Verification method and device for identifying end face defects of hot rolled steel coil

A technology for defect identification and hot-rolled steel coils, applied in neural learning methods, character and pattern recognition, image data processing, etc., can solve problems such as low efficiency, achieve low false detection rate, fast response speed, prevent over-inspection or The effect of missed detection

Pending Publication Date: 2022-01-07
武汉钢铁有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application solves the technical problem of low efficiency in verifying the identification of hot-rolled steel coil end-face defects in the prior art by providing a verification method and device for hot-rolled steel coil end-face defect recognition, and realizes improved recognition of hot-rolled steel coils. The verification efficiency of coil end face defect recognition, and the technical effect of improving the recognition rate of hot-rolled steel coil end face defect recognition

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
  • Verification method and device for identifying end face defects of hot rolled steel coil
  • Verification method and device for identifying end face defects of hot rolled steel coil
  • Verification method and device for identifying end face defects of hot rolled steel coil

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The first embodiment of the present invention provides a verification method for identifying defects on the end face of a hot-rolled steel coil, such as figure 1 shown. include:

[0040] S101, using the neural network model for end surface defect recognition to identify the image set to be identified of the end surface of the hot-rolled steel coil, and obtain N data sets; wherein, the N data sets include image sets that do not have preset defects on the end surface, And at least one of the image set with pattern edge defect on the end face, the image set with edge damage defect on the end face, the image set with edge crack defect on the end face, the image set with folding defect on the end face and the image set with burr defect on the end face, N≥ 2;

[0041] S102. Obtain the area under the receiver operating characteristic curve AUC according to the N data sets;

[0042] S103, if the AUC is within the area threshold range, determine that the neural network model ...

Embodiment 2

[0071] Based on the same inventive concept, the second embodiment of the present invention also provides a verification device for identifying defects on the end face of a hot-rolled steel coil, such as figure 2 shown, including:

[0072] The first obtaining module 201 is used to identify the to-be-recognized image set of the end face of the hot-rolled steel coil through the neural network model used for end face defect recognition, and obtain N data sets; wherein, the N data sets include the An image set with no preset defect on the end surface, an image set with a pattern edge defect on the end surface, an image set with an edge damage defect on the end surface, an image set with an edge crack defect on the end surface, and a fold defect on the end surface At least one of the image set of the image set and the image set with burr defects on the end surface, N≥2;

[0073] The second obtaining module 202 is used to obtain the area under the receiver operating characteristic ...

Embodiment 3

[0090] Based on the same inventive concept, the third embodiment of the present invention also provides a computer device, such as image 3 As shown, it includes a memory 304, a processor 302, and a computer program stored on the memory 304 and operable on the processor 302. When the processor 302 executes the program, it realizes the above-mentioned verification method for identifying defects on the end face of a hot-rolled steel coil Steps in any of the methods.

[0091] Among them, in image 3 In, bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 will include one or more processors represented by processor 302 and various types of memory represented by memory 304 circuits linked together. The bus 300 may also link together various other circuits, such as peripherals, voltage regulators, and power management circuits, etc., which are well known in the art and thus will not be further described herein. 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 relates to the technical field of strip steel quality detection, in particular to a verification method and device for identifying end face defects of a hot rolled steel coil, and the method comprises the steps: carrying out the identification of a to-be-identified image set of the end face of the hot rolled steel coil through a neural network model for end face defect identification, and obtaining N data sets, wherein the N data sets comprise at least one of an image set without preset defects on the end face, an image set with pattern edge defects on the end face, an image set with edge damage defects on the end face, an image set with edge crack defects on the end face, an image set with folding defects on the end face and an image set with burr defects on the end face, and N is greater than or equal to 2; according to the N data sets, obtaining an area AUC below an operation characteristic curve of the receiver; and if the AUC is within the area threshold range, determining that the neural network model meets a precision performance condition. According to the method, the verification efficiency of hot rolled steel coil end face defect identification is improved, and then the identification rate of hot rolled steel coil end face defect identification is improved.

Description

technical field [0001] The invention relates to the technical field of strip steel quality detection, in particular to a verification method and device for identifying defects on the end faces of hot-rolled steel coils. Background technique [0002] In the production process of hot-rolled steel coils, due to the influence of factors such as raw materials, rolling process and equipment system control, there are defects such as pattern edges, edge damage, edge cracks, folds, burrs and other defects on the end faces of steel coils. These end surface defects not only affect the aesthetics of the steel coil, but also cause the product to be degraded or changed when the steel coil is polished or re-coiled, turning high-quality products into defective products. [0003] During the strip coiling process, by designing a model or product related to the identification of hot-rolled steel coil end surface defects, the section of the hot-rolled steel coil is identified and detected. How...

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): G06T7/00G06V10/764G06N3/04G06N3/08
CPCG06T7/0004G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30116G06N3/045G06F18/241
Inventor 张雪荣布昭元汪洋赵雪松
Owner 武汉钢铁有限公司
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