Field welding system and control method thereof

Abstract

The invention relates to a field welding system and a control method thereof.The field welding system is used for conducting welding machining on the interior of a workpiece arranged in the field and comprises a moving module, a cleaning module, a welding module, a wire feeding module and a guiding module, and the cleaning module, the welding module, the wire feeding module and the guiding module are arranged on the moving module; the control module and the image acquisition assembly are arranged on the moving module; the mobile module takes one end as the front end and the other end as the rear end; the cleaning module comprises a plurality of obstacle removing brush mechanisms; the control module is used for controlling the moving module, the sweeping module, the welding module, the wire feeding module and the guiding module to conduct welding machining. According to the device, image collection is conducted on the environment in the workpiece through the image collection assembly, the number of impurities in the workpiece is determined according to the collected image, the impurities are swept through the sweeping module, then the situation that the impurities affect the moving stability of the moving module is avoided, the situation that the impurities affect follow-up welding is avoided, and the welding quality is improved.

Description

Technical Field

[0001] The present application relates to the field of welding technology, and in particular to a field welding system and a control method thereof. Background Art

[0002] In the welding production of large bridges, pressure vessels, oil and gas pipelines, etc., since many large workpieces are difficult to transport to factories for welding, welding construction needs to be carried out in a field environment.

[0003] Due to direct contact with the outside world, the field welding process is likely to be affected by adverse weather conditions such as wind, sand, rain, snow, and hail. For example, wind and sand may cause sand, gravel, and dust to be brought into the welding area, which will have an extremely adverse effect on welding accuracy, weld structure, and mechanical properties. Faced with this practical problem, in actual production, we can only use temporary sheds or curtains to prevent wind, sand, rain, snow, hail, etc. from polluting the welding area, but this will increase the investment in welding operations and reduce production efficiency. Summary of the invention

[0004] In order to solve the problems existing in the above-mentioned prior art, the purpose of the present application is to provide a field welding system and a control method thereof. The field welding system has a control module and an image acquisition component, which acquires images of the environment inside the workpiece through the image acquisition component, determines the amount of impurities such as sand, gravel and dust inside the workpiece according to the acquired images, and cleans the impurities through the cleaning module, thereby preventing the impurities such as sand, gravel and dust from affecting the moving stability of the moving module and preventing the impurities such as sand, gravel and dust from affecting subsequent welding, thereby improving the welding accuracy and quality.

[0005] The field welding system described in the present application is used for welding the inside of a workpiece arranged in the field, comprising a mobile module, and a cleaning module, a welding module, a wire feeding module and a guide module arranged on the mobile module, and also comprising a control module and an image acquisition component, wherein the control module and the image acquisition component are both arranged on the mobile module;

[0006] The mobile module has one end as the front end and the other end as the rear end;

[0007] The cleaning module includes a plurality of obstacle-clearing brush mechanisms;

[0008] The control module is used to control the moving module, the cleaning module, the welding module, the wire feeding module and the guiding module to perform welding processing.

[0009] The present application also proposes a field welding control method, which uses the field welding system as described above, and includes the following steps:

[0010] S1. Select and set welding process parameters according to the first parameter information of the required welding workpiece and the second parameter information of the welding wire used;

[0011] S2. According to the required internal width of the workpiece to be welded, the guide module is adjusted so that the guide module fits the inside of the workpiece;

[0012] S3, setting an image acquisition component on the mobile module, collecting image data inside the workpiece through the image acquisition component, and selecting the real-time moving speed of the mobile module according to the environment inside the workpiece;

[0013] S4, constructing a field weld recognition model, the mobile module moves to the required welding position, the image acquisition component obtains a real-time weld image, and recognizes the real-time weld image through the field weld recognition model to obtain a real-time weld type;

[0014] S5. Dynamically adjust the welding process parameters according to the real-time weld type, and perform welding processing on the required welding position.

[0015] Preferably, the step S1 specifically includes:

[0016] The first parameter information includes workpiece material type and workpiece thickness;

[0017] The second parameter information includes the theoretical deposition efficiency of the welding wire;

[0018] The welding process parameters include welding current and welding speed;

[0019] Obtain the workpiece material type and workpiece thickness H of the required welding workpiece, and select the corresponding workpiece material welding coefficient K according to the workpiece material type 1 , obtain the theoretical deposition efficiency η of the welding wire used;

[0020] Calculation of welding current I for initial setting 0 and welding speed V 0 , the formula is as follows:

[0021]

[0022] V 0 =V L *α 2 *K 1 *H*η

[0023] Among them, I L Indicates the theoretical basic welding current; α 1 Indicates the current adjustment factor; V 0 Indicates the theoretical basic welding speed; α 2Indicates the speed adjustment factor.

[0024] Preferably, the step S1 further includes:

[0025] The workpiece material types include carbon steel, stainless steel and alloy materials, and the workpiece material welding coefficient K 1 The values ​​include:

[0026] If the workpiece material type is carbon steel, the workpiece material welding coefficient K 1 The value ranges from 1.0 to 1.3;

[0027] If the workpiece material type is stainless steel, the workpiece material welding coefficient K 1 The value ranges from 1.4 to 1.7;

[0028] If the workpiece material type is alloy material, the workpiece material welding coefficient K 1 The value ranges from 1.8 to 2.0.

[0029] Preferably, the step S2 specifically includes:

[0030] The guide module comprises at least two groups of guide wheel assemblies, each two groups of guide wheel assemblies are arranged on the mobile module at intervals, and the same group of guide wheel assemblies comprises two guide wheel mechanisms, which are arranged on two sides of the mobile module opposite to each other, and the guide wheel mechanisms are slidably connected to the mobile module so that the guide wheel mechanisms slide away from or close to the mobile module;

[0031] Obtain the required inner width dimension B of the welding workpiece, and obtain the straight-line distance L between the end edges of two guide wheel mechanisms in each group of the guide wheel assemblies away from one end of the moving module;

[0032] If L = B, it is determined that the guidance requirements are met and the subsequent processing continues;

[0033] If L<B, it is determined that the guiding requirement is not met, and the two guiding wheel mechanisms of the same group are driven to move away from the moving module until L=B is met;

[0034] If L>B, it is determined that the guiding requirement is not met, and the two guiding wheel mechanisms in the same group are driven to move toward the moving module until L=B is met.

