Workpiece detection and shape correction method, system and device, computer equipment and storage medium

Abstract

The invention relates to a workpiece detecting and correcting method, system and device, computer equipment and a storage medium. The method comprises the steps that laser measurement data of a workpiece to be shaped is obtained, a model to be shaped is established according to the laser measurement data, the model to be shaped is compared with a standard model, initial shape correction data are obtained, the initial shape correction data comprise the shape correction amount and an initial area to be shaped, and the initial area to be shaped is obtained. Performing qualified area screening and area grade division on the initial shape correction data in sequence, determining a target to-be-corrected area and a corresponding target to-be-corrected area grade, and determining a target shape correction path and shape correction parameters based on the target to-be-corrected area and the target to-be-corrected area grade, and correcting the shape of the workpiece to be corrected based on the target shape correction path and the shape correction parameters. The workpiece correcting precision and efficiency are improved, meanwhile, the labor cost can be reduced, workpiece damage is avoided, and the applicable object range is wide.

Description

Technical Field

[0001] The present application relates to the field of manufacturing technology, and in particular to a workpiece detection and correction method, system, device, computer equipment and storage medium. Background Art

[0002] With the development of manufacturing technology, due to the particularity of materials, special requirements for dimensional accuracy and flatness, it is often difficult to meet the standard requirements for workpiece production. Profiling technology has emerged as the times require. Through special equipment, the workpiece undergoes plastic deformation, which has gradually become an important part of the workpiece manufacturing process.

[0003] In traditional technology, the shaping process usually uses uncontrollable pressure to force the application, and the range of motion of special equipment is limited. At the same time, the degree of deformation of the workpiece cannot be accurately obtained before shaping, resulting in limited types of workpieces that can be shaped and inaccurate shaping results.

[0004] Therefore, there is an urgent need in the related art for a method that can be applied to various types of workpieces and improve the accuracy and efficiency of workpiece correction. Summary of the invention

[0005] Based on this, it is necessary to provide a workpiece detection and correction method, device, computer equipment and computer-readable storage medium that can improve the workpiece correction accuracy and efficiency in order to address the above technical problems.

[0006] In a first aspect, the present application provides a workpiece detection and correction method. The method comprises:

[0007] Acquire laser measurement data of the workpiece to be calibrated, and establish a model to be calibrated according to the laser measurement data;

[0008] Comparing the model to be calibrated with the standard model to obtain initial calibration data, wherein the initial calibration data includes a calibration amount and an initial area to be calibrated;

[0009] Screening the initial calibration data for qualified areas in turn and performing area grade classification to determine target calibration areas and corresponding target calibration area grades;

[0010] Determining a target shaping path and shaping parameters based on the target shaping area and the level of the target shaping area;

[0011] The workpiece to be shaped is shaped based on the target shaped path and the shaped parameters.

[0012] Optionally, in one embodiment of the present application, the step of acquiring laser measurement data of the workpiece to be calibrated includes:

[0013] If the width of the workpiece to be shaped is within the measuring range of the laser, directly acquiring the three-dimensional data of the workpiece to be shaped;

[0014] If the width of the workpiece to be shaped exceeds the measuring range of the laser, the partition measurement data is acquired in different regions, and the partition measurement data are spliced ​​to obtain the three-dimensional data of the workpiece to be shaped.

[0015] Optionally, in one embodiment of the present application, the comparing the model to be calibrated with the standard model to obtain initial calibration data includes:

[0016] The three-dimensional data of the standard model and the model to be calibrated are compared respectively to obtain the initial area to be calibrated and the corresponding calibration amount in each direction.

[0017] Optionally, in one embodiment of the present application, the screening of qualified areas of the initial calibration data in sequence and the grading of the areas, and determining the target areas to be calibrated and the corresponding grades of the target areas to be calibrated include:

[0018] Compare the correction amount with the qualified deformation amount, screen the initial area to be corrected, remove qualified points, and determine the target area to be corrected;

[0019] The target area to be shaped is divided based on the shape correction amount, and a level of the target area to be shaped is determined.

[0020] Optionally, in one embodiment of the present application, after determining the target shaping path and shaping parameters based on the target shaping area and the target shaping area level, the method further includes:

[0021] The intermediate points of the path are eliminated based on the target correction path.

[0022] Optionally, in one embodiment of the present application, the step of obtaining laser measurement data of the workpiece to be calibrated includes:

[0023] Determine the target laser measurement method based on the shape of the workpiece to be calibrated;

[0024] The workpiece to be shaped is measured based on the target laser measurement method.

[0025] In a second aspect, the present application also provides a workpiece detection and correction system, including a workpiece shape measurement module, a data processing module, and a robot correction module, wherein:

[0026] The workpiece shape measurement module is used to perform laser measurement on the workpiece to be shaped, obtain laser measurement data of the workpiece to be shaped, and establish a model to be shaped according to the laser measurement data; compare the model to be shaped with the standard model to obtain initial shape correction data, the initial shape correction data includes the shape correction amount and the initial shape correction area, and send the initial shape correction data to the data processing module;

[0027] The data processing module is used to sequentially screen the qualified areas of the initial calibration data and perform area level classification to determine the target calibration area and the corresponding target calibration area level; determine the target calibration path and calibration parameters based on the target calibration area and the target calibration area level; and send the target calibration path and calibration parameters to the robot calibration module;

[0028] The robot shaping module is used to align the workpiece to be shaped based on the target shaping path and shaping parameters.

