CAJ | 학술논문

采用偏最小二乘法和径向基神经网络结合近红外光谱技术建立蝙蝠蛾拟青霉发酵菌丝体中虫草酸、多糖和腺苷含量的定量分析模型，模型泛化能力强且预测精度高，能够满足原料药及相关产品实际检测中的应用。通过化学诱变和液体深层发酵获得214个蝙蝠蛾拟青霉菌丝体样品，扫描获得近红外光谱，采用常规方法测定样品中虫草酸、多糖和腺苷的含量。在应用蒙特卡罗偏最小二乘法识别异常样品、确定校正集样品数量的基础上，以逼近度（Da）为评价指标，采用可移动窗口偏最小二乘法和径向基神经网络筛选特征波长变量，最佳光谱预处理方法及建模重要参数。通过比较分析，最终确定蝙蝠蛾拟青霉菌丝体中虫草酸、多糖和腺苷含量定量分析模型分别为RBFNN ，RBFNN和PLS模型，其校正集和预测集样品实验测定值与预测值间相关系数（R2p 和 R2c ）分别为0.9417和0.9663，0.9803和0.9850，0.9761和0.9728，表明模型具有很好的拟合度和预测性能。
채용편최소이승법화경향기신경망락결합근홍외광보기술건립편복아의청매발효균사체중충초산、다당화선감함량적정량분석모형，모형범화능력강차예측정도고，능구만족원료약급상관산품실제검측중적응용。통과화학유변화액체심층발효획득214개편복아의청매균사체양품，소묘획득근홍외광보，채용상규방법측정양품중충초산、다당화선감적함량。재응용몽특잡라편최소이승법식별이상양품、학정교정집양품수량적기출상，이핍근도（Da）위평개지표，채용가이동창구편최소이승법화경향기신경망락사선특정파장변량，최가광보예처리방법급건모중요삼수。통과비교분석，최종학정편복아의청매균사체중충초산、다당화선감함량정량분석모형분별위RBFNN ，RBFNN화PLS모형，기교정집화예측집양품실험측정치여예측치간상관계수（R2p 화 R2c ）분별위0.9417화0.9663，0.9803화0.9850，0.9761화0.9728，표명모형구유흔호적의합도화예측성능。
Partial least squares (PLS) and radial basis function neural network (RBFNN) combined with near infrared spectros-copy (NIR) were applied to develop models for cordycepic acid ,polysaccharide and adenosine analysis in Paecilomyces hepialid fermentation mycelium .The developed models possess well generalization and predictive ability which can be applied for crude drugs and related productions determination .During the experiment ,214 Paecilomyces hepialid mycelium samples were ob-tained via chemical mutagenesis combined with submerged fermentation .The contents of cordycepic acid ,polysaccharide and a-denosine were determined via traditional methods and the near infrared spectroscopy data were collected .The outliers were re-moved and the numbers of calibration set were confirmed via Monte Carlo partial least square (MCPLS) method .Based on the values of degree of approach (Da) ,both moving window partial least squares (MWPLS) and moving window radial basis func-tion neural network (MWRBFNN) were applied to optimize characteristic wavelength variables ,optimum preprocessing methods and other important variables in the models .After comparison ,the RBFNN ,RBFNN and PLS models were developed success-fully for cordycepic acid ,polysaccharide and adenosine detection ,and the correlation between reference values and predictive val-ues in both calibration set (R2c ) and validation set (R2p ) of optimum models was 0.941 7 and 0.966 3 ,0.980 3 and 0.985 0 ,and 0.976 1 and 0.972 8 ,respectively .All the data suggest that these models possess well fitness and predictive ability .