[0035] Preferably, the step S3 specifically includes:

[0036] The front end of the mobile module moves forward toward the inside of the workpiece, and the image acquisition component acquires images of the path along which the mobile module moves in real time to obtain a path image;

[0037] Performing grayscale processing and noise reduction processing on the path image to obtain a processed first path real-time image;

[0038] Using a contour detection algorithm to identify the impurity contours of the first path real-time image, counting the number of the impurity contours to obtain the number of impurities, and calculating the impurity area ratio and impurity density;

[0039] A movement strategy and a cleaning strategy are executed according to the impurity quantity, the impurity area ratio and the impurity density.

[0040] Preferably, the mobile strategy includes:

[0041] The initial moving speed of the moving module is preset to V Y0 , calculate the movement influence coefficient W according to the impurity number N, the impurity area proportion P and the impurity density M:

[0042]

[0043] Among them, N Lmax Indicates the maximum threshold of the preset impurity quantity; P Lmax Indicates the maximum threshold of the preset impurity area ratio; M Lmax Indicates the preset maximum threshold of impurity density; ω 1 ,ω 2 and ω 3 Are all weight coefficients, satisfying ω 1 +ω 2 +ω 3 =1;

[0044] Select the speed adjustment coefficient Q according to the movement influence coefficient W, and calculate the real-time movement speed V required by the movement module YS :

[0045] V YS =V Y0 *Q

[0046] If W≤0.3, the speed adjustment coefficient Q is Q=1;

[0047] If 0.3<W≤0.5, the value of the speed adjustment coefficient Q is Q=0.8;

[0048] If 0.5<W≤0.8, the value of the speed adjustment coefficient Q is Q=0.6;

[0049] If W>0.8, the value of the speed adjustment coefficient Q is Q=0.4.

[0050] Preferably, the cleaning strategy includes:

[0051] Determine the level of influence of impurities on the stability of the mobile module according to the impurity quantity N, the impurity area proportion P and the impurity density M;

[0052] If N≤N E , P≤P E and M≤M E If all of the above conditions are satisfied, the stability impact level is judged to be low, and the initial state of the cleaning module is maintained;

[0053] If N≤N E , P≤P E and M≤M E If any two of the above conditions are not satisfied, the stability impact level is determined to be medium, and the obstacle-clearing brush mechanism at the front end of the mobile module is started once, so that the obstacle-clearing brush mechanism at the front end of the mobile module rotates to clean impurities;

[0054] If N≤N E , P≤P E and M≤M E If none of the above conditions are satisfied, the stability impact level is judged to be high, and the obstacle-clearing brush mechanism at the front end of the mobile module is started at least twice, so that the obstacle-clearing brush mechanism at the front end of the mobile module rotates to clean impurities;

[0055] Among them, N E Indicates the preset impurity quantity safety threshold; P E Indicates the preset impurity area ratio safety threshold; M E Indicates the preset impurity density safety threshold.

[0056] Preferably, the step S4 specifically includes:

[0057] Acquire historical weld image data and corresponding weld type label data, wherein the weld type labels of the weld type label data include butt welds, fillet welds, T-welds, lap welds, plug welds, slot welds and other welds;

[0058] Performing grayscale processing, denoising processing, and image enhancement processing on the historical weld image data to obtain processed first historical weld image data;

[0059] The Canny algorithm and the gray-level co-occurrence matrix method are used to extract edge features, geometric features and texture features of the first historical weld image data to obtain a weld feature vector;

[0060] A support vector machine is used, with the weld feature vector as input and the weld type label as output, to perform model training and testing on the historical weld image data and the weld type label data, so as to obtain a trained field weld recognition model;

[0061] The mobile module moves to the desired welding position, the image acquisition component acquires a real-time weld image of the desired welding position, and inputs the real-time weld image into the field weld recognition model to identify the real-time weld type of the welding position.

[0062] Preferably, the step S5 specifically includes:

[0063] The welding adjustment coefficient G is selected according to the real-time weld type, and the welding current I is adjusted according to the welding adjustment coefficient P. 0 and the welding speed V 0 Adjust to get the actual welding current I after adjustment HS and actual welding speed V HS , the adjustment method is as follows:

[0064] I HS =I 0 *P

[0065] V HS =V 0 *P

[0066] If the weld type is a butt weld, the welding adjustment coefficient G is 1.1;

[0067] If the weld type is a fillet weld, the welding adjustment coefficient G is 1.2;

[0068] If the weld type is a T-shaped weld, the welding adjustment coefficient G is 0.9;

[0069] If the weld type is a lap weld, the welding adjustment coefficient G is 0.8;

[0070] If the weld type is a plug weld, the welding adjustment coefficient G is 1.5;

[0071] If the weld type is a slot weld, the welding adjustment coefficient G is 1.3;

[0072] If the weld type is other welds, the welding adjustment coefficient G is 1.

[0073] The advantages of a field welding system and control method thereof described in the present application are:

[0074] 1. A field welding system of the present application has a control module and an image acquisition component, which acquires images of the environment inside the workpiece through the image acquisition component, determines the amount of impurities such as sand, gravel and dust inside the workpiece based on the acquired images, and cleans the impurities through the cleaning module, thereby preventing the impurities such as sand, gravel and dust from affecting the moving stability of the moving module, and preventing the impurities such as sand, gravel and dust from affecting subsequent welding, thereby improving the welding accuracy and quality; the moving module, cleaning module, welding module, wire feeding module, guide module and other functional modules are integrated into one, and each module works together under the unified coordination of the control module, from cleaning the inside of the workpiece, position guidance to welding implementation, and welding wire transportation, to achieve a one-stop welding operation process, reduce the connection time between processes, and greatly improve welding efficiency; the wire feeding module can transport welding wire to the welding module, ensure the continuity of the welding process, and improve welding efficiency; the guide module can be adjusted according to the shape and size of the inside of the workpiece to achieve precise guidance, so that the welding system can better adapt to the welding requirements of workpieces of different sizes.

