A steel plate flaw point detection method, a detection device, and a storage medium

Abstract

The application provides a kind of steel plate flaw point detection method, detection device and computer readable storage medium, belong to visual measurement technical field.The method comprises: obtaining the target sampling point corresponding steel plate thickness of the measured steel plate;According to the difference between the target sampling point corresponding steel plate thickness and target thickness, determine whether the target sampling point is a concave flaw point;In response to the target sampling point being a concave flaw point, determine the concave type of the concave flaw point according to the contrast method.At least solve the problems of large artificial labor intensity, easy to cause missed detection, unable to adapt to the production environment of high-speed unit, low detection precision and other problems in the related art, adapt to the scene of visual measurement and steel plate detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of visual measurement, and in particular to a steel plate flaw detection method, a steel plate flaw detection device and a computer readable storage medium. BACKGROUND

[0002] Steel plate surface detection is mainly used for detecting discontinuity defects (such as pits, scratches, flaws, etc.) on the surface of a steel plate, and detection methods include manual experience detection and non-destructive testing technology based on electromagnetic induction and ultrasonic waves.

[0003] At present, the detection of large steel plates mainly uses manual visual methods. Due to the requirement of production rhythm, manual visual methods cannot detect the bottom surface of a steel plate, and thus cannot fully cover the upper and lower surfaces of the measured steel plate. Moreover, manual visual detection methods cannot numerically measure the discontinuity on the surface of a steel plate, and thus need to increase the process and use special instruments to measure the numerical value before performing steel plate grading operation. Therefore, the current detection of large steel plates has the problems of high labor intensity, easy to cause missed detection, unable to adapt to the production environment of a high-speed unit, low detection precision, etc. SUMMARY

[0004] The present application relates to the technical field of visual measurement, and in particular to a steel plate flaw detection method, a steel plate flaw detection device and a computer readable storage medium.

[0005] In a first aspect, the present application provides a steel plate flaw detection method, comprising: obtaining the thickness of a target sampling point of a measured steel plate; determining whether the target sampling point is a concave flaw point according to the difference between the thickness of the target sampling point of the measured steel plate and a target thickness; and determining the concave type of the concave flaw point according to a comparison method in response to the target sampling point being a concave flaw point.

[0006] Preferably, the concave type includes one or both of the following: upper surface concave and lower surface concave. The thickness of the target sampling point of the measured steel plate is obtained, specifically including: obtaining the coordinate data of the target sampling point on the upper surface and the lower surface of the measured steel plate wherein 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 the value of 0, 1, 2,...A, and A represents the total number of sampling points on the upper surface or the lower surface at each sampling time; and the thickness of the target sampling point is calculated according to the following formula:

[0007]

[0008] wherein, Z-axis data in the coordinate data of the target sampling point on the upper surface of the measured steel plate, Z-axis data in the coordinate data of the target sampling point on the lower surface of the measured steel plate.

[0009] Preferably, the method further comprises: determining whether the target sampling point is a concave defect point according to a difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness, and specifically comprises: determining whether the thickness of the steel plate corresponding to the target sampling point is less than or equal to a difference between the target thickness and a first threshold value; and in response to the thickness of the steel plate corresponding to the target sampling point being less than or equal to the difference between the target thickness and the first threshold value, determining that the target sampling point is a concave defect point.

[0010] Preferably, the method further comprises: in response to the thickness of the steel plate corresponding to the target sampling point being greater than the difference between the target thickness and the first threshold value and less than a sum of the target thickness and the first threshold value, determining that the target sampling point is a non-defect point.

[0011] Preferably, the method further comprises: in response to the target sampling point being a concave defect point, determining a concave type of the concave defect point according to a comparison method, and specifically comprises: in response to the target sampling point being a concave defect point, determining whether the concave defect point satisfies the following formula according to a neighboring point comparison method:

[0012]

[0013]

[0014] wherein, Z-axis data in the coordinate data of the target sampling point on the upper surface of the measured steel plate, Z-axis data in the coordinate data of the target sampling point on the lower surface of the measured steel plate.

[0015] Preferably, the method further comprises: in response to the target sampling point being a concave defect point, determining a concave type of the concave defect point according to a comparison method, and specifically comprises: in response to the target sampling point being a concave defect point, determining whether the concave defect point satisfies the following formula according to a scanning line comparison method:

[0016]

[0017]

[0018] wherein, represents the average thickness of the upper surface, represents the average thickness of the lower surface, satisfies the following formula:

[0019]

[0020] in response to the concave defect point satisfying both formula (4) and formula (5), determining the concave defect point as an upper surface concave and a lower surface concave,

[0021] in response to the concave defect point satisfying formula (4) but not satisfying formula (5), determining the concave defect point as an upper surface concave,

[0022] in response to the concave defect point not satisfying formula (4) but satisfying formula (5), determining the concave defect point as a lower surface concave.

[0023] Preferably, the determining the position of the concave defect point specifically comprises: determining the coordinate values of the X axis and the Y axis of the position of the concave defect point according to the following formula:

[0024] y = t·L (7)

[0025] x = (i+0.5)·WN (8)

[0026] wherein, L is the step length of the steel plate collected by the camera each time, W is the scanning range covered by each camera, and N is the number of points sampled by each camera each time.

