Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Method for Predicting the Coking Amount of Heavy Oil Catalytic Cracking Settler

A technology of settler and coking quantity, which is applied in the direction of instruments, special data processing applications, electrical digital data processing, etc., and can solve problems such as unplanned shutdown of refinery equipment and coking problems

Active Publication Date: 2017-11-03
CHINA UNIV OF PETROLEUM (BEIJING)
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these studies have played a certain role in delaying the sedimentation and coking problem, the coking problem still exists and causes unplanned shutdown of refinery units every year.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Method for Predicting the Coking Amount of Heavy Oil Catalytic Cracking Settler
  • A Method for Predicting the Coking Amount of Heavy Oil Catalytic Cracking Settler
  • A Method for Predicting the Coking Amount of Heavy Oil Catalytic Cracking Settler

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] The specific steps of coking amount prediction are as follows:

[0049] (1) Obtain basic data related to condensation rate, capture rate, and coke formation rate, as well as actual values ​​of condensation rate, capture rate, and coke formation rate; see Tables 1-3 for some data;

[0050] (2) Among the 100 groups of data obtained in step (1), randomly select 60 groups as training data, and 40 groups as verification data, using the method described in the summary of the invention BP neural network Obtain models to predict settler condensation, capture and coking rates;

[0051] (3) The basic data of the heavy oil catalytic cracking settler are collected on site and preprocessed, and one set of data obtained after pretreatment is respectively substituted into the condensation rate, capture rate, and coke formation rate model obtained in step (2) to obtain the settler Predicted values ​​of condensation rate, capture rate and coking rate; collect the mass flow rate of oil ...

Embodiment 2

[0054] Compared with Example 1, the only difference is: in 100 groups of basic data, 80 groups are randomly selected as training data, 20 groups are used as verification data, and the method described in the summary of the invention is used GRNN neural network Build a model to predict condensation rate, capture rate, and coke rate; predict the amount of coking in the catalytic cracking settler unit of A refinery; the prediction results are shown in Table 4.

Embodiment 3

[0056] Compared with Example 1, the only difference is that among 100 sets of basic data, 80 sets are randomly selected as training data, and 20 sets are used as verification data using the method described in the Summary of the Invention. RBF neural network Construct the models of condensation rate, capture rate and coke generation rate; predict the amount of coking in the catalytic cracking settler unit of A refinery; the prediction results are shown in Table 4.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method for predicting the coking amount of a heavy oil catalytic cracking settler, comprising the following steps: (1) obtaining basic data related to the condensation rate, capture rate and coke formation rate of the settler, and the condensation rate, capture rate and production rate For the actual value of the focal rate, preprocess the above-mentioned groups of data, and then perform normalization processing; (2) use the neural network for model training, use the basic data obtained in step (1) as the input value, and use the actual value as the expected output , to obtain a model for predicting the condensation rate, capture rate, and coke formation rate of the settler; (3) preprocess the basic data collected on the spot related to the condensation rate, capture rate, and coke formation rate of the settler, and substitute them into step (2 ) to obtain the predicted values ​​of the settler condensation rate, capture rate and coke rate, collect the mass flow rate of the oil slurry in the settler on site, and calculate the predicted value of the settler coking amount. The method provided by the invention is simple and accurate, and can be applied to actual industrial production.

Description

technical field [0001] The invention relates to the field of petrochemical industry, in particular to a method for predicting the coking amount of a heavy oil catalytic cracking settler. Background technique [0002] Heavy oil catalytic cracking (RFCC) occupies an important position in my country's oil refining industry and is an important means for refineries to improve economic efficiency. However, with the heavy and inferior quality of crude oil, the slagging rate of RFCC raw materials in my country continues to increase, and the properties of raw materials are getting worse and worse, which not only deteriorates the distribution and quality of RFCC products, but also aggravates the coking of RFCC devices. Among them, coking in the settler is the most harmful, and it is the most common occurrence at the same time. In the slightest, it will lead to poor catalyst circulation and a large amount of catalyst run-off, and in severe cases, the catalyst circulation will be interr...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/50
Inventor 蓝兴英彭丽高金森吴迎亚苏鑫
Owner CHINA UNIV OF PETROLEUM (BEIJING)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com