[0029] In a third aspect, the present application also provides a workpiece detection and correction device. The device comprises:

[0030] A calibration model building module is used to obtain laser measurement data of the workpiece to be calibrated and to build a calibration model according to the laser measurement data;

[0031] An initial calibration data acquisition module is used to compare the model to be calibrated with the standard model to obtain initial calibration data, wherein the initial calibration data includes a calibration amount and an initial area to be calibrated;

[0032] A target calibration area determination module is used to sequentially screen the qualified areas of the initial calibration data and classify the areas, and determine the target calibration area and the corresponding target calibration area level;

[0033] A target correction data determination module, used for determining a target correction path and correction parameters based on the target correction area and the level of the target correction area;

[0034] A shape correction module is used to correct the workpiece to be corrected based on the target shape correction path and the shape correction parameters.

[0035] In a fourth aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the method described in each of the above embodiments.

[0036] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in each of the above embodiments are implemented.

[0037] The above-mentioned workpiece detection and correction method, system, device, computer equipment and storage medium first obtain laser measurement data of the workpiece to be corrected, establish a correction model based on the laser measurement data, then compare the correction model with the standard model to obtain initial correction data, the initial correction data includes correction amount and initial correction area, then screen the qualified area of ​​the initial correction data in turn and divide the area into grades, determine the target correction area and the corresponding target correction area grade, then determine the target correction path and correction parameters based on the target correction area and the target correction area grade, and finally correct the workpiece to be corrected based on the target correction path and correction parameters. That is to say, when detecting and correcting a flat workpiece or a cylindrical workpiece, the correction data can be preliminarily determined by measuring the three-dimensional data and comparing it with the standard data, and the correction data can be further subdivided by screening the qualified area and dividing the area grade, while reducing labor costs and avoiding damage to the workpiece, and the scope of application is wide. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A diagram showing an application environment of a workpiece detection and correction method in one embodiment;

[0039] Figure 2 A schematic diagram of a flow chart of a workpiece detection and correction method in one embodiment;

[0040] Figure 3 A schematic flow chart of a target laser measurement method determination step in one embodiment;

[0041] Figure 4 A schematic diagram of a workpiece detection and correction system in one embodiment;

[0042] Figure 5 A schematic diagram of the operation flow of a slide motor in one embodiment;

[0043] Figure 6 A schematic diagram of scanning and detecting a flat workpiece in one embodiment;

[0044] Figure 7 is a schematic diagram of a target correction path in one embodiment;

[0045] Figure 8 A schematic diagram of a flat workpiece shape correction in one embodiment;

[0046] Fig. 9 A schematic diagram of a cylindrical workpiece inspection and correction in one embodiment;

[0047] Fig.10 It is a structural block diagram of a workpiece detection and correction device in one embodiment;

[0048] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The workpiece detection and correction method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0051] In one embodiment, Figure 2 As shown, a workpiece detection and correction method is provided, which is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0052] S201: Acquire laser measurement data of the workpiece to be calibrated, and establish a model to be calibrated according to the laser measurement data.

[0053] In the embodiment of the present application, first, the laser measurement data of the workpiece to be shaped is obtained, and the model to be shaped is established according to the laser measurement data. The workpiece to be shaped may be a flat workpiece such as a metal plate or a cylindrical workpiece such as a wheel rim, and the laser measurement data is depth data, width data, length data or angle data obtained by laser scanning the workpiece to be shaped, and a flat three-dimensional model to be shaped or a cylindrical three-dimensional model to be shaped is established based on the combination of depth data, width data, length data or any one of the three-dimensional data of depth data, width data and angle data.

[0054] S203: Compare the model to be calibrated with the standard model to obtain initial calibration data, wherein the initial calibration data includes calibration quantities and an initial area to be calibrated.

[0055] In an embodiment of the present application, after the model to be calibrated is established, the model to be calibrated is compared with the standard model, that is, the established flat-shaped three-dimensional model to be calibrated is compared with the flat-shaped standard three-dimensional model, or the cylindrical three-dimensional model to be calibrated is compared with the cylindrical standard three-dimensional model. Based on the comparison result of the three-dimensional data, the area that needs to be calibrated and the deformation of the workpiece are determined, and the corresponding initial calibration data are obtained, including the calibration amount and the initial area to be calibrated. The calibration amount corresponds to the deformation of the workpiece, and the initial area to be calibrated is composed of multiple points to be calibrated.

[0056] S205: Screening the initial calibration data for qualified areas in turn and performing area grade classification to determine target calibration areas and corresponding target calibration area grades.

[0057] In an embodiment of the present application, after the initial calibration data is obtained, a specific judgment is made on the initial calibration data, including qualified area screening and area grade division, thereby determining the target calibration area and the corresponding target calibration area grade. When calibrating the calibration points with a large calibration amount, it will affect the calibration points with a small calibration amount. Therefore, some calibration points with a small calibration amount can be filtered out through qualified area screening, and the screening criteria can be set manually. The remaining calibration points are then graded, and the division basis can be the distance between the calibration points, the average number of calibration points, or the calibration amount classification of the calibration points to be calibrated, and finally the target calibration area and the corresponding target calibration area grade are obtained.

[0058] S207: Determine a target shaping path and shaping parameters based on the target shaping area and the level of the target shaping area.