[0027] Preferably, before the acquiring the coordinate data of the target sampling points of 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 according to a collection signal cycle by using an array camera, and outputting first coordinates of the sampling points, wherein the first coordinates are in a coordinate system with the position of the array camera as the origin; converting the first coordinates of the sampling points output by each camera in the array camera to a world coordinate system according to the relative position relationship of each camera, to obtain the coordinate data of the target sampling points of the upper surface and the lower surface of the measured steel plate

[0028] In a second aspect, the present application further provides a steel plate defect point detection device, comprising an acquisition module, a determination module and a determining module.

[0029] The acquisition module is configured to acquire the thickness of the steel plate corresponding to the target sampling point of the measured steel plate. The determination module is connected to the acquisition module and is configured to determine whether the target sampling point is a concave defect point according to the difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness. The determination module is connected to the determination module and is configured to determine the concave type of the concave defect point according to the comparison method in response to the target sampling point being a concave defect point.

[0030] In a third aspect, the present application further provides a detection device, comprising a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to realize the detection method of the steel plate defect point according to the first aspect.

[0031] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the detection method of the steel plate defect point according to the first aspect.

[0032] The detection method of the steel plate defect point, the detection device and the computer readable storage medium provided by the present application can acquire the thickness data of the sampling point, compare the target thickness with the thickness data of the sampling point, and determine whether the sampling point is a concave defect point, and then determine the concave type of the concave defect point, that is, determine whether the sampling point is an upper surface concave defect point or a lower surface concave defect point. The data of the sampling point can be acquired by using a conventional visual equipment (such as a camera). The detection method based on machine vision for detecting the steel plate defect in industrial production has the characteristics of high automation degree, comprehensive detection, adaptability to high-speed machine production environment, and high detection precision compared with the manual visual method. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 It is a flowchart of a detection method of a steel plate defect point according to embodiment 1 of the present application;

[0034] Figure 2 It is a structural schematic diagram of a steel plate detection system according to embodiment 1 of the present application;

[0035] Figure 3 It is a schematic diagram of a world coordinate system according to embodiment 1 of the present application;

[0036] Figure 4 It is a schematic diagram of the upper surface concave of a steel plate according to embodiment 1 of the present application;

[0037] Figure 5 It is a scanning schematic diagram of a steel plate according to embodiment 1 of the present application;

[0038] Figure 6 It is a structural schematic diagram of a steel plate defect point detection device according to embodiment 2 of the present application;

[0039] Figure 7 Figure 3 is a structural schematic diagram of a detection device according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the skilled in the art better understand the technical solutions of the present application, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0041] It can be understood that the specific embodiments and drawings described herein are only used to explain the present application, but not to limit the present application.

[0042] It can be understood that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0043] It can be understood that, for the convenience of description, only the parts related to the present application are shown in the drawings of the present application, and the parts unrelated to the present application are not shown in the drawings.

[0044] It can be understood that each unit and module involved in the embodiments of the present application can only correspond to one entity structure, or can be composed of multiple entity structures, or multiple units and modules can be integrated into one entity structure.

[0045] It can be understood that the functions and steps marked in the flowcharts and block diagrams of the present application can occur in an order different from that marked in the drawings without conflict.

[0046] It can be understood that in the flowcharts and block diagrams of the present application, the system, device, equipment, method according to the embodiments of the present application are shown as the possible implementation architecture, function and operation. Each block in the flowchart or block diagram can represent a unit, module, program segment, code, which contains executable instructions for realizing the specified function. Moreover, each block or combination of blocks in the block diagram and flowchart can be realized by a hardware-based system for realizing the specified function, or by a combination of hardware and computer instructions.

[0047] It can be understood that the units and modules involved in the embodiments of the present application can be realized by software or hardware, for example, the units and modules can be located in a processor.

[0048] Embodiment 1:

[0049] As shown in the figure, the present embodiment provides a steel plate flaw detection method applied to the flaw detection of large steel plates or small steel plates, and the steel plate flaw detection method comprises the following steps. Figure 1 Step 101: Obtain the thickness of the steel plate corresponding to the target sampling point of the measured steel plate.

[0050] Step 101: Obtain the thickness of the steel plate corresponding to the target sampling point of the measured steel plate.

[0051] In this embodiment, a conventional visual device such as a camera can be used to acquire data of the target sampling points of the measured steel plate.

[0052] Specifically, the acquiring of the thickness of the steel plate corresponding to the target sampling points of the measured steel plate comprises steps 1011-1012:

[0053] In step 1011, coordinate data of target sampling points on the upper surface and the lower surface of the measured steel plate are acquired Wherein, 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 values of 0, 1, 2,...A, and A represents the total number of sampling points on the upper surface or the lower surface at each sampling time.

[0054] In step 1012, the thickness of the steel plate corresponding to the target sampling points is calculated according to the following formula:

[0055]

[0056] Wherein, is the Z-axis data in the coordinate data of the target sampling points on the upper surface of the measured steel plate, is the Z-axis data in the coordinate data of the target sampling points on the lower surface of the measured steel plate.

[0057] Optionally, before the acquiring of the coordinate data of the target sampling points on the upper surface and the lower surface of the measured steel plate, the steel plate defect detection method further comprises: acquiring image data of the upper surface and the lower surface of the measured steel plate according to a collection signal cycle by using an array camera, and outputting first coordinates of the sampling points, wherein the first coordinates are in a coordinate system with the position of the array camera as the origin; converting the first coordinates of the sampling points output by each camera in the array camera to a world coordinate system according to the relative position relationship of each camera, to obtain the coordinate data of the target sampling points on the upper surface and the lower surface of the measured steel plate

[0058] In this embodiment, a conventional visual device such as a camera can be used to acquire data of the target sampling points of the measured steel plate. Figure 2The steel plate detection system shown obtains coordinate data of target sampling points on the upper and lower surfaces of the measured steel plate. The steel plate detection system comprises an image acquisition device 11, a camera calibration software 12 and a data analysis software 13. The image acquisition device 11 is used to acquire image data of the upper and lower surfaces of the measured steel plate. The camera calibration software 12 is connected with the image acquisition device 11 and is used to perform data preprocessing on the acquired image data. The data analysis software 13 is connected with the camera calibration software 12 and is used to calculate the thickness standard deviation of the measured steel plate according to the preprocessed image data and evaluate 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 is used to acquire image data of the upper and lower surfaces of the measured steel plate according to the acquisition signal sent by the acquisition signal controller and output first coordinates of the sampling points, wherein the first coordinates are in a coordinate system with the position of the array camera as the origin. The acquisition signal controller is provided with an acquisition signal period, and the acquisition signal controller is used to send the acquisition signal to the array camera according to the acquisition signal period, wherein the acquisition signal period is the ratio of the steel plate step length L (unit: meter) to the steel plate transmission rate S (unit: meter / second), that is, the time interval of the acquisition signal controller sending the acquisition signal is τ = LS (unit: second), that is, the array camera shoots and acquires data once every interval τ. Specifically, the array camera comprises two groups of linear scanning cameras. The two groups of linear scanning cameras are used to be respectively fixed on the upper and lower parts of the detection gate and respectively maintain a preset shooting distance with the corresponding surfaces of the measured steel plate, wherein a plurality of linear scanning cameras in a group jointly cover the width of the measured steel plate through device cascading. One group of three-dimensional (3D) linear scanning cameras is installed on the upper and lower parts of the detection gate (i.e. above and below the measured steel plate) to acquire image data, and the cameras above (or below) jointly cover the entire width of the measured steel plate through device cascading. Each camera covers a certain length of straight line range, and 6 cameras jointly cover the width of the measured steel plate through device cascading. The number of cameras is determined by the width of the measured steel plate (or other measured objects) and the scanning range of the camera (for example, when the image data acquisition of each 3D camera covers a width of 0.45 meters, and the width of the measured steel plate is 4.2 meters, a total of 18-20 3D cameras are needed to cover the width of the upper and lower surfaces of the measured steel plate through device cascading). When the resolution of the cascaded cameras is different, according to the different resolutions of the cameras, each camera obtains a group of coordinates of pixel points of the measured steel plate in the coverage range, and outputs the first coordinates of the measured steel plate as a coordinate system with the position of each camera as the origin, and the first coordinates are marked as: Wherein p = u or p = d, u represents the camera above the upper surface of the measured steel plate, d represents the camera below the lower surface of the measured steel plate, t = 0, 1, 2,... T represents the sampling time, j = 0, 1, 2,... M represents the camera index ID, k = 0, 1, 2,... N represents the index ID of N sampling points collected by each camera each time, and all the cameras are controlled uniformly by a collection signal controller. When the collection signal controller sends a collection signal, all the cameras start shooting and collecting image data of the measured steel plate at the same time. Optionally, the image collection device further comprises a speed controller and a rolling bed. The speed controller is connected with the rolling bed, and the speed controller is provided with a steel plate transmission speed for controlling the rotating speed of the rolling bed according to the steel plate transmission speed. The rolling bed is used for placing the measured steel plate and rotating to convey the measured steel plate according to the rotating speed. In the embodiment, the speed controller and the collection signal controller are controlled cooperatively by a speed matching software. The camera calibration software comprises a coordinate conversion module. The coordinate conversion module is used for converting the first coordinates of the sampling points output by each camera to a world coordinate system according to the relative position relationship of each camera in the array camera, to obtain the converted collection data. Preferably, as shown in Figure 3 the origin O of the world coordinate system is a corner of the measured steel plate (as shown in Figure 2 the corner of the detected object shown in the figure is the unified coordinate origin O), the X axis thereof is parallel to the camera array composed of each camera, the Y axis thereof is parallel to the conveying direction of the measured steel plate, and the Z axis thereof is perpendicular to the XOY plane. The converted collection data is: Wherein i = j·N + k, j is the camera index, i takes the value of 0, 1, 2,... A, A = M·N + N M represents the total number of sampling points of any surface of the measured steel plate at each sampling time, N M ≤M represents the number of sampling points of the last camera 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 embodiment. By converting the data collected by each camera into collection data in the same coordinate system, the calculation of the thickness of the measured steel plate is facilitated, and the accuracy of the calculation result is ensured.

[0059] Step 102, determining whether the target sampling point is a concave defect point according to the difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness.

[0060] In the embodiment, when the thickness of the steel plate corresponding to the target sampling point is less than the target thickness, whether the target sampling point is a concave defect point can be determined. However, due to the mechanical vibration of the measured steel plate during the detection process, in order to improve the detection accuracy, a first threshold value is set as a tolerance thickness within the target thickness range.

[0061] Specifically, the determining whether the target sampling point is a concave defect point according to the difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness comprises: determining whether the thickness of the steel plate corresponding to the target sampling point is less than or equal to the difference between the target thickness and the first threshold value; and in response to the thickness of the steel plate corresponding to the target sampling point being less than or equal to the difference between the target thickness and the first threshold value, determining that the target sampling point is a concave defect point.

[0062] In this embodiment, the first threshold value is set as Th, and in combination with the thickness requirement of the steel plate production, when the following condition is met, the target sampling point is determined to be a concave defect point:

[0063]

[0064] For example, H is 1 cm, Th is 0.2 cm, and when the thickness of the target sampling point is less than or equal to 0.8 cm, it is determined to be a concave defect point.

[0065] Alternatively, the determining whether the target sampling point is a concave defect point according to the difference between the thickness of the steel plate corresponding to the target sampling point and the target thickness, the method for detecting the defect point of the steel plate further comprises: in response to the thickness of the steel plate corresponding to the target sampling point being greater than the difference between the target thickness and the first threshold value, and the thickness of the steel plate corresponding to the target sampling point being less than the sum of the target thickness and the first threshold value, determining that the target sampling point is a non-defect point.

[0066] Step 103, in response to the target sampling point being a concave defect point, determining the concave type of the concave defect point according to a comparison method.

[0067] In this embodiment, the concave type includes one or two of the following: upper surface concave, lower surface concave, as shown in Figure 4 The upper surface concave. The comparison method of this embodiment includes one or a combination of two of the adjacent point comparison method and the scanning line comparison method.

[0068] Alternatively, the determining the concave type of the concave defect point according to the comparison method in response to the target sampling point being a concave defect point specifically comprises:

[0069] In response to the target sampling point being a concave defect point, determining whether the concave defect point satisfies the following formula according to the adjacent point comparison method:

[0070]

[0071]

[0072] wherein, Z-axis data in the coordinate data of the concave defect point on the upper surface of the measured steel plate, Z-axis data in coordinate data of a concave defect point of a lower surface of the measured steel plate, v-1, v, v+1 are adjacent concave defect points, and Th is a first threshold value,

[0073] in response to the concave defect point satisfying formula (2) but not satisfying formula (3), determining that the concave defect point is an upper surface concave,

[0074] in response to the concave defect point satisfying formula (2) but not satisfying formula (3), determining that the concave defect point is an upper surface concave,

[0075] in response to the concave defect point not satisfying formula (2) but satisfying formula (3), determining that the concave defect point is a lower surface concave.

[0076] Optionally, in response to the target sampling point being a concave defect point, the concave type of the concave defect point is determined according to a comparison method, and the method specifically comprises:

[0077] in response to the target sampling point being a concave defect point, determining whether the concave defect point satisfies the following formula according to a scanning line comparison method:

[0078]

[0079]

[0080] wherein, the average thickness of the upper surface is represented by, the average thickness of the lower surface is represented by, satisfies the following formula:

[0081]

[0082] in response to the concave defect point satisfying formula (4) but not satisfying formula (5), determining that the concave defect point is an upper surface concave,

[0083] in response to the concave defect point satisfying formula (4) but not satisfying formula (5), determining that the concave defect point is an upper surface concave,

[0084] in response to the concave defect point not satisfying formula (4) but satisfying formula (5), determining that the concave defect point is a lower surface concave.

[0085] In this embodiment, t is the sampling time, or understood as the scanning time. The principles of formula (4) and formula (5) are: considering that there is jitter in the detection process of the steel plate, all sampling points of the steel plate thickness satisfying formula (6) are obtained, for example, sampling points of the steel plate thickness greater than 0.9 cm are obtained, the average thickness value of the steel plate is calculated based on all sampling points at the scanning time (i.e. the same scanning line where the array camera is located) of the sampling points, when the upper surface longitudinal coordinate of the concave defect point determined in step 102 is lower than the preset threshold of the average thickness coordinate value, it is determined that the concave defect point is an upper surface concave; when the lower surface longitudinal coordinate of the concave defect point determined in step 102 is higher than the preset threshold of the average thickness coordinate value, it is determined that the concave defect point is a lower surface concave. The adjacent comparison method and the scanning line comparison method are used alternatively, in order to further improve the detection accuracy, the defect type of the concave defect point can be determined and verified based on the adjacent point comparison method and the scanning line comparison method.

[0086] Optionally, after the concave defect point is determined according to the comparison method, the steel plate defect point detection method further comprises: determining the position of the concave defect point.

[0087] Specifically, the determination of the position of the concave defect point comprises:

[0088] The coordinate values of the X axis and the Y axis of the position of the concave defect point are determined according to the following formula:

[0089] y=t·L (7)

[0090] x=(i+0.5)·WN (8)

[0091] Wherein, L is the step length of the steel plate collected by the camera each time, W is the scanning range covered by each camera, and N is the number of points sampled by each camera each time.

[0092] In this embodiment, as shown in the steel plate scanning schematic diagram, Figure 5 Formula (7) is used to locate the Y coordinate of the concave defect point, the scanning step length in the Y axis direction is L each time, t=0, 1, 2, …T represents the sampling time index of the scanning, that is, the step t times, so the location is y=t·L, formula (8) is used to locate the X coordinate of the concave defect point, the width of the steel plate in the X axis direction is W, N sampling points are uniformly sampled in the X axis direction each time, and the X coordinate of the sampling point is the midpoint of each grid.

[0093] The steel plate flaw point detection method of the embodiment determines whether the sampling point is a concave flaw point by comparing the target thickness with the steel plate thickness data of the sampling point, and then determines the concave type of the concave flaw point, i.e., determines whether the sampling point is an upper surface concave flaw point or a lower surface concave flaw point. The data of the sampling point can be obtained by using a conventional visual device (such as a camera). Compared with the manual visual method, the detection method based on machine vision for detecting steel plate flaws in industrial production has the characteristics of high automation degree, comprehensive detection, adaptability to high-speed machine production environment, and high detection precision. When the type of the concave flaw point is determined based on the comparison method, the adjacent comparison method and the scanning line comparison method are used alternatively. To further improve the detection precision, the concave flaw type of the concave flaw point can be determined and verified based on the adjacent point comparison method and the scanning line comparison method. Further, the position of the concave flaw point is determined based on the step length and the camera coverage range, and the positioning method is simple and can realize accurate positioning.

[0094] Embodiment 2

[0095] As shown in Figure 6 The embodiment provides a steel plate flaw point detection device, which comprises an acquisition module 61, a determination module 62, and a determination module 63.

[0096] The acquisition module 61 is configured to acquire the steel plate thickness corresponding to the target sampling point of the measured steel plate.

[0097] The determination module 62 is connected with the acquisition module 61 and is configured to determine whether the target sampling point is a concave flaw point according to the difference between the steel plate thickness corresponding to the target sampling point and the target thickness.

[0098] The determination module 63 is connected with the determination module 62 and is configured to determine the concave type of the concave flaw point according to the comparison method in response to the target sampling point being a concave flaw point.

[0099] Optionally, the concave type includes one or both of the following: upper surface concave and lower surface concave.

[0100] The acquisition module comprises an acquisition unit and a calculation unit.

[0101] The acquisition unit is configured to acquire the coordinate data of the target sampling point on the upper surface and the lower surface of the measured steel plate. wherein 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 the value of 0, 1, 2, …A, and A represents the total number of sampling points on the upper surface or the lower surface at each sampling time.

[0102] The calculation unit is connected with the acquisition unit and is configured to calculate the steel plate thickness corresponding to the target sampling point according to the following formula:

[0103]

[0104] wherein, is the Z-axis data in the coordinate data of the target sampling point on the upper surface of the measured steel plate, is the Z-axis data in the coordinate data of the target sampling point on the lower surface of the measured steel plate.

[0105] Optionally, the steel plate flaw detection device further comprises a steel plate detection system.

[0106] The steel plate detection system is configured to acquire image data of the upper surface and the lower surface of the measured steel plate according to a signal acquisition cycle by using the array camera, and output first coordinates of the sampling points, wherein the first coordinates are in a coordinate system with the position of the array camera as the origin; and convert the first coordinates of the sampling points output by each camera in the array camera to a world coordinate system according to the relative positional relationship of each camera in the array camera, to obtain coordinate data of target sampling points on the upper surface and the lower surface of the measured steel plate.

[0107] In this embodiment, as shown in FIG. 1, the array camera 1 is used to acquire image data of the upper surface and the lower surface of the measured steel plate according to a signal acquisition cycle, and output first coordinates of the sampling points, wherein the first coordinates are in a coordinate system with the position of the array camera as the origin. Figure 2The steel plate detection system shown obtains coordinate data of target sampling points on the upper and lower surfaces of the measured steel plate. The steel plate detection system comprises an image acquisition device 11, a camera calibration software 12 and a data analysis software 13. The image acquisition device 11 is used to acquire image data of the upper and lower surfaces of the measured steel plate. The camera calibration software 12 is connected with the image acquisition device 11 and is used to perform data preprocessing on the acquired image data. The data analysis software 13 is connected with the camera calibration software 12 and is used to calculate the thickness standard deviation of the measured steel plate according to the preprocessed image data and evaluate 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 is used to acquire image data of the upper and lower surfaces of the measured steel plate according to the acquisition signal sent by the acquisition signal controller and output first coordinates of the sampling points, wherein the first coordinates are in a coordinate system with the position of the array camera as the origin. The acquisition signal controller is provided with an acquisition signal period, and the acquisition signal controller is used to send the acquisition signal to the array camera according to the acquisition signal period, wherein the acquisition signal period is the ratio of the steel plate step length L (unit: meter) to the steel plate transmission rate S (unit: meter / second), that is, the time interval of the acquisition signal controller sending the acquisition signal is τ = LS (unit: second), that is, the array camera shoots and acquires data once every interval τ. Specifically, the array camera comprises two groups of linear scanning cameras. The two groups of linear scanning cameras are used to be respectively fixed on the upper and lower parts of the detection gate and respectively maintain a preset shooting distance from the corresponding surfaces of the measured steel plate, wherein a plurality of linear scanning cameras in a group jointly cover the width of the measured steel plate through device cascading. One group of three-dimensional (3D) linear scanning cameras is installed on each of the upper and lower parts of the detection gate (i.e. above and below the measured steel plate) to acquire image data, and the cameras above (or below) jointly cover the entire width of the measured steel plate through device cascading. Each camera covers a certain length of straight line range, and six cameras jointly cover the width of the measured steel plate through device cascading. The number of cameras is determined by the width of the measured steel plate (or other measured objects) and the scanning range of the camera (for example, when the image data acquisition of each 3D camera covers a width of 0.45 meters and the width of the measured steel plate is 4.2 meters, a total of 18-20 3D cameras are needed to cover the width of the upper and lower surfaces of the measured steel plate through device cascading). When the resolution of the cascaded cameras is different, each camera obtains a group of coordinates of pixel points of the measured steel plate in the coverage range according to the different resolutions of the cameras, and outputs the first coordinates of the measured steel plate as a coordinate system with the position of each camera as the origin, and the first coordinates are marked as: wherein p = u or p = d, u represents a camera above the upper surface of the measured steel plate, d represents a camera below the lower surface of the measured steel plate, t = 0, 1, 2, … T represents a sampling time, j = 0, 1, 2, … M represents a camera index ID, and k = 0, 1, 2, … N represents an index ID of N sampling points collected by each camera each time. All the cameras are controlled by a collection signal controller. When the collection signal controller sends a collection signal, all the cameras start shooting and collecting image data of the measured steel plate at the same time. Optionally, the image collection device further comprises a speed controller and a rolling bed. The speed controller is connected with the rolling bed, and the speed controller is provided with a steel plate transmission speed for controlling the rotating speed of the rolling bed according to the steel plate transmission speed. The rolling bed is used for placing the measured steel plate and rotating to convey the measured steel plate according to the rotating speed. In the embodiment, the speed controller and the collection signal controller are controlled and cooperated by a speed matching software. The camera calibration software comprises a coordinate conversion module. 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 converted collection data. Preferably, as shown in Figure 3 the origin O of the world coordinate system is a corner of the measured steel plate (for example, as shown in Figure 2 the corner of the measured object is the unified coordinate origin O), the X axis thereof is parallel to the camera array composed of each camera, the Y axis thereof is parallel to the conveying direction of the measured steel plate, and the Z axis thereof is perpendicular to the XOY plane. The converted collection data is: wherein i = j·N+k, j is a camera index, i takes values of 0, 1, 2, … A, A = M·N+N M the total number of sampling points of any surface of the measured steel plate at each sampling time, N M ≤M represents the number of sampling points of the last camera 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 embodiment. By converting the data collected by each camera into collection data in the same coordinate system, the calculation of the thickness of the measured steel plate is facilitated, and the accuracy of the calculation result is ensured.

[0108] Optionally, the determination module comprises a judgment unit and a determination unit.

[0109] The judgment unit is used for judging whether the thickness of the target sampling point corresponding to the steel plate is less than or equal to the difference between the target thickness and the first threshold value.

[0110] The determination unit is connected with the judgment unit and is used for determining that the target sampling point is a concave defect point in response to the thickness of the target sampling point corresponding to the steel plate being less than or equal to the difference between the target thickness and the first threshold value.

[0111] Optionally, the determining unit is further configured to determine that the target sampling point is a flawless point in response to the thickness of the steel plate corresponding to the target sampling point being greater than a difference between the target thickness and the first threshold value and the thickness of the steel plate corresponding to the target sampling point being less than a sum of the target thickness and the first threshold value.

[0112] Optionally, the determining module comprises a first determining unit.

[0113] The first determining unit is configured to determine, in response to the target sampling point being a concave flaw point, whether the concave flaw point satisfies the following formula according to a neighboring point comparison method:

[0114]

[0115]

[0116] wherein, Z-axis data in coordinate data of the concave flaw point on the upper surface of the measured steel plate, Z-axis data in coordinate data of the concave flaw point on the lower surface of the measured steel plate, v-1, v, v+1 are neighboring concave flaw points, and Th is the first threshold value,

[0117] in response to the concave flaw point satisfying both the formula (2) and the formula (3), determining that the concave flaw point is an upper surface concave flaw and a lower surface concave flaw,

[0118] in response to the concave flaw point satisfying the formula (2) but not satisfying the formula (3), determining that the concave flaw point is an upper surface concave flaw,

[0119] in response to the concave flaw point not satisfying the formula (2) but satisfying the formula (3), determining that the concave flaw point is a lower surface concave flaw.

