CN115673000A - Online visual detection system and method for strip shape display in rough rolling process - Google Patents
Online visual detection system and method for strip shape display in rough rolling process Download PDFInfo
- Publication number
- CN115673000A CN115673000A CN202211275821.7A CN202211275821A CN115673000A CN 115673000 A CN115673000 A CN 115673000A CN 202211275821 A CN202211275821 A CN 202211275821A CN 115673000 A CN115673000 A CN 115673000A
- Authority
- CN
- China
- Prior art keywords
- strip
- industrial camera
- plate
- rough rolling
- plate strip
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a rough rolling process plate strip explicit type plate shape online visual detection system and a method, wherein the system comprises a plate strip detection system, a grating light grid structure light projection system, an image acquisition system, a distance adjustment system and an image processing system; when the strip enters the detection range of the thermal detector, the transmission signal triggers the grating light grid structured light projection system and the image acquisition system to start working; the image acquisition system is used for transmitting acquired image information to the image processing system in real time; the distance adjusting system is used for adjusting the distance between the grating light grid structure light projection system and the image acquisition system. The image processing system is used for processing the images transmitted by the image acquisition system in real time to obtain the three-dimensional outline of the plate strip, obtain a two-dimensional curve of the plate strip in an XOY coordinate system and a two-dimensional curve of the plate strip in a YOZ coordinate system, and further judge the degree and type of the buckle head and the camber of the plate strip.
Description
Technical Field
The invention relates to the technical field of on-line real-time detection of an explicit strip shape of a strip in a rough rolling stage of a hot rolling mill in the field of steel rolling, in particular to an on-line visual detection system and method for the explicit strip shape of the strip in the rough rolling process.
Background
The country pays more and more attention to the development of the industry, and the steel industry is taken as the basis of the industrial development, plays a vital role in the industrial development all the time, and plays a great role in warships, bridges, buildings and the like. However, in the actual production of hot continuous rolling, the rolled piece is often affected by various external factors, so that the rolled piece has the problems of warping, buckling and camber, which not only interferes the production quality and efficiency of the strip, but also correspondingly damages equipment, and brings adverse effects to the development of the whole strip production enterprise. However, because the temperature of the plate strip is too high in the production process, most of steel mills in China currently measure the buckling or warping of the plate strip in rough rolling and poking, after the plate strip is cooled down by stopping the mill and the like, a straight bar with the length of 2m is manually placed on a steel plate, and a ruler is used for manually measuring the gap between the straight bar and the steel plate (the mode is rarely used) or manually observing the gap on a production line by naked eyes, so that the production efficiency is severely restricted, and the labor is consumed. Therefore, a new non-contact measurement system needs to be developed to realize on-line real-time detection of the plate strip.
The vision measurement technology is a novel measurement technology. The important research direction of the vision measurement technology is the measurement of the geometric dimension of an object and the position of the object, and the vision measurement technology can be widely applied to active and real-time measurement processes such as on-line measurement, reverse engineering and the like. The machine vision system has the characteristics of improving the flexibility and the automation degree of production and being suitable for occasions which are not suitable for manual operation.
The machine vision technology has the outstanding advantages of high detection speed, high precision, no contact and the like. The non-contact performance of the visual detection can eliminate the influence caused by manual operation, is not limited by time, and can be used without stopping under the condition of ensuring the good equipment. The machine vision detection technology can rapidly provide the acquired field information for the control center, and the control center can display the outline condition of the product in real time, so that a good foundation is laid for automatic integrated manufacturing. The detection technology can reduce the detection cost of enterprises and can complete various detection tasks in industrial fields. People are not suitable for working in severe environments such as noisy environment, high temperature environment and the like, and the machine vision detection technology provides reliable guarantee for the work. When the product changes to other directions, the machine vision detection technology can quickly find the change and then tell an engineer to make adjustment in time, so that the appearance of the product with unqualified quality is greatly reduced.
In conclusion, because the plate strip is in a high-temperature state in the rough rolling process, manual measurement needs to be carried out after the plate strip is cooled, so that the automation degree of the production process is not high, and the manual detection cannot meet the requirements of the current industrial field more and more. Machine vision is adopted for detection, so that the detection precision, the detection efficiency and the detection automation degree are improved, and the urgent need of modern detection production is met. Therefore, the machine vision measurement is particularly important for online real-time measurement of the plate strip, and the vision measurement technology is a good choice when being applied to plate strip profile measurement due to the advantages of good reproducibility, high measurement precision, high non-contact measurement efficiency, low cost and the like.