[0059] In the embodiment of the present application, after determining the target area to be calibrated and the corresponding level of the target area to be calibrated, the target calibration path is determined based on the target area to be calibrated. Specifically, according to the three-dimensional coordinates of each point to be calibrated in the target area to be calibrated, each point can be connected to obtain a straight line segment, and then multiple straight line segments can be combined to obtain a processing path, that is, a target calibration path. At the same time, calibration parameters are determined based on the level of the target area to be calibrated, and different levels correspond to different calibration parameters, that is, corresponding to different calibration tools or calibration methods.

[0060] S209: calibrating the workpiece to be calibrated based on the target calibration path and calibration parameters.

[0061] In the embodiment of the present application, after determining the target correction path and correction parameters, the target correction path is converted into a robot motion path, and process parameters are selected according to the correction parameters to correct the workpiece to be corrected.

[0062] In the above workpiece detection and correction method, first, the laser measurement data of the workpiece to be corrected is obtained, and a correction model to be corrected is established according to the laser measurement data. Then, the correction model to be corrected is compared with the standard model to obtain initial correction data, and the initial correction data includes correction amount and initial correction area. Then, the qualified area of ​​the initial correction data is screened and the area level is divided in turn to determine the target correction area and the corresponding target correction area level. Then, the target correction path and correction parameters are determined based on the target correction area and the target correction area level. Finally, the workpiece to be corrected is corrected based on the target correction path and correction parameters. That is to say, when a flat workpiece or a cylindrical workpiece is detected and corrected, the correction data to be corrected can be preliminarily determined by measuring the three-dimensional data and comparing it with the standard data, and the correction data to be corrected can be further subdivided by the qualified area screening and area level division, which not only improves the accuracy and efficiency of the correction of the workpiece, but also reduces the labor cost and avoids damage to the workpiece, and has a wide range of applicable objects.

[0063] In one embodiment of the present application, obtaining laser measurement data of the workpiece to be calibrated includes:

[0064] S301: If the width of the workpiece to be shaped is within the measuring range of the laser, directly acquiring three-dimensional data of the workpiece to be shaped.

[0065] S303: If the width of the workpiece to be shaped exceeds the measuring range of the laser, obtaining partition measurement data by region, and splicing the partition measurement data to obtain three-dimensional data of the workpiece to be shaped.

[0066] In one embodiment of the present application, when the workpiece to be shaped is scanned by laser, if the width of the workpiece to be shaped is within the range of the laser, the three-dimensional data of the workpiece to be shaped is directly obtained. In a specific application, taking the workpiece to be shaped as a flat workpiece as an example, if the width L of the flat workpiece is within the range of the laser, the three-dimensional data of the workpiece to be shaped is directly obtained. laser Within, laser scanning can automatically obtain depth data z, width data y, laser scanning at a constant speed v above the flat workpiece, laser sampling frequency is f, scanning time is t, then the length of the flat workpiece The three-dimensional model of the flat workpiece can be established through the [x, y, z] three-dimensional data. If the width of the workpiece to be calibrated exceeds the range of the laser, the partition measurement data is obtained in different areas, and the partition measurement data is spliced ​​to obtain the three-dimensional data of the workpiece to be calibrated. In a specific application, taking the workpiece to be calibrated as a flat workpiece as an example, if the width L of the flat workpiece exceeds the range of the laser L laser , then the total number of scans is n = L / L laserAccordingly, the flat workpiece is divided into n areas according to the laser range, and the laser scans each area accordingly. Similarly, the scanning is performed at a uniform speed v, the laser sampling frequency is f, and the scanning time is t. Then the length of the flat workpiece is After the scanning is completed, the depth data z, width data y, and length data x are summarized and spliced ​​to obtain the complete three-dimensional data [x, y, z] of the flat workpiece.

[0067] In this embodiment, by using different methods to perform laser scanning on the workpiece to be shaped according to different situations, it is possible to ensure that the measured three-dimensional data of the workpiece to be shaped is complete and accurate.

[0068] In one embodiment of the present application, comparing the model to be calibrated with the standard model to obtain initial calibration data includes:

[0069] The three-dimensional data of the standard model and the model to be calibrated are compared respectively to obtain the initial area to be calibrated and the corresponding calibration amount in each direction.

[0070] In one embodiment of the present application, the depth, width, length or angle of the workpiece may be deformed. Therefore, when comparing the model to be calibrated with the standard model, the three-dimensional data of the standard model and the model to be calibrated are compared respectively, that is, the deformation conditions are judged from different dimensions such as depth, width, length or angle, and the areas that need to be calibrated in each direction and the deformation amount are determined to obtain the corresponding initial calibration data, including the calibration amount and the initial area to be calibrated. The calibration amount corresponds to the deformation amount, and the initial area to be calibrated is composed of multiple points to be calibrated.

[0071] In this embodiment, by comprehensively considering the deformation conditions in various dimensions and performing overall comparison of the models, the integrity and accuracy of the scanning detection results can be ensured.

[0072] In one embodiment of the present application, the screening of qualified areas of the initial calibration data in sequence and the grading of the areas, and the determination of the target areas to be calibrated and the corresponding grades of the target areas to be calibrated include:

[0073] S401: Compare the correction amount with the qualified deformation amount, screen the initial area to be corrected, remove qualified points, and determine the target area to be corrected.

[0074] S403: Divide the target area to be calibrated based on the calibration amount to determine the level of the target area to be calibrated.

