fruit using ahand-held NIR instrument[J]. Journal of Near InfraredSpectroscopy袁2003袁11渊4冤院283-293.