Study On Detection Method Of Ethanol Diesel Quality Based On Diagnostic Spectroscopy

More and more people choose car travel,which has brought many problems,such as the contradiction between the increasing oil resources and the increase in oil demand.In order to alleviate the contradiction,find the alternative products of petroleum fuels as soon as possible.Ethanol diesel fuel is a new type of diesel alternative fuel.However,different manufacturers of ethanol diesel quality is uneven,seriously hindered the promotion of ethanol diesel is used,therefore,needs an easy way to ethanol diesel quality for testing.In this paper,the main index of ethanol diesel was studied by Spectral diagnostic technique.To establish an accurate and reliable quantitative model for the quality index of ethanol diesel oil.The main research results were as follows:1 Taking ethanol diesel were used as the research object,by using near infrared spectroscopy,the ethanol content of ethanol and diesel oil density and viscosity of quantitative analysis,using five kinds of pretreatment methods to deal with spectral data.Three models of least squares support vector machine,principal component regression and partial least squares regression are established.The results show that the least squares support vector machine has the best modeling effect on the density,viscosity and ethanol content of ethanol diesel under the multiple scattering correction smoothing pretreatment.The correlation coefficients of prediction is 0.995,0.995 and 0.995;RMSEP is 6.8×10-4,1.13×10-2 and 0.5.714×10-1 respectively.2 Taking ethanol diesel were used as the research object.The middle infrared spectroscopy was used to collect and analyze the ethanol diesel.The original spectrum data of the infrared spectra of ethanol diesel were pretreated and the spectral data were screened.The ethanol content,density and viscosity of ethanol diesel were established respectively.The main conclusions were as follows:It is found that the UVE-SPA-CARS-PLSR had the best effect on the ethanol content,and the predicted set Rp and RMSEP of the model were 0.978 and 0.825 respectively.3 Taking ethanol diesel were used as the research object.Raman spectroscopy was used to collect and analyze the ethanol diesel.The original spectrum data of ethanol diesel Raman spectroscopy were pretreated and the spectral data were screened.The ethanol content,density and viscosity of ethanol diesel were established respectively.The main conclusions were as follows:It is found that the SPA-CARS-PLS had the best effect on the ethanol content,and the predicted set Rp and RMSEP of the model were 0.978 and 0.825 respectively.