[0075] In one embodiment of the present application, first, the initial area to be calibrated is screened, and the qualified deformation amount is set. The calibration amount and the qualified deformation amount of each point to be calibrated are compared in turn. When the calibration amount ≤ the qualified deformation amount, it means that the point is qualified and does not need calibration; when the calibration amount > the qualified deformation amount, it means that the point is unqualified and needs calibration. The initial area to be calibrated is divided into a qualified area and an unqualified area by point-by-point judgment. The qualified area is composed of multiple qualified points, and the unqualified area is composed of multiple unqualified points. After that, the qualified points are eliminated, and only the unqualified points are retained, and the corresponding unqualified area is determined as the target area to be calibrated. After that, the target area to be calibrated is divided according to the calibration amount, that is, according to different deformation degrees, the unqualified points are divided into multi-level deformation intervals, and the calibration of each deformation interval corresponds to different shot peening process parameters, that is, different target areas to be calibrated correspond to different levels.

[0076] In this embodiment, by comparing the correction amount with the qualified deformation amount, the initial area to be corrected is screened, the qualified points are eliminated, the target area to be corrected is determined, and the target area to be corrected is divided based on the correction amount to determine the level of the target area to be corrected. This can obtain more accurate data to be corrected, thereby achieving a better correction effect on the workpiece.

[0077] In one embodiment of the present application, after determining the target shaping path and shaping parameters based on the target shaping area and the target shaping area level, the method further includes:

[0078] The intermediate points of the path are eliminated based on the target correction path.

[0079] In one embodiment of the present application, the target calibration path determined based on the target area to be calibrated contains hundreds or thousands of points, but the shape of the workpiece in each path segment changes very little, so the middle points of each calibration path are eliminated and only the start and end points of each path segment are retained, that is, the key points of each target calibration path.

[0080] In this embodiment, by removing the intermediate points of the path based on the target shape correction path, the data volume of the target shape correction path can be greatly reduced, thereby reducing the number of repeated responses of the shape correction execution machine.

[0081] In one embodiment of the present application, the step of obtaining laser measurement data of the workpiece to be calibrated includes:

[0082] S501: Determine a target laser measurement method based on the shape of the workpiece to be calibrated.

[0083] S503: Measuring the workpiece to be calibrated based on the target laser measurement method.

[0084] In one embodiment of the present application, Figure 3As shown, the workpiece to be shaped can be a flat workpiece such as a metal plate or a cylindrical workpiece such as a wheel rim. The corresponding target laser measurement method is determined based on the shape of the workpiece to be shaped, and the workpiece to be shaped is measured based on the target laser measurement method. In specific applications, if the workpiece to be shaped is a flat workpiece, the target laser measurement method is that the tool is automatically replaced with a 2D line laser by the robot end flange through a quick-change tooling, and the flat workpiece is placed flat on the tool table. The 2D line laser is driven by the robot motion trajectory programming to achieve scanning of flat workpieces of various sizes. If the workpiece to be shaped is a cylindrical workpiece, the target laser measurement method is to carry a 2D line laser on the laser lifting slide, which can move up and down, and at the same time, the turntable clamps the cylindrical workpiece and rotates it, which can achieve 360-degree full-range scanning of the cylindrical workpiece, breaking through the scanning length limitation of the 2D line laser itself, and can achieve scanning of various long cylindrical workpieces.

[0085] In this embodiment, by determining a target laser measurement method based on the shape of the workpiece to be shaped, and measuring the workpiece to be shaped based on the target laser measurement method, it is possible to measure a variety of different workpieces to be shaped.

[0086] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0087] In one embodiment, Figure 4 As shown, a workpiece detection and correction system is provided, including a workpiece shape measurement module, a data processing module, and a robot correction module, wherein:

[0088] S601: The workpiece shape measurement module is used to perform laser measurement on the workpiece to be calibrated, obtain laser measurement data of the workpiece to be calibrated, and establish a model to be calibrated according to the laser measurement data; compare the model to be calibrated with the standard model to obtain initial calibration data, the initial calibration data includes the calibration amount and the initial area to be calibrated, and send the initial calibration data to the data processing module.

[0089] In the embodiment of the present application, the workpiece shape measurement module is mainly used to perform laser measurement on the workpiece to be calibrated, and to establish a model to be calibrated based on the obtained laser measurement data, and to compare the model to be calibrated with the standard model to obtain initial calibration data and send it to the data processing module. Specifically, the workpiece shape measurement module is divided into a plate measurement program and a cylinder measurement program, both of which include a motor drive control subroutine, a 2D line laser measurement subroutine, and a point cloud data preprocessing subroutine, wherein the motor drive control subroutine is used to control the laser lifting slide motor to adjust the 2D line laser measurement position and control the turntable motor to drive the turntable to rotate. The cRIO-9045 real-time controller is used as the motor drive controller to communicate with the industrial computer and the NI-9512 motion control module to generate drive pulses to achieve motor drive control. Figure 5 As shown in the figure, taking the laser lift slide motor as an example, when the laser lift slide motor starts working, the power function is called to make the Drive Enable+ terminal of the NI-9512 module in the cRIO output a signal to enable the motor driver and the electromagnetic brake, and complete the motor initialization. Then the motor drive axis attribute node Straight Line Move is called to control the Direction (CCW) terminal to output a signal to the motor driver to determine the direction of the motor's movement, and Step (CW) outputs a drive pulse to the motor driver. The output frequency and number of pulses of the drive pulse affect the motor's movement speed and displacement. The motor drive axis attribute node Read Status is called to calculate and read the motor's movement speed and position. Finally, the Stop Move function block is used to disable the motor. The laser lift slide motor drives the slide to move through a ball screw to adjust the 2D line laser measurement position. The turntable motor drives the turntable to rotate through a reducer to achieve the rotation scanning of the cylindrical workpiece. The industrial computer communicates with the cRIO-9045, and realizes the drive control of the laser lift slide and the acquisition of the movement status through the network shared variables slide position, slide, stop slide and slide complete. The control principle of the turntable motor is similar to that of the laser lifting slide motor, so it will not be repeated here.

[0090] The running objects of the 2D line laser measurement subroutine mainly include 2D line laser and laser installation equipment. The 2D line laser can simultaneously scan the surface depth z and width y of the workpiece. Optionally, the laser installation equipment corresponding to the flat workpiece includes a robot and a quick-change fixture, and the laser installation equipment corresponding to the cylindrical workpiece includes a laser lifting slide. The 2D line laser measurement subroutine is used to perform laser measurement on the workpiece to be calibrated and send the measurement data to the point cloud data preprocessing subroutine. The point cloud data preprocessing subroutine is used to establish the model to be calibrated according to the measurement data and compare it with the standard model to obtain the initial calibration data and send it to the data processing module.

[0091] S603: The data processing module is used to screen the qualified areas of the initial calibration data in turn and perform area level classification to determine the target area to be calibrated and the corresponding target area level to be calibrated; determine the target calibration path and calibration parameters based on the target area to be calibrated and the target area level to be calibrated; and send the target calibration path and calibration parameters to the robot calibration module.

[0092] In the embodiment of the present application, the data processing module is mainly used to sequentially screen the qualified areas of the initial calibration data and perform regional level division, determine the target calibration area and the corresponding target calibration area level; based on the target calibration area and the target calibration area level, obtain the target calibration path and calibration parameters and send them to the robot calibration module. Specifically, the data processing module includes a data rearrangement and bundling subroutine, a qualified area judgment subroutine, a processing area division subroutine, a processing path generation subroutine, and an invalid data elimination subroutine, wherein the initial calibration data sent by the point cloud data preprocessing subroutine is input into the data processing module in the form of a table file, and each subtable in the table file corresponds to the four types of data of the X coordinate, Y coordinate, Z coordinate and deformation of each point on the measured workpiece surface, and the data rearrangement and bundling program needs to bundle the relevant data of tens of millions of points in the table, and index the X, Y, Z coordinates and deformation of the same point in the corresponding position of each subtable and bundle them into "groups", and each "group" represents the X, Y, Z coordinates and deformation information of each point. Afterwards, the data needs to be rearranged in dot matrix format and converted into a single column so that the subsequent program can read the relevant information of each point in sequence.

[0093] The qualified area judgment subroutine is used to compare the correction amount with the qualified deformation amount, screen the initial area to be corrected, and determine the target area to be corrected. The processing area division subroutine is used to divide the target area to be corrected based on the correction amount and determine the level of the target area to be corrected. The processing path generation subroutine is used to determine the target correction path based on the target area to be corrected. Taking a flat workpiece as an example, since the X, Y, and Z coordinate information of each point on the workpiece surface is known, Z is used to compare with the standard part to calculate the deformation amount, and the X and Y coordinate information is used for positioning. Therefore, it can be based on but not limited to the Y coordinate as a reference to obtain (x i,y1) The straight line segments formed by connecting the points, and then changing the Y coordinate at a certain interval can obtain the processing path in the processing area. At the same time, the straight line segments connected under the same Y coordinate may run through multiple processing areas, so the program will also identify and divide the straight line segments to ensure that each processing path is in the same processing area. The invalid data elimination subroutine mainly includes qualified point elimination and path midpoint elimination. The qualified point elimination is because the points in the area are qualified points and do not need to be processed, so the amount of data can be reduced after elimination; the path midpoint elimination is to eliminate the midpoint of each processing path, and only retain the start and end points of each path segment, that is, the key points of each processing path.

[0094] S605: The robot shaping module is used to align the workpiece to be shaped based on the target shaping path and shaping parameters.

[0095] In the embodiment of the present application, the robot calibration module is mainly used to calibrate the workpiece to be calibrated based on the target calibration path and calibration parameters. Specifically, the robot calibration module includes a robot motion subroutine, a tool automatic switching subroutine, and a workpiece calibration subroutine. The workpiece calibration subroutine is used to convert the target calibration path into a robot motion path, and at the same time, the built-in process package of the program selects the process parameters according to the calibration parameters and sends a switching instruction to realize automatic calibration of each area of ​​the workpiece to be calibrated.

[0096] The robot motion subroutine is used to control the robot's motion trajectory according to the robot motion path, and establish the communication between the industrial computer, Beckhoff module, KUKA robot and control cabinet through LabVIEW. The industrial robot adopts the KR C4 series control cabinet, which supports PLC as the upper computer control, so the LabVIEW platform is used to simulate the PLC control, so as to realize the motion control of the industrial robot; in the KUKA control cabinet system environment, the software package and UDP communication port provided by KUKA official to support PLC are called, and the toolbox under the LabVIEW platform is communicated to establish the connection between the industrial computer and the KUKA control cabinet, so as to realize the effective transmission of the robot motion instructions between the two; any complex motion of the industrial robot can be composed of point-to-point motion (PTP), linear motion (LINE) and curved motion (CIRCULAR). By inputting the coordinates of the key trajectory points, that is, the robot motion path, and using the trajectory planning algorithm of the KUKA control cabinet itself in CP mode (Continuous Path Mode, CP), the KUKA robot motion trajectory programming is realized, and the robot continuous trajectory processing is realized.

[0097] The tool automatic switching subroutine is used to switch the correction tool according to the switching instruction. Specifically, according to the different needs of each stage, the pneumatic quick-change device is used to automatically change the tool, such as 2D line laser, ultrasonic shot peening guns of different specifications, etc. When the specified tool is automatically switched, the coordinates of the robot's key trajectory points are read, and the end of the robot reaches the reference coordinates of the specified workstation, and the safety signals are verified: end face detection signal, locking detection signal, release detection signal and tool detection signal. When the signals are normal, the vacuum pump air source is turned on through the solenoid valve control, and the quick-change device releases the female head to remove the tool and reaches the tool station to be replaced at the same time, completing the tool switching and sending the robot's motion status to the industrial computer; when the safety signal is abnormal, it enters the emergency protection state, terminates the robot movement, and the operator performs troubleshooting.

[0098] In one embodiment, Figure 4 As shown, the workpiece detection and correction system also includes an industrial computer control module. The industrial computer control module is developed under the LabVIEW environment, adopts a queue message state machine architecture, and combines the Compact RIO module to realize the communication and collaborative control of industrial robots and peripheral devices. The queue message state machine defines various states through custom enumeration data types, which at least include four states: initialization, idle, exit, and blank. The remaining states can be freely defined by the user. The initialization state is the starting state of the state machine, which is responsible for the initialization of software and hardware, such as initializing shift registers, opening files, reading configuration information, opening hardware devices, etc. After the initialization state is executed, it automatically enters the idle state. The idle state is the default state, which is responsible for responding to various operations and data requests in the program. The exit state is used to end the queue message state machine and perform some cleanup work, such as closing files, closing hardware devices, etc. The queue message state machine specifies the state switching sequence based on the working state, and is accompanied by necessary data communication. The Compact RIO control module is a product of NI. The industrial computer can control the movement of equipment in the workpiece shape measurement module, data processing module and robot calibration module at the same time through the Compact RIO module (hereinafter referred to as cRIO), Ethernet module, Real-Time module, etc. in LabVIEW software, such as the motor rotation of the pan / tilt and turntable, the switch of the solenoid valve, etc.

[0099] The following is a specific example to illustrate the specific process steps of the workpiece detection and correction method of the present application. Figure 6As shown, taking a flat metal workpiece as an example, first, S701, determine the target laser measurement method based on the shape of the workpiece to be calibrated. Then, S703, measure the workpiece to be calibrated based on the target laser measurement method. By using the quick-change fixture, install the 2D line laser 61 at the end of the robot. By programming the robot to control the scanning path, the workpiece morphology measurement of the plate is achieved. Then, S705, obtain the laser measurement data of the workpiece to be calibrated, establish the model to be calibrated according to the laser measurement data, and set the Cartesian coordinate system of the robot base to {R} and the workpiece coordinate system to {G}. At this time, the width L of the plate exceeds the range L of the laser. laser , the total number of scans is n = L / L laser , accordingly, the plate is divided into three areas according to the laser range. The manipulator 63 is connected to the line laser 61 through the quick-change fixture 62, starting from the starting point of the first area, ensuring that the center line of the line laser 61 is perpendicular to the surface of the plate 64, so that the line laser 61 scans at a uniform speed v along the X-axis direction, the laser sampling frequency is f, and the scanning time is t, then the length of the plate When scanning the subsequent area, it is necessary to ensure that the x and z coordinates of the scanning starting point are consistent. Assume that the i-th scanning data is through [x i ,y i , z i ], the scanned data are arranged in order, the point cloud data are spliced, and the final three-dimensional data of the panel is At the same time, the workpiece data is automatically saved, and a 3D model of the panel can be established based on the 3D data.

[0100] Afterwards, S707, compare the model to be calibrated with the standard model to obtain initial calibration data, wherein the initial calibration data includes the calibration amount and the initial area to be calibrated. After obtaining the complete scanned three-dimensional model, compare the entire three-dimensional data [x, y, z] obtained with the standard three-dimensional model data [x, y, Z] item by item, considering only the depth deformation of the plate, then the calibration amount of the plate is Δz=Zz, and the machining allowance of the entire plate is (x, y, Δz). The position of the machining area can be determined by (x, y).

[0101] Then, in S709-S715, the correction amount is compared with the qualified deformation amount, the initial correction area is screened, qualified points are eliminated, the target correction area is determined, the target correction area is divided based on the correction amount, the level of the target correction area is determined, the target correction path and correction parameters are determined based on the target correction area and the level of the target correction area, and the intermediate points of the path are eliminated based on the target correction path. Figure 7 As shown, the system is automatically divided into multi-level processing areas according to the correction amount, and the processing path is automatically generated, which is converted into usable data that can be directly imported into the robot correction module.

[0102] Finally, S717, the workpiece to be shaped is shaped based on the target shape-aligning path and the shape-aligning parameters. Figure 8 As shown, the coordinates of the origin of {G} in {R} are (X g ,Y g ,Z g ), the industrial computer 86 controls the manipulator 83 to move to the coordinate (X) according to the coordinate system {R} through the Compact RIO module 87. g ,Y g ,Z g ), the manipulator 83 moves to the corresponding processing area (x, y) according to the workpiece coordinate system {G}; the industrial computer 86 allows the robot to automatically switch tools and replace them with the ultrasonic shot peening gun 81, and then automatically selects the ultrasonic shot peening process parameters in the process package according to the shaping amount Δz of the workpiece, and then sends instructions through the Compact RIO module 87 to control the robot to shape the processing area by clamping the ultrasonic shot peening gun 81 through the quick-change tooling. The ultrasonic shot peening gun can use a high-speed striker flow to impact the surface of the workpiece to be shaped, so that the impacted surface and the underlying metal material undergo plastic deformation and extend, thereby gradually causing the surface of the workpiece to be shaped to undergo bidirectional bending deformation that bulges toward the sprayed surface, thereby achieving shaping processing of the metal sheet.

