Carbon steel plate weld phased array detection method, device and equipment based on machine vision and medium

Abstract

The invention relates to a carbon steel plate weld phased array detection method, device and equipment based on machine vision and a medium. Comprising the following steps: measuring appearance data of a detection object and the position of a welding seam by utilizing a visual sensor, and drawing a detection surface image of the detection object in a computer so as to plan a detection path of phased array detection equipment; measuring the height of a probe and a detection object in the phased array detection equipment in real time by using a height sensor; the computer processes the height data in real time and feeds back a processing result to a control unit of the mechanical arm in real time, so that the phased array detection equipment and the surface of the detection object are in an attached state; and according to phased array detection data, performing defect analysis on the interior of the carbon steel plate, and performing defect rating according to corresponding standards to complete detection. According to the invention, the visual and height sensors are used to obtain the spatial data of the detection object, and the phased array detection path completed by the mechanical arm is planned, so that the detection efficiency can be effectively improved.

Description

Technical Field

[0001] The invention relates to a machine vision-based phased array detection method, device, equipment and medium for carbon steel plate welds. Background Art

[0002] Welding is one of the most commonly used ways to connect steel structure components. The quality of the weld is related to the service life and structural safety of the entire steel structure component. Therefore, testing the steel structure components after welding is completed is an important step before use.

[0003] There are mainly destructive testing and nondestructive testing technologies. In comparison, nondestructive testing has the advantages of not damaging the structure and physical and chemical properties of the test object itself, and can detect surface and internal defect information of the test object. Among them, phased array testing technology, as a new type of nondestructive testing technology based on pulse reflection method, has a variety of defect result display methods and scanning methods. It is suitable for defect detection of different materials and component shapes, and has the advantages of intuitiveness and wide applicability. However, phased array testing technology mostly relies on manual operation, which requires a lot of time and energy of inspectors. Summary of the invention

[0004] In order to overcome the above-mentioned defects, the object of the present invention is to provide a carbon steel plate weld phased array detection method, device, equipment and medium based on machine vision.

[0005] To achieve the above object, the present invention provides a phased array detection method for carbon steel plate welds based on machine vision, comprising a visual sensor, a height sensor, a mechanical arm, a phased array detection device and a microcomputer, and the method comprises the following steps:

[0006] Step S01: using a visual sensor to measure the shape data of the inspection object and the location of the weld, and drawing an inspection surface image of the inspection object in a computer to plan the inspection path of the phased array inspection device;

[0007] Step S02: using a height sensor to measure the height between the probe and the detection object in the phased array detection device in real time;

[0008] Step S03: The computer processes the height data in real time and feeds back the processing result to the control unit of the robot arm in real time, so that the phased array detection device and the surface of the detection object are in a state of being in contact with each other;

[0009] Step S04: Based on the phased array detection data, the defects inside the carbon steel plate are analyzed and the defects are graded according to the corresponding standards to complete the detection.

[0010] Furthermore, the specific steps of step S01 are as follows:

[0011] The visual sensor fixed on the workbench is used to measure the inspection surface data of the inspection object, including the length and width of the carbon steel plate and the location of the weld.

[0012] Generate a plane model of the carbon steel plate inspection surface in a computer using the inspection surface data;

[0013] The generated plane model is used to plan the motion of the robot arm to adjust the detection path of the phased array detection equipment.

[0014] Furthermore, the following steps are included: providing the generated detection path to the machine for model training.

[0015] Furthermore, the step S02 is specifically as follows: using a high-precision ultrasonic height sensor fixed on the gripper of the robotic arm to measure in real time the height between the phased array probe and the surface of the detection object - the carbon steel plate with a weld.

[0016] Furthermore, the specific details of step S03 are: the computer processes the height data in real time, and feeds back the processing results to the control unit of the robotic arm in real time, and fine-tunes the movement of the robotic arm on the detection path so that the probe of the phased array detection equipment is in a fit state with the surface of the detection object.

[0017] Furthermore, the specific description of the detection surface data of the detection object measured by the visual sensor is as follows: the visual sensor adopts a CMOS or CCD industrial camera, and a calibration plate is used to determine the corresponding relationship between the world coordinate system of the visual sensor and the actual physical coordinate system;

[0018] The ACE enhancement algorithm is used to process the image to ensure that the plane image of the carbon steel plate inspection surface generated in the computer is consistent with the actual image.

[0019] Furthermore, the specific expression of the distance between the phased array probe and the surface of the detection object is: H is the distance between the phased array probe and the surface of the detection object, and the calculation formula is as follows:

[0020] H=hzs

[0021] Where h is the distance from the end face of the height sensor to the surface of the detection object, z is the height of the phased array probe, and s is the height between the height sensor and the phased array probe. The values ​​of z and s are given values ​​and are related to the fixed parameters of the probe.