[0075] 2. A field welding control method of the present application selects and sets welding process parameters according to the first parameter information of the welding workpiece and the second parameter information of the welding wire, so that the welding process can be matched with the specific workpiece and the welding wire, thereby ensuring the welding quality and improving the stability and reliability of welding; the guide module is adjusted according to the internal width size of the workpiece so that the guide module is adapted to the inside of the workpiece, which helps the mobile module to move accurately inside the workpiece, ensure the accuracy of the welding path, and improve the welding accuracy; by setting an image acquisition component on the mobile module to collect the internal image data of the workpiece, and selecting the real-time moving speed of the mobile module according to the internal environment of the workpiece, the moving speed can be adapted to the actual welding environment, avoiding the influence of the welding quality due to too fast or too slow speed, and improving the efficiency and quality of welding; constructing a field weld recognition model, which can accurately identify the weld type in the real-time weld image, provide a basis for the subsequent adjustment of the welding process parameters, and enhance the adaptability of the welding system to different weld types; dynamically adjust the welding process parameters according to the identified weld type, realize the intelligent control of the welding process, and can adopt the optimal welding parameters for different weld types, further ensure the welding quality, and improve the success rate and efficiency of welding. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 It is a structural schematic diagram of a field welding system described in the present application;

[0077] Figure 2 It is a schematic diagram of the assembly of a mobile module and a guide module of a field welding system described in the present application;

[0078] Figure 3 It is a schematic diagram of the assembly of a mobile module and a wire feeding module of a field welding system described in the present application;

[0079] Figure 4 It is a schematic diagram of the assembly of a mobile module and a cleaning module of a field welding system described in the present application;

[0080] Figure 5 It is a schematic diagram of the assembly of a mobile module and a welding module of a field welding system described in the present application;

[0081] Figure 6 It is a first structural schematic diagram of an obstacle removal brush mechanism in a field welding system described in the present application;

[0082] Figure 7 is a second structural schematic diagram of an obstacle removal brush mechanism in a field welding system described in the present application;

[0083] Figure 8 It is a flow chart of a field welding control method described in this application.

[0084] Description of reference numerals:

[0085] 10-mobile module; 101-mobile base; 102-mobile wheel; 103-handle;

[0086] 20-cleaning module; 201-obstruction-clearing brush mechanism;

[0087] 30- welding module; 301- welding gun assembly; 3012- welding gun seat;

[0088] 40-wire feeding module; 401-wire feeding disc; 402-wire feeding wheel assembly; 403-wire feeding motor;

[0089] 50-guide module; 501-guide wheel assembly; 5011-guide wheel mechanism;

[0090] 60-control module;

[0091] 70-Probe. DETAILED DESCRIPTION

[0092] like Figure 1 - Figure 8 As shown, a field welding system described in the present application is used for welding the inside of a workpiece arranged in the field, comprising a mobile module 10, and a cleaning module 20, a welding module 30, a wire feeding module 40 and a guide module 50 arranged on the mobile module 10, and further comprising a control module 60 and an image acquisition component, wherein the control module 60 and the image acquisition component are both arranged on the mobile module 10, and the image acquisition component is connected to the control module 60 by signals;

[0093] The mobile module 10 is used to move horizontally toward the inside of the workpiece. The mobile module 10 has one end as the front end and the other end as the rear end. Probes 70 are provided on both sides of the mobile module 10. The probes 70 are used to monitor the stability of the front end movement of the mobile module 10. The mobile module 10 includes a mobile base 101, a mobile wheel 102 and a handle 103.

[0094] The moving wheels 102 are arranged on both sides of the front end and the rear end of the moving base 101. The probe 70 is used to monitor the moving wheels 102 located at the front end of the moving base 101 to monitor whether there are some impurities adhering to the moving wheels 102 to affect the subsequent movement;

[0095] The handles 103 are arranged at the front and rear ends of the mobile base 101. When there is no other power drive, the mobile base 101 can be moved by dragging or pulling it by external force;

[0096] The cleaning module 20 includes a plurality of obstacle-clearing brush mechanisms 201, which are rotatably connected to the end corners on both sides of the front end of the mobile module 10 and the end corners on both sides of the rear end of the mobile module 10, and are fixedly connected to the middle of the mobile module 10. The obstacle-clearing brush mechanism 201 used has two structures. The obstacle-clearing brush mechanism 201 arranged at the end corners on both sides of the front end of the mobile module 10 and the end corners on both sides of the rear end is a first structure obstacle-clearing brush, such as Figure 6 As shown, the obstacle-clearing brush of the first structure is in a rectangular structure, and brush heads are provided on the lower edge and both side edges;

[0097] The obstacle-clearing brush mechanism 201 disposed on both sides of the middle of the mobile module 10 is a second structure obstacle-clearing brush. Figure 7 As shown, the second structure obstacle removal brush is L-shaped, and a brush head is provided on the lower edge and one of the side edges;

[0098] The brush head of the obstacle removal brush mechanism 201 arranged at the front end of the mobile module 10 is a combination of a nylon brush and a wire brush. The two lower end corners of the obstacle removal brush mechanism 201 are wire brushes, and the rest are nylon brushes, which are used to first remove impurities such as sand, dust, etc. in front of the mobile module 10. The brush head of the obstacle removal brush mechanism 201 arranged at the rear end and the middle part of the mobile module 10 is a wire brush, which is used to remove spattered metal particles generated after welding. The spattered metal particles generated after welding are relatively hard; the cleaning module 20 can clean the impurities inside the workpiece in all directions, provide a stable moving environment for the mobile module 10 and a clean surface for subsequent welding, and reduce the influence of impurities on welding quality;

