Study Of Oil Identification Technique Based On Three-dimensional Fluorescence Spectra

The measurement of mineral oil in water has caused serious concern of people. Identifying the species of mineral oil in water are needed to determine the contamination oil source and evaluating pollution fast and correctly. It has important significance for water environment prevention under control.The paper aimed at the requirement of environmental monitoring water, adopt fluorescence analytical method, 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 makes system design and the basic frame of model. Inducting PCA to pre-analyze the feature parameters of oil's three-dimensional, using the principal components of original variables as the input of network, realize the identification of oil's three-dimensional fluorescence spectrum.First of all, the basic principle and characteristic of fluorescence measurement method are discussed. The obtained fluorescence 2-Dimensional specific properties of kinds of organic substance are analyzed. Meanwhile the limitation of common 2-Dimensional fluorescence spectrum method is considered.Afterwards the total scheme of fluorescence measurement system is introduced. The system adopts the pulse xenon lamp as the excited light source. The diffractive grating is used as fluorescence signal separator,the photomultiplier (PMT) with high sensitivity and low noise is used as fluorescence signal detector. The weak signal detecting technique is based on Exact integral amplifier IVC102.Finally,Introduce the identification system for the oil's three-dimensional fluorescence spectra. And design the basic frame of model. With feature parameters of oil's three-dimensional as input of PCA , the principal components of original variables as the input vector of BP Neural network, realize the identification of oil.