WO2023151249A1

WO2023151249A1 - Online measurement system for surface cleanliness of cold-rolled strip steel

Info

Publication number: WO2023151249A1
Application number: PCT/CN2022/112421
Authority: WO
Inventors: 夏志; 张毅; 唐文; 王耀; 周云根; 熊俊伟
Original assignee: 中冶南方工程技术有限公司
Priority date: 2022-02-10
Filing date: 2022-08-15
Publication date: 2023-08-17
Also published as: CN114636708A

Abstract

An online measurement system for surface cleanliness of cold-rolled strip steel, comprising a stable roller (C1), strip steel (C2), a shielding box body (C3), a light source (C4), a lens (C5), a camera (C6), a network cable (C7), a data collection card (C8), an image processing server display (C9), and cleanliness online measurement software (C10), wherein the stable roller (C1) forms a certain wrap angle in a photographing region to inhibit vibration of the strip steel (C2); the shielding box body (C3) is used for shielding the influence of ambient light on a system light path; the lens (C5) is mounted on the camera (C6) by means of an interface; the camera (C6) and the data collection card (C8) are connected by means of the network cable (C7); the data collection card (C8) is mounted on a PCI slot of the image processing server display (C9); and the cleanliness online measurement software (C10) runs on the image processing server display (C9). The certain wrap angle is formed in the photographing region by means of the stable roller (C1) to inhibit the vibration of the strip steel (C2), so that the imaging quality of an image is clear; the influence of the ambient light on a system is shielded by means of the shielding box body (C3), so that the interference of the ambient light is small; and for the specification change of the strip steel (C2), the imaging quality is recognized and a camera (C6) position adjustment mechanism is controlled to move until the imaging quality is clear, and thus, the application range is wide.

Description

An online detection system for cold-rolled strip surface cleanliness

technical field

The invention relates to the field of cold-rolling treatment lines, in particular to an online detection system for the surface cleanliness of cold-rolled strip steel.

Background technique

In the cold rolling continuous annealing or galvanizing treatment line, after the strip steel enters the annealing furnace, under high temperature conditions, the residue on the surface of the strip steel is very easy to adhere to the furnace rolls to form furnace roll nodules, forming roll marks on the surface of the strip steel, seriously affecting product quality. In addition, the residue will affect the strip coating effect, affect the adhesion and corrosion resistance of the paint film, etc.

In order to reduce the nodulation of the furnace roll and improve the coating effect of the strip steel, the residues on the surface of the strip steel are generally cleaned by alkali spraying, alkali brushing, electrolytic cleaning, ultrasonic cleaning, water brushing and rinsing, etc. The content is controlled within the allowable range (residual oil 10mg/m ² , residual iron 10mg/m ² ).

Residues on the surface of the strip are generally measured through sampling, off-line extraction, and weighing. Sampling is difficult and the lag time is long, making it difficult to guide on-site production in a timely manner. The existing cleanliness on-line detector measures the surface cleanliness of the strip steel by the ultraviolet fluorescence method and the laser reflection receiving method, and its coverage is small (about 2 mm in diameter), and the detection results fluctuate greatly in the field application process. Therefore, there is an urgent need for an online detection system for the surface quality of cold-rolled strip steel to solve the problems existing in the ultraviolet fluorescence method and the laser reflection receiving method.

Contents of the invention

In view of the above problems, the present invention is proposed in order to provide an online detection system for the surface cleanliness of cold-rolled strip steel which overcomes the above problems or at least partially solves the above problems.

In order to solve the above technical problems, the embodiment of the present application discloses the following technical solutions:

An on-line inspection system for surface cleanliness of cold-rolled strip steel, comprising: stabilizing rolls, strip steel, shielding box, light source, lens, camera, network cable, data acquisition card, image processing server display and cleanliness on-line inspection software, wherein, The stabilizing roller forms a certain wrap angle in the shooting area to suppress the vibration of the strip steel. The shielding box is used to shield the influence of ambient light on the optical path of the system. The lens is installed on the camera through the interface, and the camera and the data acquisition card are connected through the network cable. Data acquisition The card is installed on the PCI slot of the display of the image processing server, and the cleanliness online detection software runs on the display of the image processing server.

Further, the shielding box is also used to install the light source bracket, the camera bracket and the camera position adjustment mechanism; wherein: the light source bracket on the shielding box supports and protects the light source, the camera bracket on the shielding box supports and protects the camera, and the camera on the shielding box The position adjustment mechanism can electrically adjust the horizontal, vertical and pitch angles of the camera to ensure clear image quality.