[0099] The welding module 30 is arranged in the middle of the mobile module 10 and avoids the obstacle removal brush mechanism 201. The welding module 30 includes two groups of symmetrically arranged welding gun assemblies 301, and the two groups of welding gun assemblies 301 are respectively close to the two sides of the mobile module 10; the welding module 30 also includes a welding gun seat 302, and the welding gun seat 302 is arranged on the mobile base 101. The two groups of symmetrically arranged welding gun assemblies 301 are rotatably connected to the welding gun seat 302, and the welding end of the welding gun assembly 301 extends to the outside of the mobile base 101. The welding gun assembly 301 can be rotated relative to the welding gun seat 302, so that the welding end of the welding gun assembly 301 is rotated to different height positions to weld the welds at different heights inside the workpiece;

[0100] The wire feeding module 40 is arranged near the front end of the moving module 10, and the wire feeding module 40 is connected to the welding module 30, and is used to feed the welding wire to the welding module 30; the wire feeding module 40 includes a wire feeding disc 401, a wire feeding wheel group 402 and a wire feeding motor 403, a welding wire is placed on the wire feeding disc 401, and the welding wire passes through the wire feeding wheel group 402, and then is connected to the welding gun assembly 301, and the wire feeding wheel group 402 is driven by the welding wire motor 403 to transmit the welding wire to the welding gun assembly 301;

[0101] The wire feeding module 40 has two wire feeding reels 401, two wire feeding wheel groups 402 and two wire feeding motors 403 arranged opposite to each other. One wire reel 401, one wire feeding wheel group 402 and one wire feeding motor 403 are used to provide welding wire to the same welding gun assembly 301.

[0102] The guide module 50 includes at least two sets of guide wheel assemblies 501, and each two sets of guide wheel assemblies 501 are arranged on the mobile module 10 at intervals. The same set of guide wheel assemblies 501 includes two guide wheel mechanisms 5011, which are relatively arranged on both sides of the mobile module 10, and the guide wheel mechanisms 5011 are slidably connected to the mobile module 10, so that the guide wheel mechanisms 5011 slide away from or close to the mobile module 10; this embodiment has two sets of guide wheel assemblies 501, which are composed of Figure 2 As shown, the mobile base 101 has a guide rail, the guide wheel mechanism 5011 has a slide groove adapted to the guide rail, and the guide wheel mechanism 5011 is slidably connected to the mobile base 101, so that the guide wheel mechanism 5011 slides along the guide rail away from or close to the mobile module 10, and the sliding of the guide wheel mechanism 5011 can be controlled by the control module 60;

[0103] The end of the guide wheel mechanism 5011 is a pulley, which contacts the side wall inside the workpiece. As the moving module 10 moves, the pulley slides on the side wall inside the workpiece. The two guide wheel mechanisms 5011 of the same group contact the two side walls inside the workpiece respectively, and are used to press against the side walls inside the workpiece from both sides to limit the deviation of the moving module 10.

[0104] The control module 60 is electrically connected to the moving module 10, the cleaning module 20, the welding module 30, the wire feeding module 40 and the guiding module 50 respectively, and is used to control the moving module 10, the cleaning module 20, the welding module 30, the wire feeding module 40 and the guiding module 50. The control module 60 is used to control the moving module 10, the cleaning module 20, the welding module 30, the wire feeding module 40 and the guiding module 50 to perform welding processing; the control module 60 can be controlled by a single-chip microcomputer, which has a small size, low cost and high flexibility. In other optional embodiments, the control module 60 can be controlled by a PLC (programmable logic controller);

[0105] The field welding system also includes a lighting lamp, which can be an LED lamp. The lighting lamp is arranged on the mobile module 10, and can be arranged at the front end and both sides of the mobile module 10, for illuminating the movement of the mobile module 10 and the welding process.

[0106] The present application also proposes a field welding control method, which uses the field welding system as described above and is characterized in that it includes the following steps:

[0107] S1. Select and set welding process parameters according to the first parameter information of the required welding workpiece and the second parameter information of the welding wire used;

[0108] S2. According to the required internal width of the workpiece to be welded, the guide module 50 is adjusted so that the guide module 50 is adapted to the inside of the workpiece;

[0109] S3. An image acquisition component is arranged on the mobile module 10, and image data of the interior of the workpiece is collected by the image acquisition component. The real-time moving speed of the mobile module 10 is selected according to the environment inside the workpiece. The image acquisition component can be an industrial camera, and the industrial camera is arranged on the front end and both sides of the mobile module 10 (not shown in the figure) according to the installation method of the prior art, so as to collect the path image inside the workpiece and the weld image of the required welding position;

[0110] S4, constructing a field weld recognition model, moving the mobile module 10 to the desired welding position, the image acquisition component acquiring a real-time weld image, and identifying the real-time weld image through the field weld recognition model to obtain the real-time weld type;

[0111] S5. Dynamically adjust welding process parameters according to the real-time weld type, and perform welding processing on the required welding points.

[0112] Furthermore, in this embodiment, step S1 specifically includes:

[0113] The first parameter information includes the workpiece material type and the workpiece thickness;

[0114] The second parameter information includes the theoretical deposition efficiency of the welding wire;

[0115] Welding process parameters include welding current and welding speed;

[0116] Obtain the workpiece material type and workpiece thickness H of the required welding workpiece, and select the corresponding workpiece material welding coefficient K according to the workpiece material type 1 , obtain the welding wire theoretical deposition efficiency η of the welding wire used; the welding wire theoretical deposition efficiency η can be obtained according to the factory instructions or the instruction parameter table of the welding wire used;

[0117] Calculation of welding current I for initial setting 0 and welding speed V 0 , the formula is as follows:

[0118]

[0119] V 0 =V L *α 2 *K 1 *H*η

[0120] Among them, I L Indicates the theoretical basic welding current; α 1 Indicates the current adjustment factor; V 0 Indicates the theoretical basic welding speed; α 2 Indicates the speed adjustment factor.

[0121] Furthermore, in this embodiment, step S1 further includes:

[0122] Workpiece material types include carbon steel, stainless steel and alloy materials. The welding coefficient K of the workpiece material 1 The values ​​include:

[0123] If the workpiece material type is carbon steel, the workpiece material welding coefficient K 1 The value is 1.0~1.3; the welding coefficient K of the workpiece material type is carbon steel 1 The optimal value is 1.1;

[0124] If the workpiece material type is stainless steel, the workpiece material welding coefficient K 1 The value is 1.4 to 1.7; the welding coefficient K of the workpiece material type is stainless steel 1 The optimal value is 1.6;

[0125] If the workpiece material type is alloy material, the workpiece material welding coefficient K 1 The value is 1.8~2.0; the workpiece material type is alloy material workpiece material welding coefficient K 1 The optimal value is 1.9;

[0126] An example of step S1 is as follows:

[0127] The material type of the workpiece to be welded is carbon steel, so the welding coefficient of the workpiece material K 1 Take K 1 =1.1, workpiece thickness H = 10mm;

[0128] Obtain the welding wire theoretical deposition efficiency η=90%=0.9 of the welding wire used;

[0129] Theoretical basis Welding current I L =10A, current adjustment factor α 1 =0.1mm -1 , theoretical basis welding speed V 0 =10mm / s, speed adjustment coefficient α 2 =0.15mm -1 ;

[0130] The initial welding current I 0 and welding speed V 0 They are:

[0131]

[0132] V 0 =10*0.15*1.1*10*0.9=15mm / s.

[0133] Furthermore, in this embodiment, step S2 specifically includes:

[0134] Obtain the required inner width dimension B of the welding workpiece, and obtain the straight-line distance L between the end edges of the two guide wheel mechanisms 5011 in each set of guide wheel assemblies 501 away from the end of the moving module 10;

[0135] If L=B, it is determined that the guiding requirement is met and the subsequent processing continues; when L=B, the ends of the two guide wheel mechanisms 5011 in the same set of guide wheel assemblies 501 away from the moving module 10 are in contact with the two side walls inside the workpiece respectively, and following the movement of the moving module 10, the guide wheel mechanisms 5011 slide with the side walls inside the workpiece to guide the moving module 10;

[0136] If L<B, it is determined that the guiding requirement is not met, and the two guiding wheel mechanisms 5011 of the same group are driven to move away from the moving module 10 until L=B is met;

[0137] If L>B, it is determined that the guiding requirement is not met, and the two guiding wheel mechanisms 5011 of the same group are driven to move toward the moving module 10 until L=B is met;

[0138] Here is an example:

[0139] The required internal width dimension B of the welding workpiece is obtained to be 100 mm, and the straight-line distance L between the end edges of the two guide wheel mechanisms 5011 in the same set of guide wheel assemblies 501 away from one end of the moving module 10 is 80 mm;

[0140] Therefore, if L<B, it is determined that the guiding requirement is not met, and the two guiding wheel mechanisms 5011 of the same group are driven to move away from the moving module 10 until L=B is met.

[0141] Furthermore, in this embodiment, step S3 specifically includes:

[0142] The front end of the mobile module 10 moves forward toward the inside of the workpiece, and the image acquisition component acquires images of the path of the mobile module 10 in real time to obtain a path image;

[0143] grayscale processing and noise reduction processing are performed on the path image to obtain a processed first path real-time image;

[0144] Using a contour detection algorithm to identify the impurity contours of the first path real-time image, counting the number of impurity contours to obtain the number of impurities N, and calculating the impurity area ratio P and the impurity density M;

[0145] Execute movement strategy and cleaning strategy according to the number of impurities N, impurity area ratio P and impurity density M;

[0146] Here is an example:

[0147] The front end of the mobile module 10 moves forward toward the inside of the workpiece, and the image acquisition component acquires images of the moving path at a speed of 5 frames per second. The acquired path image is a color image with a size of 640×480 pixels;

[0148] Grayscale processing of the path image is to convert the color image into a grayscale image, for example, using the weighted average method, according to the formula Gray = 0.299*R + 0.587*G + 0.114*B (R, G, B are the red, green, and blue channel values ​​of the color image, respectively) to calculate the gray value of each pixel. After processing, the original colorful path image becomes an image with only different gray levels, highlighting the brightness information of the image and removing color interference;

[0149] The median filter method is used to reduce noise on the grayscale path image. For each pixel in the image, the pixel values ​​in a 3×3 neighborhood (the size can be adjusted according to the actual situation) are taken, and these pixel values ​​are sorted by grayscale value. The middle value is taken as the new grayscale value of the pixel. For example, the grayscale values ​​of the pixels in the 3×3 neighborhood around a pixel are [10, 15, 20, 22, 25, 30, 32, 35, 40] respectively. After sorting, the middle value is 25, then the grayscale value of the pixel is updated to 25. After the noise reduction process, the random noise points in the image are effectively removed, the image becomes smoother, and the processed real-time image of the first path is obtained.

[0150] The first path real-time image is processed using a contour detection algorithm (e.g., Canny edge detection algorithm combined with contour search algorithm). For example, if 8 closed impurity contours are detected in the image, then the number of impurities N = 8. By calculating the sum of the pixel areas contained in all impurity contours and comparing them with the total area of ​​the image, it is assumed that the impurity area ratio P = 10%. Then, the number of impurity contours is divided by the actual area corresponding to the image. For example, assuming that the actual area corresponding to the image is 100 mm 2 , we get the impurity density M = 8 / 100 = 0.08 pieces / cm 2 .