Machine vision develops rapidly at home and abroad and is widely applied to various fields. Machine vision based surface detection is: PCB printed circuit detects, STM surface mounting detects, and the quality of agricultural product detects, road conditions detects, product size detects, biological medicine detects etc. and these detecting system have improved the detection precision and the production efficiency of product.
However, the existing machine vision is a bottleneck for online real-time detection and large-sized object detection, and most of previous researches aim at the detection of small parts or local objects, so that the existing machine vision has great limitation. Aiming at the online real-time detection of the explicit plate shape in a hot rolling production line in the metallurgical industry, most of the explicit plate shape detection means adopted by domestic steel mills at present are manual measurement.
Disclosure of Invention
According to the technical problem that the prior art is difficult to realize the on-line real-time detection of the explicit strip shape of the rough rolling strip, the system and the method for the on-line visual detection of the explicit strip shape of the rough rolling strip are provided. The invention can detect and analyze the position and three-dimensional information of the plate strip in real time when the plate strip is subjected to rough rolling.
The technical means adopted by the invention are as follows:
an explicit strip shape online visual inspection system for rough rolling process plate strips comprises: the system comprises a plate and strip detection system, a grating light grid structure light projection system, an image acquisition system, a distance adjustment system and an image processing system; wherein:
the strip detection system is connected with the grating light lattice structure light projection system, and when the strip enters the detection range of the thermal detector, a transmission signal triggers the grating light lattice structure light projection system and the image acquisition system to start working;
the image acquisition system is connected with the image processing system and is used for transmitting acquired image information to the image processing system in real time;
the distance adjusting system is connected with the grating light grid structure light projection system and the image acquisition system and is used for adjusting the distance between the grating light grid structure light projection system and the image acquisition system.
The image processing system is used for processing the images transmitted by the image acquisition system in real time to obtain the three-dimensional outline of the plate strip, obtain a two-dimensional curve of the plate strip in an XOY coordinate system and a two-dimensional curve of the plate strip in a YOZ coordinate system, and further judge the degree and type of the buckle head and the camber of the plate strip.
Further, the plate strip detection system comprises a plate strip, a conveying roller way and a thermal detector, wherein the plate strip is arranged on the conveying roller way, and the plate strip is conveyed into the detection range of the thermal detector through the conveying roller way.
Further, the grating light grid structure light projection system comprises a DLP projector, and the DLP projector is used for projecting grating light grid structure light patterns to the surface of the conveying roller way to wait for the plate strip to enter the range of the structure light.
Further, the image acquisition system comprises a first industrial camera and a second industrial camera, wherein the first industrial camera and the second industrial camera are symmetrically arranged relative to the central line of the conveying roller way and respectively keep an equidistant distance from the DLP projector, and the included angles between the first industrial camera and the vertical line and between the second industrial camera and the vertical line are 60 degrees, so that the cameras and the side edges of the plate strip have certain included angles for detecting the thickness of the plate strip, and the DLP projector projects structured light patterns in the vertical direction for covering the upper surface of the plate strip.
Further, the distance adjusting system comprises a sliding rail device and an equipment fixing shell; the sliding rail device, the industrial camera and the DLP projector are all arranged inside the equipment fixing shell; the equipment fixing shell is connected with the pedestrian cross ladder through a U-shaped device and a U-shaped hanging ring; the slide rail device comprises a slide rail and a device supporting rod, the slide rail is fixed on two inner measurement walls of the equipment fixing shell, the first industrial camera, the second industrial camera and the DLP projector are arranged above a cross beam of the slide rail device through camera fixing plates, and the DLP projector is located at the center of the cross beam.
Further, the fixed shell of equipment still is provided with cooling device, and cooling device is including seting up the income water hole on the fixed shell of equipment, sealed walk line hole and apopore, and be connected with the water pipe through water pipe crossover sub, the fixed shell of equipment still is provided with temperature sensor, real time monitoring device's temperature, and then the discharge of sending instruction control water pipe.
