目前针对牡丹籽油掺假量化的研究工作仍集中于单一普通植物油的掺假行为，因此有必要考虑更加 复杂的掺假造假情况。本文采用便携式近红外拉曼光谱技术结合粒子群优化广义回归神经网络算法(PSO- GRNN) 助力解译牡丹籽油复杂掺假行为。首先，采用廉价葵花籽油和玉米油的混合油品作为掺假对象，并制 备涵盖由低到高的牡丹籽油掺假浓度，且浓度梯度变化相对均匀。其次，使用便携式近红外拉曼光谱仪分别 采集所有油品样本的拉曼光谱信号，并基于谱学分析对拉曼光谱进行人工降维和权重修正。最后，建立基于 PSO-GRNN 算法的定量分析模型。结果表明基于便携式近红外拉曼光谱技术结合PSO-GRNN 算法可以实 现对牡丹籽油复杂掺假行为的解译，该方案不仅可以实现对牡丹籽油浓度的预测，还可以有效评估多种掺假 廉价植物油的浓度，其中测试集R²>0.94,RMSE<0.036 。 本文深入研究了牡丹籽油可能存在的复杂掺假 行为并提出了相应的解决方案，该方法对牡丹籽油市场监管和品质检测具有一定的借鉴意义。

The research on the quantification of peony seed oil adulteration is still focused on the adulteration of a single cheap vegetable oil,so it is necessary to consider more complex a- dulteration.This paper uses portable near-infrared Raman spectroscopy technology combined with particle swarm optimization generalized regression neural network algorithm(PSO GRNN)to help interpret the complex adulteration behavior of peony seed oil.Firstly,the mixed oil of cheap sunflower seed oil and corn oil was used as the adulteration object.The a- dulteration concentration of peony seed oil was prepared from low to high,and the concen- tration gradient was relatively uniform.Secondly,a portable near-infrared Raman spectrom- eter was used to collect the Raman spectrum signals of all oil samples.The Raman spectra were  manually  reduced   and  weighted  based   on  spectral  analysis.Finally,a  quantitative   anal- ysis  model  based  on  PSO-GRNN  algorithm  was  established.The  results  show  that  the  com- plex  adulteration  behavior  of peony  seed  oil  can  be  interpreted  based  on  portable  near-infra- red  Raman  spectroscopy  technology  combined  with  the  PSO-GRNN   algorithm.This  scheme can predict the  concentration  of peony  seed  oil  and  effectively  evaluate  the  concentration  of various   cheap   vegetable    oils.The   test   set    of   the   model   R²>0.94,RMSE<0.036.This   pa- per deeply  studied the possible complex adulteration of peony  seed oil  and proposed the cor- responding  solutions.This  method   is  significant  for  the  market   supervision  and  quality  de- tection of peony seed oil.