A control method, device and storage medium of a crawling welding robot

Abstract

The present application provides a control method, device and storage medium for a crawling welding robot, the method comprising: acquiring a weld laser image at a preset interval; determining the left-side stored inflection point coordinates and the right-side stored inflection point coordinates and updating them in the left-side stored inflection point coordinate set and the right-side stored inflection point coordinate set, respectively; performing a coordinate point stability analysis on the most recently updated left-side stored inflection point coordinates in the left-side stored inflection point coordinate set, and performing a coordinate point stability analysis on the most recently updated right-side stored inflection point coordinates in the right-side stored inflection point coordinate set; determining the motion mode of the crawling welding robot, and controlling the crawling welding robot to move according to the corresponding operating mode to complete the welding of the weld.

Description

Technical Field

[0001] The present application relates to the technical field of welding robots, and in particular to a control method, device and storage medium for a crawling welding robot. Background Art

[0002] In the prior art, crawling welding robots are used to weld metal workpieces such as steel plates. The crawling machine weld tracking is real-time tracking, and usually the inflection point coordinates of the weld are identified for tracking. The accuracy of the weld coordinates directly affects the accuracy and reliability of the crawling machine tracking. Under actual working conditions, the welds of metal workpieces are often not very regular, and there are interferences such as polishing reflections, lack of meat, welding slag, and uneven grooves. Affected by this, the weld inflection points in the laser image will have unclear features, and the detected inflection points may fluctuate and deviate from the actual position of the weld inflection points. Without relying on prior information, it is difficult to accurately locate the exact position of the weld inflection point, and the crawling welding robot cannot accurately complete the welding task. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide a control method, device and storage medium for a crawling welding robot, so as to control the crawling welding robot to accurately complete the welding task.

[0004] In a first aspect, the present application provides a control method for a crawling welding robot, the method comprising: acquiring a weld laser image at a preset interval; for each weld laser image acquired, determining the left-side stored inflection point coordinates and the right-side stored inflection point coordinates based on the weld laser image, and updating them in the left-side stored inflection point coordinate set and the right-side stored inflection point coordinate set, respectively; performing a coordinate point stability analysis on the most recently updated left-side stored inflection point coordinates in the left-side stored inflection point coordinate set to determine whether the left-side stored inflection point coordinates meet the tracking conditions, and performing a coordinate point stability analysis on the most recently updated right-side stored inflection point coordinates in the right-side stored inflection point coordinate set to determine whether the right-side stored inflection point coordinates meet the tracking conditions; determining the motion mode of the crawling welding robot based on the result of determining whether the tracking conditions are met, and controlling the crawling welding robot to move in the corresponding operating mode to complete the welding of the weld.

[0005] Preferably, the operating mode includes an inflection point tracking mode and a parallel posture mode, and the motion mode of the crawling welding robot is determined in the following manner: when the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates do not meet the tracking conditions, the crawling welding robot is controlled to move in the parallel posture mode; when one of the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates meets the tracking conditions, the optimized inflection point coordinates corresponding to the other side are determined according to the stored inflection point coordinates that meet the tracking conditions, and the midpoint coordinates of the weld are determined according to the stored inflection point coordinates that meet the tracking conditions and the corresponding optimized inflection point coordinates, so as to control the crawling welding robot to move in the inflection point tracking mode; when the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates both meet the tracking conditions, the midpoint coordinates of the weld are determined according to the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates, so as to control the crawling welding robot to move in the inflection point tracking mode.

[0006] Preferably, for the left-side stored inflection point coordinates or the right-side stored inflection point coordinates, it is determined whether the tracking condition is met in the following manner: determine the continuity result between the most recently updated stored inflection point coordinates and the last target inflection point coordinate in the target inflection point coordinate set on the same side; if the continuity result is yes, then determine that the left-side stored inflection point coordinates or the right-side stored inflection point coordinates meet the tracking condition; if the continuity result is no, then determine that the left-side stored inflection point coordinates or the right-side stored inflection point coordinates do not meet the tracking condition; wherein, the target inflection point coordinate set is one of the left-side target inflection point coordinate set and the right-side target inflection point coordinate set, and the continuity result between any two adjacent target inflection point coordinates in the target inflection point coordinate set is yes.

[0007] Preferably, the step of determining the result of continuity between the most recently updated stored inflection point coordinate and the last target inflection point coordinate in the target inflection point coordinate set on the same side specifically includes: determining the first coordinate value of the most recently updated stored inflection point coordinate in the X-axis direction, and determining the second coordinate value of the last target inflection point coordinate in the corresponding target inflection point coordinate set in the X-axis direction; comparing the difference between the second coordinate value and the first coordinate value with a preset difference; if the difference is greater than the preset difference, determining the result of continuity between the two current inflection point coordinates to be no; if the difference is not greater than the preset difference, determining the result of continuity between the two current inflection point coordinates to be yes.

