CN115876782A - Method and device for detecting flaw point of steel plate and storage medium - Google Patents
Method and device for detecting flaw point of steel plate and storage medium Download PDFInfo
- Publication number
- CN115876782A CN115876782A CN202211563355.2A CN202211563355A CN115876782A CN 115876782 A CN115876782 A CN 115876782A CN 202211563355 A CN202211563355 A CN 202211563355A CN 115876782 A CN115876782 A CN 115876782A
- Authority
- CN
- China
- Prior art keywords
- steel plate
- flaw
- sampling point
- dent
- thickness
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 234
- 239000010959 steel Substances 0.000 title claims abstract description 234
- 238000000034 method Methods 0.000 title claims abstract description 90
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000005070 sampling Methods 0.000 claims abstract description 163
- 230000007547 defect Effects 0.000 claims abstract description 84
- 238000001514 detection method Methods 0.000 claims abstract description 50
- 230000004044 response Effects 0.000 claims abstract description 47
- 238000004590 computer program Methods 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 abstract description 9
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000005096 rolling process Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000009776 industrial production Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a method and a device for detecting flaw points of a steel plate and a computer readable storage medium, and belongs to the technical field of vision measurement. The method comprises the following steps: acquiring the thickness of a steel plate corresponding to a target sampling point of the measured steel plate; judging whether the target sampling point is a hollow defect point or not according to the difference value between the thickness of the steel plate corresponding to the target sampling point and the target thickness; and in response to the target sampling point being the recessed flaw, determining the recessed type of the recessed flaw according to a contrast method. The method at least solves the problems that manual visual steel plate detection in the related technology is high in labor intensity, easy to cause missing detection, incapable of adapting to the production environment of a high-speed unit, low in detection precision and the like, and is suitable for scenes of visual measurement and steel plate detection.
Description
Technical Field
The present invention relates to the field of vision measurement technologies, and in particular, to a method and an apparatus for detecting a flaw point on a steel plate, and a computer-readable storage medium.
Background
The steel plate surface detection is mainly used for detecting discontinuous defects (such as pits, scratches, flaws and the like) on the steel plate surface, and the detection method comprises an artificial experience detection method and a nondestructive detection technology based on electromagnetic induction and ultrasound.
At present, a manual visual method is mainly used for detecting the large steel plate and is limited by the requirement of production takt, and the bottom surface of the steel plate cannot be detected by the manual visual method, so that the upper surface and the lower surface of the detected steel plate cannot be completely covered; and the manual visual detection method can not carry out numerical measurement on the discontinuity of the surface of the steel plate, and needs to add working procedures and carry out steel plate grading operation after measuring the numerical value by using a special instrument, so that the detection of the current large-sized steel plate has the problems of high manual labor intensity, easy detection omission, incapability of adapting to the production environment of a high-speed unit, low detection precision and the like.
Disclosure of Invention
The present invention provides a method, a device and a computer readable storage medium for detecting a flaw point of a steel plate, which at least solve the problems of high labor intensity, easy detection omission, incapability of adapting to the production environment of a high-speed unit, low detection precision and the like in manual visual steel plate detection in the related art.
In a first aspect, the present invention provides a method for detecting a flaw point of a steel plate, comprising: acquiring the thickness of a steel plate corresponding to a target sampling point of the measured steel plate; judging whether the target sampling point is a sink defect point or not according to the difference value between the thickness of the steel plate corresponding to the target sampling point and the target thickness; and in response to the target sampling point being the recessed defect, determining the recessed type of the recessed defect according to a contrast method.
Preferably, the depression types include one or both of: the upper surface is concave and the lower surface is concave. The method for acquiring the thickness of the steel plate corresponding to the target sampling point of the measured steel plate specifically comprises the following steps: acquiring coordinate data of target sampling points on the upper surface and the lower surface of a measured steel plateWherein p = u represents the upper surface of the measured steel plate, p = d represents the lower surface of the measured steel plate, T =0,1,2,. T represents the sampling time, i takes a value of 0,1,2,. A, a represents the total number of sampling points of the upper surface or the lower surface at each sampling time; calculating the thickness of the steel plate corresponding to the target sampling point according to the following formula:
wherein,is Z-axis data in the coordinate data of the target sampling point on the upper surface of the measured steel plate, and is used for judging whether the sample is on the upper surface of the measured steel plate or not>The Z-axis data is the Z-axis data in the coordinate data of the target sampling point on the lower surface of the measured steel plate.
Preferably, the determining whether the target sampling point is a sink defect point according to the difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness includes: judging whether the thickness of the steel plate corresponding to the target sampling point is less than or equal to the difference value between the target thickness and a first threshold value; and judging the target sampling point as a recessed flaw point in response to the fact that the thickness of the steel plate corresponding to the target sampling point is smaller than or equal to the difference value between the target thickness and the first threshold value.
Preferably, the method further includes determining whether the target sampling point is a sink defect according to a difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness, and the method further includes: and judging the target sampling point to be a non-defective point in response to the fact that the thickness of the steel plate corresponding to the target sampling point is larger than the difference value between the target thickness and the first threshold value and the thickness of the steel plate corresponding to the target sampling point is smaller than the sum value of the target thickness and the first threshold value.
Preferably, the determining the recess type of the recessed defect according to a contrast method in response to the target sampling point being the recessed defect specifically includes: and in response to the target sampling point being the recessed flaw, judging whether the recessed flaw meets the following formula according to an adjacent point comparison method:
wherein,is the Z-axis data in the coordinate data of the dent flaw point on the upper surface of the tested steel plate, and is used for judging whether the flaw point is in the normal state or not>The method comprises the steps that for Z-axis data in coordinate data of a recessed flaw on the lower surface of a measured steel plate, v-1, v and v +1 are adjacent recessed flaws, th is a first threshold value, in response to the fact that the recessed flaws simultaneously meet formula (2) and formula (3), the recessed flaw is determined to be upper surface recessed and lower surface recessed, in response to the fact that the recessed flaws meet formula (2) but do not meet formula (3), the recessed flaw is determined to be upper surface recessed, in response to the fact that the recessed flaw does not meet formula (2) but meet formula (3), the recessed flaw is determined to be lower surface recessed.