Furthermore, the strip explicit type online visual inspection system for the rough rolling process is arranged at an inlet and an outlet of the rough rolling mill, the inlet is arranged at a position away from the rough rolling mill by a certain distance and is provided with a pedestrian crossing ladder, and the outlet is arranged under an existing frame on site and is positioned right above the strip conveying roller.
The invention also provides a rough rolling process strip explicit strip shape online visual detection method based on the rough rolling process strip explicit strip shape online visual detection system, which comprises the following steps:
adjusting the distances between the first industrial camera, the second industrial camera and the DLP projector and the plate strip through a sliding rail device;
adjusting a grating light grid structure light pattern projected by a DLP projector to enable the edge of the grating light grid structure light pattern to coincide with the edge of the ideal plate strip;
calibrating an explicit strip shape online visual detection system of a rough rolling process strip by using an improved Zhang Zhengyou calibration algorithm, wherein the explicit strip shape online visual detection system comprises internal parameters and external parameters of a first industrial camera and a second industrial camera; a relative position matrix of the first industrial camera, the second industrial camera and the DLP projector, namely a rotation matrix and a translation matrix;
when the thermal detector detects the plate strip, a work starting instruction is sent, and the first industrial camera, the second industrial camera and the DLP projector start to work;
the moving speed of the plate strip and the technological parameters of the rolling mill provided by the steel mill control system are transmitted to the rough rolling process plate strip explicit shape online visual detection system, a first industrial camera and a second industrial camera synchronously shoot images in real time, and shooting frequency is adjusted in real time according to the moving speed of the plate strip provided by the steel mill control system so as to facilitate splicing of subsequent images;
transmitting images shot by a first industrial camera and a second industrial camera to an image processing system for corresponding image preprocessing, including filtering processing, binarization processing and threshold segmentation;
extracting three-dimensional characteristic point clouds from the preprocessed image by using a canny operator;
matching three-dimensional point clouds of plate strips of the double cameras at the same moment obtained by a canny operator, taking a y axis as a boundary line, adopting points from a negative value to a 0 value as a first industrial camera, adopting points from the 0 value to a positive value as a second industrial camera, and matching two results to obtain complete three-dimensional data of the plate strips at the moment;
according to the obtained complete strip three-dimensional data at each moment, because the shooting frequency is obtained according to the strip speed, the overlapped part of two images is identified, and the last line of data of one image is assigned to the first line of data of the next image, so that the splicing of the images is completed;
performing surface fitting on the spliced image data by using a surface fitting algorithm to obtain a complete plate strip three-dimensional contour cloud picture;
and judging the types and the generation processes of the buckle ends and the camber of the plate strip in real time according to the plate strip three-dimensional contour cloud picture.
Compared with the prior art, the invention has the following advantages:
1. the on-line visual detection system for the explicit plate shape of the plate strip in the rough rolling process can detect and analyze the position and three-dimensional information of the plate strip in real time when the plate strip is subjected to the rough rolling process.
2. The invention provides an online visual detection system for the explicit plate shape of a plate strip in the rough rolling process, which adopts two cameras on the left and the right to realize online synchronous measurement.
3. According to the plate strip explicit type plate shape online visual detection system in the rough rolling process, the slide rail device can accurately control the distance between the double industry camera and the DLP projector and the plate strip.
4. According to the on-line visual detection system for the strip shape display in the rough rolling process, the temperature sensor monitors the temperature inside and outside the fixed shell of the equipment in real time, so that the flow of cooling water is controlled in real time, and the safe working environment of the detection system is ensured.
5. The invention provides an on-line visual detection system for an explicit plate shape of a plate strip in a rough rolling process, which is a non-contact binocular detection system for the explicit plate shape of the plate strip in a hot rolling production line. The intelligent degree of a production line is increased while the precision and the efficiency are ensured.
6. The on-line visual detection system for the explicit strip shape of the rough rolling process plate strip, provided by the invention, has the advantages of real-time performance, high speed, visualization of three-dimensional outline and the like, and realizes on-line real-time detection of the explicit strip shape of the hot rolling production line.
Based on the reasons, the method can be widely popularized in the fields of on-line real-time detection of the explicit plate shape of the plate strip in the rough rolling stage of a hot rolling mill in the field of steel rolling and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of the system of the present invention.