[0008] Preferably, the preset width value is the average width value of the weld, and the step of determining the corresponding optimized inflection point coordinates on the other side according to the stored inflection point coordinates that meet the tracking conditions specifically includes: when the right-side stored inflection point coordinates meet the tracking conditions, the difference between the third coordinate value of the right-side stored inflection point coordinates in the X-axis direction and the preset width value is used as the fourth coordinate value of the left-side optimized inflection point coordinates in the X-axis direction, wherein the coordinate value of the left-side optimized inflection point coordinates in the Y-axis direction is the same as the coordinate value of the right-side stored inflection point coordinates in the Y-axis direction; when the left-side stored inflection point coordinates meet the tracking conditions, the sum of the fifth coordinate value of the left-side stored inflection point coordinates in the X-axis direction and the preset width value is used as the sixth coordinate value of the right-side optimized inflection point coordinates in the X-axis direction, wherein the coordinate value of the right-side optimized inflection point coordinates in the Y-axis direction is the same as the coordinate value of the left-side stored inflection point coordinates in the Y-axis direction.

[0009] Preferably, for each weld laser image, the left-side stored inflection point coordinates or the right-side stored inflection point coordinates are determined in the following manner: performing image preprocessing on the weld laser image; identifying the preprocessed weld laser image to output the identified left-side candidate inflection point coordinates and the right-side candidate inflection point coordinates; for any one of the left-side candidate inflection point coordinates and the right-side candidate inflection point coordinates, when the number of such candidate inflection point coordinates is one, then the candidate inflection point coordinate is used as the corresponding left-side stored inflection point coordinates or the right-side stored inflection point coordinates; for any one of the left-side candidate inflection point coordinates and the right-side candidate inflection point coordinates, when the number of such candidate inflection point coordinates is multiple, then the corresponding left-side stored inflection point coordinates or the right-side stored inflection point coordinates are screened out from the multiple candidate inflection point coordinates.

[0010] Preferably, the corresponding left-side stored inflection point coordinates or the right-side stored inflection point coordinates are screened out from multiple candidate inflection point coordinates in the following manner: for each candidate inflection point coordinate among the multiple candidate inflection point coordinates, the distance value between the candidate inflection point coordinate and the previous stored inflection point coordinate in the set where the candidate inflection point coordinate is located is calculated; based on the size of each distance value, the candidate inflection point coordinate corresponding to the target distance value is determined to be the corresponding left-side stored inflection point coordinate or the right-side stored inflection point coordinate.

[0011] In a second aspect, the present application also provides a control device for a crawling welding robot, the device comprising:

[0012] An acquisition module, used for acquiring weld seam laser images at preset intervals;

[0013] An updating module is used to determine the left-side stored inflection point coordinates and the right-side stored inflection point coordinates for each weld seam laser image acquired based on the weld seam laser image, and update them in the left-side stored inflection point coordinate set and the right-side stored inflection point coordinate set respectively;

[0014] An analysis module, used to perform a coordinate point stability analysis on the left-side stored inflection point coordinate set to determine whether the left-side stored inflection point coordinate set meets the tracking condition, and to perform a coordinate point stability analysis on the right-side stored inflection point coordinate set to determine whether the right-side stored inflection point coordinate set meets the tracking condition;

[0015] The mode control module determines the movement mode of the crawling welding robot according to the result of determining whether the tracking condition is met, and controls the crawling welding robot to move according to the corresponding operation mode to complete the welding of the weld.

[0016] In a third aspect, the present application also provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the control method of the crawling welding robot as described above are performed.

[0017] In a fourth 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 control method of the crawling welding robot as described above are executed.

[0018] The present application provides a control method, device and storage medium for a crawling welding robot. The method includes acquiring a weld laser image at a preset interval; for each weld laser image acquired, based on the weld laser image, determining the left stored inflection point coordinates and the right stored inflection point coordinates, and updating them in the left stored inflection point coordinate set and the right stored inflection point coordinate set respectively; performing a coordinate point stability analysis on the left stored inflection point coordinate set to determine whether the left stored inflection point coordinate set meets the tracking condition, and performing a coordinate point stability analysis on the right stored inflection point coordinate set to determine whether the right stored inflection point coordinate set meets the tracking condition; determining the movement mode of the crawling welding robot according to the result of determining whether the tracking condition is met, and controlling the crawling welding robot to move according to the corresponding operation mode to complete the welding of the weld. The continuous stability of the inflection point can be analyzed, and then a suitable operation mode can be determined to control the crawling welding robot to accurately complete the welding task.

[0019] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A flow chart of a control method for a crawling welding robot provided in an embodiment of the present application;

[0022] Figure 2 A flowchart of the steps of tracking condition analysis provided by an embodiment of the present application;

[0023] Figure 3 A flow chart of the steps of continuity analysis provided in an embodiment of the present application;

[0024] Figure 4 A schematic diagram of the structure of a control system of a crawling welding robot provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of the structure of a control device for a crawling welding robot provided in an embodiment of the present application;

[0026] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0028] First, the application scenarios to which the present application is applicable are introduced. The present application can be applied to the control of a crawling welding robot when performing a welding task.

[0029] The crawler welding robot is attached to the workpiece by magnets, and uses laser sensors to identify the position of the weld, track the weld, and weld while tracking. The crawler machine weld tracking is real-time tracking, usually identifying the inflection point coordinates of the weld for tracking. The accuracy of the weld coordinates directly affects the accuracy and reliability of the crawler machine tracking.