Preferably, the determining the recess type of the recessed defect according to a contrast method in response to the target sampling point being the recessed defect specifically includes: and responding to the fact that the target sampling point is the recessed defect, judging whether the recessed defect meets the following formula or not according to a scanning line pair comparison method:
wherein,means the average thickness of the upper surface, <' > is> The following table is shownAverage thickness of the face, <' > v>The following formula is satisfied:
determining the dent flaw as an upper surface dent and a lower surface dent in response to the dent flaw satisfying both formula (4) and formula (5),
determining the dent flaw as an upper surface dent in response to the dent flaw satisfying formula (4) but not satisfying formula (5),
in response to the dent defect not satisfying formula (4) but satisfying formula (5), the dent defect is determined to be a lower surface dent.
Preferably, the determining the position of the dent flaw point specifically includes: determining the coordinate values of the X axis and the Y axis of the position of the recessed flaw point according to the following formula:
y=t·L (7)
x=(i+0.5)·WN (8)
wherein, L is the steel plate stepping length collected by each camera, W is the scanning range covered by each camera, and N is the number of points sampled by each camera each time.
Preferably, before the acquiring the coordinate data of the target sampling points on the upper surface and the lower surface of the measured steel plate, the method further comprises: acquiring image data of the upper surface and the lower surface of the measured steel plate by adopting an array camera according to an acquisition signal period, and outputting a first coordinate of a sampling point, wherein the first coordinate is in a coordinate system taking the position of the array camera as an origin; converting the first coordinates of the sampling points output by each camera into a world coordinate system according to the relative position relationship of each camera in the array camera to obtain the coordinate data of the target sampling points on the upper surface and the lower surface of the measured steel plate
In a second aspect, the present invention further provides a device for detecting a steel plate flaw, including an obtaining module, a determining module, and a determining module.
And the acquisition module is used for acquiring the thickness of the steel plate corresponding to the target sampling point of the measured steel plate. And the judging module is connected with the obtaining module and used for judging whether the target sampling point is a hollow defect point or not according to the difference value between the thickness of the steel plate corresponding to the target sampling point and the target thickness. And the determining module is connected with the judging module and used for determining the recess type of the recess defect according to the contrast method in response to the target sampling point being the recess defect.
In a third aspect, the present invention further provides a detection apparatus, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the method for detecting a steel plate flaw according to the first aspect.
In a fourth aspect, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for detecting a steel plate defect according to the first aspect.
According to the steel plate flaw detection method, the steel plate flaw detection device and the computer readable storage medium, the steel plate thickness data of the sampling point is obtained, the target thickness is compared with the steel plate thickness data of the sampling point, whether the sampling point is the recessed flaw is judged, and then the recessed type of the recessed flaw is determined, namely whether the sampling point is the recessed flaw on the upper surface or the recessed flaw on the lower surface is determined. Conventional vision equipment (e.g., a camera) may be employed to acquire data for the sample points. Compared with a manual visual method, the method for detecting the flaws of the steel plate in the industrial production based on the machine vision has the characteristics of higher automation degree, comprehensive detection, suitability for the production environment of a high-speed unit and high detection precision.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting a flaw point of a steel plate in embodiment 1 of the present invention;
fig. 2 is a schematic structural diagram of a steel plate detection system according to embodiment 1 of the present invention;
FIG. 3 is a schematic view of a world coordinate system according to embodiment 1 of the present invention;
FIG. 4 is a schematic view showing the depression of the upper surface of a steel sheet according to example 1 of the present invention;
FIG. 5 is a schematic view of steel plate scanning according to embodiment 1 of the present invention;
fig. 6 is a schematic structural diagram of a device for detecting flaws in a steel plate according to embodiment 2 of the present invention;
fig. 7 is a schematic structural diagram of a detection apparatus according to embodiment 3 of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the following detailed description will be made with reference to the accompanying drawings.
It is to be understood that the specific embodiments and figures described herein are merely illustrative of the invention and are not limiting of the invention.
It is to be understood that the embodiments and features of the embodiments can be combined with each other without conflict.
It is to be understood that, for the convenience of description, only parts related to the present invention are shown in the drawings of the present invention, and parts not related to the present invention are not shown in the drawings.
It should be understood that each unit and module related in the embodiments of the present invention may correspond to only one physical structure, may also be composed of multiple physical structures, or multiple units and modules may also be integrated into one physical structure.
It will be understood that, without conflict, the functions, steps, etc. noted in the flowchart and block diagrams of the present invention may occur in an order different from that noted in the figures.
It is to be understood that the flowchart and block diagrams of the present invention illustrate the architecture, functionality, and operation of possible implementations of systems, apparatus, devices and methods according to various embodiments of the present invention. Each block in the flowchart or block diagrams may represent a unit, module, segment, code, which comprises executable instructions for implementing the specified function(s). Furthermore, each block or combination of blocks in the block diagrams and flowchart illustrations can be implemented by hardware-based systems that perform the specified functions or by a combination of hardware and computer instructions.
It is to be understood that the units and modules involved in the embodiments of the present invention may be implemented by software, and may also be implemented by hardware, for example, the units and modules may be located in a processor.