[0022] To achieve the above-mentioned purpose, the carbon steel plate weld phased array detection device based on machine vision of the present invention comprises:

[0023] Workbench;

[0024] The visual sensor is fixed on the workbench and is used to measure the appearance data of the inspection object and the location of the weld;

[0025] A robotic arm, fixed on a workbench, used to carry the probe of a phased array detection device;

[0026] A height sensor is fixed at the front end of the robotic arm and is used to measure the height between the probe and the test object in the phased array test equipment in real time;

[0027] The computer is used to draw the detection surface image of the detection object based on the data of the visual sensor; at the same time, it processes the height data in real time and feeds back the processing results to the control unit of the robotic arm in real time, so that the phased array detection equipment and the surface of the detection object are in a fit state.

[0028] To achieve the above-mentioned purpose, the terminal device of the present invention includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and is characterized in that when the processor loads and executes the computer program, the above-mentioned machine vision-based carbon steel plate weld phased array detection method is adopted.

[0029] To achieve the above-mentioned purpose, the computer-readable storage medium of the present invention stores a computer program, and is characterized in that when the computer program is loaded and executed by a processor, the above-mentioned machine vision-based carbon steel plate weld phased array detection method is adopted.

[0030] The present invention generates a plane model of the detection surface of the detection object in a microcomputer through machine vision, which is convenient for the inspector to directly plan the path of phased array detection in the computer, that is, the movement of the mechanical arm. The entire detection process does not require manual hand-held operation, which can improve the detection efficiency. In addition, the detection path is used for machine learning and detection model training. As the number of detection objects increases and the detection model is continuously improved, the subsequent detection path is also completed by the detection device, further improving the detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic diagram of the overall process of the present invention;

[0032] Figure 2 It is a phased array detection path planning diagram of the detection object of the present invention;

[0033] Figure 3 is a schematic diagram of a phased array detection robot arm of the present invention; DETAILED DESCRIPTION

[0034] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0035] In the description of the present invention, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0036] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0037] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0038] Example 1

[0039] The carbon steel plate weld phased array detection device based on machine vision of the present invention comprises:

[0040] Workbench;

[0041] The visual sensor is fixed on the workbench and is used to measure the appearance data of the inspection object and the location of the weld;

[0042] A robotic arm, fixed on a workbench, is used to carry the probe of a phased array detection device; Figure 3 As shown,

[0043] A height sensor is fixed at the front end of the robotic arm and is used to measure the height between the probe and the test object in the phased array test equipment in real time;

[0044] The computer is used to draw the detection surface image of the detection object based on the data of the visual sensor; at the same time, it processes the height data in real time and feeds back the processing results to the control unit of the robotic arm in real time, so that the phased array detection equipment and the surface of the detection object are in a fit state.

[0045] Example 2

[0046] This embodiment provides a phased array detection method for carbon steel plate welds based on machine vision, which specifically includes the following steps:

[0047] Step S01: The visual sensor measures the length and width of the inspection object - the carbon steel plate with weld and the location of the weld, and draws the inspection surface image of the inspection object in the computer so that the inspector can plan the phased array inspection path and provide machine learning and model training;

[0048] Step S02: The height sensor measures the height between the phased array probe and the inspection object - the carbon steel plate with a weld in real time;

[0049] Step S03: The computer processes the height data in real time, and feeds back the processing result to the control unit of the robot arm in real time, so that the phased array probe is in a fitting state with the surface of the detection object;

[0050] Step S04: The inspector analyzes the defects inside the carbon steel plate based on the phased array inspection data and defect images and performs defect rating according to the corresponding standards to complete the inspection.

[0051] Specifically, step S01 includes: firstly, the visual sensor fixed on the top of the workbench first measures the inspection surface data of the inspection object - the carbon steel plate with a weld, including the length and width of the carbon steel plate and the position of the weld, and then the microcomputer processes the data and generates a plane image of the inspection surface of the carbon steel plate in the computer, so that the inspector can plan the movement of the robot arm in the image, that is, the schematic diagram of the phased array inspection path is as follows: Figure 2 When the robot moves according to the set phased array detection path, in the parallel direction (longitudinal direction) of the scanning path, the robot moves forward and backward by controlling the joints of the robot; in the vertical direction (lateral direction) of the scanning path, the robot moves left and right by controlling the slide rail and the motor. Figure 3 As shown. At the same time, for the planned phased array detection path, the detection device is provided with machine learning to establish a model database. Moreover, as the number of detection objects continues to increase and the detection model database continues to improve, the subsequent detection path does not need to be manually planned, and the detection device completes this part of the planning by itself. Visual sensors include CMOS or CCD industrial cameras.

[0052] Specifically, step S02 includes: measuring the height data information between the phased array probe and the detection object - the detection surface of the carbon steel plate with weld in real time through a high-precision ultrasonic height sensor fixed on the gripper of the robotic arm, and transmitting the height data to a microcomputer for data processing.

[0053] Specifically, step S03 includes: the microcomputer processes the height data of the phased array probe and the detection surface of the detection object in real time, and feeds back the processing results to the control unit of the robot arm in real time. The robot arm control unit issues instructions to fine-tune the joint movements of the robot arm on the detection path, so that the phased array probe and the surface of the detection object are in a fit state, avoiding inaccurate phased array detection at a certain point due to the probe's spatial position not being in direct contact with the detection surface, thereby affecting the final detection result.