[0030] In actual working conditions, welds are often not very regular, with interferences such as polishing reflection, lack of meat, welding slag, and uneven grooves. Affected by this, the weld inflection point in the laser image will have unclear features, and the detected inflection point may fluctuate and deviate from the actual weld inflection point position, especially when transitioning from filling to covering, it becomes shallower or even flatter, the laser line becomes flat, and the weld inflection point on the image disappears for a short time. Without relying on prior information, it is difficult to accurately locate the true position of the weld inflection point. At this time, if tracking welding is performed based on inaccurate inflection points, the position of the weld will be inaccurate.

[0031] The crawling welding robot has at least the following two operating modes: turning point tracking mode and parallel posture mode. The turning point tracking mode refers to PID tracking based on the left and right turning points determined based on the weld laser image to control the movement of the crawling welding robot. The parallel posture mode refers to controlling the crawling welding robot to move parallel to the center line of the weld according to the average value of the weld width. Based on this, the embodiment of the present application provides a control method, device and storage medium for a crawling welding robot.

[0032] See also Figure 1 , Figure 1 The following is a flow chart of a control method for a crawling welding robot provided in an embodiment of the present application. Figure 1 As shown, the control method of the crawling welding robot provided in the embodiment of the present application includes the following steps:

[0033] S101, acquiring a weld laser image at preset intervals.

[0034] The principle of the existing crawling welding robot tracking welds is as follows: the laser installed at the front of the crawling welding robot emits laser to the weld, and the image sensor on the crawling welding robot scans the weld to obtain the weld laser image and sends it to the host computer. The host computer processes the weld laser image, identifies the weld inflection point coordinates, and sends them to the slave computer. The slave computer performs PID (Proportion Integration Differentiation) tracking on the inflection point coordinates, controls the speed of the wheels on both sides of the crawling machine to track the weld for welding. The weld laser image includes the weld within a certain range and the laser image irradiated on the weld.

[0035] S102, for each weld seam laser image acquired, based on the weld seam laser image, determine the left-side stored inflection point coordinates and the right-side stored inflection point coordinates, and update them in the left-side stored inflection point coordinate combination and the right-side stored inflection point coordinate set, respectively.

[0036] After the host computer of the crawling welding robot obtains the weld laser image, the left candidate inflection point coordinates and the right candidate inflection point coordinates can be output through the recognition algorithm. The host computer needs to analyze the left candidate inflection point coordinates and the right candidate inflection point coordinates to determine more accurate left storage inflection point coordinates and right storage inflection point coordinates and store them in the storage space. Only the latest N inflection point coordinate pairs are retained in the storage space here. If the inflection point coordinates on both the left and right sides fail to be recognized here, the inflection point tracking mode cannot be run and the parallel posture mode is switched. When in the parallel posture mode, you can switch back to the inflection point tracking mode according to the control command.

[0037] Here, the inflection point coordinates output by the recognition algorithm are established based on the image coordinate system.

[0038] The left-side stored inflection point coordinate set includes N left-side stored inflection point coordinates arranged in time sequence. The right-side stored inflection point coordinate set includes N right-side stored inflection point coordinates arranged in time sequence.

[0039] S103. Perform a coordinate point stability analysis on the most recently updated left-side stored inflection point coordinates in the left-side stored inflection point coordinate set to determine whether the left-side stored inflection point coordinates meet the tracking conditions, and perform a coordinate point stability analysis on the most recently updated right-side stored inflection point coordinates in the right-side stored inflection point coordinate set to determine whether the right-side stored inflection point coordinates meet the tracking conditions.

[0040] In step S103, each time the left-side stored inflection point coordinates and the right-side stored inflection point coordinates are acquired and updated, a determination is made as to whether the currently updated set of inflection point coordinate pairs meets the tracking condition.

[0041] S104. Determine the motion mode of the crawling welding robot according to the result of whether the inflection point coordinate set stored on the left and the inflection point coordinate set stored on the right meet the tracking conditions, and control the crawling welding robot to move according to the corresponding operation mode to complete the welding of the weld.

[0042] In step S104, if the stored inflection point coordinates on one side meet the tracking condition, or the stored inflection point coordinates on both sides meet the tracking condition, the inflection point tracking mode is run. If the stored inflection point coordinates on both sides do not meet the tracking condition, or the inflection points on both sides are not identified, the parallel attitude mode is run.

[0043] The control method of a crawling welding robot provided in the embodiment of the present application can analyze the spatiotemporal continuity of the inflection point of the weld, determine whether the inflection point is stable, and select a stable inflection point for tracking. If the inflection points are all unstable, the parallel posture mode is switched to avoid using inaccurate inflection points for tracking, thereby ensuring the accuracy of the weld.

[0044] In one embodiment of the present application, for each weld laser image, the left-side stored inflection point coordinates or the right-side stored inflection point coordinates are determined in the following manner:

[0045] The weld seam laser image is preprocessed, which includes removing arc light, spatter interference, etc. in the image.

[0046] The preprocessed weld laser image is identified to output the identified left candidate inflection point coordinates and right candidate inflection point coordinates. There are many ways to detect the inflection point of the weld laser image, such as the inflection point of the laser center point curve, the intersection of the straight line, etc. In general, the weld is V-shaped, and each identification can correspond to the identification of two inflection points on the left and right (including the inflection point coordinates). If the image quality is poor, there may be multiple inflection point coordinates (left candidate inflection point coordinates and right candidate inflection point coordinates).

[0047] For any candidate inflection point coordinates of the left candidate inflection point coordinates and the right candidate inflection point coordinates, when the number of such candidate inflection point coordinates is one, the candidate inflection point coordinates is used as the corresponding left stored inflection point coordinates or right stored inflection point coordinates; for any candidate inflection point coordinates of the left candidate inflection point coordinates and the right candidate inflection point coordinates, when the number of such candidate inflection point coordinates is multiple, the corresponding left stored inflection point coordinates or right stored inflection point coordinates are screened out from the multiple candidate inflection point coordinates. The inflection point identified based on the weld laser image is used as the candidate inflection point.

[0048] When there are multiple left candidate inflection point coordinates or multiple right candidate inflection point coordinates, the corresponding left stored inflection point coordinates or right stored inflection point coordinates are screened out from the multiple candidate inflection point coordinates in the following manner:

[0049] For each candidate inflection point coordinate among the multiple candidate inflection point coordinates, calculate the distance value between the candidate inflection point coordinate and the previous stored inflection point coordinate in the set where the candidate inflection point coordinate is located. According to the size of each distance value, determine that the candidate inflection point coordinate corresponding to the target distance value is the corresponding left stored inflection point coordinate or right stored inflection point coordinate.

[0050] The crawling welding robot determines the rule of updating the weld inflection point coordinates according to the time distribution of the weld inflection point coordinates, and records the weld inflection point coordinates of the latest N moments for analysis, including storing the inflection point coordinates on the left and storing the inflection point coordinates on the right. That is, the storage space of the inflection point robot stores the latest N inflection point coordinate pairs.

[0051] In one embodiment of the present application, the operation mode includes an inflection point tracking mode and a parallel posture mode, and the motion mode of the crawling welding robot is determined by:

[0052] In the first case, when the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates do not meet the tracking conditions, the crawling welding robot is controlled to move in parallel posture mode. When the two stored inflection point coordinates in the latest updated inflection point coordinate pair do not meet the tracking conditions, the inflection point tracking module is not used, and the parallel posture mode is switched.

[0053] like Figure 2 As shown, Figure 2 A flowchart of the steps of tracking condition analysis provided by an embodiment of the present application. Specifically, for the inflection point coordinates stored on the left or the inflection point coordinates stored on the right, determine whether the tracking condition is met in the following manner:

[0054] S201 , determining the continuity result between the most recently updated stored inflection point coordinate and the last target inflection point coordinate in the target inflection point coordinate set on the same side.

[0055] S202, if the result of the continuity is yes, determining that the left-side stored inflection point coordinates or the right-side stored inflection point coordinates meet the tracking condition;

[0056] S203: If the result of the continuity is no, it is determined that the left-side stored inflection point coordinates or the right-side stored inflection point coordinates do not meet the tracking condition.

[0057] The target inflection point coordinate set is one of a left target inflection point coordinate set and a right target inflection point coordinate set, and the result of the continuity between any two adjacent target inflection point coordinates in the target inflection point coordinate set is yes.

[0058] The principle of the inflection point tracking mode is to classify all the inflection point coordinates in the left stored inflection point coordinate set and the right stored inflection point coordinate set, and screen out the inflection points with continuity to form the left target inflection point coordinate set and the right target inflection point coordinate set, and based on each inflection point coordinate pair in the left target inflection point coordinate set and the right target inflection point coordinate set, predict the midpoint coordinates of the weld to guide the crawling welding robot to control the position of the welding gun. Here, the acquisition moments corresponding to the adjacent target inflection points in the left target inflection point coordinate set and the right target inflection point coordinate set may be discontinuous.

[0059] like Figure 3 As shown, in step S201, the step of determining the continuity result between the latest updated stored inflection point coordinate and the last target inflection point coordinate in the target inflection point coordinate set on the same side specifically includes:

[0060] S2020, determining the first coordinate value of the most recently updated stored inflection point coordinate in the X-axis direction, and determining the second coordinate value of the last target inflection point coordinate in the corresponding target inflection point coordinate set in the X-axis direction;

[0061] S2022, comparing the difference between the second coordinate value and the first coordinate value with a preset difference;

[0062] S2024, if the difference is greater than the preset difference, determining the result of the continuity between the current two inflection point coordinates is no;

[0063] S2026. If the difference is not greater than the preset difference, the result of determining the continuity between the current two inflection point coordinates is yes.

[0064] Exemplarily, the Nth left-side stored inflection point coordinate P is calculated A (X1, Y1) and the Nth left target turning point coordinate P B The distance value S of (X2, Y2) on the X axis = |X1-X2|. If S ≤ the preset difference value T, then P A With P B Discontinuous. A It is also impossible to filter into the left target turning point set, and at this time the crawling welding robot is not suitable for executing the turning point tracking mode.

[0065] The X-axis here is the direction perpendicular to the weld on the weld laser image. In different application scenarios, the distance value on the Y-axis can also be calculated, which needs to be determined according to the shooting method of the weld laser image.

[0066] In the second case, when one of the most recently updated stored inflection point coordinates on the left and the most recently updated stored inflection point coordinates on the right meets the tracking condition, the corresponding optimized inflection point coordinates on the other side are determined according to the stored inflection point coordinates that meet the tracking condition, and the midpoint coordinates of the weld are determined according to the stored inflection point coordinates that meet the tracking condition and the corresponding optimized inflection point coordinates, so as to control the crawling welding robot to move in the inflection point tracking mode.

[0067] Specifically, the preset width value is the average width value of the weld, and the step of determining the optimized inflection point coordinates corresponding to the other side according to the stored inflection point coordinates that meet the tracking conditions specifically includes:

[0068] When the right-side stored inflection point coordinates meet the tracking conditions, the difference between the third coordinate value of the right-side stored inflection point coordinates in the X-axis direction and the preset width value is used as the fourth coordinate value of the left-side optimized inflection point coordinates in the X-axis direction, wherein the coordinate value of the left-side optimized inflection point coordinates in the Y-axis direction is the same as the coordinate value of the right-side stored inflection point coordinates in the Y-axis direction.

[0069] When the left-side stored inflection point coordinates meet the tracking conditions, the sum of the fifth coordinate value of the left-side stored inflection point coordinates in the X-axis direction and the preset width value is used as the sixth coordinate value of the right-side optimized inflection point coordinates in the X-axis direction, wherein the coordinate value of the right-side optimized inflection point coordinates in the Y-axis direction is the same as the coordinate value of the left-side stored inflection point coordinates in the Y-axis direction.

[0070] The calculation formula here can be expressed as:

[0071]

[0072]

[0073] Where W is the average width of the weld, is the fourth coordinate value, x R is the third coordinate value, is the sixth coordinate value, x L is the fifth coordinate value.

[0074] In the third case, when the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates both meet the tracking conditions, the weld midpoint coordinates are determined based on the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates to control the crawling welding robot to move in the inflection point tracking mode.

[0075] If the most recently updated inflection point coordinates are aligned and the inflection points on both the left and right sides meet the tracking conditions, the crawling welding robot can be controlled to move in the inflection point tracking mode. If only the inflection point on one side meets the tracking conditions, the inflection point coordinates on the other side can be predicted based on the inflection point coordinates on the side that meets the tracking conditions to determine the midpoint coordinates of the weld and input them into the PID algorithm for tracking.

[0076] In one embodiment of the present application, the invention further includes analyzing the inflection point coordinate set stored on the left side and the inflection point coordinate set stored on the right side respectively to determine whether there is fluctuation in each set.

[0077] When it is determined that one of the sets has fluctuations, if the crawling welding robot is running in the inflection point tracking mode at this time, the specific way to change the inflection point tracking mode is to single-side inflection point tracking. That is, the coordinates of the midpoint of the weld are determined by the inflection point coordinates on the side without fluctuations to guide the crawling welding robot to control the position of the welding gun.

[0078] When it is determined that there is no fluctuation in both sets, if the crawling welding robot is running in the parallel posture mode at this time, the crawling welding robot can be controlled to switch back to the inflection point tracking mode, specifically, the bilateral inflection point tracking.

[0079] Here, by performing continuity analysis on the stored inflection point coordinate set retained in the storage space, the operation mode of the crawling welding robot can be switched instantly according to the identification of the inflection point, thereby ensuring the accuracy of welding.

[0080] Specifically, whether each set has fluctuation is determined by the following method:

[0081] For each set in the left-side stored inflection point coordinate set or the right-side stored inflection point coordinate set, determine the continuity result corresponding to each stored inflection point coordinate in the set;

[0082] If the number of negative results of the corresponding continuity in the set is greater than a preset number, it is determined that there is fluctuation in the set.

[0083] The preset quantity here can be For the analysis of the continuity of the stored inflection point coordinates, reference may be made to the analysis results of steps S2020 to S2026.

[0084] like Figure 4 As shown, Figure 4 A structural schematic diagram of a control system of a crawling welding robot provided in an embodiment of the present application. In one embodiment of the present application, a control system of a crawling welding robot is also provided, including a weld inflection point detection unit, an inflection point analysis and processing unit, and a crawling machine tracking control unit.

[0085] The weld inflection point detection unit includes an image preprocessing part and an inflection point detection part. The image preprocessing part preprocesses the weld laser image to remove arc light and spatter interference in the image. The inflection point detection part defines rules to detect the inflection point of the weld laser image. The defined rules include the inflection point of the laser center point curve, the intersection of the straight line, etc.

[0086] The inflection point analysis and processing unit analyzes and processes the candidate inflection points obtained by the inflection point detection unit by defining rules, including selecting inflection points according to the spatiotemporal information of the inflection points and updating the coordinates of the weld inflection points.

[0087] The rule for selecting the inflection point is divided into two cases: before arc tracking and after arc tracking.

[0088] Before arc starting tracking, the crawler is stationary. According to the similarity rule, the weld inflection points are determined from the candidate inflection points. The similarity rule here is that if there are two detected candidate inflection points, they respectively correspond to the left and right inflection points of the weld; if there are more than two candidate inflection points, then according to the spatial distance relationship with the historical weld inflection points, the nearest inflection point is assigned as the weld inflection point. The rule for updating the coordinates of the weld inflection points is to determine the updated coordinates of the weld inflection points at the current moment according to the distribution of the weld inflection point coordinates in time, and transmit the updated coordinates of the weld inflection points to the tracking control unit of the crawler.

[0089] The rule for determining the updated coordinates of the weld inflection points according to the time distribution of the weld inflection point coordinates is to record and analyze the weld inflection point coordinates of the nearest N moments, including the left inflection point and the right inflection point. The weld width and the average width are obtained from the left and right inflection points. The N inflection point coordinates recorded are divided into two categories:

[0090] The first category is continuously stable inflection points, and the inflection points therein all satisfy |x i -x i-1 |<T, and its length is known. The second category is inflection points other than this. Similarly, according to |x i -x i-1 |<T, the continuity of the inflection point coordinates of this type is analyzed to determine whether there are new continuously stable inflection points and the inflection point length.

[0091] According to the analysis of the inflection points, the inflection point coordinates at the current moment are updated, including: if the inflection points on both sides are continuous, the inflection point coordinates remain unchanged; if the inflection points on one side are continuous and the inflection points on the other side are not continuous, then the inflection point coordinates of the discontinuous side are updated according to the average width; if there are new continuously stable inflection points among the second-category inflection points on the discontinuous side, a re-tracking signal is obtained.

[0092] The tracking control unit, according to the set control strategy, if the inflection points on one side are continuous and there are fluctuations on the other side, then according to the inflection point coordinates on the continuous side, PID tracking is restarted, that is, tracking the single-side stable inflection points; if there are fluctuations in the inflection points on both sides, the attitude of the crawler is adjusted to be parallel to the weld, and the crawler is controlled to crawl straight; if a re-tracking signal is received, PID tracking is restarted.

[0093] Based on the same inventive concept, in the embodiments of the present application, a control device for a crawler welding robot corresponding to the control method of the crawler welding robot is also provided. Since the principle of solving problems by the device in the embodiments of the present application is similar to the control method of the above-mentioned crawler welding robot in the embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0094] Please refer to Figure 5 , Figure 5 , which is a schematic structural diagram of the control device for the crawler welding robot provided by the embodiments of the present application. The control device 400 includes:

[0095] An acquisition module 410 is used to acquire a weld laser image at a preset interval;

[0096] An updating module 420 is used to determine the left-side stored inflection point coordinates and the right-side stored inflection point coordinates for each weld seam laser image acquired based on the weld seam laser image, and update the left-side stored inflection point coordinate set and the right-side stored inflection point coordinate set respectively;

[0097] An analysis module 430 is used to perform a coordinate point stability analysis on the most recently updated left-side stored inflection point coordinates in the left-side stored inflection point coordinate set to determine whether the left-side stored inflection point coordinates meet the tracking condition, and to perform a coordinate point stability analysis on the most recently updated right-side stored inflection point coordinates in the right-side stored inflection point coordinate set to determine whether the right-side stored inflection point coordinates meet the tracking condition;

[0098] The mode control module 440 determines the movement mode of the crawling welding robot according to whether the inflection point coordinate set stored on the left and the inflection point coordinate set stored on the right meet the tracking conditions, and controls the crawling welding robot to move according to the corresponding operation mode to complete the welding of the weld.

[0099] In a preferred embodiment, the operating mode includes an inflection point tracking mode and a parallel posture mode, and the mode control module 440 determines the motion mode of the crawling welding robot in the following manner: when the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates do not meet the tracking conditions, the crawling welding robot is controlled to move in the parallel posture mode; when one of the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates meets the tracking conditions, the corresponding optimized inflection point coordinates on the other side are determined according to the stored inflection point coordinates that meet the tracking conditions, and the midpoint coordinates of the weld are determined according to the stored inflection point coordinates that meet the tracking conditions and the corresponding optimized inflection point coordinates, so as to control the crawling welding robot to move in the inflection point tracking mode; when the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates both meet the tracking conditions, the midpoint coordinates of the weld are determined according to the latest updated left-side stored inflection point coordinates and the latest updated right-side stored inflection point coordinates, so as to control the crawling welding robot to move in the inflection point tracking mode.

[0100] In a preferred embodiment, for the left-side stored inflection point coordinates or the right-side stored inflection point coordinates, the analysis module 430 determines whether the tracking condition is met in the following manner: determine the continuity result between the most recently updated stored inflection point coordinates and the last target inflection point coordinate in the target inflection point coordinate set on the same side; if the continuity result is yes, determine that the left-side stored inflection point coordinates or the right-side stored inflection point coordinates meet the tracking condition; if the continuity result is no, determine that the left-side stored inflection point coordinates or the right-side stored inflection point coordinates do not meet the tracking condition; wherein, the target inflection point coordinate set is one of the left-side target inflection point coordinate set and the right-side target inflection point coordinate set, and the continuity result between any two adjacent target inflection point coordinates in the target inflection point coordinate set is yes.

[0101] In a preferred embodiment, the analysis module 430 is specifically used to determine the first coordinate value of the most recently updated stored inflection point coordinate in the X-axis direction, and to determine the second coordinate value of the last target inflection point coordinate in the corresponding target inflection point coordinate set in the X-axis direction; to compare the difference between the second coordinate value and the first coordinate value with the preset difference; if the difference is greater than the preset difference, then determining the result of the continuity between the two current inflection point coordinates is no; if the difference is not greater than the preset difference, then determining the result of the continuity between the two current inflection point coordinates is yes.