Fig. 2 is a schematic view of a principle of a binocular detection system according to an embodiment of the present invention.
Fig. 3 is a chessboard calibration board provided by the embodiment of the present invention.
FIG. 4 is a corner detection during calibration of the detection system of the present invention.
FIG. 5 is a flow chart of the operation of the detection system of the present invention.
Fig. 6 is a schematic diagram of image stitching according to an embodiment of the present invention.
Fig. 7 is a flowchart of image stitching according to an embodiment of the present invention.
In the figure: 1. an image processing system; 2. an image acquisition system; 3. a pedestrian crossing ladder; 4. a device mounting housing; 5. a U-shaped device; 6. a second industrial camera; 7. a first industrial camera; 8. a DLP projector; 9. a slide rail device; 10. high-throwing glass; 11. plate and strip; 12. a conveying roller way; 13. u-shaped rings.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise. Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate. Any specific values in all examples shown and discussed herein are to be construed as exemplary only and not as limiting. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
In the description of the present invention, it is to be understood that the orientation or positional relationship indicated by the directional terms such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal" and "top, bottom", etc., are generally based on the orientation or positional relationship shown in the drawings, and are used for convenience of description and simplicity of description only, and in the absence of any contrary indication, these directional terms are not intended to indicate and imply that the device or element so referred to must have a particular orientation or be constructed and operated in a particular orientation, and therefore should not be considered as limiting the scope of the present invention: the terms "inner and outer" refer to the inner and outer relative to the profile of the respective component itself.
For ease of description, spatially relative terms such as "over 8230 \ 8230;,"' over 8230;, \8230; upper surface "," above ", etc. may be used herein to describe the spatial relationship of one device or feature to another device or feature as shown in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if a device in the figures is turned over, devices described as "above" or "on" other devices or configurations would then be oriented "below" or "under" the other devices or configurations. Thus, the exemplary terms "at 8230; \8230; above" may include both orientations "at 8230; \8230; above" and "at 8230; \8230; below". The device may be otherwise variously oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
It should be noted that the terms "first", "second", and the like are used to define the components, and are only used for convenience of distinguishing the corresponding components, and the terms have no special meanings unless otherwise stated, and therefore, the scope of the present invention should not be construed as being limited.
As shown in fig. 1, the present invention provides an on-line visual inspection system for explicit plate shape of plate and strip in rough rolling process, which is arranged at the inlet and outlet of the rough rolling mill, the inspection system is located right above the conveying roller 12, and the central line of the inspection device coincides with the central line of the conveying roller, and comprises: the system comprises a plate and strip detection system, a grating light grid structure light projection system, an image acquisition system, a distance adjustment system and an image processing system; wherein:
the plate strip detection system is connected with the grating light grid structure light projection system, and when the plate strip enters the detection range of the thermal detector, the transmission signal triggers the grating light grid structure light projection system to start working;
the grating light grid structured light projection system is connected with the image acquisition system, and when the plate strip enters a structured light range, a transmission signal triggers the image acquisition system to start working;
the image acquisition system is connected with the image processing system and is used for transmitting acquired image information to the image processing system in real time;
the distance adjusting system is connected with the grating light grid structure light projection system and the image acquisition system and is used for adjusting the distance between the grating light grid structure light projection system and the image acquisition system.
The image processing system is used for processing the images transmitted by the image acquisition system in real time to obtain the three-dimensional outline of the plate strip, obtain a two-dimensional curve of the plate strip in an XOY coordinate system and a two-dimensional curve of the plate strip in a YOZ coordinate system, and further judge the degree and the type of the buckle heads and the camber of the plate strip.
In specific implementation, as a preferred embodiment of the invention, the strip detection system comprises a strip 11, a conveying roller 12 and a thermal detector, wherein the strip 11 is arranged on the conveying roller 12, and the strip 11 is conveyed by the conveying roller 12 to enter a detection range of the thermal detector.
In specific implementation, as a preferred embodiment of the present invention, the grating light grid structured light projection system includes a DLP projector 8, configured to project a grating light grid structured light pattern onto the surface of the conveying roller 12 to wait for the plate strip 11 to enter the structured light range.