[0103] The following is another specific embodiment to illustrate the specific process steps of the workpiece detection and correction method of the present application. Fig. 9 As shown, taking a cylindrical workpiece wheel hub as an example, first, S801, determine the target laser measurement method based on the shape of the workpiece to be calibrated, then, S803, measure the workpiece to be calibrated based on the target laser measurement method, install the 2D line laser 92 on the lifting slide 91, fix the wheel hub 93 on the turntable 94, and realize the workpiece morphology measurement of the wheel hub through the movement of the lifting slide 91 and the turntable 94. Then, S805, obtain the laser measurement data of the workpiece to be calibrated, establish the model to be calibrated according to the laser measurement data, set the Cartesian coordinate system of the robot base to {R} and the workpiece coordinate system to {G}. At this time, the width L of the rim exceeds the range L of the laser. laser , then the total number of scans is n = L / L laser , accordingly, the wheel hub is divided into two areas according to the laser range, and the 2D line laser 92 scans each area of ​​the wheel hub 93 through the lifting slide 91. The wheel hub 93 is mounted on the wheel hub clamping table 94 and rotates at a constant angular velocity w. The angle of a full rotation is 360°. The laser sampling frequency is f, and the angle of the wheel hub is Assume that the i-th scan data is [θ i ,y i , z i], the scanned data are arranged in order, the point cloud data are spliced, and the final three-dimensional data of the wheel hub is At the same time, the workpiece data is automatically saved, and a complete 3D model of the wheel hub scan can be obtained based on the 3D data.

[0104] Afterwards, S807, compare the model to be calibrated with the standard model to obtain initial calibration data, wherein the initial calibration data includes the calibration amount and the initial area to be calibrated. After obtaining the complete scanned three-dimensional model, compare the entire three-dimensional data [θ, y, z] obtained with the standard three-dimensional model data [θ, y, z] item by item, considering only the deformation of the surface depth of the wheel hub, then the calibration amount of the wheel hub is Δz=Zz, and the machining allowance of the entire wheel hub is (θ, y, Δz). The position of the machining area can be determined by (θ, y).

[0105] Then, S809-S815, compare the correction amount with the qualified deformation amount, screen the initial correction area, remove qualified points, determine the target correction area, divide the target correction area based on the correction amount, determine the level of the target correction area, determine the target correction path and correction parameters based on the target correction area and the level of the target correction area, and remove the intermediate points of the path based on the target correction path. Figure 7 As shown, the system is automatically divided into multi-level processing areas according to the correction amount, and the processing path is automatically generated, which is converted into usable data that can be directly imported into the robot correction module.

[0106] Finally, S817, the workpiece to be calibrated is calibrated based on the target calibration path and calibration parameters. The coordinates of the origin of {G} in {R} are (X g ,Y g ,Z g ), the industrial computer 98 controls the manipulator 97 through the Compact RIO module 99 to move to the coordinate (X) according to the coordinate system {R} g ,Y g ,Z g ), the manipulator 97 moves to (θ, y) with point C as the center of the circle; the industrial computer 98 automatically selects the ultrasonic shot peening process parameters in the process package according to the correction amount Δz of the workpiece, and then sends instructions through the Compact RIO module 99 to control the robot to correct the processing area by clamping the ultrasonic shot peening gun 95 through the quick-change tooling. The ultrasonic shot peening gun can use a high-speed striker flow to impact the surface of the workpiece to be corrected, so that the impacted surface and the underlying metal material undergo plastic deformation and extend, thereby gradually causing the surface of the workpiece to be corrected to undergo bidirectional bending deformation that bulges toward the sprayed surface, thereby realizing the correction of the wheel hub.

[0107] Based on the same inventive concept, the embodiment of the present application also provides a workpiece detection and correction device for implementing the workpiece detection and correction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more workpiece detection and correction device embodiments provided below can refer to the limitations of the workpiece detection and correction method above, and will not be repeated here.

[0108] In one embodiment, Fig.10 As shown, a workpiece detection and correction device 1000 is provided, comprising: a correction model establishment module 1001, an initial correction data acquisition module 1003, a target correction area determination module 1005, a target correction data determination module 1007 and a correction module 1009, wherein:

[0109] The calibration model building module 1001 is used to obtain laser measurement data of the workpiece to be calibrated, and to build the calibration model according to the laser measurement data.

[0110] The initial correction data acquisition module 1003 is used to compare the model to be corrected with the standard model to obtain initial correction data, wherein the initial correction data includes correction quantities and an initial area to be corrected.

[0111] The target correction area determination module 1005 is used to sequentially screen the qualified areas of the initial correction data and perform area level classification to determine the target correction area and the corresponding target correction area level.

[0112] The target correction data determination module 1007 is used to determine the target correction path and correction parameters based on the target correction area and the level of the target correction area.

[0113] The shape correction module 1009 is used to correct the shape of the workpiece to be corrected based on the target shape correction path and the shape correction parameters.

