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

High-speed wire rod quality defect diagnosis and traceability method based on distributed Bayesian network

A Bayesian network, high-speed wire technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as twist, can not meet the requirements of high-speed wire diagnosis and traceability, scratches, etc., to achieve flexible information fusion Effect

Pending Publication Date: 2020-12-18
ZHEJIANG UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The production of high-speed wire has the characteristics of continuous, high-speed and high temperature, and it often has the following quality defects: decarburization, cracks, out-of-ovality, strength, area shrinkage, stuttering, ears, folding, concave-convex pits, torsion, scratches , poor strip shape, substandard dimensions on both sides of the sky and earth, indentation, etc.
However, the traditional data-driven modeling method is difficult to apply to large-scale data, and cannot meet the requirements of high-speed wire rod diagnosis and traceability. Traceability brings great difficulties; (2) High real-time requirements, the wire rolling speed can reach 200m / s; (3) The data scale is large, and the annual cumulative data capacity of a single production line reaches TB level

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
  • High-speed wire rod quality defect diagnosis and traceability method based on distributed Bayesian network
  • High-speed wire rod quality defect diagnosis and traceability method based on distributed Bayesian network
  • High-speed wire rod quality defect diagnosis and traceability method based on distributed Bayesian network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The invention discloses a high-speed wire rod quality defect diagnosis and source tracing method based on a distributed Bayesian network. This method first collects the normal working condition data of the steel high-speed wire rolling process, combines the process mechanism and the big data of the production process, decomposes the whole production process into several sections, and then builds a distributed shell with multi-layer structure based on the data characteristics and process knowledge. The Yeesian network constructs local monitoring statistics, global monitoring statistics, local contribution and global contribution, and finally realizes the diagnosis and traceability of high-speed wire quality defects through information fusion.

[0062] Specific steps are as follows:

[0063] Step 1: Collect the normal working condition data of the high-speed wire rolling process to obtain the training sample set for modeling with process variable set M;

[0064] Step 2...

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 high-speed wire rod quality defect diagnosis and tracing method based on a distributed Bayesian network. The method comprises the following steps: firstly, collecting normalworking condition data of a steel high-speed wire rod rolling process, decomposing a whole production process into a plurality of sections by combining a process mechanism and production process big data, then constructing a distributed Bayesian network with a multi-layer structure based on data characteristics and process knowledge, and constructing a local monitoring statistic, a global monitoring statistic, a local contribution degree and a global contribution degree, and finally realizing high-speed wire rod quality defect diagnosis and traceability through information fusion. By applyingthe method, deep-level quality anomaly tracing, propagation path analysis and root positioning in the high-speed wire rolling process can be achieved, and safe and stable operation of the high-speed wire rolling process is guaranteed.

Description

technical field [0001] The invention belongs to the field of industrial process control, in particular to a high-speed wire quality defect diagnosis and traceability method based on a distributed Bayesian network. Background technique [0002] For a long time, wire products in the iron and steel industry have been important and widely used metal products in my country's national economic construction. The process technology and equipment level of my country's wire rod production line are improving day by day. The annual production capacity of a production line has grown from tens of thousands of tons in the past to more than one million tons at present, and the production efficiency has been greatly improved. Important features of wire rod production are high rolling speed, high product quality and high equipment efficiency. The production of high-speed wire has the characteristics of continuous, high-speed and high temperature, and it often has the following quality defect...

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
IPC IPC(8): G06K9/62
CPCG06F18/29G06F18/2415Y02P90/30
Inventor 宋执环魏驰航陈光捷
Owner ZHEJIANG UNIV
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