[0054] Specifically, the step S04 includes: the inspector performs defect analysis inside the carbon steel plate based on the defect data and image information presented by the phased array detection device on the microcomputer and performs defect rating according to corresponding standards to complete the detection.

[0055] In particular, the present invention also provides a microcomputer device, comprising a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps in any one of steps S01 to S04 of the machine vision-based phased array detection method for carbon steel plates with welds.

[0056] The above-mentioned supporting microcomputer device also provides a computer-readable storage medium on which a computer program is stored. The program can be stored in a medium including but not limited to a disk, an optical disk, etc. When the computer program is executed by the processor, the phased array detection method of carbon steel plate with weld based on machine vision of the above-mentioned embodiment is adopted.

[0057] The present invention is described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of ordinary technicians in the field without departing from the purpose of the present invention. Many other changes and modifications that do not depart from the concept and scope of the present invention should be regarded as the protection scope of the present invention.

[0058] In the description of this specification, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0059] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A phased array detection method for carbon steel plate welds based on machine vision, characterized in that: The method comprises the following steps: Step S01: using a visual sensor to measure the shape data of the inspection object and the location of the weld, and drawing an inspection surface image of the inspection object in a computer to plan the inspection path of the phased array inspection device; Step S02: using a height sensor to measure the height between the probe and the detection object in the phased array detection device in real time; Step S03: The computer processes the height data in real time and feeds back the processing result to the control unit of the robot arm in real time, so that the phased array detection device and the surface of the detection object are in a state of being in contact with each other; Step S04: Based on the phased array detection data, the defects inside the carbon steel plate are analyzed and the defects are graded according to the corresponding standards to complete the detection.

2. The carbon steel plate weld phased array detection method based on machine vision according to claim 1 is characterized in that: The specific steps of step S01 are as follows: The visual sensor fixed on the workbench is used to measure the inspection surface data of the inspection object, including the length and width of the carbon steel plate and the location of the weld. Generate a plane model of the carbon steel plate inspection surface in a computer using the inspection surface data; The generated plane model is used to plan the motion of the robot arm to adjust the detection path of the phased array detection equipment.

3. The method for detecting carbon steel plate weld seams based on machine vision according to claim 2, characterized in that: The following steps are also included: The generated detection path is used for machine learning and model training.

4. The carbon steel plate weld phased array detection method based on machine vision according to claim 1, characterized in that: The specific step S02 is: using a high-precision ultrasonic height sensor fixed on the gripper of the robotic arm to measure the height between the phased array probe and the surface of the detection object - the carbon steel plate with a weld in real time.

5. The carbon steel plate weld phased array detection method based on machine vision according to claim 1, characterized in that: The specific steps of step S03 are as follows: the computer processes the height data in real time, and feeds back the processing result to the control unit of the robot arm in real time, and fine-tunes the movement of the robot arm on the detection path so that the probe of the phased array detection device is in a fit state with the surface of the detection object.

6. The carbon steel plate weld phased array detection method based on machine vision according to claim 2, characterized in that: The specific description of the detection surface data of the detection object measured by the visual sensor is as follows: the visual sensor adopts a CMOS or CCD industrial camera, and a calibration plate is used to determine the corresponding relationship between the world coordinate system of the visual sensor and the actual physical coordinate system; The ACE enhancement algorithm is used to process the image to ensure that the plane image of the carbon steel plate inspection surface generated in the computer is consistent with the actual image.

7. The carbon steel plate weld phased array detection method based on machine vision according to claim 3 is characterized in that: The specific expression of the distance between the phased array probe and the surface of the test object is: H is the distance between the phased array probe and the surface of the test object, and the calculation formula is as follows: H=hzs Where h is the distance from the end face of the height sensor to the surface of the detection object, z is the height of the phased array probe, and s is the height between the height sensor and the phased array probe. The values ​​of z and s are given values ​​and are related to the fixed parameters of the probe.

8. A phased array detection device for carbon steel plate welds based on machine vision, characterized in that: include: Workbench; The visual sensor is fixed on the workbench and is used to measure the appearance data of the inspection object and the location of the weld; A robotic arm, fixed on a workbench, used to carry the probe of a phased array detection device; A height sensor is fixed at the front end of the robotic arm and is used to measure the height between the probe and the test object in the phased array test equipment in real time; The computer is used to draw the detection surface image of the detection object based on the data of the visual sensor; at the same time, it processes the height data in real time and feeds back the processing results to the control unit of the robotic arm in real time, so that the phased array detection equipment and the surface of the detection object are in a fit state.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor loads and executes the computer program, the machine vision-based phased array detection method for carbon steel plate welds according to claim 1 is adopted.

10. A computer-readable storage medium having a computer program stored therein, characterized in that: When the computer program is loaded and executed by the processor, the machine vision-based phased array detection method for carbon steel plate welds according to claim 1 is adopted.

Images