介绍了运用神经网络进行模式识别的基本原理，将主成分分析法和BP神经网络相结合，提出矿物油三维荧光谱鉴别方案，并进行了系统设计,建立了基本的模型框架.选取矿物油三维荧光谱的特征参量，组成原始特征向量，采用主成分分析法进行预处理，而后选取主成分运用BP神经网络实现油种鉴别.该方法减少了输入变量的维数，消除了各输入变量的相关性，同时简化了网络结构，提高了程序运行的速度.通过实例进行了分析，结果证明该方法有效地实现了矿物油三维荧光谱的油种鉴别，同时该系统也可用于其它物质的光谱识别技术领域.

The basic pattern recognition theory of artificial neural network is introduced.The identification system for the oil′s three-dimensional fluorescence spectra is established based on the principal component analysis (PCA) and BP neural network method,and the system design and the basic frame of model are made.PCA was inducted to pre-analyze the feature parameters of oil′s three-dimensional, the principal components of original variables were used as the input of network, then the network output realized the identification of oil′s three-dimensional fluorescence spectrum. This method can cut down the dimensions of original input,eliminate the relativity between variables,at the same time simplify the network structure,and improve the convergence speed.Actual instance was tested effectively that the PCA-BP neural network compared with the normal neural network reduced training time and possesses better performance. Results showed that the method can be used to realize the identification of oil's three-dimensional fluorescence spectrum.