Further, the cleanliness online detection software runs on the display of the processing server, and the cleanliness online detection software is composed of an image data collection and visualization module, an imaging quality detection and camera adjustment module, and a cleanliness online detection module; wherein, the image data collection and visualization module The strip steel surface image is read from the camera through the network cable, stored in the hard disk of the computer host computer and visualized on the computer monitor; the imaging quality detection and camera adjustment module identifies the imaging quality and controls the movement of the camera position adjustment mechanism according to the change of the strip steel specification. Until the image quality is clear; the cleanliness online detection module detects the residue particles through image preprocessing and area detection, extracts multiple features of the residue particles, and then uses the classification recognition method to classify and identify the target, and finally counts the residue particles of different particle sizes Quantity, give the cleanliness code according to the cleanliness standard and prompt the parameter adjustment of the cleaning process section.

Further, multiple features of the residual particles are extracted, including at least geometric shape, grayscale, projection and texture features of the residual particles.

Further, the classification recognition method is used for target classification recognition, and the classification recognition method includes artificial neural network, Adaboost or decision tree method.

Further, according to the cleanliness standard, the cleanliness code is given and the parameter adjustment of the cleaning process section is prompted, and the cleanliness standard is the cleanliness standard IS016232.

Further, the light source is LED light source, the camera adopts a line array camera, the network cable adopts Cameralink network cable for high-speed image transmission, and the image processing server monitor is equipped with a high-performance GPU for image processing algorithms to identify particles from high-resolution images on the surface of the strip. Target calculation .

Furthermore, on the basis of the online detection system for the surface cleanliness of cold-rolled strip steel, the characteristics of incoming strip steel and the process parameters of the cleaning section can be combined to statistically analyze the cleanliness of different steel types, different specifications and different cleaning processes, and the given Suggestions for cleaning process improvement.

The beneficial effects of the above-mentioned technical solutions provided by the embodiments of the present invention at least include:

The invention discloses an online detection system for the surface cleanliness of cold-rolled strip steel, comprising: a stabilizing roll, strip steel, a shielding box, a light source, a lens, a camera, a network cable, a data acquisition card, an image processing server display, and an online cleanliness detection system Software, in which, the stabilizing roller forms a certain wrap angle in the shooting area to suppress the vibration of the strip steel, and the shielding box is used to shield the influence of ambient light on the optical path of the system. The lens is installed on the camera through the interface, and the camera is connected to the data acquisition card through the network cable. Up, the data acquisition card is installed on the PCI slot of the display of the image processing server, and the cleanliness online detection software runs on the display of the image processing server.

This system is based on the camera to capture the surface image of the strip steel, by identifying the particle target and its particle size from the high-resolution image of the strip surface, counting the particle size and quantity, and giving the cleanliness code, which has a high degree of digitization and quantification; the system is stable through The roller forms a certain wrap angle in the shooting area, suppressing the vibration of the strip steel, and the image quality is clear; the system shields the impact of ambient light on the system optical path through the shielding box, and is less disturbed by the ambient light; the system identifies the imaging quality and The movement of the camera position adjustment mechanism is controlled until the imaging quality is clear and the adaptation range is wide.

The technical solutions of the present invention will be described in further detail below with reference to the accompanying drawings and embodiments.

Description of drawings

The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the description, and are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the attached picture:

Fig. 1 is in the embodiment 1 of the present invention, the composition diagram of the online detection system of cold-rolled strip surface cleanliness;

Fig. 2 is a schematic diagram of the recognition results of the online cleanliness detection software in Embodiment 1 of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

In order to solve the problems existing in the prior art, an embodiment of the present invention provides an online detection system for the surface cleanliness of cold-rolled strip steel.

Example 1

This embodiment discloses an online detection system for surface cleanliness of cold-rolled steel strip C2, including: stabilizing roll C1, steel strip C2, shielding box C3, light source C4, lens C5, camera C6, network cable C7, and data acquisition card C8 , Image processing server monitor C9 and cleanliness online detection software C10, wherein, the stabilizing roller C1 forms a certain wrap angle in the shooting area to suppress the vibration of the strip steel C2, the shielding box C3 is used to shield the influence of ambient light on the system optical path, and the lens C5 Install on the camera C6 through the interface, connect the camera C6 and the data acquisition card C8 through the network cable C7, the data acquisition card C8 is installed on the PCI slot of the display C9 of the image processing server, and the cleanliness online detection software C10 runs on the image processing server on the monitor C9.