[0151] Furthermore, in this embodiment, the mobile strategy includes:

[0152] The initial moving speed of the moving module 10 is preset to V Y0 , calculate the movement influence coefficient W according to the impurity number N, impurity area proportion P and impurity density M:

[0153]

[0154] Among them, N Lmax Indicates the maximum threshold of the preset impurity quantity; P Lmax Indicates the maximum threshold of the preset impurity area ratio; M Lmax Indicates the preset maximum threshold of impurity density; ω 1 ,ω 2 and ω 3 Are all weight coefficients, satisfying ω 1 +ω 2 +ω 3 =1;

[0155] Select the speed adjustment coefficient Q according to the movement influence coefficient W, and calculate the real-time movement speed V required by the movement module 10 YS :

[0156] V YS =V Y0 *Q

[0157] If W≤0.3, the value of the speed adjustment coefficient Q is Q=1;

[0158] If 0.3<W≤0.5, the value of the speed adjustment coefficient Q is Q=0.8;

[0159] If 0.5<W≤0.8, the value of the speed adjustment coefficient Q is Q=0.6;

[0160] If W>0.8, the speed adjustment coefficient Q is Q=0.4;

[0161] Here is an example:

[0162] The initial moving speed V of the preset moving module 10 Y0 =10mm / s, preset maximum threshold value of impurity quantity N Lmax = 20, preset the maximum threshold of impurity area ratio P Lmax =40%, preset maximum impurity density threshold M Lmax =0.2pcs / cm 2 ,ω 1 =0.3,ω 2 =0.4,ω 3 =0.3;

[0163] According to the above example, the number of impurities N = 8, the impurity area ratio P = 10%, and the impurity density M = 0.08 / cm 2 ;

[0164] but

[0165] If 0.3<W≤0.5 is satisfied, the value of the speed adjustment coefficient Q is Q=0.8;

[0166] Then the real-time moving speed V required by the moving module 10 is YS =10*0.8=8mm / s.

[0167] Furthermore, in this embodiment, the cleaning strategy includes:

[0168] Determine the level of influence of the impurities on the stability of the mobile module 10 according to the impurity quantity N, the impurity area ratio P and the impurity density M;

[0169] If N≤N E , P≤P E and M≤M E If all of the above conditions are satisfied, the stability impact level is judged to be low, and the initial state of the cleaning module 20 is maintained;

[0170] If N≤N E , P≤P E and M≤M EIf any two of the above conditions are not satisfied, the stability impact level is determined to be medium, and the obstacle removal brush mechanism 201 at the front end of the mobile module 10 is started once, so that the obstacle removal brush mechanism 201 at the front end of the mobile module 10 rotates to clean impurities;

[0171] If N≤N E , P≤P E and M≤M E If none of the above conditions are satisfied, the stability impact level is determined to be high, and the obstacle-clearing brush mechanism 201 at the front end of the mobile module 10 is started at least twice, so that the obstacle-clearing brush mechanism 201 at the front end of the mobile module 10 rotates to clean impurities; the obstacle-clearing brush mechanism 201 rotates toward the side of the mobile module 10, rotates back to the initial position after cleaning once, and then rotates again, so that each rotation cleans the impurities in front of the mobile module 10 to both sides, so as to prevent the impurities from affecting the movement of the mobile module 10;

[0172] Among them, N E Indicates the preset impurity quantity safety threshold; P E Indicates the preset impurity area ratio safety threshold; M E Indicates the preset impurity density safety threshold;

[0173] Here is an example:

[0174] Preset impurity quantity safety threshold N E =5, preset impurity area ratio safety threshold P E =5%, preset impurity density safety threshold M E =0.05pcs / cm 2 ;

[0175] According to the above, the number of impurities N = 8, the impurity area ratio P = 10%, and the impurity density M = 0.08 / cm 2 ;

[0176] Then N≤N E , P≤P E and M≤M E If none of the above conditions are satisfied, the stability impact level is judged to be high, and the obstacle removal brush mechanism 201 located at the front end of the mobile module 10 is started at least twice to clean impurities.

[0177] Furthermore, in this embodiment, step S4 specifically includes:

[0178] Obtain historical weld image data and corresponding weld type label data, where the weld type labels of the weld type label data include butt welds, fillet welds, T-welds, lap welds, plug welds, slot welds and other welds; other welds may be cross welds, bottom-lock butt welds and other weld types;

[0179] Performing grayscale processing, denoising processing, and image enhancement processing on the historical weld image data to obtain processed first historical weld image data;

[0180] The Canny algorithm and gray-level co-occurrence matrix method are used to extract the edge features, geometric features and texture features of the first historical weld image data to obtain the weld feature vector;

[0181] A support vector machine is used with weld feature vector as input and weld type label as output to train and test the historical weld image data and weld type label data to obtain a trained field weld recognition model.

[0182] The mobile module 10 moves to the desired welding position, and the image acquisition component acquires the real-time weld image of the desired welding position, and inputs the real-time weld image into the field weld recognition model to identify the real-time weld type of the welding position;

[0183] Here is an example:

[0184] Obtain 1,000 historical weld image data, corresponding to 1,000 weld type label data, including 300 butt weld images, 250 fillet weld images, 200 T-weld images, 150 lap weld images, 50 plug weld images, 30 slot weld images, and 20 other weld images;

[0185] The 1000 color historical weld images were grayed out according to the formula Gray = 0.299*R + 0.587*G + 0.114*B (R, G, B are the red, green, and blue channel values ​​of the color image, respectively) to remove color interference.

[0186] The Gaussian filtering denoising method is used. For each grayscale image, the noise in the image is smoothed by setting appropriate Gaussian kernel parameters (e.g., standard deviation σ = 0.5, kernel size 3 × 3) to make the image clearer.

[0187] The denoised image is processed using a histogram equalization method to enhance the image contrast and make the weld features more obvious, thereby obtaining the processed first historical weld image data;

[0188] Perform feature extraction on the first historical weld image data, use the Canny algorithm, set appropriate high and low thresholds (for example, the low threshold is 50 and the high threshold is 150), perform edge detection on the first historical weld image data, and obtain edge contour information of the weld;

[0189] Calculate the area, perimeter and aspect ratio of the weld area. For example, for a butt weld image, the weld area is calculated to be S = 500 pixels. 2, perimeter C = 100 pixels, aspect ratio 2:1;

[0190] The gray-level co-occurrence matrix method is used to calculate the texture feature values ​​such as contrast, entropy, and energy. For example, the contrast of a fillet weld image calculated under the gray-level co-occurrence matrix is ​​0.3, the entropy is 0.8, and the energy is 0.2, and the weld feature vector is obtained comprehensively.

[0191] The support vector machine (SVM) algorithm is used, the weld feature vector is used as input, and the corresponding weld type label (such as butt weld, fillet weld, etc.) is used as output. The 1000 sets of data are divided into training sets (700 sets) and test sets (300 sets) in a ratio of 7:3. The training set data is used to train the SVM model, and the model parameters are adjusted (for example, the kernel function selects the radial basis function, and the penalty parameter C=10). Then, the test set data is used for testing to evaluate the recognition accuracy and other indicators of the model, and finally a trained field weld recognition model is obtained.

[0192] The mobile module 10 moves to the desired welding position, and the image acquisition component acquires the real-time weld image of the desired welding position, and inputs the real-time weld image into the field weld recognition model to identify the real-time weld type of the welding position.

[0193] Furthermore, in this embodiment, step S5 specifically includes:

[0194] Select the welding adjustment factor G according to the real-time weld type, and adjust the welding current I according to the welding adjustment factor P. 0 and welding speed V 0 Adjust to get the actual welding current I after adjustment HS and actual welding speed V HS , the adjustment method is as follows:

[0195] I HS =I 0 *P

[0196] V HS =V 0 *P

[0197] If the weld type is a butt weld, the welding adjustment factor G is 1.1;

[0198] If the weld type is a fillet weld, the welding adjustment factor G is 1.2;

[0199] If the weld type is a T-shaped weld, the welding adjustment factor G is 0.9;

[0200] If the weld type is a lap weld, the welding adjustment factor G is 0.8;

[0201] If the weld type is a plug weld, the welding adjustment factor G is 1.5;

[0202] If the weld type is a slot weld, the welding adjustment factor G is 1.3;

[0203] If the weld type is other welds, the welding adjustment factor G is 1;

[0204] Here is an example:

[0205] If the weld type at the welding point is identified as a butt weld by the field weld identification model, the welding adjustment coefficient G = 1.1;

[0206] According to the welding current I obtained in step S1 0 =12A and welding speed V 0 =15mm / s;

[0207] Calculate the actual welding current I after adjustment HS and actual welding speed V HS They are:

[0208] I HS =12*1.1=13.2A;

[0209] V HS =15*1.1=16.5mm / s.

[0210] In summary, a field welding control method selects and sets welding process parameters according to the first parameter information of the welding workpiece and the second parameter information of the welding wire, so as to match the welding process with the specific workpiece and the welding wire, thereby ensuring the welding quality and improving the stability and reliability of welding; adjusting the guide module 50 according to the internal width of the workpiece so that the guide module 50 is adapted to the inside of the workpiece, which helps the mobile module 10 to move accurately inside the workpiece, ensure the accuracy of the welding path, and improve the accuracy of welding; by setting an image acquisition component on the mobile module 10 to collect the internal image data of the workpiece, and according to the internal environment of the workpiece Selecting the real-time moving speed of the mobile module 10 can make the moving speed adapt to the actual welding environment, avoid affecting the welding quality due to too fast or too slow speed, and improve the efficiency and quality of welding; constructing a field weld recognition model can accurately identify the weld type in the real-time weld image, provide a basis for subsequent adjustment of welding process parameters, and enhance the adaptability of the welding system to different weld types; dynamically adjust the welding process parameters according to the identified weld type, realize the intelligent control of the welding process, and can adopt the optimal welding parameters for different weld types, further ensure the welding quality, and improve the success rate and efficiency of welding.

[0211] In the description of the present application, it should be understood that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "lateral, vertical, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the device or element referred to must have a specific direction or be constructed and operated in a specific direction, and therefore cannot be understood as limiting the scope of protection of the present application.

[0212] For those skilled in the art, various other corresponding changes and deformations can be made according to the technical solutions and concepts described above, and all of these changes and deformations should fall within the protection scope of the claims of this application.

Claims

1. A field welding system for welding the inside of a workpiece arranged in the field, comprising a moving module (10), and a cleaning module (20), a welding module (30), a wire feeding module (40) and a guide module (50) arranged on the moving module (10), characterized in that: It also includes a control module (60) and an image acquisition component, wherein the control module (60) and the image acquisition component are both arranged on the mobile module (10); The mobile module (10) has one end as the front end and the other end as the rear end; The cleaning module (20) comprises a plurality of obstacle-clearing brush mechanisms (201); The control module (60) is used to control the moving module (10), the cleaning module (20), the welding module (30), the wire feeding module (40) and the guiding module (50) to perform welding processing.

2. A field welding control method, using the field welding system as claimed in claim 1, characterized in that: The following steps are involved: S1. Select and set welding process parameters according to the first parameter information of the required welding workpiece and the second parameter information of the welding wire used; S2. adjusting the guide module (50) according to the internal width of the required welding workpiece so that the guide module (50) is adapted to the interior of the workpiece; S3, arranging an image acquisition component on the mobile module (10), collecting image data inside the workpiece through the image acquisition component, and selecting a real-time moving speed of the mobile module (10) according to the environment inside the workpiece; S4, constructing a field weld recognition model, the mobile module (10) moves to a desired welding position, the image acquisition component acquires a real-time weld image, and recognizes the real-time weld image through the field weld recognition model to obtain a real-time weld type; S5. Dynamically adjust the welding process parameters according to the real-time weld type, and perform welding processing on the required welding position.

3. The field welding control method according to claim 2, characterized in that: The step S1 specifically includes: The first parameter information includes workpiece material type and workpiece thickness; The second parameter information includes the theoretical deposition efficiency of the welding wire; The welding process parameters include welding current and welding speed; Obtain the workpiece material type and workpiece thickness H of the required welding workpiece, select the corresponding workpiece material welding coefficient K1 according to the workpiece material type, and obtain the welding wire theoretical deposition efficiency η of the welding wire used; Calculate the welding current I0 and welding speed V0 for initial setting, the formula is as follows: V0=V L *a2*K1*H*h Among them, I L It represents the theoretical basic welding current; α1 represents the current adjustment coefficient; V0 represents the theoretical basic welding speed; α2 represents the speed adjustment coefficient.

4. The field welding control method according to claim 3, characterized in that: The step S1 further comprises: The workpiece material types include carbon steel, stainless steel and alloy materials, and the values ​​of the workpiece material welding coefficient K1 include: If the workpiece material type is carbon steel, the workpiece material welding coefficient K1 is 1.0 to 1.3; If the workpiece material type is stainless steel, the workpiece material welding coefficient K1 is 1.4 to 1.7; If the workpiece material type is alloy material, the workpiece material welding coefficient K1 is 1.8-2.