Example 1:
as shown in fig. 1, the present embodiment provides a method for detecting a steel plate flaw, which is applied to detect a flaw of a large steel plate or a small steel plate, and the method for detecting a steel plate flaw includes:
In this embodiment, a conventional vision device, such as a camera, may be used to obtain data of a target sampling point of a measured steel plate.
Specifically, the acquiring of the thickness of the steel plate corresponding to the target sampling point of the measured steel plate includes steps 1011 to 1012:
step 1011, obtaining coordinate data of target sampling points on the upper surface and the lower surface of the measured steel plateWhere p = u denotes the upper surface of the steel plate to be measured, p = d denotes the lower surface of the steel plate to be measured, T =0,1,2,. T denotes the sampling time, i takes a value of 0,1,2,. A, and a denotes the total number of sampling points of the upper surface or the lower surface at each sampling time.
Step 1012, calculating the thickness of the steel plate corresponding to the target sampling point according to the following formula:
wherein,is Z-axis data in the coordinate data of the target sampling point on the upper surface of the measured steel plate, and is combined with the coordinate data of the target sampling point on the upper surface of the measured steel plate>The Z-axis data is the Z-axis data in the coordinate data of the target sampling point on the lower surface of the measured steel plate.
Optionally, before the acquiring the coordinate data of the target sampling points on the upper surface and the lower surface of the measured steel plate, the method for detecting the flaw of the steel plate further includes: acquiring image data of the upper surface and the lower surface of the measured steel plate by adopting an array camera according to an acquisition signal period, and outputting a first coordinate of a sampling point, wherein the first coordinate is in a coordinate system taking the position of the array camera as an origin; converting the first coordinates of the sampling points output by each camera into a world coordinate system according to the relative position relationship of each camera in the array camera to obtain the coordinate data of the target sampling points on the upper surface and the lower surface of the measured steel plate
In this embodiment, a steel plate detection system as shown in fig. 2 is used to obtain coordinate data of target sampling points on the upper surface and the lower surface of a measured steel plate. The steel plate detection system comprises an image acquisition device 11, camera calibration software 12 and data analysis software 13. And the image acquisition device 11 is used for acquiring the image data of the upper surface and the lower surface of the measured steel plate. And the camera calibration software 12 is connected with the image acquisition device 11 and is used for performing data preprocessing on the acquired image data. And the data analysis software 13 is connected with the camera calibration software 12 and used for calculating the thickness standard deviation of the measured steel plate according to the preprocessed image data and evaluating the thickness uniformity of the measured steel plate according to the thickness standard deviation. Optionally, the image acquisition device comprises an array camera and an acquisition signal controller. The array camera is connected with the acquisition signal controller and used for acquiring image data of the upper surface and the lower surface of the measured steel plate according to the acquisition signal sent by the acquisition signal controller and outputting a first coordinate of a sampling point, wherein the first seat is connected with the acquisition signal controllerThe target is in a coordinate system with the position of the array camera as the origin. The acquisition signal controller is internally provided with an acquisition signal period, and is used for sending acquisition signals to the array camera according to the acquisition signal period, wherein the acquisition signal period is the ratio of the steel plate stepping length L (unit: meter) to the steel plate transmission rate S (unit: meter/second), namely the time interval of the acquisition signal controller for sending the acquisition signals is as follows: τ = LS (unit: second), that is, the array camera captures and acquires data once every interval τ. In particular, the array camera includes two sets of linear scanning cameras. And the two groups of linear scanning cameras are used for being fixedly arranged at the upper part and the lower part of the detection gate respectively and keeping a preset shooting distance between the two groups of linear scanning cameras and the corresponding surfaces of the detected steel plate respectively, wherein the plurality of linear scanning cameras in the group cover the width of the detected steel plate together in a device cascading mode. A group of three-dimensional (3D) linear scanning cameras are respectively arranged on the upper portion and the lower portion of a detection gate (namely, above and below a steel plate to be detected) to acquire image data, and the upper (or lower) cameras are cascaded through equipment to jointly cover the width of the whole detected steel plate. Each camera covers a straight line range with a certain length, and 6 cameras jointly cover the width of the steel plate to be tested in an equipment cascade mode. The number of the cameras is determined by the width of the steel plate (or other measured object) to be measured and the scanning range of the cameras (for example, when the acquisition coverage width of the image data of each 3D camera is 0.45 meter, and the width of the steel plate to be measured is 4.2 meters, a total of 18 to 20 3D cameras are required to cover the width of the upper and lower surfaces of the whole steel plate to be measured in a device cascade manner). When the resolutions of the cascaded cameras are different, according to the different resolutions of the cameras, each camera obtains a group of coordinates related to the pixel points of the measured steel plate in the coverage range, and outputs a first coordinate of the measured steel plate as a coordinate system based on the position of each camera as an origin, and the first coordinate mark is used as:where p = u or p = d, u denotes a camera above the upper surface of the measured steel plate, d denotes a camera below the lower surface of the measured steel plate, T =0,1,2,. T denotes a sampling time, j =0,1,2,. M denotes a camera index ID, k =0,1,2,. N denotes each phaseThe machine collects the index ID of N sampling points at each time, all the cameras are uniformly controlled by the signal collection controller, and when the signal collection controller sends out collection signals, all the cameras start to shoot and collect the image data of the measured steel plate at the same time. Optionally, the image acquisition device further comprises a rate controller and a roller bed. And the speed controller is connected with the rolling machine, and the steel plate transmission speed is arranged in the speed controller and is used for controlling the rotating speed of the rolling machine according to the steel plate transmission speed. And the rolling machine is used for placing the steel plate to be measured and rotating according to the rotating speed so as to convey the steel plate to be measured. In this embodiment, the rate controller and the acquisition signal controller are controlled and cooperated by rate matching software. The camera calibration software includes a coordinate conversion module. And the coordinate conversion module is used for converting the first coordinates of the sampling points output by each camera into a world coordinate system according to the relative position relationship of each camera in the array camera to obtain the converted acquisition data. Preferably, as shown in fig. 3, the origin O of the world coordinate system is a corner of the measured steel plate (a corner of the detected object is a uniform coordinate origin O as shown in fig. 2), the X axis of the world coordinate system is parallel to the camera array formed by the cameras, the Y axis of the world coordinate system is parallel to the conveying direction of the measured steel plate, the Z axis of the world coordinate system is perpendicular to the XOY plane, and the converted collected data is:Where i = j · N + k, j is the camera index, i takes a value of 0,1, 2.. A, a = M · N + N M Represents the total number of sampling points, N, of any surface of the steel plate to be tested at each sampling moment M M represents the number of sampling points of the last camera for shooting any surface of the steel plate to be measured. It should be noted that the origin of the world coordinate system is not limited to a corner of the measured steel plate in the present embodiment. The data collected by each camera is converted into the collected data in the same coordinate system, so that the subsequent calculation of the thickness of the measured steel plate is facilitated, and the accuracy of the calculation result is ensured.
