Deep penetration type welding system and method based on infrared laser

Abstract

The invention is suitable for the technical field of laser welding, and provides a deep penetration type welding system and method based on infrared laser. The process setting module generates process parameters, a working path and preset deep penetration data according to the appearance data; the laser emission module emits laser for welding; the workpiece moving module moves the workpiece according to the working path; the image recognition module is used for collecting a surface image of each frame during workpiece welding in real time; the temperature monitoring module is used for monitoring the real-time welding temperature of the infrared laser welding area in real time; the image fusion module is used for generating deep penetration quality data according to the multi-frame surface image, the process parameters and the real-time welding temperature; and the process adjusting module is used for comparing the deep penetration quality data with preset deep penetration data and adjusting process parameters. The device solves the problems of unstable welding quality and low welding efficiency of penetration fusion welding, and achieves the effects of improving the welding depth and quality and reducing welding defects.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of laser welding, more particularly, it relates to a deep penetration welding system and method based on infrared laser. BACKGROUND

[0002] In modern industrial production, the demand for welding of many materials is increasing, especially in situations with strict requirements for welding depth and quality. Traditional welding methods, such as electric arc welding, often have many problems when achieving deep penetration welding, for example, the heat-affected zone is too large, which easily leads to material deformation and deterioration of the microstructure and performance; the welding speed is slow, and the production efficiency is low.

[0003] Although existing laser welding technology has improved these problems to some extent, it still has limitations for deep penetration welding of some special materials and complex structures. For example, ordinary laser welding has low energy absorption rate when facing high reflectivity materials, making it difficult to achieve efficient deep penetration welding; and defects such as pores and cracks are easily generated during the welding process, affecting the welding quality.

[0004] Therefore, a deep penetration welding system and method based on infrared laser is proposed to solve the above problems. SUMMARY

[0005] In view of the deficiencies in the prior art, the purpose of the present application is to provide a deep penetration welding system and method based on infrared laser that improves welding depth and quality and reduces welding defects.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a deep penetration welding system based on infrared laser, comprising a data acquisition module, a process setting module, a laser emission module, a workpiece moving module, an image recognition module, a temperature monitoring module, an image fusion module, and a process adjustment module; the data acquisition module is used to acquire the shape data of the workpiece; the process setting module is used to generate process parameters, a working path, and preset deep penetration data according to the shape data; the laser emission module is used to emit infrared laser and converge the infrared laser to the surface of the workpiece; the workpiece moving module is used to place the workpiece on the workbench and move the workpiece according to the working path; the image recognition module is used to acquire the surface image of each frame in real time when the workpiece is welded; the temperature monitoring module is used to monitor the real-time welding temperature of the infrared laser welding area in real time; the image fusion module is used to generate deep penetration quality data according to the surface image of multiple frames, process parameters, and real-time welding temperature; the process adjustment module is used to compare the deep penetration quality data, the preset deep penetration data, and the set threshold value, and adjust the process parameters.

[0007] The present application further provides: The image fusion module comprises a multi-frame fusion unit and a data prediction unit; The multi-frame fusion unit is used for integrating surface images of continuous multiple frames, and image robust data is obtained through a dynamic threshold algorithm. The data prediction unit is used for predicting deep melting quality data according to the image robust data, the process parameters and the real-time welding temperature.

[0008] By adopting the technical scheme, real-time dynamic regulation and control can be realized in the welding process, production efficiency is improved and the welding cycle is shortened through deep melting prediction.

[0009] A deep melting type welding method based on infrared laser, using a deep melting type welding system based on infrared laser as described above, comprising the following steps: S1, placing a workpiece on a workbench and collecting shape data of the workpiece; S2, generating process parameters, a working path and preset deep melting data according to the shape data; S3, configuring infrared laser and the workbench according to the process parameters, and moving the workbench according to the working path to perform welding of the workpiece; S4, collecting surface images of each frame and real-time welding temperature of the infrared laser welding area in real time when the workpiece is welded; S5, integrating surface images of continuous multiple frames, and obtaining image robust data through a dynamic threshold algorithm; S6, predicting deep melting quality data according to the image robust data, the process parameters and the real-time welding temperature; S7, comparing the deep melting quality data, the preset deep melting data and a set threshold value, and adjusting the process parameters, and repeating steps S3 to S7 until welding processing is completed and the cycle is stopped, and the equipment stops running.

[0010] The application is further provided that in S6, the deep melting quality data is obtained through a deep melting depth prediction algorithm, and the formula of the deep melting depth prediction algorithm is:

[0011] wherein d pred is deep melting quality data, is real-time welding temperature, P is laser intensity, v is workpiece moving speed, EdgeIntensity is image robust data, alpha1 is temperature change coefficient, alpha2 is power change coefficient, alpha3 is speed change coefficient, alpha4 is image change coefficient, and b is bias compensation coefficient.

[0012] In S7, the application is further provided that: S71, calculating a target bias value from the deep melting quality data and the preset deep melting data; S72, comparing the target bias value with a set threshold value; If the target deviation value is greater than the set threshold, then proceed to S73; If the target deviation value is not greater than the set threshold, then proceed to S74; S73. Calculate the adjusted process parameters based on the deviation value and the process parameters described in S6. S74. Keep the process parameters described in S6 unchanged.

[0013] The present invention is further configured such that, in S71, the formula for calculating the target deviation value is:

[0014] in, The deviation value is d. target This is the preset deep melting data.

[0015] The present invention is further configured such that, in S73, the calculation formula for the adjusted process parameters is:

[0016] Where, k P This is the power adjustment coefficient.

[0017] By adopting the above technical solution, the depth of penetration after welding can be dynamically adjusted during welding, which can effectively reduce the occurrence of welding defects such as porosity and cracks, thereby improving the stability and reliability of welding quality and welding efficiency.

[0018] In summary, this application includes at least one of the following beneficial technical effects: 1. The welding process can be dynamically controlled in real time, and production efficiency can be improved and the welding cycle can be shortened through deep penetration prediction.

[0019] 2. By dynamically adjusting the depth of penetration after welding, the occurrence of welding defects, such as porosity and cracks, can be effectively reduced, thereby improving the stability and reliability of welding quality and welding efficiency. Attached Figure Description

[0020] Fig. 1 This is a schematic diagram of the relationship of a deep penetration welding system based on infrared laser in this invention; Fig. 2 This is a schematic diagram of steps S1-S4 of a deep-penetration welding method based on infrared laser in this invention; Fig. 3 This is a schematic diagram of steps S4-S7 of a deep-penetration welding method based on infrared laser in this invention. Detailed Implementation

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] It should be noted that, unless otherwise specified, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0023] Please see Figs. 1-3 The present invention provides the following technical solutions: Example 1, see Fig. 1 A deep-penetration welding system based on infrared laser includes a data acquisition module, a process setting module, a laser emission module, a workpiece movement module, an image recognition module, a temperature monitoring module, an image fusion module, and a process adjustment module. The data acquisition module is used to collect the workpiece's shape data, which includes the workpiece thickness, workpiece material, workpiece welding path dimensions, and laser reflectivity.

[0024] The process setting module is used to generate process parameters, working path and preset deep melting data based on the shape data; among them, the process parameters include laser intensity P, laser focusing distance and workpiece moving speed v.

[0025] The laser emitting module emits both an indicator laser and an infrared laser, converging them into a single optical path so they are both directed at the workpiece surface. The indicator laser is a low-power visible light beam, primarily used for positioning and indication; the infrared laser is a high-power working laser, used for the actual welding. The two laser beams are spatially aligned via a coupler, providing a visual indication of the welding position, facilitating pre-welding alignment and adjustments, and improving positioning accuracy and operational safety.

[0026] The workpiece movement module places the workpiece on the worktable and moves it according to the work path. Specifically, this movement is achieved through a 3D moving platform. The actual position of the workpiece's weld point is calculated and compared with a pre-set target position to determine the positional deviation of the weld point in the X and Y directions. Based on this deviation information, the system sends control commands to the 3D moving platform. The platform moves the workpiece until the actual position of the weld point coincides with the target position, thus achieving precise adjustment of the weld point's position. After locating the initial weld point, the workpiece moves according to the work path to complete the welding process.

[0027] The image recognition module is used to acquire surface images of the workpiece in real time for each frame during welding. The temperature monitoring module is used to monitor the real-time welding temperature in the infrared laser welding area. .

[0028] The image fusion module is used to generate deep melt quality data based on multiple frames of surface images, process parameters, and real-time welding temperature. The image fusion module includes a multi-frame fusion unit and a data prediction unit; The multi-frame fusion unit is used to integrate surface images from multiple consecutive frames and obtain robust image data through a dynamic thresholding algorithm. The data prediction unit is used to predict deep melt quality data based on image robust data, process parameters, and real-time welding temperature. The image fusion module employs multi-frame image fusion and dynamic thresholding algorithms to improve the accuracy of spot recognition in interference environments and ensure reliable system operation.

[0029] The process adjustment module is used to compare and adjust process parameters based on deep melting quality data, preset deep melting data, and set thresholds.