In specific implementation, as a preferred embodiment of the present invention, the image capturing system includes a first industrial camera 7 and a second industrial camera 6, the first industrial camera 7 and the second industrial camera 6 are symmetrically arranged with respect to a center line of the conveying roller 12, and respectively maintain an equidistant distance from the DLP projector 8, and an included angle between the first industrial camera 7 and the vertical line of the second industrial camera 6 is 60 °, so that a certain included angle is formed between the cameras and a side edge of the strip 11, and is used for detecting a thickness of the strip 11, and the DLP projector 8 projects a structured light pattern in a vertical direction, and is used for covering an upper surface of the strip 11.
In specific implementation, as a preferred embodiment of the present invention, the distance adjustment system includes a sliding rail device 9, an equipment fixing housing 4; the sliding rail device 9, the industrial camera and the DLP projector 8 are all arranged in the equipment fixing shell 4; the equipment fixing shell 4 is connected with the pedestrian cross ladder 3 through a U-shaped device 5 and a U-shaped hanging ring 13; slide rail device 9 includes slide rail and device bracing piece, and the slide rail is fixed on surveying the wall in two of equipment stationary housing, and first industry camera 7, second industry camera 6, DLP projecting apparatus 8 all set up in slide rail device 9's crossbeam top through the camera fixed plate, and DLP projecting apparatus 8 is located the center department of crossbeam. The slide rail device 9 is used for adjusting the distances between the first industrial camera 7, the second industrial camera 6, the DLP projector 8 and the conveying roller 12, so that the detection system and the plate belt 11 can be ensured in an effective detection range, and the interference of other external environments is reduced; in this embodiment, the first industrial camera 7 and the second industrial camera 6 are symmetrical with respect to the central line of the detection system, and are respectively spaced from the DLP projector 8 by 0.9m, and the included angles between the first industrial camera 7 and the vertical line and between the second industrial camera 6 and the vertical line are 60 °, so that the cameras and the side edge of the strip have a certain included angle, the thickness of the strip can be detected, and the DLP projector projects a structured light pattern in the vertical direction, which just covers the upper surface of the strip;
in specific implementation, as a preferred embodiment of the present invention, the equipment fixing housing 4 is further provided with a cooling device, the cooling device includes a water inlet hole, a sealed wiring hole and a water outlet hole formed in the equipment fixing housing 4, and is connected to a water pipe through a water pipe adapter, the equipment fixing housing 4 is further provided with a temperature sensor, the temperature of the device is monitored in real time, and then a command is sent to control the water flow rate of the water pipe.
As shown in fig. 2, which is a working flow chart of the strip explicit strip shape online visual inspection system in the rough rolling process of the present invention, before the start of inspection, the system is opened, then system calibration is performed, the internal parameters and external parameters of the dual industrial cameras are determined, and the projection matrix M of the dual cameras is determined. Then, the method works formally, the plate belt enters the detection system, the detection system starts to collect images, the image processing system 1 receives the images transmitted by the image collection system 2 in real time, then image preprocessing and edge contour extraction are carried out, three-dimensional feature point extraction is carried out next step, data fusion is carried out on the three-dimensional feature points of the extracted images shot by the double cameras, the last line of data obtained by image fusion is assigned to the first line of the next image, a complete image splicing result is obtained, and the buckling head and the camber of the explicit plate shape are automatically identified.
The invention also provides a rough rolling process plate strip explicit shape online visual detection method based on the rough rolling process plate strip explicit shape online visual detection system, which comprises the following steps:
adjusting the distances between the first industrial camera 7, the second industrial camera 6 and the DLP projector 8 and the conveying roller table 12, and taking the cross section of the conveying roller table 12 as a reference plane;
the system calibration adopts an improved version based on Zhangyingyou calibration algorithm to calibrate the first industrial camera 7 and the second industrial camera 6, and determines the internal and external parameters of the cameras: focal length f of industrial camera, CCD tilt factor gamma, camera center position (u) 0 ,v 0 ) Imaging point pixel coordinates (u, v), world coordinate system (X) w Y w Z w ) Scale factor s, camera internal parameter A, rotation matrix R, translation matrix T and projection matrix H.
H＝A[R T]
Due to the existence of the protective glass, the object point offset delta, M is introduced into the improvement 1 Is an internal parameter matrix of an industrial camera without a protective glass, M 2 Is an external parameter matrix of an industrial camera without a protective glass, M 3 Is a glass refraction affecting matrix.
