光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2014年
6期
1707-1710
,共4页
近红外光谱%异常样品剔除%油页岩%含油率
近紅外光譜%異常樣品剔除%油頁巖%含油率
근홍외광보%이상양품척제%유혈암%함유솔
Near-infrared spectroscopy%Outliers detection%Oil shale%Oil yield
研究了漫反射近红外（NIR）光谱法分析油页岩含油率过程中异常样品的识别和剔除方法。在近红外光谱定量分析中，环境变化和操作失误等都会产生异常样品，异常样品的存在会导致模型的预测能力下降，因此异常样品的剔除是建模过程中的关键步骤。分别采用主成分分析-马氏距离（PCA-MD）法和半数重采样（RHM）法识别油页岩光谱数据中的异常样品，通过剔除异常样品后所建的偏最小二乘（PLS）分析模型的性能来评价PCA-MD与RHM方法对异常样品的识别能力。实验中考察了不同 MD阈值和RHM置信度对异常样品剔除结果的影响，比较了单独和同时应用PCA-MD及RHM法识别并剔除异常样品后所得PLS模型的预测能力。结果表明：与所有样品参与建模时预测偏差均方根（RMSEP）相比，采用PCA-MD法时阈值取平均值与标准偏差之和时 RMSEP 降低了48．3％；采用 RHM法时置信度取85％时 RMSEP 降低了27．5％；同时采用PCA-MD法和RHM法时RMSEP降低了44．8％，研究内容有效地提高了分析模型的预测能力。
研究瞭漫反射近紅外（NIR）光譜法分析油頁巖含油率過程中異常樣品的識彆和剔除方法。在近紅外光譜定量分析中，環境變化和操作失誤等都會產生異常樣品，異常樣品的存在會導緻模型的預測能力下降，因此異常樣品的剔除是建模過程中的關鍵步驟。分彆採用主成分分析-馬氏距離（PCA-MD）法和半數重採樣（RHM）法識彆油頁巖光譜數據中的異常樣品，通過剔除異常樣品後所建的偏最小二乘（PLS）分析模型的性能來評價PCA-MD與RHM方法對異常樣品的識彆能力。實驗中攷察瞭不同 MD閾值和RHM置信度對異常樣品剔除結果的影響，比較瞭單獨和同時應用PCA-MD及RHM法識彆併剔除異常樣品後所得PLS模型的預測能力。結果錶明：與所有樣品參與建模時預測偏差均方根（RMSEP）相比，採用PCA-MD法時閾值取平均值與標準偏差之和時 RMSEP 降低瞭48．3％；採用 RHM法時置信度取85％時 RMSEP 降低瞭27．5％；同時採用PCA-MD法和RHM法時RMSEP降低瞭44．8％，研究內容有效地提高瞭分析模型的預測能力。
연구료만반사근홍외（NIR）광보법분석유혈암함유솔과정중이상양품적식별화척제방법。재근홍외광보정량분석중，배경변화화조작실오등도회산생이상양품，이상양품적존재회도치모형적예측능력하강，인차이상양품적척제시건모과정중적관건보취。분별채용주성분분석-마씨거리（PCA-MD）법화반수중채양（RHM）법식별유혈암광보수거중적이상양품，통과척제이상양품후소건적편최소이승（PLS）분석모형적성능래평개PCA-MD여RHM방법대이상양품적식별능력。실험중고찰료불동 MD역치화RHM치신도대이상양품척제결과적영향，비교료단독화동시응용PCA-MD급RHM법식별병척제이상양품후소득PLS모형적예측능력。결과표명：여소유양품삼여건모시예측편차균방근（RMSEP）상비，채용PCA-MD법시역치취평균치여표준편차지화시 RMSEP 강저료48．3％；채용 RHM법시치신도취85％시 RMSEP 강저료27．5％；동시채용PCA-MD법화RHM법시RMSEP강저료44．8％，연구내용유효지제고료분석모형적예측능력。
In the present paper,the outlier detection methods for determination of oil yield in oil shale using near-infrared (NIR) diffuse reflection spectroscopy was studied.During the quantitative analysis with near-infrared spectroscopy,environmental change and operator error will both produce outliers.The presence of outliers will affect the overall distribution trend of samples and lead to the decrease in predictive capability.Thus,the detection of outliers are important for the construction of high-quality calibration models.The methods including principal component analysis-Mahalanobis distance (PCA-MD)and resampling by half-means (RHM)were applied to the discrimination and elimination of outliers in this work.The thresholds and confidences for MD and RHM were optimized using the performance of partial least squares (PLS)models constructed after the elimination of outliers,respectively.Compared with the model constructed with the data of full spectrum,the values of RMSEP of the mod-els constructed with the application of PCA-MD with a threshold of a value equal to the sum of average and standard deviation of MD,RHM with the confidence level of 85%,and the combination of PCA-MD and RHM,were reduced by 48. 3%,27. 5% and 44. 8%,respectively.The predictive ability of the calibration model has been improved effectively.
