Abstract: At present, the testing engine for measuring the cetane number of diesel is very expensive, and the prediction accuracy of the existing cetane index is low. It is urgent to establish a diesel cetane number prediction model with high prediction accuracy. Based on 450 representative samples of diesel, a database including physical and chemical properties, hydrocarbon group composition and cetane number of diesel was established. Using stepwise regression analysis, statistical product and service solutions (SPSS) software, two cetane number prediction models based on physical and chemical properties of diesel and based on hydrocarbon group composition of diesel were established, respectively. F-test, T-test and residual analysis were used to verify the validity of the models. The accuracy of the two models was compared by calculating root mean square error.The results showed that two models were all valid,and the accuracy of the model based on physical and chemical properties ofdiesel was better than that of the model based on hydrocarbon group composition of diesel.

Key words: diesel, cetane number, physicochemical property, hydrocarbon groups, prediction model