And 102, judging whether the target sampling point is a sink defect according to the difference value between the thickness of the steel plate corresponding to the target sampling point and the target thickness.
In this embodiment, when the thickness of the steel plate corresponding to the target sampling point is smaller than the target thickness, it can be determined whether the target sampling point is a hollow defect. However, since the steel plate to be detected may have mechanical vibration during the detection process, in order to improve the detection accuracy, the first threshold value is set to be the tolerance thickness within the target thickness range.
Specifically, the determining whether the target sampling point is the sink defect point according to the difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness includes: judging whether the thickness of the steel plate corresponding to the target sampling point is smaller than or equal to the difference value between the target thickness and a first threshold value; and judging the target sampling point as a recessed flaw point in response to the fact that the thickness of the steel plate corresponding to the target sampling point is smaller than or equal to the difference value between the target thickness and the first threshold value.
In this embodiment, the first threshold is set to Th, and the thickness requirement of steel plate production is combined, and when the following conditions are met, the target sampling point is determined to be a hollow defect:
for example, the value of H is 1 cm, the value of Th is 0.2 cm, and when the thickness of the target sampling point is less than or equal to 0.8 cm, the defect is determined to be a hollow defect.
Optionally, the method for detecting a steel plate flaw further includes: and judging the target sampling point as a clear defect point in response to the fact that the thickness of the steel plate corresponding to the target sampling point is larger than the difference value between the target thickness and the first threshold value and the thickness of the steel plate corresponding to the target sampling point is smaller than the sum value of the target thickness and the first threshold value.
And 103, in response to the target sampling point being the recessed flaw, determining the recessed type of the recessed flaw according to a contrast method.
In this embodiment, the depression type includes one or two of the following: the upper surface is concave and the lower surface is concave, as shown in fig. 4. The comparison method of the present embodiment includes one or a combination of both of the adjacent dot comparison method and the scanning line comparison method.
Optionally, the determining, in response to the target sampling point being a recessed defect, a recessed type of the recessed defect according to a contrast method specifically includes:
and in response to the target sampling point being the recessed flaw, judging whether the recessed flaw meets the following formula according to an adjacent point comparison method:
wherein,is the Z-axis data in the coordinate data of the dent flaw point on the upper surface of the tested steel plate, and is used for judging whether the flaw point is in the normal state or not>Is Z-axis data in the coordinate data of the recessed flaw on the lower surface of the measured steel plate, v-1, v and v +1 are adjacent recessed flaws, th is a first threshold value,
determining the dent flaw point as an upper surface dent and a lower surface dent in response to the dent flaw point satisfying both of the formula (2) and the formula (3),
determining the dent flaw as an upper surface dent in response to the dent flaw satisfying formula (2) but not satisfying formula (3),
in response to the dent defect not satisfying formula (2) but satisfying formula (3), the dent defect is determined to be a lower surface dent.
Optionally, the determining, in response to the target sampling point being a recessed defect, a recessed type of the recessed defect according to a contrast method specifically includes:
and responding to the target sampling point as the recessed flaw point, and judging whether the recessed flaw point meets the following formula according to a scanning line pair comparison method:
wherein,means for indicating the mean thickness of the upper surface> Represents the average thickness of the lower surface, < > is greater or less>The following formula is satisfied:
determining the dent flaw as an upper surface dent and a lower surface dent in response to the dent flaw satisfying both formula (4) and formula (5),
determining the dent flaw as an upper surface dent in response to the dent flaw satisfying formula (4) but not satisfying formula (5),
in response to the depression defect not satisfying formula (4) but satisfying formula (5), the depression defect is determined to be a lower surface depression.
In this embodiment, t is a sampling time or a scanning time. The principle of equations (4) and (5) is: considering the shake of the steel plate in the detection process, acquiring all sampling points of which the thickness of the steel plate meets the formula (6), for example, acquiring sampling points of which the thickness of the steel plate is greater than 0.9 cm, calculating the average thickness value of the steel plate by using all sampling points on the scanning moment (namely the same scanning line where the array camera is located) of the sampling points, and determining that the recessed flaw is an upper surface recessed defect when the vertical coordinate of the upper surface of the recessed flaw determined in the step 102 is lower than the preset threshold of the average thickness coordinate value; and when the ordinate of the lower surface of the recessed flaw determined in the step 102 is higher than the preset threshold of the average thickness coordinate value, determining that the recessed flaw is a recessed lower surface. And the adjacent point comparison method and the scanning line comparison method are alternatively used, so that the defect type of the dent defect can be determined and verified based on the adjacent point comparison method and the scanning line comparison method together for further improving the detection precision.