0.

5. The field welding control method according to claim 2, characterized in that: The step S2 specifically includes: The guide module (50) comprises at least two groups of guide wheel assemblies (501), each two groups of guide wheel assemblies (501) are arranged on the mobile module (10) at intervals, and the same group of guide wheel assemblies (501) comprises two guide wheel mechanisms (5011), the two guide wheel mechanisms (5011) are arranged on two sides of the mobile module (10) opposite to each other, and the guide wheel mechanisms (5011) are slidably connected to the mobile module (10) so that the guide wheel mechanisms (5011) can slide away from or close to the mobile module (10); Obtaining the required internal width dimension B of the welding workpiece, and obtaining the straight-line distance L between the end edges of two guide wheel mechanisms (5011) in each group of the guide wheel assemblies (501) away from one end of the moving module (10); If L = B, it is determined that the guidance requirements are met and the subsequent processing continues; If L<B, it is determined that the guidance requirement is not met, and the two guide wheel mechanisms (5011) in the same group are driven to move in a direction away from the mobile module (10) until L=B is met; If L>B, it is determined that the guidance requirement is not met, and the two guide wheel mechanisms (5011) of the same group are driven to move in a direction close to the mobile module (10) until L=B is met.

6. The field welding control method according to claim 2, characterized in that: The step S3 specifically includes: The front end of the mobile module (10) moves forward toward the inside of the workpiece, and the image acquisition component acquires images of the path along which the mobile module (10) moves in real time to obtain a path image; Performing grayscale processing and noise reduction processing on the path image to obtain a processed first path real-time image; Using a contour detection algorithm to identify the impurity contours of the first path real-time image, counting the number of the impurity contours to obtain the impurity number N, and calculating the impurity area ratio P and the impurity density M; A moving strategy and a cleaning strategy are executed according to the impurity number N, the impurity area proportion P and the impurity density M.

7. The field welding control method according to claim 6, characterized in that: The mobile strategy includes: The initial moving speed of the moving module (10) is preset to be V Y0 , calculate the movement influence coefficient W according to the impurity number N, the impurity area proportion P and the impurity density M: Among them, N Lmax Indicates the maximum threshold of the preset impurity quantity; P Lmax Indicates the maximum threshold of the preset impurity area ratio; M Lmax Indicates the preset maximum threshold of impurity density; ω1, ω2 and ω3 are all weight coefficients, satisfying ω1+ω2+ω3=1; The speed adjustment coefficient Q is selected according to the movement influence coefficient W, and the real-time movement speed V required by the movement module (10) is calculated. YS : V YS =V Y0 *Q If W≤0.3, the speed adjustment coefficient Q is Q=1; If 0.3<W≤0.5, the value of the speed adjustment coefficient Q is Q=0.8; If 0.5<W≤0.8, the value of the speed adjustment coefficient Q is Q=0.6; If W>0.8, the value of the speed adjustment coefficient Q is Q=0.

4.

8. The field welding control method according to claim 7, characterized in that: The cleaning strategy includes: Determining the level of influence of the impurities on the stability of the mobile module (10) according to the impurity quantity N, the impurity area proportion P and the impurity density M; If N≤N E , P≤P E and M≤M E If all of the above conditions are satisfied, the stability impact level is judged to be low, and the initial state of the cleaning module (20) is maintained; If N≤N E , P≤P E and M≤M E If any two of the above conditions are not satisfied, the stability impact level is determined to be medium, and the obstacle removal brush mechanism (201) located at the front end of the mobile module (10) is started once, so that the obstacle removal brush mechanism (201) at the front end of the mobile module (10) rotates to clean impurities; If N≤N E , P≤P E and M≤M E If none of the above conditions are satisfied, the stability impact level is judged to be high, and the obstacle removal brush mechanism (201) located at the front end of the mobile module (10) is activated at least twice, so that the obstacle removal brush mechanism (201) at the front end of the mobile module (10) rotates to clean impurities; Among them, N E Indicates the preset impurity quantity safety threshold; P E Indicates the preset impurity area ratio safety threshold; M E Indicates the preset impurity density safety threshold.

9. The field welding control method according to claim 4, characterized in that: The step S4 specifically includes: Acquire historical weld image data and corresponding weld type label data, wherein the weld type labels of the weld type label data include butt welds, fillet welds, T-welds, lap welds, plug welds, slot welds and other welds; Performing grayscale processing, denoising processing, and image enhancement processing on the historical weld image data to obtain processed first historical weld image data; The Canny algorithm and the gray-level co-occurrence matrix method are used to extract edge features, geometric features and texture features of the first historical weld image data to obtain a weld feature vector; A support vector machine is used, with the weld feature vector as input and the weld type label as output, to perform model training and testing on the historical weld image data and the weld type label data, so as to obtain a trained field weld recognition model; The mobile module (10) moves to a desired welding location, the image acquisition component acquires a real-time weld image of the desired welding location, and inputs the real-time weld image into the field weld recognition model to identify and obtain the real-time weld type of the welding location.

10. The field welding control method according to claim 9, characterized in that: The step S5 specifically includes: The welding adjustment coefficient G is selected according to the real-time weld type, and the welding current I0 and the welding speed V0 are adjusted according to the welding adjustment coefficient P to obtain the adjusted actual welding current I HS and actual welding speed V HS , the adjustment method is as follows: I HS =I0*P V HS =V0*P If the weld type is a butt weld, the welding adjustment coefficient G is 1.1; if the weld type is a fillet weld, the welding adjustment coefficient G is 1.2; if the weld type is a T-weld, the welding adjustment coefficient G is 0.9; if the weld type is a lap weld, the welding adjustment coefficient G is 0.8; if the weld type is a plug weld, the welding adjustment coefficient G is 1.5; if the weld type is a slot weld, the welding adjustment coefficient G is 1.3; if the weld type is other welds, the welding adjustment coefficient G is 1.

Images