Optimization Modeling and Empirical Research on Gasoline Octane Loss Based on Data Analysis

Abstract

Gasoline is one of the most consumed light petroleum products in transportation and other industries. This paper proposes a method for optimizing gasoline octane loss using data analysis technology aimed at optimizing the production process and minimizing the loss of gasoline octane. Firstly, the data are screened and the high-dimensional data are reduced to construct the neural network prediction model optimized by genetic algorithm. After utilizing the model for prediction, the optimal operating condition is achieved. Secondly, ensuring that the gasoline emission meets the standard, the octane loss is reduced by adjusting the operating variables. Thirdly, actual data are collected and calculated to obtain the main operating variables and their optimal operating conditions of a petrochemical company affecting the catalytic cracking gasoline S-Zorb unit, thus providing companies using S-Zorb units with reference data for optimizing gasoline catalytic cracking processes. Fourthly, the superiority of the proposed method was verified by comparing it with the other methods. This paper intends to contribute to better modeling the progress of gasoline catalytic cracking by adequately considering the impact of multiple factors, improving the quality of refined oil products of chemical enterprises, saving the economic cost of chemical enterprises, and protecting the atmospheric environment.