Arc butt weld feature point recognition system and method based on interval peak value

Abstract

The invention discloses an arc butt weld feature point recognition system and method based on interval peak value, relates to the field of welding technology, and includes: a work platform, a welding controller, a manual teaching pendant and a manual compensation remote rod. By acquiring the image of the weld and identifying the weld interval peak value, filtering and removing noise points are realized through simple calculation and comparison of the distance between data points and the size of the ordinate, and the feature points can be successfully extracted to realize the search of arc feature points. The overall algorithm has a small amount of calculation, a short running time, and can quickly obtain the recognition result. In addition, the system has a simple structure, is easy to disassemble and maintain, saves computer resources, has a low cost, is highly portable and practical, and improves the accuracy and stability of arc feature point recognition.

Description

Technical Field

[0001] The invention relates to the technical field of welding, and in particular to a system and method for identifying characteristic points of arc butt welds based on interval peak values. Background Art

[0002] Robot welding technology has been widely used in many industrial and civilian fields. It is a very important manufacturing technology. The key is to quickly and accurately identify and extract weld feature points. The general processing steps of weld feature point recognition algorithms based on structured light stripe images are: image filtering, centerline extraction, curve fitting and feature point recognition. These algorithms rely on linear fitting of structured light stripes to determine weld feature points. When the workpiece surface is relatively rough, the accuracy of the algorithm will inevitably be affected. It is also possible to extract the sharp points of structured light stripes as weld feature points through corner point detection, but this type of algorithm has high requirements on the imaging quality of structured light stripe images and requires complex image smoothing. The above existing algorithms are mainly aimed at straight welds, calculating intersections or sharp points as feature points, and are not applicable to feature point recognition on arcs. Summary of the invention

[0003] The embodiment of the present invention provides a system and method for identifying arc butt weld feature points based on interval peak values. By searching for interval peak values ​​and simply calculating and comparing the distances between data points and the sizes of the ordinates, filtering and removing noise points are achieved, and feature points can be successfully extracted to achieve the search for arc feature points. The overall algorithm has a small amount of calculation, a short running time, and can quickly obtain recognition results. In addition, the system has a simple structure, is easy to disassemble and maintain, saves computer resources, has a low cost, is highly portable, and is highly practical, thereby improving the accuracy and stability of arc feature point recognition.

[0004] The arc butt weld feature point recognition system based on interval peak value includes:

[0005] A working platform, the working platform comprising a welding gun, a horizontal and vertical cross slide, a line laser sensor, a two-axis servo motor and a point laser sensor;

[0006] Wherein, the welding gun is arranged on the horizontal vertical cross slide, the line laser sensor and the point laser sensor are respectively arranged on both sides of the welding gun, and the output end of the two-axis servo motor is connected to the input end of the horizontal vertical cross slide, so as to drive the welding gun to slide on the horizontal vertical cross slide;

[0007] A welding controller, wherein a signal input end of the welding controller is communicatively connected to the signal output ends of the line laser sensor and the point laser sensor respectively, and a signal output end of the welding controller is communicatively connected to the signal input end of the two-axis servo motor;

[0008] An artificial teaching pendant, a signal input end of the artificial teaching pendant is communicatively connected with a signal output end of the welding controller;

[0009] A manual compensation joystick, wherein the signal input and output ends of the manual compensation joystick are respectively communicatively connected with the signal input and output ends of the welding controller.

[0010] Furthermore, the point laser sensor and the line laser sensor are used to capture and scan weld image data, and are communicatively connected with the welding controller via the Modbus TCP communication protocol.

[0011] Furthermore, the number of the working platforms is at least one, each of which is communicatively connected to the welding controller.

[0012] Furthermore, the manual teaching pendant and the manual compensation rocker are used to receive control signals issued by the welding controller. The manual teaching pendant and the manual compensation rocker are also used to compensate for the position accuracy of the welding gun, the point laser sensor and the line laser sensor. When the machine positioning is inaccurate, manual position compensation is performed by operating the manual compensation rocker.

[0013] In a second aspect, an embodiment of the present invention provides a method for identifying characteristic points of arc butt welds based on interval peak values, comprising the following steps:

[0014] Step 1, bind line laser sensor: bind horizontal and vertical line laser sensors;

[0015] Step 2, calibrate the line laser sensor and the horizontal axis: set the corresponding relationship between the horizontal axis, the vertical axis and the line laser sensor;

[0016] Step 3: Calibrate the vertical and horizontal relationship:

[0017] (1) Line laser calibration: directly input the data of each deviation and send the data to the line laser sensor via Modbus TCP. Line laser calibration can also be performed by moving the end point of the welding wire five times, obtaining the coordinates of the five welding wire end points and the data of the laser sensor, and sending the data to the line laser sensor via Modbus TCP.

[0018] (2) Point laser calibration: Move the wire end point three times, obtain the three wire end point coordinates and point laser simulation, and calculate the relationship between the simulation and the axis;

[0019] Step 4, obtaining the coordinates of the characteristic points of the laser weld and the point laser: starting to obtain the coordinates of the characteristic points of the laser weld and the point laser;

[0020] Step 5, set the delay time and compensate the horizontal axis and the vertical axis: compensate through the working platform according to the characteristic points; set the delay time and compensate the horizontal axis and the vertical axis;

[0021] Step 6, manual joystick compensation: Use the joystick or buttons to make manual compensation. Each time you input manual compensation, it will be directly added to the number of line laser sensors and point laser sensors for compensation.

[0022] Step 7: Determine whether an end instruction is received: stop if an end instruction is received, and repeat step 4 if an end instruction is not received.

[0023] Furthermore, in step 5, the horizontal axis compensation method is: the horizontal axis is directly compensated after reading the value from the line laser sensor, and compensation is delayed after reading. The delay time can be configured in units of 100ms, and the maximum time is less than 20S. When the line laser sensor outputs a value of 0, no compensation is performed; vertical axis compensation: the vertical axis reads the voltage from the analog quantity, and after calibration and conversion, it is a direct compensation value; the compensation time needs to be delayed, and the delay time can be configured in units of 100ms, and the maximum time is less than 2S.

[0024] Further, the step 4 comprises the following steps:

[0025] Step 41, data shooting: adjusting the posture of the welding gun and the line laser sensor to shoot weld images from as many angles as possible;

[0026] Step 42, format conversion: extracting the horizontal coordinate and vertical coordinate values ​​of all data points in each frame from the original weld image in the raw format as the original data;

[0027] Step 43, data reading and preprocessing: after obtaining the original data, effectively preprocess each frame of data;

[0028] Step 44, finding the initial peak point;

[0029] Step 45, dividing the filtering space according to the initial peak point and performing smoothing filtering on the data in the interval;

[0030] Step 46, find the peak point again and record the coordinates.

[0031] Furthermore, the preprocessing method in step 43 is: delete the data points whose horizontal and vertical coordinate values ​​are empty or 0, then calculate the average value of the vertical coordinates of all data in the current frame, and finally retain the data points whose vertical coordinates differ from the average value by 1000, and the remaining points are deleted as abnormal points.

[0032] Furthermore, in step 43, the specific implementation method is: first set the distance threshold d, record the initial position of the first point as 0, the initial position of the second point as 1, and then start from the first point, calculate the distance between the two points, and then compare it with the distance threshold d, and only retain points less than the threshold d.

[0033] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least: the present invention realizes filtering and removing noise points by searching for interval peaks, and can successfully extract feature points and realize the search for arc feature points through simple calculation and comparison of the distance between data points and the size of the vertical coordinates. The overall algorithm has a small amount of calculation and a short running time, and the recognition results can be obtained quickly. In addition, the system has a simple structure, is easy to disassemble and maintain, saves computer resources, has a low cost, is highly portable and practical, and improves the accuracy and stability of arc feature point recognition.

[0034] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0035] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0037] Figure 1 It is a structural diagram of a circular arc butt weld feature point recognition system based on interval peak value disclosed in an embodiment of the present invention;

[0038] Figure 2 It is a schematic diagram of the working process of the arc butt weld feature point recognition system based on interval peak value disclosed in an embodiment of the present invention;

[0039] Figure 3 It is a schematic flow chart of a method for identifying characteristic points of arc butt welds based on interval peak values ​​disclosed in an embodiment of the present invention;

[0040] Figure 4 A schematic diagram of the initial feature point recognition result disclosed in an embodiment of the present invention;

[0041] Figure 5 A schematic diagram of filtering interval selection disclosed in an embodiment of the present invention;

[0042] Figure 6 This is a schematic diagram of the final feature point recognition result disclosed in an embodiment of the present invention.

[0043] Reference numerals:

[0044] 100. Working platform; 101. Welding gun; 102. Horizontal and vertical cross slide; 103. Line laser sensor; 104. Two-axis servo motor; 105. Point laser sensor; 200. Welding controller; 300. Manual teaching pendant; 400. Manual compensation joystick. DETAILED DESCRIPTION

[0045] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] Embodiment 1

[0047] like Figure 1 As shown, the embodiment of the present invention provides an arc butt weld feature point recognition system based on interval peak value, including: a work platform 100, the work platform 100 includes a welding gun 101, a horizontal vertical cross slide 102, a line laser sensor 103, a two-axis servo motor 104 and a point laser sensor 105, the number of the work platform 100 is at least one, and each is communicated with the welding controller 200, the welding gun 101 is arranged on the horizontal vertical cross slide 102, the line laser sensor 103 and the point laser sensor 105 are respectively arranged on both sides of the welding gun 101, and the point laser sensor 105 and the line laser sensor 103 are used to shoot and scan weld image data, and transmit the data to the welding controller 200 through Modbus. The TCP communication protocol is connected to the welding controller 200 for communication, the output end of the two-axis servo motor 104 is connected to the input end of the horizontal vertical cross slide 102, and is used to drive the welding gun 101 to slide on the horizontal vertical cross slide 102, the welding controller 200, the signal input end of the welding controller 200 is connected to the signal output end of the line laser sensor 103 and the point laser sensor 105 for communication, the signal output end of the welding controller 200 is connected to the signal input end of the two-axis servo motor 104 for communication, the manual teaching pendant 300, the signal input end of the manual teaching pendant 300 The input end is communicatively connected with the signal output end of the welding controller 200, the manual compensation joystick 400, the signal input and output ends of the manual compensation joystick 400 are respectively communicatively connected with the signal input and output ends of the welding controller 200, the manual teaching pendant 300 and the manual compensation joystick are used to receive the control signal sent by the welding controller 200, the manual teaching pendant 300 and the manual compensation joystick are also used for position accuracy compensation of the welding gun 101, the point laser sensor 105 and the line laser sensor 103. When the machine positioning is inaccurate, the position is manually compensated by operating the manual compensation joystick 400.

[0048] The present invention controls the two-axis servo motor 104 through the welding controller 200 to drive the welding gun 101 to slide on the horizontal vertical cross slide 102. At the same time, the line laser sensor 103 and the point laser sensor 105 take real-time images of the weld during the movement and send them to the welding controller 200 for weld analysis to obtain feature points, and compensate the point laser sensor 105, the line laser sensor 103 and the two-axis servo motor 104 according to the feature points obtained by analysis. At the same time, when the machine positioning is inaccurate, the operator can also perform manual compensation according to the feature points through the manual teaching device 300 and the manual compensation joystick 400. Each time the manual compensation is input, it is directly added to the number of sensors for compensation. This solves the problem that the current existing robot welding technology mainly targets straight welds, calculates intersections or cusps as feature points, and is not applicable to feature point recognition on arcs.

[0049] Embodiment 2

[0050] The embodiment of the present invention also discloses a method for identifying characteristic points of arc butt welds based on interval peak values, such as Figure 2-6 As shown, the following steps are included:

[0051] Step 1, binding line laser sensors: binding horizontal and vertical line laser sensors 103;

[0052] Specifically, the line laser sensors 103 at the horizontal position and the vertical position are bound.

[0053] Step 2, calibrating the line laser sensor and the horizontal axis: setting the corresponding relationship between the horizontal axis, the vertical axis and the line laser sensor 103;

[0054] Specifically, the positional relationship between the line laser sensor 103 and the horizontal axis and the vertical axis is set according to the horizontal position and the vertical position of the line laser sensor 103 respectively;

[0055] Step 3: Calibrate the vertical and horizontal relationship:

[0056] (1) Line laser calibration: directly input the data of each deviation and send the data to the line laser sensor 103 via Modbus TCP; the line laser calibration can also be performed by moving the end point of the welding wire five times, obtaining the coordinates of the end point of the welding wire five times and the data of the laser sensor, and sending the data to the line laser sensor 103 via Modbus TCP;

[0057] (2) Point laser calibration: Move the wire end point three times, obtain the three wire end point coordinates and point laser simulation, and calculate the relationship between the simulation and the axis;

[0058] Step 4, obtain the coordinates of the laser weld feature points and the laser point: start to obtain the coordinates of the laser weld feature points and the laser point, such as Figure 3As shown, step 4 includes the following steps:

[0059] Step 41, data capture: adjusting the postures of the welding gun 101 and the line laser sensor 103 to capture weld images from as many angles as possible;

[0060] Step 42, format conversion: extracting the horizontal coordinate and vertical coordinate values ​​of all data points in each frame from the original weld image in the raw format as the original data;

[0061] Step 43, data reading and preprocessing: after obtaining the original data, each frame of data is effectively preprocessed. The preprocessing method is: delete the data points whose horizontal and vertical coordinate values ​​are empty or 0, then calculate the average value of the vertical coordinates of all data in the current frame, and finally retain the data points whose vertical coordinates differ from the average value by 1000, and the remaining points are deleted as abnormal points. The specific implementation method is: first set the distance threshold d, record the initial position of the first point as 0, the initial position of the second point as 1, and then start from the first point, calculate the distance between the two points, and then compare it with the distance threshold d, and only retain the points less than the threshold d;

[0062] Step 44, finding the initial peak point;

[0063] Specifically, three consecutive intervals are set with a width of threshold th, and the average values ​​of the vertical coordinates of the data points in these three intervals are calculated respectively. When the average value m1 of the second interval is greater than the average value m0 of the first interval and the average value m2 of the third interval, the left endpoint of the second interval is recorded as p0; continue to traverse backward and repeat the above calculation to find the left endpoint of the second peak interval, recorded as p1, such as Figure 4 As shown;

[0064] Step 45, dividing the filtering space according to the initial peak point and performing smoothing filtering on the data in the interval;

[0065] Specifically, after finding the initial feature points p0 and p1, the left feature point p0 is moved to the right by th to obtain the right endpoint of the left filtering interval, and the right feature point is moved to the left by th to obtain the left endpoint of the right interval, such as Figure 5 As shown, in the left and right filtering intervals, the data are filtered and smoothed respectively;

[0066] Step 46, find the peak point again and record the coordinates;

[0067] Specifically, the method of finding the maximum peak interval in step 44 is repeated in the filtering intervals on the left and right sides, and then the point with the largest ordinate in the maximum peak interval is found as the final feature point. The final recognition result is as follows: Figure 6As shown in the figure, the gray dots are the retained data points, the black dots are the interference points such as noise that need to be filtered out, and the black square points represent the feature points that are finally recognized and saved; compare the feature points of the current frame with the previous frame. If the distance between the feature points of the previous and next frames exceeds a certain threshold k, or one or more feature points are found in the current frame, it is considered to be a false detection, and the feature points of the previous frame continue to be used;

[0068] Step 5, set the delay time and compensate the horizontal axis and the vertical axis: compensate through the work platform 100 according to the feature points; set the delay time and compensate the horizontal axis and the vertical axis. The horizontal axis compensation method is: the horizontal axis is directly compensated after reading the value from the line laser sensor 103. After reading, it needs to be delayed before compensation. The delay time can be configured in units of 100ms, and the maximum time is less than 20S. When the output of the line laser sensor 103 is a value of 0, no compensation is made; vertical axis compensation: the vertical axis reads the voltage from the analog quantity, and it is directly compensated after calibration conversion; the compensation time needs to be delayed, and the delay time can be configured in units of 100ms, and the maximum time is less than 2S;

[0069] Step 6, manual joystick compensation: use the joystick or button to perform manual compensation. Each time the manual compensation is input, it is directly added to the number of line laser sensors 103 and point laser sensors 105 for compensation;

[0070] Step 7: Determine whether the end instruction is received: stop if the end instruction is received, and repeat step 4 if the end instruction is not received.

[0071] The method for identifying arc butt weld feature points based on interval peak values ​​disclosed in the present embodiment realizes filtering and removing noise points by searching for interval peak values ​​and by simple calculation and comparison of the distance between data points and the size of the ordinate, and can successfully extract feature points to achieve the search for arc feature points. The overall algorithm has a small amount of calculation and a short running time, and the recognition results can be obtained quickly. In addition, the system has a simple structure, is easy to disassemble and maintain, saves computer resources, has a low cost, is highly portable and practical, and improves the accuracy and stability of arc feature point recognition.

[0072] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to a specific order or hierarchy.

[0073] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0074] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0075] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0076] For software implementation, the technology described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions of this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0077] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. The arc butt weld feature point recognition system based on interval peak value is characterized by: include: A working platform, the working platform comprising a welding gun, a horizontal and vertical cross slide, a line laser sensor, a two-axis servo motor and a point laser sensor; Wherein, the welding gun is arranged on the horizontal vertical cross slide, the line laser sensor and the point laser sensor are respectively arranged on both sides of the welding gun, and the output end of the two-axis servo motor is connected to the input end of the horizontal vertical cross slide, so as to drive the welding gun to slide on the horizontal vertical cross slide; A welding controller, wherein a signal input end of the welding controller is communicatively connected to the signal output ends of the line laser sensor and the point laser sensor respectively, and a signal output end of the welding controller is communicatively connected to the signal input end of the two-axis servo motor; An artificial teaching pendant, a signal input end of the artificial teaching pendant is communicatively connected with a signal output end of the welding controller; A manual compensation rocker, the signal input and output ends of the manual compensation rocker are respectively communicatively connected with the signal input and output ends of the welding controller; The working process of the arc butt weld feature point recognition system based on interval peak value is as follows: Step 1, Bind Line Laser Sensor: Bind horizontal and vertical line laser sensors; Step 2, calibrate the line laser sensor and the horizontal axis: set the corresponding relationship between the horizontal axis, the vertical axis and the line laser sensor; Step 3: Calibrate the vertical and horizontal relationship: (1) Line laser calibration: directly input the data of each deviation and send the data to the line laser sensor via Modbus TCP; or line laser calibration moves the wire end point five times, obtains the coordinates of the wire end point five times and the data of the laser sensor, and sends the data to the line laser sensor via Modbus TCP; (2) Point laser calibration: Move the wire end point three times, obtain the three wire end point coordinates and point laser simulation, and calculate the relationship between the simulation and the axis; Step 4, obtaining the coordinates of the characteristic points of the laser weld and the point laser: starting to obtain the coordinates of the characteristic points of the laser weld and the point laser; Step 5, set the delay time and compensate the horizontal axis and the vertical axis: compensate through the working platform according to the characteristic points; set the delay time and compensate the horizontal axis and the vertical axis; Step 6, manual joystick compensation: Use the joystick or buttons to make manual compensation. Each time the manual compensation is input, it is directly added to the number of line laser sensors and point laser sensors for compensation; Step 7: Determine whether an end instruction is received: stop if an end instruction is received, and repeat step 4 if an end instruction is not received.

2. The arc butt weld feature point recognition system based on interval peak value according to claim 1, characterized in that: The point laser sensor and the line laser sensor are used to capture and scan weld image data, and are connected to the welding controller through the Modbus TCP communication protocol.

3. The arc butt weld feature point recognition system based on interval peak value according to claim 1, characterized in that: The number of the working platforms is at least one, and each of them is communicatively connected to the welding controller.

4. The arc butt weld feature point recognition system based on interval peak value according to claim 1, characterized in that: The manual teaching pendant and the manual compensation rocker are used to receive control signals sent by the welding controller. The manual teaching pendant and the manual compensation rocker are also used to compensate for the position accuracy of the welding gun, the point laser sensor and the line laser sensor. When the machine positioning is inaccurate, manual position compensation is performed by operating the manual compensation rocker.

5. A method for identifying characteristic points of arc butt welds based on interval peak values, applied to a system for identifying characteristic points of arc butt welds based on interval peak values ​​as claimed in any one of claims 1 to 4, characterized in that: The following steps are involved: Step 1, Bind Line Laser Sensor: Bind horizontal and vertical line laser sensors; Step 2, calibrate the line laser sensor and the horizontal axis: set the corresponding relationship between the horizontal axis, the vertical axis and the line laser sensor; Step 3: Calibrate the vertical and horizontal relationship: (1) Line laser calibration: directly input the data of each deviation and send the data to the line laser sensor via Modbus TCP; or line laser calibration moves the wire end point five times, obtains the coordinates of the wire end point five times and the data of the laser sensor, and sends the data to the line laser sensor via Modbus TCP; (2) Point laser calibration: Move the wire end point three times, obtain the three wire end point coordinates and point laser simulation, and calculate the relationship between the simulation and the axis; Step 4, obtaining the coordinates of the characteristic points of the laser weld and the point laser: starting to obtain the coordinates of the characteristic points of the laser weld and the point laser; Step 5, set the delay time and compensate the horizontal and vertical axes: compensate through the working platform according to the feature points; Set the delay time and compensate the horizontal and vertical axes; Step 6, manual joystick compensation: Use the joystick or buttons to make manual compensation. Each time the manual compensation is input, it is directly added to the number of line laser sensors and point laser sensors for compensation; Step 7: Determine whether an end instruction is received: stop if an end instruction is received, and repeat step 4 if an end instruction is not received.

6. The method for identifying characteristic points of arc butt welds based on interval peak values ​​according to claim 5, characterized in that: In step 5, the horizontal axis compensation method is: the horizontal axis is directly compensated after reading the value from the line laser sensor, and compensation is delayed after reading. The delay time can be configured in units of 100ms, and the maximum time is less than 20S. When the line laser sensor outputs a value of 0, no compensation is performed; vertical axis compensation: the vertical axis reads the voltage from the analog quantity, and it is directly compensated after calibration conversion; the compensation time needs to be delayed, and the delay time can be configured in units of 100ms, and the maximum time is less than 2S.

7. The method for identifying characteristic points of arc butt welds based on interval peak values ​​according to claim 5, characterized in that: The step 4 comprises the following steps: Step 41, data capture: adjusting the posture of the welding gun and the line laser sensor to capture weld images from multiple angles; Step 42, format conversion: extracting the horizontal coordinate and vertical coordinate values ​​of all data points in each frame from the original weld image in the raw format as the original data; Step 43, data reading and preprocessing: after obtaining the original data, effectively preprocess each frame of data; Step 44, finding the initial peak point; Step 45, dividing the filtering space according to the initial peak point and performing smoothing filtering on the data in the interval; Step 46, find the peak point again and record the coordinates.

8. The method for identifying characteristic points of arc butt welds based on interval peak values ​​according to claim 7, characterized in that: In step 43, the specific implementation method is: first set the distance threshold d, record the initial position of the first point as 0, and the initial position of the second point as 1, then start from the first point, calculate the distance between the two points, and then compare it with the distance threshold d, and only retain points less than the threshold d.

Images