摘  要：針對室外光照對近紅外光譜檢測帶來誤差的問題，提出基于模型傳遞來減少檢測誤差的方法。以圓黃梨為樣品，分析樣品在室內(nèi)、室外陰影下的近紅外光譜，建立室內(nèi)光譜的偏最小二乘（PLS）模型。采用直接校正（direct standardization，DS）算法，減小室內(nèi)外光譜差距，使得室內(nèi)PLS模型能預(yù)測室外光譜。結(jié)果表明：在室內(nèi)建立的模型能預(yù)測經(jīng)DS算法傳遞后的室外光譜，預(yù)測決定系數(shù)（r2p）和預(yù)測均方根誤差（root mean square error of prediction，RMSEP）分別為0.71和0.374，能有效解決室外光照對光譜檢測的影響。

關(guān)鍵詞：近紅外光譜；直接校正；光照影響；模型傳遞；糖度

文獻(xiàn)標(biāo)志碼：A       文章編號：1674-5124（2015）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