[0102] In a preferred embodiment, the preset width value is the average width value of the weld, and also includes a correction module for determining the corresponding optimized inflection point coordinates on the other side based on the stored inflection point coordinates that meet the tracking conditions, specifically including: when the right-side stored inflection point coordinates meet the tracking conditions, the difference between the third coordinate value of the right-side stored inflection point coordinates in the X-axis direction and the preset width value is used as the fourth coordinate value of the left-side optimized inflection point coordinates in the X-axis direction, wherein the coordinate value of the left-side optimized inflection point coordinates in the Y-axis direction is the same as the coordinate value of the right-side stored inflection point coordinates in the Y-axis direction; when the left-side stored inflection point coordinates meet the tracking conditions, the sum of the fifth coordinate value of the left-side stored inflection point coordinates in the X-axis direction and the preset width value is used as the sixth coordinate value of the right-side optimized inflection point coordinates in the X-axis direction, wherein the coordinate value of the right-side optimized inflection point coordinates in the Y-axis direction is the same as the coordinate value of the left-side stored inflection point coordinates in the Y-axis direction.

[0103] In a preferred embodiment, for each weld laser image, the update module 420 determines the left-side stored inflection point coordinates or the right-side stored inflection point coordinates by: performing image preprocessing on the weld laser image; identifying the preprocessed weld laser image to output the identified left-side candidate inflection point coordinates and the right-side candidate inflection point coordinates; for any one of the left-side candidate inflection point coordinates and the right-side candidate inflection point coordinates, when the number of such candidate inflection point coordinates is one, then the candidate inflection point coordinate is used as the corresponding left-side stored inflection point coordinates or the right-side stored inflection point coordinates; for any one of the left-side candidate inflection point coordinates and the right-side candidate inflection point coordinates, when the number of such candidate inflection point coordinates is multiple, then the corresponding left-side stored inflection point coordinates or the right-side stored inflection point coordinates are screened out from the multiple candidate inflection point coordinates.

[0104] In a preferred embodiment, the update module 420 filters out the corresponding left-side stored inflection point coordinates or the right-side stored inflection point coordinates from multiple candidate inflection point coordinates in the following manner: for each candidate inflection point coordinate among the multiple candidate inflection point coordinates, calculate the distance value between the candidate inflection point coordinate and the previous stored inflection point coordinate in the set where the candidate inflection point coordinate is located; and according to the size of each distance value, determine that the candidate inflection point coordinate corresponding to the target distance value is the corresponding left-side stored inflection point coordinate or the right-side stored inflection point coordinate.

[0105] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown in , the electronic device 500 includes a processor 510 , a memory 520 and a bus 530 .

[0106] The memory 520 stores machine-readable instructions executable by the processor 510. When the electronic device 500 is running, the processor 510 communicates with the memory 520 via the bus 530. When the machine-readable instructions are executed by the processor 510, the above-mentioned Figure 1 The steps of the control method of the crawling welding robot in the method embodiment shown and the specific implementation method can be found in the method embodiment, which will not be repeated here.

[0107] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The steps of the control method of the crawling welding robot in the method embodiment shown and the specific implementation method can be found in the method embodiment, which will not be repeated here.

[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0109] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0112] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0113] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A control method for a crawling welding robot, characterized in that: The method comprises: Acquire weld seam laser images at preset intervals; For each weld seam laser image acquired, based on the weld seam laser image, the left-side stored inflection point coordinates and the right-side stored inflection point coordinates are determined, and updated in the left-side stored inflection point coordinate set and the right-side stored inflection point coordinate set respectively; Performing a coordinate point stability analysis on the most recently updated left-side stored inflection point coordinates in the left-side stored inflection point coordinate set to determine whether the left-side stored inflection point coordinates meet the tracking condition, and performing a coordinate point stability analysis on the most recently updated right-side stored inflection point coordinates in the right-side stored inflection point coordinate set to determine whether the right-side stored inflection point coordinates meet the tracking condition; According to the result of determining whether the tracking condition is met, the movement mode of the crawling welding robot is determined, and the crawling welding robot is controlled to move according to the corresponding operation mode to complete the welding of the weld.

2. The method according to claim 1, wherein the operation modes include an inflection point tracking mode and a parallel attitude mode, wherein: The motion mode of the crawling welding robot is determined by: When the most recently updated left-side stored inflection point coordinates and the most recently updated right-side stored inflection point coordinates do not satisfy the tracking condition, the crawling welding robot is controlled to move in a parallel posture mode; When one of the most recently updated left-side stored inflection point coordinates and the most recently updated right-side stored inflection point coordinates meets the tracking condition, the optimized inflection point coordinates corresponding to the other side are determined according to the stored inflection point coordinates that meet the tracking condition, and the midpoint coordinates of the weld are determined according to the stored inflection point coordinates that meet the tracking condition and the corresponding optimized inflection point coordinates, so as to control the crawling welding robot to move in an inflection point tracking mode; When the most recently updated left-side stored inflection point coordinates and the most recently updated right-side stored inflection point coordinates both meet the tracking conditions, the weld midpoint coordinates are determined based on the most recently updated left-side stored inflection point coordinates and the most recently updated right-side stored inflection point coordinates to control the crawling welding robot to move in an inflection point tracking mode.

