Octane number loss prediction method based on particle swarm algorithm and neural network

Abstract

The invention provides an octane number loss prediction method based on a particle swarm algorithm and a neural network. The method comprises the steps: firstly, collecting the original data and octane number loss value data of an operation variable in a catalytic cracking gasoline refining desulfurization device, and carrying out the preprocessing of the original data of the operation variable; secondly, performing feature screening on the processed data by adopting decision tree regression and Pearson correlation coefficients to obtain feature variables; then training the four-layer BP neural network by utilizing sample data and octane number loss value data corresponding to the characteristic variables to obtain an octane number loss prediction model; and finally, performing iterative optimization on the sample data corresponding to the characteristic variables by using a particle swarm algorithm and an octane number loss prediction model, and outputting the value of the characteristic variable corresponding to the minimum octane number loss value. According to the method, the particle swarm algorithm and the BP neural network are combined to search for the value of the characteristic variable corresponding to the minimum octane number loss value, so that the repeated training process is avoided, and the prediction efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of petrochemical industry, in particular to a method for predicting octane number loss based on particle swarm algorithm and neural network. Background technique [0002] With the development of industry, people have caused some damage to the environment while enjoying a more convenient life. Today's world pays more and more attention to environmental protection issues. The main fuel of small vehicles is gasoline, and the emission of automobile exhaust is one of the main factors causing atmospheric environmental pollution. Because of the rapid development of the automobile market, the consumption of gasoline is increasing, resulting in an increasing amount of automobile exhaust pollutants released into the atmosphere. my country has formulated increasingly strict gasoline quality standards for this. The focus of gasoline cleaning is to reduce the sulfur and olefin content in gasoline while maintaining its o...

AI Technical Summary

Problems solved by technology

[0004] In view of the deficiencies in the above-mentioned background technology, the present invention proposes a method for predicting octane loss based on particle swarm algorithm and neural network, which solves the problem of relatively few variables in the existing data association model and the analysis of raw materials by mechanism modeling High requirements, untimely response to process optimization, and poor optimization results

Images