[0120] Optionally, the determining module further comprises a second determining unit.

[0121] The second determining unit is configured to determine, in response to the target sampling point being a concave flaw point, whether the concave flaw point satisfies the following formula according to a scanning line comparison method:

[0122]

[0123]

[0124] wherein, denotes an average thickness of the upper surface, denotes an average thickness of the lower surface, satisfies the following formula:

[0125]

[0126] Since the dents simultaneously satisfy formulas (4) and (5), the dents are determined to be dents on the upper surface and dents on the lower surface.

[0127] In response to the dent satisfying formula (4) but not formula (5), the dent is determined to be a dent on the upper surface.

[0128] In response to the fact that the dent does not satisfy formula (4) but satisfies formula (5), the dent is determined to be a dent on the lower surface.

[0129] Optionally, the device for detecting defects in steel plates may also include a positioning module.

[0130] The positioning module is used to determine the location of the dent or defect.

[0131] Optionally, the positioning module is specifically used to determine the X-axis and Y-axis coordinates of the location of the dented defect point according to the following formula:

[0132] y = t·L (7)

[0133] x=(i+0.5)·WN (8)

[0134] Where L is the step length of the steel plate captured by the camera each time, W is the scanning range covered by each camera, and N is the number of points sampled by each camera each time.

[0135] Example 3:

[0136] like Figure 7 As shown, this embodiment provides a detection device, including a memory 71 and a processor 72. The memory 71 stores a computer program, and the processor 72 is configured to run the computer program to implement the steel plate defect detection method as described in Embodiment 1.

[0137] Example 4:

[0138] This embodiment provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the steel plate defect detection method as described in Embodiment 1.

[0139] The steel plate flaw point detection device of embodiment 2, the detection device of embodiment 3 and the computer readable storage medium of embodiment 4 are used to acquire the steel plate thickness data of the sampling point, and compare the target thickness with the steel plate thickness data of the sampling point to determine whether the sampling point is a concave flaw point, and determine the concave type of the concave flaw point, i.e., determine whether the sampling point is an upper surface concave flaw point or a lower surface concave flaw point. The data of the sampling point is acquired by using a conventional visual device (such as a camera). The detection device for detecting the steel plate flaw in industrial production based on machine vision has the characteristics of high automation, comprehensive detection, adaptability to high-speed machine group production environment, and high detection precision compared with the manual visual method. When the contrast method is used to determine the type of the concave flaw point, the adjacent contrast method and the scanning line contrast method are used alternatively, and for further improving the detection precision, the adjacent point contrast method and the scanning line contrast method are used together to determine and verify the flaw type of the concave flaw point. Further, the positioning module is used to determine the position of the concave flaw point based on the step length and the camera coverage range, and the positioning device is simple and can realize accurate positioning.

[0140] It can be understood that the above embodiments are only exemplary embodiments adopted for illustrating the principles of the present application, and the present application is not limited thereto. Various modifications and improvements can be made by those skilled in the art without departing from the spirit and essence of the present application, and these modifications and improvements are also considered to be within the protection scope of the present application.

Claims

1. A method of detecting a flaw point of a steel sheet, characterized by, include: Obtain the thickness of the steel plate corresponding to the target sampling point of the steel plate being tested; The difference between the steel plate thickness corresponding to the target sampling point and the target thickness is used to determine whether the target sampling point is a dent or defect point. Since the target sampling point is a concave defect, the concave defect type is determined by comparison. The types of depressions include one or two of the following: upper surface depression, lower surface depression, The process of obtaining the steel plate thickness corresponding to the target sampling point of the steel plate being tested specifically includes: Obtaining coordinate data of target sampling points of upper and lower surfaces of the measured steel plate based on a visual device Wherein, 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 the value of 0, 1, 2,...A, and A represents the total number of sampling points of the upper surface or the lower surface at each sampling time. The thickness of the steel plate corresponding to the target sampling point is calculated using the following formula: wherein, Z-axis data in the coordinate data of the target sampling point on the upper surface of the measured steel plate, Z-axis data in the coordinate data of the target sampling point on the lower surface of the measured steel plate, The response that the target sampling point is a dented defect point, and the determination of the dented defect point type based on the comparison method, specifically includes: Since the target sampling point is a concave defect, the following formula is used to determine whether the concave defect satisfies the following formula based on the adjacent point comparison method: wherein, is Z-axis data in coordinate data of a concave defect point on the upper surface of the steel sheet to be measured, is Z-axis data in coordinate data of a concave defect point on the lower surface of the steel sheet to be measured, v-1, v, v+1 are adjacent concave defect points, and Th is a first threshold value, Since the dents simultaneously satisfy formulas (2) and (3), the dents are determined to be dents on the upper surface and dents on the lower surface. In response to the dent satisfying formula (2) but not formula (3), the dent is determined to be a dent on the upper surface. In response to the fact that the dent does not satisfy formula (2) but satisfies formula (3), the dent is determined to be a dent on the lower surface.

