Method for determining technological parameters in flow industrial process

A technology of process parameters and process industry, applied in electrical digital data processing, special data processing applications, instruments, etc., can solve the problems of ineffective control of product quality, difficult to adjust process parameters, and easy occurrence of waste products, etc., to achieve optimization. Determine the effect of convenience and speed, simple operation, and improved production efficiency

Inactive Publication Date: 2012-12-19
INNER MONGOLIA UNIV OF SCI & TECH
View PDF1 Cites 51 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, in the production process of major domestic process industries, the adjustment of process parameters mainly depends on manual experience, and the method of exhaustive trial and error is used to set the parameters. When the working conditions change frequently, it is difficult to adjust the process parameters in a timely and accurate manner only by manual experience , resulting in product quality not being effectively controlled, serious waste, and prone to waste

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
  • Method for determining technological parameters in flow industrial process
  • Method for determining technological parameters in flow industrial process
  • Method for determining technological parameters in flow industrial process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Example 1 Method for Determining Process Parameters Based on Data-Driven Process Industry

[0027] technology roadmap as figure 1 As shown, the specific steps are:

[0028] The first step is to establish a quality model extraction method: firstly, normalize the existing production data to eliminate the influence of different dimensions, use the data extracted in the production process to establish a quality model, and use the method of rule extraction to extract process parameters The rule knowledge between quality indicators and quality indicators forms a rule base;

[0029] The second step is to set the quality target value, the initial value of the algorithm parameter and the initial value of the process process parameter: when the process parameter is initialized, first find its corresponding rule according to the given quality target value, and then initialize the process parameter in the rule Within the scope of optimization, reduce the optimization space and sp...

Embodiment 2

[0038] Embodiment 2 Simulation experiment

[0039] In order to verify the effectiveness of the method of the present invention, a simulation experiment is carried out on the method for optimizing and determining process parameters in the present invention.

[0040] The simulation experiment takes the hot-dip galvanizing production process of an iron and steel enterprise as an example, and optimizes the process parameters according to the given quality index.

[0041] Process parameters include: air knife pressure p , the distance from the air knife to the strip d and unit speed v , the target product quality is the zinc layer weight w .

[0042] In the production process, generally by adjusting p , d , v These three process parameters are used to control the weight of the zinc layer on the strip w .

[0043] When producing a specified zinc layer weight, these three parameters need to be adjusted at the same time. At present, it is mainly operated by manual experience,...

Embodiment 3

[0050] Example 3 Decision tree extraction rules

[0051] Similarly, using the same data, using the decision tree to extract rules, the remaining 200 sets of data are used to verify the model.

[0052] Here, the weight data of the zinc layer should be classified first, and according to the different requirements for the weight of the zinc layer, the weight of the zinc layer can be divided into three categories, that is, 115 w ≤146 (Class 1), 80 ≤ w w p , d , v as the leaf node of the tree.

[0053] image 3 For the obtained decision tree, the corresponding rules are:

[0054]

[0055] The rule accuracy reaches 94.34%.

[0056] To coat the strip surface with 60 g / m 2 When the weight of the zinc layer is determined, it can be found that the weight of the zinc layer corresponds to rule 4, that is, the value range of the process parameters is restricted.

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 discloses a method for determining technological parameters in a flow industrial process. The method includes the steps of firstly, collecting production data, and using the technological parameters as input and product quality and output to build quality models; secondly, using rule extraction to extract corresponding rules between the input and the output from the production data so as to form a rule library; and thirdly, using optimization to find rules corresponding to given quality indexes according to the given quality indexes, initiating the technological parameters in the range of the rules, using the initiated technological parameters as input of the quality models to predict product quality, calculating errors between the predicted quality and the quality indexes, and correcting to find optimal parameters to enable the errors between the predicted quality and the quality indexes to be minimum. By the method, product yield is improved effectively and production cost is lowered.

Description

[0001] technical field [0002] The invention relates to a data-driven method for determining technological parameters of a process industry. Background technique [0003] The production process of the process industry generally has the characteristics of multi-variable, nonlinear, and strong coupling. With dynamic characteristics, it is difficult to accurately describe it with a mechanism model. At the same time, due to its very complicated production process, there is a big gap in the quality of products produced by domestic process industries compared with similar foreign products, mainly manifested in unstable product quality, low service life, and high scrap rate. [0004] In the final analysis, the control of product quality is still the problem of setting process parameters, that is, the process parameters are reversed according to the quality indicators of the product. [0005] At present, in the production process of major domestic process industries, the adjustme...

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 Applications(China)
IPC IPC(8): G06F17/50G06N3/02G06N3/12
Inventor 王建国张文兴石炜张永强杨斌
Owner INNER MONGOLIA UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap