Welcome to Francis Academic Press

Academic Journal of Engineering and Technology Science, 2021, 4(8); doi: 10.25236/AJETS.2021.040806.

Study on the Loss Process of Gasoline Octane Number Based on Principal Component Analysis


Yuqing Yang, Zhengfu Li, Liping Wu

Corresponding Author:
Zhengfu Li

School of Computer Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, 222005, China


This paper mainly takes the octane number loss in the gasoline refining process as the research object, and studies the main variables that affect the octane number loss and the prediction of octane number loss. In this paper, the data are screened out based on the 3 σ principle, and then the main variables are determined based on the principal component analysis (PCA). The sample size of the original data is 325 and the variables are 367. First of all, the descriptive statistics of the data samples are carried out to get the approximate range of the data. According to the different conditions satisfied by the data, Pearson correlation coefficient and Spelman rank correlation coefficient are selected to calculate and analyze the correlation between the two variables. Then the principal component analysis method was used to select the main variables affecting the octane number loss, and the index of 367 variables was reduced to 17 independent and representative variables, and the cumulative contribution rate of 17 variables reached 80.7%. Taking into account the continuous expansion of data samples in the future, the solution method of factor analysis is provided.


Correlation coefficient, principal component analysis, factor analysis

Cite This Paper

Yuqing Yang, Zhengfu Li, Liping Wu. Study on the Loss Process of Gasoline Octane Number Based on Principal Component Analysis. Academic Journal of Engineering and Technology Science (2021) Vol. 4, Issue 8: 43-47. https://doi.org/10.25236/AJETS.2021.040806.


[1] Zhang Xiaopeng, Ma Lijing, Empirical Research on Employment Rate Factors in China, Modern Trade and Industry, 20(5): 29-30, 2008.

[2] Wang Xuemin, Application of Multivariate Statistical Analysis [M], Shanghai, Shanghai University of Finance and Economics Press, 209-244, 2017.

[3] Fan Tongda, Jiang Bing, Multiple linear regression model of water Consumption based on principal component Analysis: A case study of Anhui Province, Infrastructure Optimization, 28 (2): 53-55, 2007.

[4] Lv Qiongshuai. Optimization and Research of BP Neural Network [D]. Zhengzhou University, 2011.