3. The method according to claim 2, characterized in that For the left-side stored inflection point coordinates or the right-side stored inflection point coordinates, whether the tracking condition is met is determined in the following way: Determine the result of the continuity between the most recently updated stored inflection point coordinate and the last target inflection point coordinate in the target inflection point coordinate set on the same side; If the result of the continuity is yes, determining that the left-side stored inflection point coordinates or the right-side stored inflection point coordinates meet the tracking condition; If the result of the continuity is no, it is determined that the left-side stored inflection point coordinates or the right-side stored inflection point coordinates do not meet the tracking condition; The target inflection point coordinate set is one of a left target inflection point coordinate set and a right target inflection point coordinate set, and the result of the continuity between any two adjacent target inflection point coordinates in the target inflection point coordinate set is yes.

4. The method according to claim 3, characterized in that The step of determining the result of the continuity between the most recently updated stored inflection point coordinate and the last target inflection point coordinate in the target inflection point coordinate set on the same side specifically includes: Determine the first coordinate value of the most recently updated stored inflection point coordinate in the X-axis direction, and determine the second coordinate value of the last target inflection point coordinate in the corresponding target inflection point coordinate set in the X-axis direction; comparing a difference between the second coordinate value and the first coordinate value with a preset difference; If the difference is greater than the preset difference, determining the result of the continuity between the current two inflection point coordinates is no; If the difference is not greater than the preset difference, the result of determining the continuity between the current two inflection point coordinates is yes.

5. The method according to claim 2, characterized in that: The preset width value is the average width value of the weld, and the step of determining the optimized inflection point coordinates corresponding to the other side according to the stored inflection point coordinates that meet the tracking conditions specifically includes: When the right-side stored inflection point coordinates meet the tracking condition, the difference between the third coordinate value of the right-side stored inflection point coordinates in the X-axis direction and the preset width value is used as the fourth coordinate value of the left-side optimized inflection point coordinates in the X-axis direction, wherein the coordinate value of the left-side optimized inflection point coordinates in the Y-axis direction is the same as the coordinate value of the right-side stored inflection point coordinates in the Y-axis direction; When the left-side stored inflection point coordinates meet the tracking conditions, the sum of the fifth coordinate value of the left-side stored inflection point coordinates in the X-axis direction and the preset width value is used as the sixth coordinate value of the right-side optimized inflection point coordinates in the X-axis direction, wherein the coordinate value of the right-side optimized inflection point coordinates in the Y-axis direction is the same as the coordinate value of the left-side stored inflection point coordinates in the Y-axis direction.

6. The method according to claim 1, characterized in that For each weld seam laser image, the left-side stored inflection point coordinates or the right-side stored inflection point coordinates are determined in the following manner: Performing image preprocessing on the weld laser image; Recognize the preprocessed weld laser image to output the identified left candidate inflection point coordinates and right candidate inflection point coordinates; For any one of the left candidate inflection point coordinates and the right candidate inflection point coordinates, when the number of the candidate inflection point coordinates is one, the candidate inflection point coordinate is used as the corresponding left stored inflection point coordinate or the right stored inflection point coordinate; For any one of the left candidate inflection point coordinates and the right candidate inflection point coordinates, when the number of such candidate inflection point coordinates is multiple, the corresponding left stored inflection point coordinates or the right stored inflection point coordinates are screened out from the multiple candidate inflection point coordinates.

7. The method according to claim 6, characterized in that The corresponding left-side stored inflection point coordinates or right-side stored inflection point coordinates are filtered out from multiple candidate inflection point coordinates in the following manner: For each candidate inflection point coordinate among the plurality of candidate inflection point coordinates, calculating a distance value between the candidate inflection point coordinate and a previously stored inflection point coordinate in the set where the candidate inflection point coordinate belongs; According to the size of each distance value, the candidate inflection point coordinates corresponding to the target distance value are determined to be the corresponding left-side stored inflection point coordinates or the right-side stored inflection point coordinates.

8. A control device for a crawling welding robot, characterized in that: The device comprises: An acquisition module, used for acquiring weld seam laser images at preset intervals; An updating module is used to determine the left-side stored inflection point coordinates and the right-side stored inflection point coordinates for each weld seam laser image acquired based on the weld seam laser image, and update them in the left-side stored inflection point coordinate set and the right-side stored inflection point coordinate set respectively; An analysis module, configured to perform a coordinate point stability analysis on the most recently updated left-side stored inflection point coordinates in the left-side stored inflection point coordinate set to determine whether the left-side stored inflection point coordinates meet the tracking condition, and to perform a coordinate point stability analysis on the most recently updated right-side stored inflection point coordinates in the right-side stored inflection point coordinate set to determine whether the right-side stored inflection point coordinates meet the tracking condition; The mode control module determines the movement mode of the crawling welding robot according to the result of determining whether the tracking condition is met, and controls the crawling welding robot to move according to the corresponding operation mode to complete the welding of the weld.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the control method of the crawling welding robot as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the control method of the crawling welding robot as claimed in any one of claims 1 to 7 are executed.

Images