[0030] The above system enables real-time dynamic control during the welding process, and the deep penetration prediction can improve production efficiency and shorten the welding cycle.

[0031] Example 2, see Figs. 2-3 A deep-penetration welding method based on infrared laser, using the aforementioned deep-penetration welding system based on infrared laser, includes the following steps: S1. Place the workpiece on the worktable and collect the workpiece's shape data; S2. Generate process parameters, working path and preset deep melting data based on shape data; S3. Configure the infrared laser and worktable according to the process parameters, and move the worktable according to the work path to weld the workpiece. S4. Real-time acquisition of surface images of the workpiece during welding and real-time welding temperature of the infrared laser welding area for each frame. S5. Integrate surface images from multiple consecutive frames and obtain robust image data through a dynamic thresholding algorithm. The robust image data can include edge density, brightness distribution, morphological indices, etc.

[0032] S6. Based on the image robust data, process parameters, and real-time welding temperature, combined with the deep penetration depth prediction algorithm, the deep penetration quality data is obtained; The formula for the deep melting depth prediction algorithm is as follows:

[0033] Where, d pred For deep melting quality data, P is the real-time welding temperature, v is the laser intensity, v is the workpiece moving speed, EdgeIntensity is the image robustness data, α1 is the temperature change coefficient, α2 is the power change coefficient, α3 is the speed change coefficient, α4 is the image change coefficient, and b is the deviation compensation coefficient. α1, α2, α3, α4 and b are all model coefficients obtained through multiple welding tests or debugging training. For example, in S5, the image robustness data EdgeIntensity is obtained as 8. This EdgeIntensity data specifically refers to the edge intensity value in the image features. In S2, the laser intensity P is set to 800W, the workpiece moving speed v is 2mm / s, and the real-time welding temperature is set in S4. Assuming a temperature of 150℃, a power variation coefficient α1 of 0.02 (meaning that for every 1℃ increase in temperature, the depth of penetration increases by 0.02 units), a power variation coefficient α2 of 0.08 (meaning that for every 1W increase in power, the depth of penetration increases by 0.08 units), a speed variation coefficient α3 of 10 (the coefficient of the reciprocal of the speed term, reflecting the positive effect of decreased speed on penetration), an image variation coefficient α4 of 0.5 (meaning that for every 1 unit increase in edge strength, the depth of penetration increases by 0.5 units), and a deviation compensation coefficient b of 1.5, substituting these values ​​into the formula yields:

[0034] Then the deep melting mass data d pred The calculated result is 77.5.

[0035] S7. Based on the deep penetration quality data, preset deep penetration data, and set threshold, compare and adjust the process parameters. Repeat steps S3 to S7 until the welding process is completed, then stop the cycle and the equipment stops running. The more specific steps for S7 are as follows: S71. Calculate the target deviation value from the deep melting quality data and the preset deep melting data; wherein, the formula for calculating the target deviation value is:

[0036] in, The deviation value is d. target Preset deep melting data; Referring to the example above, let's assume the preset deep melting data d target At this point, the value is 80. Deviation from target value The values ​​are consistent, both being 2.5.

[0037] S72. Compare the target deviation value with the set threshold, wherein the set threshold is obtained through multiple tests or adjustments.

[0038] If the target deviation value is greater than the set threshold, then proceed to S73; If the target deviation value is not greater than the set threshold, then proceed to S74; Referring to the example above, assuming a threshold of 1.5 is set, then the target deviation value... If the value exceeds the set threshold, proceed to step S73.

[0039] S73. Calculate the adjusted process parameters based on the deviation value and the process parameters in S6. The adjusted process parameters mainly refer to the laser power or workpiece moving speed. During adjustment, only one of the laser power or workpiece moving speed needs to be adjusted to achieve dynamic adjustment. If dynamic adjustment is achieved by adjusting the laser power, the formula for the adjusted laser power is:

[0040] Where, k P This is the power adjustment coefficient, which is derived through multiple learning processes; If dynamic adjustment is achieved by adjusting the workpiece movement speed, the formula for the adjusted workpiece movement speed is:

[0041] Where, k v This is the workpiece speed adjustment coefficient, which is obtained through multiple learning processes; The logic for dynamic adjustment in the two formulas above is as follows: When d pred <d target When the penetration depth is insufficient, the laser power can be increased or the workpiece moving speed can be decreased to achieve adjustment. When d pred >d target When the penetration depth is too large, the laser power can be reduced or the workpiece moving speed can be increased to achieve adjustment.

[0042] Referring to the example above, assuming that power adjustment is used as the dynamic adjustment method, the power adjustment coefficient k P If the value is 100, then the adjusted laser power P new It is 1050W.

[0043] S74. Keep the process parameters in S6 unchanged.

[0044] The above methods can solve the problem that traditional welding cannot effectively weld the inside of the workpiece and requires flipping and secondary welding. By dynamically adjusting the welding penetration depth, the occurrence of welding defects such as porosity and cracks is effectively reduced, improving the stability and reliability of welding quality and increasing welding efficiency.

[0045] Obviously, the embodiments described above are merely some, not all, embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort should fall within the scope of protection of the present invention.

Claims

1. A deep-penetration welding system based on infrared laser, characterized in that: include: The data acquisition module is used to collect the workpiece's shape data; The process setting module is used to generate process parameters, working paths, and preset deep melting data based on the shape data; The laser emitting module is used to emit infrared laser light and focus it onto the surface of the workpiece. The workpiece moving module is used to place the workpiece on the worktable and move the workpiece according to the work path; The image recognition module is used to acquire surface images of the workpiece in real time for each frame during welding. The temperature monitoring module is used to monitor the real-time welding temperature of the infrared laser welding area. The image fusion module is used to generate deep melt quality data based on multiple frames of surface images, process parameters, and real-time welding temperature. as well as The process adjustment module is used to compare and adjust process parameters based on deep melting quality data, preset deep melting data, and set thresholds.

2. The infrared laser-based deep-penetration welding system according to claim 1, characterized in that: The shape data includes workpiece thickness, workpiece material, workpiece welding path dimensions, and laser reflectivity.

3. The infrared laser-based deep-penetration welding system according to claim 2, characterized in that: The process parameters include laser intensity, laser focusing distance, and workpiece moving speed.

4. The infrared laser-based deep-penetration welding system according to claim 3, characterized in that: The image fusion module includes a multi-frame fusion unit and a data prediction unit; The multi-frame fusion unit is used to integrate surface images of multiple consecutive frames and obtain robust image data through a dynamic thresholding algorithm. The data prediction unit is used to predict deep melt quality data based on image robust data, process parameters, and real-time welding temperature.

5. A deep-penetration welding method based on infrared laser, using the deep-penetration welding system based on infrared laser as described in claim 4, characterized in that, Includes the following steps: S1. Place the workpiece on the worktable and collect the workpiece's shape data; S2. Generate process parameters, working path and preset deep melting data based on shape data; S3. Configure the infrared laser and worktable according to the process parameters, and move the worktable according to the work path to weld the workpiece. S4. Real-time acquisition of surface images of the workpiece during welding and real-time welding temperature of the infrared laser welding area for each frame. S5. Integrate surface images from multiple consecutive frames and obtain robust image data through a dynamic thresholding algorithm; S6. Based on image robust data, process parameters, and real-time welding temperature prediction, deep penetration quality data is obtained. S7. Compare the deep penetration quality data, preset deep penetration data and set threshold, and adjust the process parameters. Then repeat steps S3 to S7 until the welding process is completed and the cycle stops, and the equipment stops running.

6. The deep-penetration welding method based on infrared laser according to claim 5, characterized in that: In S6, the deep melting quality data is obtained through a deep melting depth prediction algorithm, the formula of which is: ； Where, d pred For deep melting quality data, P is the real-time welding temperature, v is the laser intensity, v is the workpiece moving speed, EdgeIntensity is the image robustness data, α1 is the temperature change coefficient, α2 is the power change coefficient, α3 is the speed change coefficient, α4 is the image change coefficient, and b is the deviation compensation coefficient.

7. The deep-penetration welding method based on infrared laser according to claim 5, characterized in that, The more specific steps for S7 are as follows: S71. Calculate the target deviation value by combining the deep melting quality data and the preset deep melting data; S72. Compare the target deviation value with the set threshold; If the target deviation value is greater than the set threshold, then proceed to S73; If the target deviation value is not greater than the set threshold, then proceed to S74; S73. Calculate the adjusted process parameters based on the target deviation value and the process parameters described in S6. S74. Keep the process parameters described in S6 unchanged.

8. The deep-penetration welding method based on infrared laser according to claim 7, characterized in that, In S71, the formula for calculating the target deviation value is: ； in, The deviation value is d. target This is the preset deep melting data.

9. The deep-penetration welding method based on infrared laser according to claim 7, characterized in that, In S73, the formula for calculating the adjusted process parameters is: ； Where, k P This is the power adjustment coefficient.

10. A deep-penetration welding method based on infrared laser according to claim 7, characterized in that, In S73, the formula for calculating the adjusted process parameters is: ； Where, k v This is the workpiece speed adjustment coefficient.

Images