And (4) obtaining the internal and external parameters of the first industrial camera 7 and the second industrial camera 6 of the plate and the position geometric relationship between the internal and external parameters by the calibration model.
The camera calibration tool box in MATLAB software is developed for the second time, the cameras are kept still, the first industrial camera 7 and the second industrial camera 6 are made to shoot images by changing the position of the calibration plate, each camera shoots ten groups of pictures, and then the internal and external parameters, the distortion coefficient, the projection matrix H and the position parameters between the duplex industrial cameras are solved.
Transmitting the images shot by the first industrial camera 7 and the second industrial camera 6 to an image processing system for corresponding image preprocessing, including filtering processing, binarization processing and threshold segmentation; the pretreatment comprises the following steps: filtering, binarization and threshold segmentation to obtain an image only containing plate and strip information, processing the image shot by the duplex camera, extracting three-dimensional point cloud of the image shot by the duplex camera by a triangulation method and solving the deformation of the structure light pattern, wherein the point cloud data set extracted by the first industrial camera is P 1 (t 1 )......P 1 (t n ) The point cloud data set extracted by the second industrial camera is P 2 (t 1 )......P 2 (t n ) The data fusion is mainly to take out the first industrial camera t 1 Point cloud data P of time 1 (t 1 ) Taking out the second industrial camera t at the point where the value of x is from a negative value to a value of 0 2 Point cloud data P of time 2 (t 1 ) The x value of the point is from 0 to a positive value, and the two new data sets are fused to obtain the complete t of the plate strip 1 Three-dimensional feature point cloud P (t) of time 1 ) And then by analogy to obtain P (t) 1 )......P(t n )；
For image data splicing, aiming at the complete t of the plate band obtained by data fusion 1 Three-dimensional feature point cloud P of moment 1 (t), first, a data set P is input (t) 1 )：
P(t 1 ) The last line of data in (1) is taken as t 2 Time of day data set P (t) 2 ) The first row of data of (1) then has:
and sequentially recursion is carried out, and finally the three-dimensional data splicing of the whole plate strip is realized to obtain the final plate strip three-dimensional data P (t).
The method comprises the steps of obtaining a two-dimensional curve of the plate strip in an XOY coordinate system and a two-dimensional curve of the plate strip in a YOZ coordinate system, judging the degree and the type of the camber according to the difference between the two-dimensional curve in the XOY coordinate system and an original conveying roller way, judging the buckling degree and the buckling descending degree of a buckling head in the two-dimensional curve in the YOZ coordinate system, and further judging the degree and the type of the buckling head and the camber of the plate strip.
The principle of the binocular detection system is shown in fig. 3:
Ω c1 : first industrial camera coordinate system O c1 -X c1 Y c1 Z c1 Origin O c1 At the optical center of the lens, Z c1 The axis coincides with the camera optical axis; x c1 Axis, Y c1 The axes are respectively parallel to the horizontal axis and the longitudinal axis of the imaging surface;
Ω c2 : first industrial camera coordinate system O c2 -X c2 Y c2 Z c2 Origin O c2 At the optical center of the lens, Z c2 The axis coincides with the camera optical axis; x c2 Axis, Y c2 The axes being parallel to the transverse and longitudinal axes of the imaging plane
o-xy is an image coordinate system; u-v is a pixel coordinate system, and the abscissa u and the ordinate v of a pixel are respectively the number of columns and the number of rows in the image array;
Ω w : world coordinate system O w -X w Y w Z w It is used to characterize the spatial position of an object, being a reference frame in space, the world coordinate system (X) of any point in space w Y w Z w ) The Z axis is parallel to the central axis of the DLP projector 7, and the XOY plane is a reference plane in the measurement model;
p is an object point, the projection of which on the reference surface is P', and P is an imaging point shot by a camera;
the relation expression of the pixel point and the world coordinate coefficient can be obtained through the model:
f x effective focal length of the camera in the x direction;
f y effective focal length of the camera in y direction;
alpha is the angle between the structured light plane and the optical axis of the camera.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not depart from the spirit of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. An explicit strip shape online visual inspection system for rough rolling process plate strips is characterized by comprising: the system comprises a plate and strip detection system, a grating light grid structure light projection system, an image acquisition system, a distance adjustment system and an image processing system; wherein:
the strip detection system is connected with the grating light grid structure light projection system, and when the strip enters the detection range of the thermal detector, the transmission signal triggers the grating light grid structure light projection system and the image acquisition system to start working;
the image acquisition system is connected with the image processing system and is used for transmitting acquired image information to the image processing system in real time;
the distance adjusting system is connected with the grating light grid structure light projection system and the image acquisition system and is used for adjusting the distance between the grating light grid structure light projection system and the image acquisition system.
