Steel plate detection method based on deep learning, tail early warning method, electronic equipment and computer storage medium

A technology of deep learning and detection method, which is applied in the field of steel plate curling, can solve problems such as affecting the detection effect, generating a large amount of fog, and blocking the target steel plate, so as to achieve the effect of improving reliability, improving efficiency, and enriching the production process

Pending Publication Date: 2021-08-10
LIAONING SINODOM SECURITY TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method also has certain defects: the steel plate passes through the rolling mill before curling, alternating cold and hot, and a large amount of fog will be generated during the process, which will cause the target steel plate to be blocked, thus affecting the detection effect
[0005] To sum up, it can be seen that there are still many deficiencies mentioned above in the existing technology for steel plate detection and identification and tail warning, and a stable and reliable solution technology is urgently needed

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 detection method based on deep learning, tail early warning method, electronic equipment and computer storage medium
  • Steel plate detection method based on deep learning, tail early warning method, electronic equipment and computer storage medium
  • Steel plate detection method based on deep learning, tail early warning method, electronic equipment and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] see figure 1 , figure 1 It is a schematic flowchart of a steel plate detection method based on deep learning disclosed in the embodiment of the present application. Such as figure 1 As shown, a steel plate detection method based on deep learning in the embodiment of the present application, the method includes:

[0060] S1, collecting steel plate sample images covering all time periods to construct an image training set;

[0061] S2, manually annotating the steel plate sample images in the image training set, and inputting the annotated image training set into a deep learning recognition model for training;

[0062] S3, collecting the steel plate image in real time, inputting the steel plate image into the trained deep learning recognition model, the deep learning recognition model recognizes the steel plate, and calculates the front and rear boundaries of the steel plate in the steel plate image.

[0063] In the embodiment of the application, the application constr...

Embodiment 2

[0090] see figure 2 , figure 2 It is a structural schematic diagram of a steel plate tail-to-tail warning method disclosed in the embodiment of the present application. Such as figure 2 As shown, a kind of steel plate tail early warning method of the embodiment of the present application:

[0091] Using the steel plate detection method based on deep learning as described in Embodiment 1 to identify the steel plate and its head and tail boundaries;

[0092] Detecting whether the head and tail of the steel plate cross the first reference line and the second reference line respectively, and if so, output an early warning signal; wherein, the steel plate passes through the first reference line and the second reference line in sequence;

[0093] Wherein, the method also includes:

[0094] Detecting the time difference when the head / tail of the steel plate respectively passes through the first reference line and the second reference line, and obtaining the distance between th...

Embodiment 3

[0097] see image 3 , image 3 It is a schematic structural diagram of an electronic device disclosed in the embodiment of this application. Such as image 3 As shown, an electronic device according to an embodiment of the present application, the device includes:

[0098] a memory storing executable program code;

[0099] a processor coupled to the memory;

[0100] The processor invokes the executable program code stored in the memory to execute the steps of the method described in the first embodiment.

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 detection method based on deep learning. The method comprises the following steps: S1, collecting steel plate sample images covering all time periods to construct an image training set; S2, performing manual annotation on steel plate sample images in the image training set, and inputting the annotated image training set into a deep learning recognition model to train the image training set; S3, collecting a steel plate image in real time, inputting the steel plate image into the trained deep learning recognition model, recognizing the steel plate by the deep learning recognition model, and calculating the head and tail edges of the steel plate in the steel plate image. According to the scheme, the image recognition technology based on the deep learning algorithm is used for replacing a traditional manual observation mode to detect the steel plate, early warning is given out after the steel plate leaves, tail alignment and steel plate curling are achieved, and universal applicability is achieved.

Description

technical field [0001] The present application relates to the technical field of steel plate curling, and specifically relates to a steel plate detection method based on deep learning, a tail-to-tail warning method, electronic equipment, and a computer storage medium. Background technique [0002] Object detection based on deep learning is an important problem in deep learning research. In recent years, target detection algorithms have changed with each passing day, and great progress has been made. The target detection algorithm is roughly divided into two categories: one is the two-stage detection task, that is, the target candidate frame is calculated first, and then the candidate frame is classified and regressed; the other is the one-stage detection task, that is, the target is directly predicted in one step The location and category of the target. The former has high accuracy and slow speed, while the latter has fast speed and relatively low accuracy. [0003] In th...

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): G06T7/00G06T7/13G06T5/00G06N3/04
CPCG06T7/0004G06T7/13G06T5/002G06T2207/20081G06N3/045
Inventor 丁武林琳李林陈学志于洋
Owner LIAONING SINODOM SECURITY 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