2. The method for detecting defects in steel plates according to claim 1, characterized in that, Before acquiring the coordinate data of the target sampling points on the upper and lower surfaces of the steel plate being tested, the method further includes: An array camera is used to acquire image data of the upper and lower surfaces of the steel plate under test according to the acquisition signal period, and outputs the first coordinates of the sampling points, wherein the first coordinates are in a coordinate system with the position of the array camera as the origin; According to the relative position relationship of each camera in the array camera, the first coordinates of the sampling points output by each camera are converted into the world coordinate system to obtain coordinate data of target sampling points of the upper surface and the lower surface of the measured steel plate 3. The method of claim 1, wherein the method is characterized by: The step of determining whether a target sampling point is a dent defect based on the difference between the steel plate thickness corresponding to the target sampling point and the target thickness specifically includes: Determine whether the thickness of the steel plate corresponding to the target sampling point is less than or equal to the difference between the target thickness and the first threshold. In response to the steel plate thickness corresponding to the target sampling point being less than or equal to the difference between the target thickness and the first threshold, the target sampling point is determined to be a concave defect point.

4. The method of claim 3, wherein the method is characterized by: The step of determining whether a target sampling point is a dent defect point based on the difference between the steel plate thickness corresponding to the target sampling point and the target thickness also includes: If the thickness of the steel plate corresponding to the target sampling point is greater than the difference 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 of the target thickness and the first threshold, the target sampling point is determined to be a defect-free point.

5. The method of claim 1, wherein the method is characterized by: The response that the target sampling point is a dented defect point, and the determination of the dented defect point type based on the comparison method, specifically includes: Since the target sampling point is a concave defect, the following formula is used to determine whether the concave defect satisfies the following formula based on the scan line comparison method: in, Indicates the average thickness of the upper surface. Indicates the average thickness of the lower surface. Satisfy the following formula: Since the dents simultaneously satisfy formulas (4) and (5), the dents are determined to be dents on the upper surface and dents on the lower surface. In response to the dent satisfying formula (4) but not formula (5), the dent is determined to be a dent on the upper surface. In response to the fact that the dent does not satisfy formula (4) but satisfies formula (5), the dent is determined to be a dent on the lower surface.

6. The method for detecting defects in steel plates according to claim 1, characterized in that, After determining the type of dent based on the comparison method, the method further includes: Determine the location of the dent or defect.

7. The method for detecting defects in steel plates according to claim 6, characterized in that, Determining the location of the dented defect specifically includes: The X and Y coordinates of the location of the dent or defect point can be determined using the following formula: y = t·L (7) x=(i+0.5)·W / N (8) Where L is the step length of the steel plate captured by the camera each time, W is the scanning range covered by each camera, and N is the number of points sampled by each camera each time.

8. A device for detecting defects in steel plates, characterized in that, It includes an acquisition module, a judgment module, and a determination module. The acquisition module is used to obtain the thickness of the steel plate corresponding to the target sampling point of the steel plate being tested. The determination module, connected to the acquisition module, is used to determine whether a target sampling point is a dent or defect based on the difference between the steel plate thickness corresponding to the target sampling point and the target thickness. The determination module, connected to the judgment module, is used to determine the type of depression of the depression point based on a comparison method when the target sampling point is a depression defect point. The types of dents include one or both of the following: upper surface dent, lower surface dent. The acquisition module includes an acquisition unit and a calculation unit. The acquisition unit is used to acquire the coordinate data of target sampling points on the upper and lower surfaces of the steel plate under test based on a vision device. Where p = u represents the upper surface of the steel plate being measured, p = d represents the lower surface of the steel plate being measured, t = 0, 1, 2, ... T represents the sampling time, i takes values ​​of 0, 1, 2, ... A, and A represents the total number of sampling points on the upper or lower surface at each sampling time. The calculation unit, connected to the acquisition unit, is used to calculate the steel plate thickness corresponding to the target sampling point according to the following formula: in, The Z-axis data is the coordinate data of the target sampling point on the upper surface of the steel plate being tested. The Z-axis data is from the coordinate data of the target sampling point on the lower surface of the steel plate being tested. The determining module includes a first determining unit. The first determining unit is used to determine whether the dented defect point satisfies the following formula based on the adjacent point comparison method in response to the target sampling point being a dented defect point: in, This refers to the Z-axis data in the coordinate data of the dents and defects on the upper surface of the steel plate being tested. This represents the Z-axis data of the coordinates of the dents on the lower surface of the steel plate being tested, where v-1, v, and v+1 are adjacent dents, and Th is the first threshold. Since the dents simultaneously satisfy formulas (2) and (3), the dents are determined to be dents on the upper surface and dents on the lower surface. In response to the dent satisfying formula (2) but not formula (3), the dent is determined to be a dent on the upper surface. In response to the fact that the dent does not satisfy formula (2) but satisfies formula (3), the dent is determined to be a dent on the lower surface.

9. A detection device, characterized in that, The device includes 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 defects in steel plates as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for detecting defects in steel plates as described in any one of claims 1-7.

Images