Laser cutting beam automatic centering method and system based on molten pool and medium

Abstract

The invention provides a laser cutting beam automatic centering method and system based on a molten pool and a medium, and belongs to the technical field of laser cutting beam centring. The method comprises the steps that in the laser cutting process, images containing a nozzle and the molten pool are periodically collected, nozzle contour extraction and circle center calibration are dynamically conducted on the collected images, and the nozzle contour is obtained; obtaining nozzle circle center coordinates; performing nozzle defect judgment based on the nozzle contour and the nozzle circle center coordinate; if the nozzle has defects, alarm or shutdown operation is executed; monitoring whether the laser cutting system is collided or not in real time; if the collision event is monitored, nozzle calibration is conducted again; when the nozzle collides, the center coordinate of the molten pool is extracted from the collected image, and the offset of the center coordinate of the nozzle is calculated; and when the offset exceeds the preset tolerance, the laser cutting head is controlled to conduct light beam centering adjustment. By means of dynamic nozzle calibration and centering adjustment, the cutting precision and quality are improved, manual intervention is reduced, and the system reliability is enhanced.

Description

Technical Field

[0001] This application belongs to the field of laser cutting beam alignment technology, specifically relating to an automatic laser cutting beam alignment method, system, and medium based on a molten pool. Background Technology

[0002] Laser cutting utilizes a high-energy-density laser beam to irradiate the workpiece, causing it to melt rapidly. Simultaneously, a high-speed gas stream ejected from the nozzle blows away the molten material, thus achieving the cutting process. During this process, the concentricity (alignment) of the laser beam and the nozzle is a crucial factor in ensuring cutting quality and precision, as well as preventing nozzle burnout.

[0003] Currently, there are two main methods for nozzle alignment detection. The first is manual alignment, where operators apply adhesive tape to the nozzle surface and visually inspect the hole position after a low-power laser beam is applied. This method is only suitable for static inspection before cutting and cannot monitor and adjust for beam deviation caused by collisions during processing. The second method is automatic alignment based on machine vision. This method uses a camera to capture images of the molten pool and calculates the distance between the center of the molten pool and the center of a pre-calibrated nozzle to determine the deviation. However, the core drawback of this method is that nozzle calibration (i.e., the nozzle center and radius) is completed in one step before cutting. If the laser head collides during cutting, causing a change in the physical position or shape of the nozzle, the system will still use the old calibration data, leading to serious errors in all subsequent alignment calculations and adjustments, posing a significant risk. Furthermore, existing vision methods have a single standard for detecting defects in the nozzle itself, resulting in insufficient accuracy and a high risk of misjudgment.

[0004] Therefore, there is an urgent need for an integrated solution that can dynamically adapt to changes in nozzle condition throughout the cutting process and simultaneously and with high precision complete nozzle health diagnosis and automatic beam alignment. Summary of the Invention

[0005] In a first aspect, embodiments of this application provide an automatic laser cutting beam alignment method based on a molten pool, comprising the following steps: S1. During the laser cutting process, a first image containing the nozzle is periodically acquired, and the nozzle contour is dynamically extracted and the center is calibrated based on the acquired first image to obtain the nozzle center coordinates at the current moment; S2. Based on the extracted nozzle profile and the calibrated nozzle center coordinates, determine the nozzle defects; If the nozzle is defective, an alarm or shutdown operation will be executed; If the nozzle is free of defects, proceed to step S3; S3. Real-time monitoring of whether the laser cutting system experiences collisions; If a collision event is detected, it is determined that the nozzle calibration should be re-performed, and the process returns to step S1; If no collision event is detected, proceed to step S4; S4. Periodically acquire a second image containing the molten pool, extract the center coordinates of the molten pool from the acquired second image, and calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle at the current moment; When the offset exceeds the preset tolerance, the laser cutting head is controlled to perform beam alignment adjustment; Return to step S3.

[0006] Furthermore, the specific steps of step S1 are as follows: S11. Perform grayscale conversion and filtering preprocessing on the acquired raw image; S12. Extract the nozzle profile from the preprocessed image; S13. Perform circular curve fitting on the nozzle profile to calculate the nozzle center coordinates and nozzle radius. Through grayscale conversion, filtering, and circular curve fitting, ensure accurate calibration of the nozzle center and radius, and improve the accuracy of centering adjustment.

[0007] Furthermore, the nozzle defect judgment in step S2 is performed in at least one of the following ways: The roundness is determined based on the nozzle profile calculation; The judgment is based on the eccentricity of the nozzle profile; The defect detection is judged based on the ratio of the actual area of ​​the nozzle profile to the theoretical area calculated from the calibrated radius. Multiple methods, including roundness, eccentricity, and area ratio, are used to identify nozzle defects, improving the accuracy and reliability of defect detection.

[0008] Furthermore, the roundness determination based on the nozzle profile calculation is specifically as follows: Calculate the area of ​​the nozzle profile and perimeter ; The nozzle roundness is calculated using the following formula. :

[0009] nozzle roundness Compared with the preset first threshold Compare; If the nozzle roundness Less than the preset first threshold If the nozzle deviates from its circular shape due to wear or deformation, it is determined that the nozzle has a defect. The roundness calculation formula can accurately determine whether the nozzle has deviated from its circular shape due to wear or deformation, allowing for timely detection of nozzle defects.

[0010] Furthermore, the determination based on the eccentricity of the nozzle profile is specifically as follows: Obtain the minimum bounding rectangle of the nozzle profile; The nozzle eccentricity is calculated using the following formula:

[0011] in, It is the nozzle eccentricity. Let be the longer side of the smallest bounding rectangle of the nozzle profile. The shorter side of the smallest bounding rectangle of the nozzle profile; nozzle eccentricity With the preset second threshold Compare; If the nozzle eccentricity Greater than the preset second threshold If the eccentricity is not found, the nozzle is determined to be defective. The eccentricity calculation formula can accurately determine whether nozzle eccentricity is caused by deformation, further improving the accuracy of nozzle defect detection.

[0012] Furthermore, the specific steps for determining the area based on the ratio of the actual area of ​​the nozzle profile to the theoretical area calculated from the calibration radius are as follows: Based on the calibrated nozzle radius Calculate the theoretical area of ​​the nozzle. ; Obtain the actual area of ​​the nozzle profile ; The ratio of the actual area to the theoretical area of ​​the nozzle is calculated using the following formula. :

[0013] area ratio Compared with the preset third threshold Compare; If the area ratio Less than the preset third threshold If the actual area of ​​the nozzle is not found to be the theoretical area, it can be determined that the nozzle has a defect. By calculating the ratio of the actual area to the theoretical area of ​​the nozzle, it is possible to accurately determine whether the nozzle area has changed due to blockage or wear, thus improving the nozzle defect detection method.

[0014] Furthermore, the specific steps in step S4 include: S41. Analyze the characteristics of the molten pool profile to determine the orientation of the molten pool head; S42. Calculate the centroid coordinates of the head region of the molten pool, and use the centroid coordinates as the center coordinates of the molten pool; S43. Calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle using the following formula. :

[0015] Among them, ( , () represents the coordinates of the center of the molten pool. , () represents the coordinates of the nozzle center; S44. Adjust the offset Compare with a preset distance threshold: If offset If the distance is greater than or equal to the preset distance threshold, the laser cutting head is controlled to perform centering adjustment according to the offset direction and amount of the molten pool center coordinates relative to the nozzle center coordinates. After completion, the process returns to step S3. If offset If the distance is less than the preset threshold, the process returns directly to step S3. By analyzing the molten pool contour features and calculating the offset, the laser beam can be precisely adjusted for alignment, ensuring high precision in the cutting process.

[0016] Furthermore, when acquiring the first image for nozzle contour extraction and center calibration in step S1, the first image acquisition parameters are used; In step S4, when acquiring the second image used to extract the center coordinates of the molten pool, the second image acquisition parameters are used. The exposure time for the first image acquisition parameter is longer than that for the second image acquisition parameter. By setting different exposure times, it is ensured that the acquired images meet the requirements for nozzle calibration and molten pool detection, thereby improving the system's adaptability and accuracy.

[0017] Secondly, embodiments of this application also provide an automatic laser cutting beam alignment system based on a molten pool, comprising: The dynamic nozzle calibration module is used to periodically acquire a first image containing the nozzle during the laser cutting process, and dynamically extract the nozzle contour and calibrate the center based on the acquired first image to obtain the nozzle center coordinates at the current moment. The defect detection module is used to determine nozzle defects based on the extracted nozzle profile and the calibrated nozzle center coordinates; if a defect is found in the nozzle, an alarm or shutdown operation is executed. The collision monitoring module is used to monitor whether a collision occurs in the laser cutting system in real time; if a collision event is detected, it determines that the nozzle calibration should be re-performed. The alignment judgment and adjustment module is used to periodically acquire a second image containing the molten pool when the nozzle collides, extract the center coordinates of the molten pool from the acquired second image, and calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle at the current moment; when the offset exceeds the preset tolerance, the laser cutting head is controlled to perform beam alignment adjustment.

[0018] Thirdly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the automatic alignment method for laser cutting beams based on a molten pool as described in the first aspect.

[0019] As can be seen from the above technical solutions, this application has the following advantages: The automatic laser cutting beam alignment method, system, and medium based on the molten pool provided in this application ensure that the laser beam is always concentric with the nozzle through dynamic nozzle calibration and real-time alignment adjustment, avoiding cutting quality problems caused by beam deviation; by monitoring collision events in real time and recalibrating the nozzle, the impact of nozzle position or shape changes caused by collisions on the cutting process is avoided, reducing the risk of equipment failure; automated alignment adjustment reduces manual intervention, avoiding downtime caused by manual alignment adjustment and improving production efficiency; real-time monitoring and adjustment prevent equipment damage caused by beam deviation or nozzle defects, extending the service life of the laser cutting head and related components; and automated nozzle defect detection and alignment adjustment reduce the frequency of manual inspection and adjustment, lowering labor costs. Attached Figure Description

[0020] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic flowchart of the automatic laser cutting beam alignment method based on the molten pool of the present invention.

[0022] Figure 2 This is an image of the nozzle of the present invention.

[0023] Figure 3 This is the nozzle contour image extracted according to the present invention.

[0024] Figure 4 This is an image showing the nozzle calibration results of the present invention.

[0025] Figure 5 This is an image of the molten pool in this invention.

[0026] Figure 6 This is an image showing the detection results of the molten pool center in this invention.

[0027] Figure 7 This is a schematic diagram of the automatic laser cutting beam alignment system based on the molten pool of the present invention. Detailed Implementation

[0028] Various embodiments of this disclosure will be described more fully in the detailed steps of the automatic beam alignment method for laser cutting based on a molten pool described below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0029] For example, laser cutting melts the workpiece using a high-energy laser beam, and then the molten material is blown away by a high-speed gas stream from the nozzle to complete the cut. In this process, the concentricity (alignment) of the laser beam and the nozzle is crucial to ensuring cutting quality, accuracy, and preventing nozzle damage. Currently, there are two main methods for alignment detection: one is manual alignment, where the operator applies adhesive tape to the nozzle surface and observes the hole position after a low-power laser spot attack. However, this method is only suitable for static inspection before cutting and cannot monitor and adjust beam offset in real time during processing. The second method is automatic alignment based on machine vision, which uses a camera to capture images of the molten pool and calculates the distance between the center of the molten pool and the pre-calibrated nozzle center to determine offset. However, this method has the drawback that nozzle calibration is completed once before cutting. If the laser head collides during cutting, causing the nozzle position or shape to change, the system still uses the old calibration data, leading to serious errors in subsequent alignment calculations and adjustments, posing a significant risk. Furthermore, existing vision methods have a single standard for detecting nozzle defects, resulting in low accuracy and a high risk of misjudgment.

[0030] Therefore, there is an urgent need for an integrated solution that can dynamically adapt to changes in nozzle condition throughout the cutting process and simultaneously and with high precision complete nozzle health diagnosis and automatic beam alignment.

[0031] To address the aforementioned issues, this embodiment provides an automatic laser cutting beam alignment method based on the molten pool, which includes dynamic nozzle calibration and alignment adjustment, improving cutting accuracy and quality, reducing manual intervention, and enhancing system reliability.

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Please see Figure 1 The diagram shows a flowchart of an automatic laser cutting beam alignment method based on a molten pool in a specific embodiment. The method includes the following steps: S1. During the laser cutting process, a first image containing the nozzle is periodically acquired, and the nozzle contour is dynamically extracted and the center is calibrated based on the acquired first image to obtain the nozzle center coordinates at the current moment; It should be noted that by periodically acquiring images and dynamically extracting the nozzle outline and center calibration, the nozzle center coordinates can be obtained in real time, adapting to changes in the nozzle state during the cutting process and ensuring the accuracy of centering adjustment. S2. Based on the extracted nozzle profile and the calibrated nozzle center coordinates, determine the nozzle defects; If the nozzle is defective, an alarm or shutdown operation will be executed; If the nozzle is free of defects, proceed to step S3; It should be noted that by judging defects through nozzle profile and center coordinates, problems such as nozzle wear, deformation or blockage can be detected in time, avoiding cutting quality problems caused by nozzle defects and reducing the risk of equipment damage. S3. Real-time monitoring of whether the laser cutting system experiences collisions; If a collision event is detected, it is determined that the nozzle calibration should be re-performed, and the process returns to step S1; If no collision event is detected, proceed to step S4; It should be noted that real-time monitoring of collision events and recalibration of the nozzle can promptly correct changes in nozzle position or shape caused by collisions, ensuring the reliability of subsequent alignment adjustments and avoiding cutting errors caused by incorrect calibration data. S4. Periodically acquire a second image containing the molten pool, extract the center coordinates of the molten pool from the acquired second image, and calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle at the current moment; When the offset exceeds the preset tolerance, the laser cutting head is controlled to perform beam alignment adjustment; Return to step S3; It should be noted that by periodically acquiring images of the molten pool and calculating the offset, the beam offset can be monitored in real time and automatically adjusted to ensure that the laser beam is always located at the center of the nozzle, thereby improving the cutting quality and accuracy.

[0034] This embodiment ensures that the laser beam is always concentric with the nozzle through dynamic nozzle calibration, nozzle defect detection, collision monitoring, and centering adjustment. This improves cutting accuracy and quality, reduces the risk of equipment damage caused by beam deviation or nozzle defects, lowers manual inspection and maintenance costs, enhances overall system reliability, and increases production efficiency.

[0035] Furthermore, as a refinement and extension of the specific implementation methods of the above embodiments, in order to fully illustrate the specific implementation process of this embodiment, another automatic laser cutting beam alignment method based on the molten pool is provided. This method can simultaneously realize dynamic nozzle calibration, nozzle defect detection, collision monitoring, and automatic beam alignment adjustment throughout the entire laser cutting process, effectively solving problems such as static calibration failure, low defect judgment accuracy, and inability to adjust in real time in the prior art. The hardware configuration and preset core parameters are as follows: (a) Hardware configuration The laser cutting equipment used is a 3000W fiber laser cutting machine equipped with an autofocus laser cutting head; Image acquisition uses an industrial CMOS camera with a 25mm lens, mounted on the side of the laser cutting head at a 45° angle to the cutting head axis, ensuring simultaneous capture of nozzle and molten pool images. Auxiliary components: The laser cutting head is equipped with a collision sensor (detection accuracy ±0.1mm) for real-time monitoring of collision events; it is also equipped with a servo motor-driven beam adjustment mechanism with an adjustment accuracy of ±0.005mm. (II) Core Parameter Preset Image acquisition cycle: The first image (including the nozzle) and the second image (including the molten pool) are both acquired at 1 frame every 50ms; Image acquisition parameters: first image exposure time 10000μs, gain 0dB; second image exposure time 5000μs, gain 0dB. Differentiated parameters ensure clear nozzle outline and complete molten pool features. Defect judgment thresholds: Preset first threshold (circularity) 0.80, second threshold (eccentricity) 0.20, third threshold (area ratio) 0.90; Centering adjustment threshold: The preset tolerance for the offset between the center of the molten pool and the center of the nozzle is 5 pixels (corresponding to an actual distance of 0.05mm). The method includes the following steps: S1. During the laser cutting process, a first image containing the nozzle is periodically acquired, and the nozzle contour is dynamically extracted and the center is calibrated based on the acquired first image to obtain the nozzle center coordinates at the current moment; The specific steps of step S1 are as follows: S11. Perform grayscale conversion and filtering preprocessing on the acquired raw image; S12. Extract the nozzle profile from the preprocessed image; S13. Fit a circular curve to the nozzle profile to calculate the coordinates of the nozzle center and the nozzle radius; For example, after laser cutting is initiated, an industrial camera acquires a first image containing the nozzle according to a preset cycle, such as... Figure 2As shown, the original image resolution is 2448×2048 pixels; The first image is preprocessed: the color image is first converted into an 8-bit grayscale image, and then a 5×5 Gaussian filter kernel is used for filtering to remove noise interference caused by splatter during the cutting process; The nozzle contour is extracted using the Canny edge detection algorithm, such as... Figure 3 As shown, a continuous and complete nozzle profile curve is obtained by filling small gaps in the profile through morphological closing operations. By performing least-squares circular curve fitting on the nozzle profile, the current nozzle center coordinates (x1, y1) = (1243, 1057) pixels are calculated, and the nozzle radius r = 193 pixels (corresponding to an actual radius of 1.93 mm). Figure 4 As shown; It should be noted that by using grayscale conversion, filtering, and circular curve fitting, the precise calibration of the nozzle's center and radius is ensured, thereby improving the accuracy of the centering adjustment. S2. Based on the extracted nozzle profile and the calibrated nozzle center coordinates, determine the nozzle defects; If the nozzle is defective, an alarm or shutdown operation will be executed; If the nozzle is free of defects, proceed to step S3; The nozzle defect assessment in step S2 is performed in at least one of the following ways: The roundness is determined based on the nozzle profile calculation; The judgment is based on the eccentricity of the nozzle profile; The judgment is based on the ratio of the actual area of ​​the nozzle profile to the theoretical area calculated based on the calibration radius; It should be noted that by using multiple methods such as roundness, eccentricity, and area ratio to judge nozzle defects, the accuracy and reliability of defect detection are improved. Specifically, the roundness determination based on the nozzle profile calculation is as follows: Calculate the area of ​​the nozzle profile and perimeter ; The nozzle roundness is calculated using the following formula. :

[0036] nozzle roundness Compared with the preset first threshold Compare; If the nozzle roundness Less than the preset first threshold If so, the nozzle is determined to be defective; It should be noted that the roundness calculation formula can accurately determine whether the nozzle has deviated from its round shape due to wear or deformation, and promptly detect nozzle defects. The determination based on the eccentricity of the nozzle profile is as follows: Obtain the minimum bounding rectangle of the nozzle profile; The nozzle eccentricity is calculated using the following formula:

[0037] in, It is the nozzle eccentricity. Let be the longer side of the smallest bounding rectangle of the nozzle profile. The shorter side of the smallest bounding rectangle of the nozzle profile; nozzle eccentricity With the preset second threshold Compare; If the nozzle eccentricity Greater than the preset second threshold If so, the nozzle is determined to be defective; It should be noted that the eccentricity calculation formula can accurately determine whether the nozzle is eccentric due to deformation, thereby further improving the accuracy of nozzle defect detection. The specific steps for determining the ratio of the actual area of ​​the nozzle profile to the theoretical area calculated based on the calibrated radius are as follows: Based on the calibrated nozzle radius Calculate the theoretical area of ​​the nozzle. ; Obtain the actual area of ​​the nozzle profile ; The ratio of the actual area to the theoretical area of ​​the nozzle is calculated using the following formula. :

[0038] area ratio Compared with the preset third threshold Compare; If the area ratio Less than the preset third threshold If so, the nozzle is determined to be defective; It should be noted that by calculating the ratio of the actual area of ​​the nozzle to the theoretical area, it is possible to accurately determine whether the nozzle area has changed due to blockage or wear, thus improving the means of nozzle defect detection. For example, based on the extracted nozzle profile and calibration parameters, the nozzle status is comprehensively judged through three methods. If all of the following conditions are met, the nozzle is determined to be defect-free; otherwise, an alarm is triggered and the machine is stopped: Circularity assessment: The actual area of ​​the nozzle profile is calculated using OpenCV's contourArea function. =116200 pixels 2 The arcLength function calculates the perimeter of the outline. Length = 1212 pixels. Substituting this into the formula, the roundness is... The calculated roundness is 0.98, which is greater than the preset first threshold of 0.80; Eccentricity determination: Obtain the smallest bounding rectangle of the nozzle profile, measure the long side a = 388 pixels and the short side b = 385 pixels, and substitute them into the formula for nozzle eccentricity. The calculated nozzle eccentricity is 0.1241, which is less than the preset second threshold of 0.20. Area ratio determination: Calculate the theoretical area based on the calibrated radius. =116422 pixels 2 Substituting into the formula, the area ratio = The calculated area ratio is 0.998, which is greater than the preset third threshold of 0.90. S3. Real-time monitoring of whether the laser cutting system experiences collisions; If a collision event is detected, it is determined that the nozzle calibration should be re-performed, and the process returns to step S1; If no collision event is detected, proceed to step S4; For example, during laser cutting, a collision sensor monitors the contact state between the laser cutting head and the workpiece or other objects in real time, with a sampling frequency of 100Hz. If the sensor detects a collision signal (e.g., the cutting head collides with the edge of the material with a collision force greater than 5N), it determines that a collision event has occurred. The system automatically returns to step S1 to re-extract the nozzle profile and recalibrate the center point, updating the nozzle center point coordinates.

[0039] If no collision event is detected, proceed to the next step of molten pool center detection and alignment judgment; S4. Periodically acquire a second image containing the molten pool, extract the center coordinates of the molten pool from the acquired second image, and calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle at the current moment; When the offset exceeds the preset tolerance, the laser cutting head is controlled to perform beam alignment adjustment; Return to step S3; The specific steps in step S4 include: S41. Analyze the characteristics of the molten pool profile to determine the orientation of the molten pool head; S42. Calculate the centroid coordinates of the head region of the molten pool, and use the centroid coordinates as the center coordinates of the molten pool; S43. Calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle using the following formula. :

[0040] Among them, ( , () represents the coordinates of the center of the molten pool. , () represents the coordinates of the nozzle center; S44. Adjust the offset Compare with a preset distance threshold: If offset If the distance is greater than or equal to the preset distance threshold, the laser cutting head is controlled to perform centering adjustment according to the offset direction and amount of the molten pool center coordinates relative to the nozzle center coordinates. After completion, the process returns to step S3. If offset If the distance is less than the preset distance threshold, return directly to step S3; For example, the industrial camera periodically acquires a second image containing the molten pool according to the second image acquisition parameters, such as... Figure 5 As shown, the melt pool mask region is segmented using a semantic segmentation model, and the melt pool contour is extracted. Analysis of the molten pool contour features: The molten pool is teardrop-shaped, with its head facing the direction of laser cutting. The head orientation is determined based on the direction of the long side of the smallest bounding rectangle of the molten pool.

[0041] The moments function is used to calculate the centroid coordinates of the head region of the molten pool, as follows: Figure 6 As shown, this is taken as the center coordinates of the molten pool (x2, y2) = (1246, 1060) pixels; Substitute into the offset formula The offset is calculated. If the pixel value is less than the preset tolerance of 5 pixels, no adjustment is needed; return to step S3 to continue monitoring. If the offset changes due to vibration during the cutting process, for example, if the center coordinates of the molten pool are measured to be (x2, y2) = (1250, 1065) pixels, the offset can be calculated. Pixels, greater than the preset tolerance: The system sends control signals to the beam adjustment mechanism based on the offset direction (7 pixels off in the positive x-axis direction and 8 pixels off in the positive y-axis direction).

[0042] The servo motor drives the internal lens to move 0.07mm along the negative x-axis and 0.08mm along the negative y-axis. After completing the centering adjustment, return to step S3. It should be noted that by analyzing the molten pool contour features and calculating the offset, the laser beam can be precisely adjusted for alignment, ensuring high precision in the cutting process.

[0043] The special scenario handling in this embodiment includes nozzle defect handling and post-collision recalibration. Specifically, nozzle defect handling includes: If the nozzle becomes deformed due to wear during the cutting process, and the measured roundness is 0.75 (less than 0.80), the system will immediately trigger an audible and visual alarm, and simultaneously control the laser cutting equipment to stop, prompting the operator to replace the nozzle. After replacement, the process will be restarted by re-executing step S1.

[0044] Recalibration after collision: If the cutting head collides with the workpiece, the collision sensor triggers a signal, the system automatically interrupts the cutting, and returns to step S1 to reacquire the nozzle image. After contour extraction and fitting, the nozzle center coordinates are updated to (1241, 1055) pixels to ensure that subsequent centering calculations are based on the latest nozzle status.

[0045] In one embodiment of the present invention, unlike the above embodiments, when acquiring the first image for nozzle contour extraction and center calibration in step S1, the first image acquisition parameters are used. In step S4, when acquiring the second image used to extract the center coordinates of the molten pool, the second image acquisition parameters are used. The exposure time of the first image acquisition parameter is longer than the exposure time of the second image acquisition parameter; It should be noted that by setting different exposure times, the acquired images can be ensured to meet the requirements of nozzle calibration and molten pool detection, thereby improving the system's adaptability and accuracy.

[0046] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0047] like Figure 7 As shown, the following are embodiments of the automatic alignment system for laser cutting beams based on molten pool provided in this disclosure. This system and the automatic alignment method for laser cutting beams based on molten pool in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the automatic alignment system for laser cutting beams based on molten pool, please refer to the embodiments of the automatic alignment method for laser cutting beams based on molten pool described above.

[0048] The system includes: The dynamic nozzle calibration module is used to periodically acquire a first image containing the nozzle during the laser cutting process, and dynamically extract the nozzle contour and calibrate the center based on the acquired first image to obtain the nozzle center coordinates at the current moment. The defect detection module is used to determine nozzle defects based on the extracted nozzle profile and the calibrated nozzle center coordinates; if a defect is found in the nozzle, an alarm or shutdown operation is executed. The collision monitoring module is used to monitor whether a collision occurs in the laser cutting system in real time; if a collision event is detected, it determines that the nozzle calibration should be re-performed. The alignment judgment and adjustment module is used to periodically acquire a second image containing the molten pool when the nozzle collides, extract the center coordinates of the molten pool from the acquired second image, and calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle at the current moment; when the offset exceeds the preset tolerance, the laser cutting head is controlled to perform beam alignment adjustment.

[0049] This embodiment achieves real-time beam alignment during laser cutting through the interactive collaboration of a dynamic nozzle calibration module, a defect detection module, a collision monitoring module, and an alignment judgment and adjustment module. This improves cutting accuracy and quality, extends equipment lifespan, reduces manual inspection and maintenance costs, and enhances the overall reliability of the system.

[0050] The storage medium provided in this application stores a program product capable of implementing an automatic alignment method for laser cutting beams based on a molten pool.

[0051] The automatic laser cutting beam alignment method based on the molten pool includes: periodically acquiring a first image containing the nozzle during the laser cutting process, and dynamically extracting the nozzle contour and calibrating the center point based on the acquired first image to obtain the nozzle center coordinates at the current moment; judging nozzle defects based on the extracted nozzle contour and the calibrated nozzle center coordinates; if the nozzle has a defect, executing an alarm or stopping operation; monitoring whether the laser cutting system collides in real time; if a collision event is detected, determining to recalibrate the nozzle; when a nozzle collision occurs, periodically acquiring a second image containing the molten pool, extracting the molten pool center coordinates from the acquired second image, and calculating the offset between the molten pool center coordinates and the nozzle center coordinates at the current moment; when the offset exceeds a preset tolerance, controlling the laser cutting head to adjust the beam alignment.

[0052] In some possible implementations, the automatic laser cutting beam alignment method based on molten pool of this disclosure can be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0053] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0054] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for automatic laser cutting beam alignment based on a molten pool, characterized in that, Includes the following steps: S1. During the laser cutting process, a first image containing the nozzle is periodically acquired, and the nozzle contour is dynamically extracted and the center is calibrated based on the acquired first image to obtain the nozzle center coordinates at the current moment; S2. Based on the extracted nozzle profile and the calibrated nozzle center coordinates, determine the nozzle defects; If the nozzle is defective, an alarm or shutdown operation will be executed; If the nozzle has no defects, proceed to step S3; S3. Real-time monitoring of whether the laser cutting system experiences collisions; If a collision event is detected, it is determined that the nozzle calibration should be re-performed, and the process returns to step S1; If no collision event is detected, proceed to step S4; S4. Periodically acquire a second image containing the molten pool, extract the center coordinates of the molten pool from the acquired second image, and calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle at the current moment; When the offset exceeds the preset tolerance, the laser cutting head is controlled to perform beam alignment adjustment; Return to step S3.

2. The automatic laser cutting beam alignment method based on molten pool according to claim 1, characterized in that, The specific steps of step S1 are as follows: S11. Perform grayscale conversion and filtering preprocessing on the acquired raw image; S12. Extract the nozzle profile from the preprocessed image; S13. Perform circular curve fitting on the nozzle profile to calculate the nozzle center coordinates and nozzle radius.

3. The automatic laser cutting beam alignment method based on molten pool according to claim 1, characterized in that, The nozzle defect assessment in step S2 is performed in at least one of the following ways: The roundness is determined based on the nozzle profile calculation; The judgment is based on the eccentricity of the nozzle profile; The determination is based on the ratio of the actual area of ​​the nozzle profile to the theoretical area calculated based on the calibrated radius.

4. The automatic laser cutting beam alignment method based on molten pool according to claim 3, characterized in that, The roundness determination based on nozzle profile calculation is as follows: Calculate the area of ​​the nozzle profile and perimeter ; The nozzle roundness is calculated using the following formula. : nozzle roundness Compared with the preset first threshold Compare; If the nozzle roundness Less than the preset first threshold If so, the nozzle is determined to be defective.

5. The automatic laser cutting beam alignment method based on molten pool according to claim 3, characterized in that, The determination based on the eccentricity of the nozzle profile is as follows: Obtain the minimum bounding rectangle of the nozzle profile; The nozzle eccentricity is calculated using the following formula: in, It is the nozzle eccentricity. Let be the longer side of the smallest bounding rectangle of the nozzle profile. The shorter side of the smallest bounding rectangle of the nozzle profile; nozzle eccentricity With the preset second threshold Compare; If the nozzle eccentricity Greater than the preset second threshold If so, the nozzle is determined to be defective.

6. The automatic laser cutting beam alignment method based on molten pool according to claim 3, characterized in that, The specific steps for determining the ratio of the actual area of ​​the nozzle profile to the theoretical area calculated based on the calibrated radius are as follows: Based on the calibrated nozzle radius Calculate the theoretical area of ​​the nozzle. ; Obtain the actual area of ​​the nozzle profile ; The ratio of the actual area to the theoretical area of ​​the nozzle is calculated using the following formula. : area ratio Compared with the preset third threshold Compare; If the area ratio Less than the preset third threshold If so, the nozzle is determined to be defective.

7. The automatic laser cutting beam alignment method based on molten pool according to claim 1, characterized in that, The specific steps in step S4 include: S41. Analyze the characteristics of the molten pool profile to determine the orientation of the molten pool head; S42. Calculate the centroid coordinates of the head region of the molten pool, and use the centroid coordinates as the center coordinates of the molten pool; S43. Calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle using the following formula. : Among them, ( , () represents the coordinates of the center of the molten pool. , () represents the coordinates of the nozzle center; S44. Adjust the offset Compare with a preset distance threshold: If offset If the distance is greater than or equal to the preset distance threshold, the laser cutting head is controlled to perform centering adjustment according to the offset direction and amount of the molten pool center coordinates relative to the nozzle center coordinates. After completion, the process returns to step S3. If offset If the distance is less than the preset distance threshold, return directly to step S3.

8. The automatic laser cutting beam alignment method based on molten pool according to claim 1, characterized in that, When acquiring the first image for nozzle contour extraction and center calibration in step S1, the first image acquisition parameters are used. In step S4, when acquiring the second image used to extract the center coordinates of the molten pool, the second image acquisition parameters are used. The exposure time of the first image acquisition parameter is longer than the exposure time of the second image acquisition parameter.

9. An automatic laser cutting beam alignment system based on a molten pool, characterized in that, include: The dynamic nozzle calibration module is used to periodically acquire a first image containing the nozzle during the laser cutting process, and dynamically extract the nozzle contour and calibrate the center based on the acquired first image to obtain the nozzle center coordinates at the current moment. The defect detection module is used to determine nozzle defects based on the extracted nozzle profile and the calibrated nozzle center coordinates; if a defect is found in the nozzle, an alarm or shutdown operation is executed. The collision monitoring module is used to monitor whether a collision occurs in the laser cutting system in real time; if a collision event is detected, it determines that the nozzle calibration should be re-performed. The alignment judgment and adjustment module is used to periodically acquire a second image containing the molten pool when the nozzle collides, extract the center coordinates of the molten pool from the acquired second image, and calculate the offset between the center coordinates of the molten pool and the center coordinates of the nozzle at the current moment; when the offset exceeds the preset tolerance, the laser cutting head is controlled to perform beam alignment adjustment.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the step of automatic centering of the laser cutting beam based on the molten pool as described in any one of claims 1 to 8.

Images