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

Steel plate shape abnormity identification method based on depth random forest

A random forest, steel plate shape technology, applied in neural learning methods, character and pattern recognition, computer parts and other directions, can solve problems affecting industrial production efficiency, product production quality, shape failure, and easy deformation of steel plate shape.

Pending Publication Date: 2020-05-08
NORTHEASTERN UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the current steel plate production, due to the many procedures in the steel plate production process, the shape of the obtained steel plate is easily deformed, resulting in shape failure
The shape of the steel plate is calibrated by manual observation to judge the type of fault in the shape of the plate, and then decide to adjust it in the next step. The judgment and decision made by this kind of manual observation and detection is highly subjective and lacks objective qualitative and quantitative methods. Standards, prone to false positives and negatives, affecting industrial production efficiency and product quality

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
  • Steel plate shape abnormity identification method based on depth random forest
  • Steel plate shape abnormity identification method based on depth random forest
  • Steel plate shape abnormity identification method based on depth random forest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] A method for identifying anomalies in steel plate shape based on deep random forests, such as figure 1 shown, including the following steps:

[0035] Step 1: Sampling and measuring the thickness of the kth steel plate after the shear line process in the thick plate production process, and obtaining the thickness data set H of the kth steel plate k ={h k (i,j),i∈{1,2,...,M},j∈{1,2,...,N k}}, and collect the shape quality label y of the kth steel plate k ;

[0036] Among them, k∈{1,2,...,S}, S is the total number of steel plates, h k (i, j) is the thickness of the kth steel plate at the sampling point (i, j), i is the serial number of the sampling point in the width direction of the steel plate, j is the serial number of the sampling point in the longitudinal direction of the steel plate, M is the thickness of the sampling point in th...

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 provides a steel plate shape abnormity identification method based on a depth random forest and relates to the technical field of steel plate shape abnormity identification. The method comprises the following steps that: the thickness data set and plate shape quality labels of steel plates are acquired, the relative thickness data set of the steel plates are calculated, up-sampling or down-sampling are performed on the relative thickness data set, so that steel plates with consistent sampling points in a length direction and a width direction can be obtained, normalization processing is performed on the relative thickness data set; a steel plate shape anomaly recognition model based on the depth random forest is constructed and trained by using a training sample set and a verification sample set with feature vectors representing the relative thickness of the steel plates adopted as input and the plate shape quality labels of the steel plates as output, so that an optimaldepth random forest model can be obtained; and the thickness data set of to-be-detected steel plates can be collected, feature vectors representing the relative thickness of the to-be-detected steel plates are calculated and inputted into an optimal depth random forest model, so that the plate shape quality labels of the to-be-detected steel plates can be obtained.

Description

technical field [0001] The invention relates to the technical field of product quality anomaly identification, in particular to a method for identifying anomalies in steel plate shape based on deep random forests. Background technique [0002] With the continuous development of modern chemical industry, petroleum, metallurgy, machinery, logistics and other industries in the direction of large-scale, complex and continuous, the identification and classification of product production quality is also more important. In the modern steel rolling production process, the shape of the steel plate is a key product quality index, so the abnormal identification of the shape of the steel plate has become an important step to improve the efficiency of steel production. In the current steel plate production, due to the many procedures in the steel plate production process, the shape of the obtained steel plate is easily deformed, resulting in shape failure. The shape of the steel plate i...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06V10/44G06N3/045G06F18/24323Y02P90/30
Inventor 刘强常学敏
Owner NORTHEASTERN 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