光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2014年
12期
3257-3261
,共5页
近红外%变量选择%棉麻混纺织物%棉含量
近紅外%變量選擇%棉痳混紡織物%棉含量
근홍외%변량선택%면마혼방직물%면함량
Near infrared%Variable selection%Cotton/ramie blended fabric%Cotton content
纺织品纤维成分的快速检测对其生产过程质量监控、贸易和市场监督均具有重要的意义。利用近红外光谱技术联合变量优选对棉麻混纺织物中的棉含量进行快速检测研究。采用NIRFlex N-500型傅里叶近红外光谱仪在4000～10000 cm －1光谱范围内采集样本的反射光谱，对样本光谱进行范围初选和预处理分析。在此基础上，利用 UVE（uninformative variables elimination），SPA（successive projections algorithm）及CARS （competitive adaptive reweighted sampling ）方法对光谱变量进行优选，再应用 PLS （partial least squares）建立棉麻混纺织物中的棉含量预测模型。最后，采用最优预测模型对未参与建模的样本进行预测。研究结果表明，4052～8000 cm －1光谱范围为棉含量较优的建模光谱范围。C A RS变量选择方法能较为有效地提高预测模型的精度，CARS-PLS模型的校正集、预测集相关系数和均方根误差分别为0.903，0.749和8.01％，12.93％。因此，近红外光谱联合C A RS变量优选可以用于棉麻混纺织物棉含量的快速检测，C A RS方法可以有效简化预测模型，提高预测模型性能。
紡織品纖維成分的快速檢測對其生產過程質量鑑控、貿易和市場鑑督均具有重要的意義。利用近紅外光譜技術聯閤變量優選對棉痳混紡織物中的棉含量進行快速檢測研究。採用NIRFlex N-500型傅裏葉近紅外光譜儀在4000～10000 cm －1光譜範圍內採集樣本的反射光譜，對樣本光譜進行範圍初選和預處理分析。在此基礎上，利用 UVE（uninformative variables elimination），SPA（successive projections algorithm）及CARS （competitive adaptive reweighted sampling ）方法對光譜變量進行優選，再應用 PLS （partial least squares）建立棉痳混紡織物中的棉含量預測模型。最後，採用最優預測模型對未參與建模的樣本進行預測。研究結果錶明，4052～8000 cm －1光譜範圍為棉含量較優的建模光譜範圍。C A RS變量選擇方法能較為有效地提高預測模型的精度，CARS-PLS模型的校正集、預測集相關繫數和均方根誤差分彆為0.903，0.749和8.01％，12.93％。因此，近紅外光譜聯閤C A RS變量優選可以用于棉痳混紡織物棉含量的快速檢測，C A RS方法可以有效簡化預測模型，提高預測模型性能。
방직품섬유성분적쾌속검측대기생산과정질량감공、무역화시장감독균구유중요적의의。이용근홍외광보기술연합변량우선대면마혼방직물중적면함량진행쾌속검측연구。채용NIRFlex N-500형부리협근홍외광보의재4000～10000 cm －1광보범위내채집양본적반사광보，대양본광보진행범위초선화예처리분석。재차기출상，이용 UVE（uninformative variables elimination），SPA（successive projections algorithm）급CARS （competitive adaptive reweighted sampling ）방법대광보변량진행우선，재응용 PLS （partial least squares）건립면마혼방직물중적면함량예측모형。최후，채용최우예측모형대미삼여건모적양본진행예측。연구결과표명，4052～8000 cm －1광보범위위면함량교우적건모광보범위。C A RS변량선택방법능교위유효지제고예측모형적정도，CARS-PLS모형적교정집、예측집상관계수화균방근오차분별위0.903，0.749화8.01％，12.93％。인차，근홍외광보연합C A RS변량우선가이용우면마혼방직물면함량적쾌속검측，C A RS방법가이유효간화예측모형，제고예측모형성능。
Rapid detection of textile fiber components is very important for production process of quality control ,trading and market surveillance .The objective of this research was to assess cotton content in cotton/ramie blended fabric quickly by near in-frared (NIR) spectrum technology and variable selection methods .Reflectance spectra of samples were acquired by a NIRFlex N-500 Fourier spectroscopy in the range of 4 000~10 000 cm -1 ,primary election of spectral range and pretreatment analysis were conducted first .Then ,three variable selection methods such as UVE (uninformative variables elimination ) ,SPA (successive projections algorithm ) and CARS (competitive adaptive reweighted sampling ) were used to select sensitive variables .After that , PLS (partial least squares) was used to develop calibration model for cotton content of cotton/ramie blended fabric ,and the best calibration model was used to predict cotton content of samples in prediction set .The result indicates that range of 4 052~8 000 cm -1 is optimal spectral range for cotton content modeling .CARS method is an efficient method to improve model performance , the correlation coefficient and root mean square error of CARS-PLS for calibration and prediction sets are 0.903 ,0.749 and 8.01% ,12.93% ,respectively .So NIR spectra combined with CARS method is feasible for assessing cotton content in cotton/ramie blended fabric ,and CARS method can simplify model ,improve model performance .