In this embodiment, the shielding box C3 is also used to install the light source C4 bracket, the camera C6 bracket, and the camera C6 position adjustment mechanism; wherein: the light source C4 bracket on the shielding box C3 supports and protects the light source C4, and the camera on the shielding box C3 The C6 bracket supports and protects the camera C6, and the position adjustment mechanism of the camera C6 on the shielding box C3 electrically adjusts the horizontal, vertical and pitch angles of the camera C6 to ensure clear image quality.

In some preferred embodiments, during the production process, continuous image acquisition is performed to acquire images of the cleanliness of the strip C2 surface at different time periods, different specifications, and different steel types. Considering the service life, brightness, uniformity and price, the strip LED light source C4 is selected as the system light source C4C4, the camera C6C6 uses the high-resolution high-frequency line scan camera C6, and the network cable C7C7 uses the Cameralink network cable C7 for high-speed image transmission and image processing The server monitor C9C9 is equipped with high-performance GPU for image processing algorithm to identify particulate matter target calculation from the high-resolution image of the strip C2 surface.

In this embodiment, the cleanliness online detection software C10 runs on the display of the processing server, and the cleanliness online detection software C10 is composed of an image data collection and visualization module, an imaging quality detection and camera C6 adjustment module, and a cleanliness online detection module; wherein, The image data acquisition and visualization module reads the strip steel C2 surface image taken from the camera C6 through the network cable C7, stores it in the hard disk of the computer host computer and visually displays it on the computer monitor; the image quality detection and camera C6 adjustment module is aimed at the specification change of the strip steel C2, Identify the image quality and control the movement of the camera C6 position adjustment mechanism until the image quality is clear; the cleanliness online detection module detects the residual particles through image preprocessing and area detection, extracts multiple features of the residual particles, and then uses the classification recognition method Target classification and identification, and finally count the number of residue particles with different particle sizes, give the cleanliness code according to the cleanliness standard and prompt the parameter adjustment of the cleaning process section. Preferably, multiple features of the residual particles are extracted, including at least geometric shape, gray scale, projection and texture features of the residual particles. The target classification and recognition is carried out by using classification recognition method, which includes artificial neural network, Adaboost or decision tree method. Give the cleanliness code according to the cleanliness standard and prompt the parameter adjustment of the cleaning process section; give the cleanliness code according to the cleanliness standard IS016232 or other cleanliness standards and prompt the parameter adjustment of the cleaning process section.

When the cleanliness online inspection software is running, the image quality inspection and camera C6 adjustment module will identify the image quality and control the movement of the camera C6 position adjustment mechanism for the change of strip steel C2 specification until the image quality is clear; the cleanliness online inspection module passes image preprocessing and Area detection detects residue particles, etc., as shown in Figure 2, extracts features such as geometry, grayscale, projection, and texture, and then uses artificial neural networks, Adaboost, or decision trees to classify and identify targets, and finally counts the differences. The number of particle size residue particles, as shown in Table 1, gives the cleanliness code according to the cleanliness standard IS016232 or other cleanliness standards and prompts for parameter adjustment in the cleaning process section.

Table 1 Residue particle size and quantity statistics

In some preferred embodiments, on the basis of the online detection system for the surface cleanliness of the cold-rolled strip C2, the characteristics of the incoming material of the strip C2 and the process parameters of the cleaning section can be combined to statistically analyze different steel types, different specifications and different cleaning process strips Steel C2 cleanliness, giving suggestions for improving the cleaning process.

This system is based on the camera C6 to take the surface image of the strip steel C2, by identifying the particle target and its particle size from the high-resolution image of the strip C2 surface, counting the particle size and quantity, and giving the cleanliness code, which has a high degree of digitization and quantification; The system forms a certain wrap angle in the shooting area through the stabilizing roller C1 to suppress the vibration of the steel strip C2, and the image imaging quality is clear; the system shields the influence of the ambient light on the system optical path through the shielding box C3, and the interference by the ambient light is small; the system is aimed at the strip steel C2 Specification changes, identify the imaging quality and control the movement of the camera C6 position adjustment mechanism until the imaging quality is clear and the application range is wide.

It is understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not meant to be limited to the specific order or hierarchy described.

In the foregoing Detailed Description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, the invention lies in less than all features of a single disclosed embodiment. Thus the following claims are hereby expressly incorporated into the Detailed Description, with each claim standing on its own as a separate preferred embodiment of this invention.

Those skilled in the art should also understand that various illustrative logical blocks, modules, circuits and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software or a combination thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be a component of the processor. The processor and storage medium can be located in the ASIC. The ASIC may be located in the user terminal. Of course, the processor and the storage medium may also exist in the user terminal as discrete components.

For a software implementation, the techniques described in this application can be implemented with modules (eg, procedures, functions, and so on) that perform the functions described herein. These software codes can be stored in memory units and executed by processors. The memory unit can be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.

The foregoing description includes illustrations of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods to describe the above-mentioned embodiments, but those skilled in the art should recognize that various embodiments can be further combined and permuted. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "comprises" is used in the specification or claims, the word is encompassed in a manner similar to the term "comprises" as interpreted when "comprises" is used as a link in the claims. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".

Claims

An online detection system for surface cleanliness of cold-rolled strip steel, characterized in that it includes: stabilizing rolls, strip steel, shielding box, light source, lens, camera, network cable, data acquisition card, image processing server display and cleanliness online detection Software, in which, the stabilizing roller forms a certain wrap angle in the shooting area to suppress the vibration of the strip steel, and the shielding box is used to shield the influence of ambient light on the optical path of the system. The lens is installed on the camera through the interface, and the camera is connected to the data acquisition card through the network cable. Up, the data acquisition card is installed on the PCI slot of the display of the image processing server, and the cleanliness online detection software runs on the display of the image processing server.
An online detection system for cold-rolled strip surface cleanliness as claimed in claim 1, wherein the shielding box is also used to install a light source bracket, a camera bracket and a camera position adjustment mechanism; wherein: the light source bracket on the shielding box Support and protect the light source, the camera bracket on the shielding box supports and protects the camera, and the camera position adjustment mechanism on the shielding box electrically adjusts the horizontal, vertical and pitch angles of the camera to ensure clear image quality.
A kind of cold-rolled strip surface cleanliness online detection system as claimed in claim 1, is characterized in that, cleanliness online detection software runs on the processing server display, cleanliness online detection software consists of image data acquisition and visualization module, imaging quality The detection and camera adjustment module and the cleanliness online detection module are composed; among them, the image data acquisition and visualization module reads the strip steel surface image taken from the camera through the network cable, stores it in the hard disk of the computer host computer, and visualizes it on the computer monitor; the image quality inspection The camera adjustment module identifies the image quality and controls the movement of the camera position adjustment mechanism according to the change of the steel strip specification until the image quality is clear; the cleanliness online detection module detects the residual particles through image preprocessing and area detection, and extracts more residual particles. Then use the classification recognition method to classify and identify the target, and finally count the number of residue particles with different particle sizes, give the cleanliness code according to the cleanliness standard and prompt the adjustment of the parameters of the cleaning process section.
The online detection system for surface cleanliness of cold-rolled strip steel according to claim 3, wherein a plurality of features of residual particles are extracted, at least including geometric shape, gray scale, projection and texture features of residual particles.
The online detection system for surface cleanliness of cold-rolled strip steel according to claim 3, characterized in that the classification and recognition method is used for target classification and recognition, and the classification and recognition method includes artificial neural network, Adaboost or decision tree method.
The online detection system for cold-rolled strip surface cleanliness as claimed in claim 3, wherein the cleanliness code is given according to the cleanliness standard and prompts for parameter adjustment of the cleaning process section, and the cleanliness standard is the cleanliness standard IS016232.
The online detection system for surface cleanliness of cold-rolled strip steel according to claim 1, wherein the light source is an LED light source, the camera is a line array camera, the network cable is a Cameralink network cable for high-speed image transmission, and the image processing server display configuration High-performance GPU is used for image processing algorithm to recognize particle target calculation from high-resolution images of strip steel surface.
An online detection system for surface cleanliness of cold-rolled strip steel as claimed in claim 1, characterized in that, on the basis of the online detection system for surface cleanliness of cold-rolled strip steel, the characteristics of the incoming material of the strip steel and the process parameters of the cleaning section are integrated , can statistically analyze the strip cleanliness of different steel types, different specifications and different cleaning processes, and give suggestions for improving the cleaning process.