The image processing system is used for processing the images transmitted by the image acquisition system in real time to obtain the three-dimensional outline of the plate strip, obtain a two-dimensional curve of the plate strip in an XOY coordinate system and a two-dimensional curve of the plate strip in a YOZ coordinate system, and further judge the degree and the type of the buckle heads and the camber of the plate strip.
2. The explicit strip shape online visual detection system for the rough rolling process according to claim 1, wherein the strip detection system comprises a strip, a conveying roller way and a thermal detector, the strip is arranged on the conveying roller way, and the strip is conveyed through the conveying roller way into a detection range of the thermal detector.
3. The rough rolling process strip explicit strip shape online vision inspection system of claim 1, wherein the grating light grid structured light projection system comprises a DLP projector for projecting a grating light grid structured light pattern onto the surface of the transport table waiting for the strip to enter the structured light range.
4. The on-line visual strip shape detection system in the rough rolling process according to claim 1, wherein the image acquisition system comprises a first industrial camera and a second industrial camera, the first industrial camera and the second industrial camera are symmetrically arranged relative to a central line of the conveying roller way and respectively keep an equal distance with a DLP projector, an included angle between the first industrial camera and a vertical line of the second industrial camera is 60 degrees, so that the cameras and the side edges of the strip have a certain included angle for detecting the thickness of the strip, and a projection structured light pattern of the DLP projector is in a vertical direction and is used for covering the upper surface of the strip.
5. The rough rolling process strip explicit strip shape online visual inspection system of claim 1, wherein the distance adjustment system comprises a slide rail device, a device fixing shell; the sliding rail device, the industrial camera and the DLP projector are all arranged inside the equipment fixing shell; the equipment fixing shell is connected with the pedestrian cross ladder through a U-shaped device and a U-shaped hanging ring; the slide rail device comprises a slide rail and a device supporting rod, the slide rail is fixed on two inner measuring walls of the equipment fixing shell, the first industrial camera, the second industrial camera and the DLP projector are arranged above a cross beam of the slide rail device through camera fixing plates, and the DLP projector is located at the center of the cross beam.
6. The rough rolling process plate strip explicit plate shape online visual inspection system according to claim 5, wherein the equipment fixing housing is further provided with a cooling device, the cooling device comprises a water inlet hole, a sealed wire routing hole and a water outlet hole which are formed in the equipment fixing housing, and is connected with a water pipe through a water pipe adapter, the equipment fixing housing is further provided with a temperature sensor, the temperature of the device is monitored in real time, and then a command is sent to control the water flow of the water pipe.
7. An on-line visual strip shape detection system in a rough rolling process according to claim 1, wherein the on-line visual strip shape detection system is installed at an inlet and an outlet of a rough rolling mill, the inlet is installed at a certain distance from the rough rolling mill and is provided with a pedestrian cross ladder, and the outlet is installed below an existing frame on site and is located right above a strip conveying roller.