Optionally, after determining the type of the dent flaw according to the contrast method, the method for detecting the steel plate flaw further comprises: and determining the position of the recessed flaw point.
Specifically, the determining the location of the dent flaw comprises:
determining the coordinate values of the X axis and the Y axis of the position of the dent flaw according to the following formula:
y=t·L (7)
x=(i+0.5)·WN (8)
wherein, L is the steel plate stepping length collected by each camera, W is the scanning range covered by each camera, and N is the number of points sampled by each camera each time.
In this embodiment, as shown in the schematic steel plate scanning diagram shown in fig. 5, formula (7) is used to locate the Y coordinate of the dent flaw, the step length of each scanning in the Y axis direction is L, T =0,1,2, \8230, T represents the sampling time index of the scanning, i.e., the step is performed T times, so that the positioning is Y = T · L, formula (8) is used to locate the X coordinate of the dent flaw, the width of the steel plate in the X axis direction is W, N samples are uniformly sampled in the X axis direction each time, and the X coordinate of the points is the midpoint of each grid.
In the method for detecting a steel plate flaw of the embodiment, the steel plate thickness data of the sampling point is obtained, the target thickness is compared with the steel plate thickness data of the sampling point to judge whether the sampling point is a recessed flaw, and then the recessed type of the recessed flaw is determined, that is, whether the sampling point is a recessed flaw on the upper surface or a recessed flaw on the lower surface is determined. Conventional vision equipment (e.g., a camera) may be employed to acquire data for the sample points. Compared with a manual visual method, the method for detecting the flaws of the steel plate in the industrial production based on the machine vision has the characteristics of higher automation degree, comprehensive detection, suitability for the production environment of a high-speed unit and high detection precision. When the type of the dent defect is determined based on the contrast method, the adjacent contrast method and the scanning line contrast method are alternatively used, and in order to further improve the detection precision, the defect type of the dent defect can be determined and verified based on the adjacent contrast method and the scanning line contrast method together. Furthermore, the position of the pit flaw point is determined based on the stepping length and the coverage range of the camera, and the positioning method is simple and convenient and can realize accurate positioning.
Example 2:
as shown in fig. 6, the present embodiment provides a device for detecting a steel plate flaw, which includes an obtaining module 61, a determining module 62, and a determining module 63.
And the obtaining module 61 is configured to obtain a thickness of the steel plate corresponding to the target sampling point of the measured steel plate.
And the judging module 62 is connected with the obtaining module 61 and is used for judging whether the target sampling point is a hollow defect point according to the difference value between the thickness of the steel plate corresponding to the target sampling point and the target thickness.
And the determining module 63 is connected with the judging module 62 and is used for determining the recess type of the recessed defect according to a contrast method in response to the target sampling point being the recessed defect.
Optionally, the depression type includes one or both of: the upper surface is concave and the lower surface is concave.
The acquisition module comprises an acquisition unit and a calculation unit.
An acquisition unit for acquiring coordinate data of target sampling points on the upper and lower surfaces of the steel plateWhere p = u denotes the upper surface of the steel sheet to be measured, p = d denotes the lower surface of the steel sheet to be measured, T =0,1,2, \8230, T denotes sampling time, i takes a value of 0,1,2, \8230A, and A denotes the total number of sampling points on the upper surface or the lower surface at each sampling time.
The calculating unit is connected with the obtaining unit and used for calculating the thickness of the steel plate corresponding to the target sampling point according to the following formula:
wherein,is Z-axis data in the coordinate data of the target sampling point on the upper surface of the measured steel plate, and is combined with the coordinate data of the target sampling point on the upper surface of the measured steel plate>The Z-axis data is the Z-axis data in the coordinate data of the target sampling point on the lower surface of the measured steel plate.
Optionally, the device for detecting a flaw point on a steel plate further comprises a steel plate detection system.
The steel plate detection system is used for acquiring image data of the upper surface and the lower surface of a measured steel plate by adopting an array camera according to an acquisition signal period and outputting a first coordinate of a sampling point, wherein the first coordinate is in a coordinate system taking the position of the array camera as an origin; converting the first coordinates of the sampling points output by each camera into a world coordinate system according to the relative position relationship of each camera in the array camera to obtain the coordinate data of the target sampling points on the upper surface and the lower surface of the measured steel plate
In this embodiment, a steel plate detection system as shown in fig. 2 is used to obtain coordinate data of target sampling points on the upper surface and the lower surface of a steel plate to be detected. The steel plate detection system comprises an image acquisition device 11, camera calibration software 12 and data analysis software 13. And the image acquisition device 11 is used for acquiring the image data of the upper surface and the lower surface of the measured steel plate. And the camera calibration software 12 is connected with the image acquisition device 11 and is used for performing data preprocessing on the acquired image data. Data analysis software 13 connected to the camera calibration software 12 for calculating the data according to the preprocessed image dataAnd evaluating the thickness uniformity of the measured steel plate according to the thickness standard deviation. Optionally, the image acquisition device comprises an array camera and an acquisition signal controller. And the array camera is connected with the acquisition signal controller and is used for acquiring image data of the upper surface and the lower surface of the measured steel plate according to the acquisition signal sent by the acquisition signal controller and outputting a first coordinate of the sampling point, wherein the first coordinate is in a coordinate system taking the position of the array camera as an origin. The acquisition signal controller is internally provided with an acquisition signal period and is used for sending acquisition signals to the array camera according to the acquisition signal period, wherein the acquisition signal period is the ratio of the steel plate stepping length L (unit: meter) to the steel plate transmission rate S (unit: meter/second), namely the time interval for sending the acquisition signals by the acquisition signal controller is as follows: τ = LS (unit: second), that is, the array camera captures and acquires data once every interval τ. In particular, the array camera includes two sets of linear scanning cameras. And the two groups of linear scanning cameras are used for being fixedly arranged at the upper part and the lower part of the detection gate respectively and keeping a preset shooting distance between the two groups of linear scanning cameras and the corresponding surfaces of the detected steel plate respectively, wherein the plurality of linear scanning cameras in the group cover the width of the detected steel plate together in a device cascading mode. A group of three-dimensional (3D) linear scanning cameras are respectively arranged on the upper portion and the lower portion (namely the upper portion and the lower portion of a steel plate to be detected) of the detection gate to collect image data, and the upper portion (or the lower portion) of the detection gate covers the width of the whole detected steel plate together through equipment cascade connection. Each camera covers a straight line range with a certain length, and 6 cameras jointly cover the width of the steel plate to be tested in an equipment cascade mode. The number of the cameras is determined by the width of the steel plate (or other object to be measured) to be measured and the scanning range of the cameras (for example, when the acquisition coverage width of the image data of each 3D camera is 0.45 meter, and the width of the steel plate to be measured is 4.2 meters, a total of 18 to 20 3D cameras are required to cover the width of the upper and lower surfaces of the whole steel plate to be measured in a device cascade manner). When the resolutions of the cascaded cameras are different, each camera obtains a group of coordinates of pixel points related to the measured steel plate in the coverage range according to the different resolutions of the cameras, and outputs a first coordinate of the measured steel plate based on the respective camera positionSet as the coordinate system of the origin, the first coordinate mark is:p = u or p = d, u represents a camera above the upper surface of the steel plate to be measured, d represents a camera below the lower surface of the steel plate to be measured, T =0,1,2,. T represents a sampling time, j =0,1,2,. M represents a camera index ID, k =0,1,2,. N represents an index ID of each camera acquiring N sampling points at a time, all the cameras are uniformly controlled by the acquisition signal controller, and when the acquisition signal controller sends out an acquisition signal, all the cameras simultaneously start to shoot and acquire image data of the steel plate to be measured. Optionally, the image acquisition device further comprises a rate controller and a roller bed. And the speed controller is connected with the rolling machine, and the steel plate transmission speed is arranged in the speed controller and is used for controlling the rotating speed of the rolling machine according to the steel plate transmission speed. And the rolling machine is used for placing the steel plate to be measured and rotating according to the rotating speed so as to convey the steel plate to be measured. In this embodiment, the rate controller and the acquisition signal controller are controlled and cooperated by rate matching software. The camera calibration software includes a coordinate conversion module. And the coordinate conversion module is used for converting the first coordinates of the sampling points output by each camera into a world coordinate system according to the relative position relationship of each camera in the array camera to obtain the converted acquisition data. Preferably, as shown in fig. 3, the origin O of the world coordinate system is a corner of the measured steel plate (a corner of the detected object is a uniform coordinate origin O as shown in fig. 2), the X axis of the world coordinate system is parallel to the camera array formed by the cameras, the Y axis of the world coordinate system is parallel to the conveying direction of the measured steel plate, the Z axis of the world coordinate system is perpendicular to the XOY plane, and the converted collected data is:Where i = j · N + k, j is the camera index, i takes the value 0,1,2 M Representing the total number of sampling points, N, of any surface of the steel plate to be tested at each sampling moment M M represents the number of sampling points of the last camera for shooting any surface of the measured steel plate. It should be noted that the origin of the world coordinate system is not limited to a corner of the measured steel plate in the present embodiment. By converting data acquired by each camera intoAnd data are collected in the same coordinate system, so that the subsequent calculation of the thickness of the measured steel plate is facilitated, and the accuracy of the calculation result is ensured.
Optionally, the determination module comprises a determination unit and a determination unit.
And the judging unit is used for judging whether the thickness of the steel plate corresponding to the target sampling point is less than or equal to the difference value between the target thickness and the first threshold value.
And the judging unit is connected with the judging unit and used for judging the target sampling point as the dent defect point in response to the condition that the thickness of the steel plate corresponding to the target sampling point is less than or equal to the difference value between the target thickness and the first threshold value.
Optionally, the determining unit is further configured to determine the target sampling point to be a clear defect point in response to that the thickness of the steel plate corresponding to the target sampling point is greater than the difference value between the target thickness and the first threshold, and the thickness of the steel plate corresponding to the target sampling point is less than the sum value between the target thickness and the first threshold.
Optionally, the determining means comprises a first determining unit.
The first determining unit is used for responding to the target sampling point as the recessed defect point and judging whether the recessed defect point meets the following formula or not according to a neighbor comparison method:
wherein,is the Z-axis data in the coordinate data of the dent flaw point on the upper surface of the tested steel plate, and is combined with the coordinate data of the dent flaw point on the upper surface of the tested steel plate>Is Z-axis data in the coordinate data of the recessed flaw on the lower surface of the measured steel plate, v-1, v and v +1 are adjacent recessed flaws, th is the firstThe threshold value is set to a value that is,
determining the dent flaw point as an upper surface dent and a lower surface dent in response to the dent flaw point satisfying both of the formula (2) and the formula (3),
determining the dent flaw as an upper surface dent in response to the dent flaw satisfying formula (2) but not satisfying formula (3),
in response to the dent defect not satisfying formula (2) but satisfying formula (3), the dent defect is determined to be a lower surface dent.
Optionally, the determining module further comprises a second determining unit.
The second determining unit is used for responding to the target sampling point as the recessed defect point and judging whether the recessed defect point meets the following formula according to a scanning line pair comparison method:
wherein,means the average thickness of the upper surface, <' > is> Represents the average thickness of the lower surface, < > is greater or less>The following formula is satisfied:
determining the dent flaw as an upper surface dent and a lower surface dent in response to the dent flaw satisfying both formula (4) and formula (5),
determining the dent flaw as an upper surface dent in response to the dent flaw satisfying formula (4) but not satisfying formula (5),
in response to the dent defect not satisfying formula (4) but satisfying formula (5), the dent defect is determined to be a lower surface dent.
Optionally, the device for detecting a flaw of a steel plate further comprises a positioning module.
And the positioning module is used for determining the position of the recessed flaw point.
Optionally, the positioning module is specifically configured to determine coordinate values of an X axis and a Y axis of the location of the flaw defect according to the following formula:
y=t·L (7)
x=(i+0.5)·WN (8)
wherein, L is the steel plate stepping length collected by each camera, W is the scanning range covered by each camera, and N is the number of points sampled by each camera each time.
Example 3:
as shown in fig. 7, the present embodiment provides a detection apparatus, which includes a memory 71 and a processor 72, wherein the memory 71 stores a computer program, and the processor 72 is configured to run the computer program to implement the method for detecting a steel plate defect according to embodiment 1.
Example 4:
the present embodiment provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the method of detecting a steel plate flaw as described in embodiment 1.
The steel plate defect detecting apparatus of embodiment 2, the detecting apparatus of embodiment 3, and the computer-readable storage medium of embodiment 4 are configured to acquire steel plate thickness data of a sampling point, and compare a target thickness with the steel plate thickness data of the sampling point to determine whether the sampling point is a recessed defect, and to determine a recess type of the recessed defect, that is, to specify whether the sampling point is a recessed defect on an upper surface or a recessed defect on a lower surface. For acquiring data of the sample points using conventional vision equipment, such as a camera. The detection device for detecting the flaws of the steel plate in industrial production based on machine vision has the characteristics of higher automation degree, comprehensive detection, suitability for the production environment of a high-speed unit and high detection precision compared with a manual visual method. When the method is used for determining the type of the dent defect by adopting the contrast method, the adjacent contrast method and the scanning line contrast method are alternatively used, so that the method is used for determining and verifying the defect type of the dent defect by adopting the adjacent contrast method and the scanning line contrast method together for further improving the detection precision. Furthermore, the positioning module is used for determining the position of the recessed flaw point based on the stepping length and the coverage range of the camera, and the positioning device is simple and convenient and can realize accurate positioning.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and scope of the invention, and such modifications and improvements are also considered to be within the scope of the invention.
Claims (12)
1. A method for detecting flaw points of a steel plate is characterized by comprising the following steps:
acquiring the thickness of a steel plate corresponding to a target sampling point of the measured steel plate;
judging whether the target sampling point is a hollow defect point or not according to the difference value between the thickness of the steel plate corresponding to the target sampling point and the target thickness;
and in response to the target sampling point being the recessed flaw, determining the recessed type of the recessed flaw according to a contrast method.
2. The method of detecting plate blemishes of claim 1, wherein the type of depression comprises one or both of: the upper surface is concave, the lower surface is concave,
the method for acquiring the thickness of the steel plate corresponding to the target sampling point of the measured steel plate specifically comprises the following steps:
obtainingCoordinate data of target sampling points on the upper surface and the lower surface of the measured steel plateWherein p = u represents the upper surface of the measured steel plate, p = d represents the lower surface of the measured steel plate, T =0,1,2,. T represents the sampling time, i takes a value of 0,1,2,. A represents the total number of sampling points of the upper surface or the lower surface at each sampling time;
calculating the thickness of the steel plate corresponding to the target sampling point according to the following formula:
wherein,is Z-axis data in the coordinate data of the target sampling point on the upper surface of the measured steel plate, and is used for judging whether the sample is on the upper surface of the measured steel plate or not>The Z-axis data is the Z-axis data in the coordinate data of the target sampling point on the lower surface of the measured steel plate.
3. The method for detecting flaws on a steel plate according to claim 2, wherein before the obtaining the coordinate data of the target sampling points on the upper surface and the lower surface of the steel plate to be detected, the method further comprises:
acquiring image data of the upper surface and the lower surface of the measured steel plate by adopting an array camera according to an acquisition signal period, and outputting a first coordinate of a sampling point, wherein the first coordinate is in a coordinate system taking the position of the array camera as an origin;
converting the first coordinates of the sampling points output by each camera into a world coordinate system according to the relative position relationship of each camera in the array camera to obtain the coordinate data of the target sampling points on the upper surface and the lower surface of the measured steel plate
4. The method for detecting the steel plate defect according to claim 1, wherein the determining whether the target sampling point is the recessed defect according to the difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness specifically comprises:
judging whether the thickness of the steel plate corresponding to the target sampling point is smaller than or equal to the difference value between the target thickness and a first threshold value;
and judging the target sampling point as a recessed flaw point in response to the fact that the thickness of the steel plate corresponding to the target sampling point is smaller than or equal to the difference value between the target thickness and the first threshold value.
5. The method for detecting the steel plate defect of claim 4, wherein the step of determining whether the target sampling point is the recessed defect according to the difference between the steel plate thickness corresponding to the target sampling point and the target thickness further comprises the following steps:
and judging the target sampling point as a clear defect point in response to the fact that the thickness of the steel plate corresponding to the target sampling point is larger than the difference value between the target thickness and the first threshold value and the thickness of the steel plate corresponding to the target sampling point is smaller than the sum value of the target thickness and the first threshold value.
6. The method for detecting a steel plate defect according to claim 2, wherein the determining the recess type of the recess defect according to a contrast method in response to the target sampling point being the recess defect specifically comprises:
and in response to the target sampling point being the recessed flaw, judging whether the recessed flaw meets the following formula according to an adjacent point comparison method:
wherein,is the Z-axis data in the coordinate data of the dent flaw point on the upper surface of the tested steel plate, and is used for judging whether the flaw point is in the normal state or not>Is Z-axis data in the coordinate data of the recessed flaw on the lower surface of the measured steel plate, v-1, v and v +1 are adjacent recessed flaws, th is a first threshold value,
determining the dent flaw point as an upper surface dent and a lower surface dent in response to the dent flaw point satisfying both of the formula (2) and the formula (3),
determining the dent flaw as an upper surface dent in response to the dent flaw satisfying formula (2) but not satisfying formula (3),
in response to the dent defect not satisfying formula (2) but satisfying formula (3), the dent defect is determined to be a lower surface dent.
7. The method for detecting a steel plate defect according to claim 2, wherein the determining the recess type of the recess defect according to a contrast method in response to the target sampling point being the recess defect specifically comprises:
and responding to the target sampling point as the recessed flaw point, and judging whether the recessed flaw point meets the following formula according to a scanning line pair comparison method:
wherein,means the average thickness of the upper surface, <' > is> Means for indicating the average thickness of the lower surface>The following formula is satisfied:
determining the dent flaw as an upper surface dent and a lower surface dent in response to the dent flaw satisfying both formula (4) and formula (5),
determining the dent flaw as an upper surface dent in response to the dent flaw satisfying formula (4) but not satisfying formula (5),
in response to the dent defect not satisfying formula (4) but satisfying formula (5), the dent defect is determined to be a lower surface dent.
8. The method of detecting plate blemishes of claim 2, further comprising, after said determining the type of dent of a dent blemish according to a contrast method:
and determining the position of the recessed flaw point.
9. The method for detecting plate blemishes according to claim 8, wherein the determining the positions of the dent blemishes specifically comprises:
determining the coordinate values of the X axis and the Y axis of the position of the dent flaw according to the following formula:
y=t·L (7)
x=(i+0.5)·W/N (8)
wherein, L is the steel plate stepping length collected by each camera, W is the scanning range covered by each camera, and N is the number of points sampled by each camera.
10. A steel plate flaw point detection device is characterized by comprising an acquisition module, a judgment module and a determination module,
an acquisition module for acquiring the steel plate thickness corresponding to the target sampling point of the measured steel plate,
the judging module is connected with the obtaining module and used for judging whether the target sampling point is a hollow defect according to the difference value between the thickness of the steel plate corresponding to the target sampling point and the target thickness,
and the determining module is connected with the judging module and used for responding to the fact that the target sampling point is the recessed defect point and determining the recessed type of the recessed defect point according to a contrast method.
11. A detection apparatus, characterized by comprising a memory in which a computer program is stored and a processor arranged to run the computer program to implement a method of detection of steel plate defects according to any of claims 1-9.
12. A computer-readable storage medium, having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, implements a method of detecting steel plate defects according to any one of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211563355.2A CN115876782A (en) | 2022-12-07 | 2022-12-07 | Method and device for detecting flaw point of steel plate and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211563355.2A CN115876782A (en) | 2022-12-07 | 2022-12-07 | Method and device for detecting flaw point of steel plate and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115876782A true CN115876782A (en) | 2023-03-31 |
Family
ID=85766323
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211563355.2A Pending CN115876782A (en) | 2022-12-07 | 2022-12-07 | Method and device for detecting flaw point of steel plate and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115876782A (en) |
-
2022
- 2022-12-07 CN CN202211563355.2A patent/CN115876782A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109696356B (en) | Geosynthetic material tensile sample global strain field measuring device and method | |
CN102393181B (en) | Automatic online detection method and device of angle steel geometric parameters | |
CN115791830A (en) | Steel plate detection system, steel plate detection method and electronic equipment | |
CN112540089B (en) | Application method of digital imaging system in concrete bridge crack detection and analysis | |
CN107817044B (en) | Device and method for measuring plate vibration based on machine vision | |
CN109544533A (en) | A kind of metal plate defect detection and measure based on deep learning | |
CN110276752B (en) | APP detection method for concrete surface crack characteristics based on android system | |
CN113554697A (en) | Cabin section profile accurate measurement method based on line laser | |
CN113222937A (en) | Detection method and detection device for appearance peripheral surface defects of nuclear fuel pellet | |
CN102183206B (en) | Line width measuring method for line on printed circuit board (PCB) | |
CN108844469B (en) | Method and system for testing workpiece step height based on laser | |
Zeinali et al. | Accurate structural dynamic response monitoring of multiple structures using one CCD camera and a novel targets configuration | |
CN115728240A (en) | Steel plate scratch detection method, detection device and storage medium | |
CN113446932A (en) | Non-contact crack measuring method and system | |
CN117109481A (en) | Method for detecting and evaluating overall flatness and overcurrent capacity of concrete with overcurrent surface | |
CN117537706A (en) | Sheet metal hole positioning size detection method based on three-axis coordinate conversion and monocular vision fusion | |
CN115876782A (en) | Method and device for detecting flaw point of steel plate and storage medium | |
CN201277864Y (en) | Internal orientation element and distortion tester | |
CN106969707B (en) | A kind of detection device and its control method | |
CN109444150A (en) | Contactless crackle measurement method and its device | |
CN112734712B (en) | Imaging detection method and system for health state of ship vibration equipment | |
CN112378313A (en) | Special calibration scale and method for multi-target digital image detection | |
CN114397090A (en) | Method for quickly measuring parallelism of optical axis of continuous zooming camera | |
CN115791802A (en) | Detection method and detection device for flaw surface of steel plate and storage medium | |
CN112504137B (en) | Multi-target digital image detection method based on cloud computing |
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 |