[0114] In one embodiment of the present application, the calibration model building module is also used to:

[0115] If the width of the workpiece to be shaped is within the measuring range of the laser, directly acquiring the three-dimensional data of the workpiece to be shaped;

[0116] If the width of the workpiece to be shaped exceeds the measuring range of the laser, the partition measurement data is acquired in different regions, and the partition measurement data are spliced ​​to obtain the three-dimensional data of the workpiece to be shaped.

[0117] In one embodiment of the present application, the initial shape correction data acquisition module is further used to:

[0118] The three-dimensional data of the standard model and the model to be calibrated are compared respectively to obtain the initial area to be calibrated and the corresponding calibration amount in each direction.

[0119] In one embodiment of the present application, the target correction area determination module is further used to:

[0120] Compare the correction amount with the qualified deformation amount, screen the initial area to be corrected, remove qualified points, and determine the target area to be corrected;

[0121] The target area to be shaped is divided based on the shape correction amount, and a level of the target area to be shaped is determined.

[0122] The workpiece detection and correction device also includes an invalid data elimination module.

[0123] In one embodiment of the present application, the invalid data elimination module is further used to:

[0124] The intermediate points of the path are eliminated based on the target correction path.

[0125] The workpiece detection and correction device also includes a measurement mode selection module.

[0126] In one embodiment of the present application, the measurement mode selection module is further used to:

[0127] Determine the target laser measurement method based on the shape of the workpiece to be calibrated;

[0128] The workpiece to be shaped is measured based on the target laser measurement method.

[0129] Each module in the above workpiece detection and correction device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0130] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.11As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a workpiece detection and correction method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0131] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0132] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0134] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0135] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0136] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0137] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A workpiece detection and correction method, characterized in that: The method comprises: Acquire laser measurement data of the workpiece to be calibrated, and establish a model to be calibrated according to the laser measurement data; Comparing the model to be calibrated with the standard model to obtain initial calibration data, wherein the initial calibration data includes a calibration amount and an initial area to be calibrated; Screening the initial calibration data for qualified areas in turn and performing area grade classification to determine target calibration areas and corresponding target calibration area grades; Determining a target shaping path and shaping parameters based on the target shaping area and the level of the target shaping area; The workpiece to be shaped is shaped based on the target shaped path and the shaped parameters.

2. The method according to claim 1, characterized in that: The step of obtaining laser measurement data of the workpiece to be calibrated comprises: If the width of the workpiece to be shaped is within the measuring range of the laser, directly acquiring the three-dimensional data of the workpiece to be shaped; If the width of the workpiece to be shaped exceeds the measuring range of the laser, the partition measurement data is acquired in different regions, and the partition measurement data are spliced ​​to obtain the three-dimensional data of the workpiece to be shaped.

3. The method according to claim 1, characterized in that The step of comparing the model to be calibrated with the standard model to obtain initial calibration data comprises: The three-dimensional data of the standard model and the model to be calibrated are compared respectively to obtain the initial area to be calibrated and the corresponding calibration amount in each direction.

4. The method according to claim 1, characterized in that The screening of qualified areas of the initial calibration data in sequence and the grading of the areas, and the determination of target calibration areas and corresponding target calibration area grades include: Compare the correction amount with the qualified deformation amount, screen the initial area to be corrected, remove qualified points, and determine the target area to be corrected; The target area to be shaped is divided based on the shape correction amount, and a level of the target area to be shaped is determined.

5. The method according to claim 1, characterized in that After determining the target shaping path and shaping parameters based on the target shaping area and the target shaping area level, the following further comprises: The intermediate points of the path are eliminated based on the target correction path.

6. The method according to claim 1, characterized in that The step of obtaining laser measurement data of the workpiece to be calibrated includes: Determine the target laser measurement method based on the shape of the workpiece to be calibrated; The workpiece to be shaped is measured based on the target laser measurement method.

7. A workpiece detection and correction system, characterized in that: It includes workpiece shape measurement module, data processing module and robot shape correction module, among which: The workpiece shape measurement module is used to perform laser measurement on the workpiece to be shaped, obtain laser measurement data of the workpiece to be shaped, and establish a model to be shaped according to the laser measurement data; compare the model to be shaped with the standard model to obtain initial shape correction data, the initial shape correction data includes the shape correction amount and the initial shape correction area, and send the initial shape correction data to the data processing module; The data processing module is used to sequentially screen the qualified areas of the initial calibration data and perform area level classification to determine the target calibration area and the corresponding target calibration area level; determine the target calibration path and calibration parameters based on the target calibration area and the target calibration area level; and send the target calibration path and calibration parameters to the robot calibration module; The robot shaping module is used to align the workpiece to be shaped based on the target shaping path and shaping parameters.

8. A workpiece detection and correction device, characterized in that: The device comprises: A calibration model building module is used to obtain laser measurement data of the workpiece to be calibrated and to build a calibration model according to the laser measurement data; An initial calibration data acquisition module is used to compare the model to be calibrated with the standard model to obtain initial calibration data, wherein the initial calibration data includes a calibration amount and an initial area to be calibrated; A target calibration area determination module is used to sequentially screen the qualified areas of the initial calibration data and classify the areas, and determine the target calibration area and the corresponding target calibration area level; A target correction data determination module, used for determining a target correction path and correction parameters based on the target correction area and the level of the target correction area; A shape correction module is used to correct the workpiece to be corrected based on the target shape correction path and the shape correction parameters.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images