8. An online visual detection method for the explicit strip shape of a rough rolling process plate strip based on the online visual detection system for the explicit strip shape of the rough rolling process plate strip of any one of claims 1 to 7, which is characterized by comprising the following steps:
adjusting the distances between the first industrial camera, the second industrial camera and the DLP projector and the plate strip through a sliding rail device;
adjusting a grating light grid structure light pattern projected by a DLP projector to enable the edge of the grating light grid structure light pattern to coincide with the edge of the ideal plate strip;
calibrating the explicit strip shape online visual detection system of the rough rolling process strip by using an improved Zhang Zhengyou calibration algorithm, wherein the explicit strip shape online visual detection system comprises internal parameters and external parameters of a first industrial camera and a second industrial camera; a relative position matrix of the first industrial camera, the second industrial camera and the DLP projector, namely a rotation matrix and a translation matrix;
when the thermal detector detects the plate strip, a work starting instruction is sent, and the first industrial camera, the second industrial camera and the DLP projector start to work;
the moving speed of the plate strip and the technological parameters of the rolling mill provided by the steel mill control system are transmitted to the rough rolling process plate strip explicit shape online visual detection system, a first industrial camera and a second industrial camera synchronously shoot images in real time, and shooting frequency is adjusted in real time according to the moving speed of the plate strip provided by the steel mill control system so as to facilitate splicing of subsequent images;
transmitting images shot by a first industrial camera and a second industrial camera to an image processing system for corresponding image preprocessing, including filtering processing, binarization processing and threshold segmentation;
extracting the three-dimensional characteristic point cloud of the preprocessed image by using a canny operator;
matching three-dimensional point clouds of plate strips of the double cameras at the same moment obtained by a canny operator, taking a y axis as a boundary line, adopting points from a negative value to a 0 value as a first industrial camera, adopting points from the 0 value to a positive value as a second industrial camera, and matching two results to obtain complete three-dimensional data of the plate strips at the moment;
according to the obtained complete strip three-dimensional data at each moment, because the shooting frequency is obtained according to the strip speed, the overlapped part of two images is identified, and the last line of data of one image is assigned to the first line of data of the next image, so that the splicing of the images is completed;
performing surface fitting on the spliced image data by using a surface fitting algorithm to obtain a complete plate strip three-dimensional contour cloud picture;
and judging the types and the generation processes of the buckle ends and the camber of the plate strip in real time according to the plate strip three-dimensional contour cloud picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211275821.7A CN115673000A (en) | 2022-10-18 | 2022-10-18 | Online visual detection system and method for strip shape display in rough rolling process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211275821.7A CN115673000A (en) | 2022-10-18 | 2022-10-18 | Online visual detection system and method for strip shape display in rough rolling process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115673000A true CN115673000A (en) | 2023-02-03 |
Family
ID=85066800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211275821.7A Pending CN115673000A (en) | 2022-10-18 | 2022-10-18 | Online visual detection system and method for strip shape display in rough rolling process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115673000A (en) |
-
2022
- 2022-10-18 CN CN202211275821.7A patent/CN115673000A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103759638B (en) | A kind of part detection method | |
| CN110530869A (en) | A kind of detection system based on location information and image information | |
| CN106840033A (en) | A kind of profile of steel rail detection means and method based on image procossing | |
| CN106931881A (en) | A kind of polyphaser visible detection method | |
| CN109405755B (en) | Large-size pipe plate aperture and pitch measuring device and measuring method | |
| CN106996748A (en) | A kind of wheel footpath measuring method based on binocular vision | |
| CN104457577A (en) | Machine-vision-oriented non-contact type workpiece positioning and measuring method | |
| CN108489394A (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device and method | |
| CN105158273A (en) | Optical cable surface defect detecting system based on planar array CMOS cameras | |
| WO2016209412A1 (en) | System and method for measuring reflected optical distortion in contoured panels having specular surfaces | |
| US5214490A (en) | Sheet dimension measurement system | |
| WO2016209410A1 (en) | Non-contact gaging system and method for contoured panels having specular surfaces | |
| CN110986834A (en) | Automatic assembly pipe penetration monitoring method | |
| CN105327950A (en) | Hot rolling intermediate billet camber detecting device and detecting method considering thickness change | |
| CN108805940B (en) | Method for tracking and positioning zoom camera in zooming process | |
| CN108364318A (en) | A kind of planar dimension monocular measuring method for eliminating protective glass refractive effect | |
| CN115384052A (en) | Intelligent laminating machine automatic control system | |
| CN107084677B (en) | A kind of heat- treated steel band deformation detection method and device based on machine vision | |
| CN208171175U (en) | Six-face detection device is used in a kind of production of plate | |
| CN105445285A (en) | Visual detection device and method for wire rods without tension constraint | |
| CN208042989U (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device | |
| CN204027528U (en) | A kind of vision inspection apparatus | |
| CN108732148A (en) | A kind of fluorescent magnetic particle flaw detection on-line measuring device and method | |
| Yan et al. | Online deviation measurement system of the strip in the finishing process based on machine vision | |
| CN115673000A (en) | Online visual detection system and method for strip shape display in rough rolling process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |