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

Steel plate shape quality anomaly detection method based on CART decision tree

A steel plate shape and anomaly detection technology, applied in the direction of instrumentation, calculation, character and pattern recognition, etc., can solve the problems of frequent misclassification, no quantitative standard, affecting efficiency and product quality, etc.

Active Publication Date: 2019-11-29
NORTHEASTERN UNIV
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This kind of manual observation and detection is highly subjective, there is no quantitative standard, and the actual misclassification is relatively frequent, which greatly affects the 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 quality anomaly detection method based on CART decision tree
  • Steel plate shape quality anomaly detection method based on CART decision tree
  • Steel plate shape quality anomaly detection method based on CART decision tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0057] like figure 1 Shown, the abnormality detection method of steel plate shape quality based on CART decision tree of the present invention, comprises the following steps:

[0058] Step 1: Data collection: Sampling and measuring the thickness of the kth steel plate after the shear line, and obtaining the thickness data set of the kth steel plate as A k ={a 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 ;

[0059] Among them, k∈{1,2,...,K}, K is the total number of steel plates, a 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 t...

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 the technical field of steel plate shape quality anomaly detection, and provides a steel plate shape quality anomaly detection method based on a CART decision tree. The methodincludes: firstly, collecting a thickness data set and a plate shape quality label of a steel plate, and calculating a relative thickness data set of the steel plate; extracting steel plate quality related characteristics representing the relative thickness of the steel plate as optimal overrun rate and fluctuation parameters of the relative thickness in the length and width directions, and constructing a steel plate shape quality sample set; constructing and training a CART decision tree-based steel plate shape quality anomaly detection model by using the training sample set and taking the feature vector representing the relative thickness of the steel plate as input and the shape quality label of the steel plate as output to obtain an optimal sub-tree; and finally, collecting a thickness data set of the to-be-detected steel plate, calculating and inputting a feature vector representing the relative thickness of the to-be-detected steel plate into the optimal sub-tree to obtain a plate shape quality label. The objectivity, accuracy and real-time performance of steel plate shape quality anomaly detection can be improved.

Description

technical field [0001] The invention relates to the technical field of abnormality detection of steel plate shape quality, in particular to a method for detecting abnormality of steel plate shape quality based on a CART decision tree. Background technique [0002] Medium and thick plates are an indispensable steel product for the modernization of the country, and are widely used in shipbuilding, oil platforms, boilers, pressure vessels, pipelines, buildings, bridges, and heavy vehicles. In the production of modern medium and heavy plates, with the continuous expansion of the proportion of high value-added steel grades, users' requirements for plate shape quality continue to increase, especially for steel plate roughness accuracy requirements are becoming more and more stringent. However, at present, the control of the cross-sectional shape and flatness of the steel plate has not yet reached high quality. Due to the uneven temperature distribution of the steel plate after coo...

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
CPCG06F18/24323G06F18/214Y02P90/30
Inventor 刘强胡磊丁进良
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