Water guide laser light-water coupling automatic calibration method

Abstract

The application provides a water guide laser light-water coupling automatic calibration method applied to a water guide laser light-water coupling automatic calibration system. The calibration method comprises the following steps: when a laser collimation head receives a laser beam, the relative position image of a light spot generated by the laser beam and a nozzle is acquired, a temporary image converted according to the relative position image is subjected to edge detection to extract edge features therein, the light spot edge features are subjected to circle detection to obtain a light spot detection result; the nozzle edge features are detected to obtain a nozzle detection result; and based on the light spot detection result and the nozzle detection result, the light path of the laser beam is changed by an electric light path calibration module to adjust the position of the light spot, so as to realize automatic calibration of light-water coupling. The application automatically adjusts the light spot position, eliminates errors possibly caused by manual adjustment, improves calibration efficiency and stability, and reduces consumption of human resources.

Description

Technical Field

[0001] This invention relates to the field of water-guided laser coupling technology, and more specifically, to an automatic calibration method for water-guided laser light-water coupling. Background Technology

[0002] In water-guided laser processing technology, effective coupling of the laser beam and the water jet is crucial for achieving high-quality processing. This requires precise optical path calibration of the laser beam to ensure perfect alignment between the laser spot and the sapphire nozzle in the water-guided laser system. However, the heating effect of the laser beam on optical components (such as the sapphire nozzle) during processing causes spot position drift, further increasing the frequency of optical path calibration requirements.

[0003] Currently, optical path calibration mainly relies on manual adjustment, with operators relying on visual observation and experience to make adjustments manually. This method has many shortcomings in practical applications. First, the accuracy of calibration is highly dependent on the operator's experience and skill level, resulting in significant subjectivity. Second, errors are prone to occur during manual calibration, leading to unstable calibration results and consequently affecting processing accuracy. Finally, manual calibration is inefficient, especially when multiple calibrations are performed, which can easily lead to a decrease in production efficiency. Summary of the Invention

[0004] The problem solved by this invention is one or more of the aforementioned related technical problems.

[0005] To address the aforementioned problems, this invention provides an automatic calibration method for water-guided laser optical-water coupling, applied to an automatic calibration system for water-guided laser optical-water coupling. The automatic calibration system includes a laser collimator, a coaxial monocular vision inspection module, an electric optical path calibration module, and a coupling cavity equipped with a nozzle. The automatic calibration method for water-guided laser optical-water coupling includes:

[0006] When the laser collimator receives the laser beam...

[0007] The coaxial monocular vision detection module acquires an image showing the relative position of the laser beam spot and the nozzle, and then converts the relative position image to obtain a temporary image.

[0008] Edge detection is performed on the temporary image to extract edge features, including spot edge features and nozzle edge features;

[0009] The edge features of the light spot are subjected to circle detection to obtain the light spot detection result;

[0010] Based on the improved Hough gradient circular transform, the nozzle edge features are used for detection to obtain nozzle detection results;

[0011] Based on the spot detection results and the nozzle detection results, the optical path of the laser beam is changed by the electric optical path calibration module to adjust the position of the spot, so as to achieve automatic calibration of the optical-water coupling.

[0012] Optionally, the step of detecting nozzles based on the improved Hough gradient circular transform according to the nozzle edge features to obtain nozzle detection results includes:

[0013] The gradient information of each edge point in the nozzle edge feature is determined, and a parameter space is constructed based on the gradient information; the gradient information includes the gradient magnitude and gradient direction.

[0014] Multiple candidate circle centers are determined based on the gradient magnitude and gradient direction of each edge point, and voting is performed on each candidate circle center in the parameter space to generate multiple temporary candidate circle centers;

[0015] The corresponding candidate circle is determined based on the temporary candidate circle center and the preset radius parameter;

[0016] The overlap of each candidate circle is detected based on the nozzle edge features, and the candidate circle with the highest overlap is taken as the nozzle detection result.

[0017] Optionally, the electric optical path calibration module includes an electric deflector. Based on the spot detection results and the nozzle detection results, the electric optical path calibration module changes the optical path of the laser to adjust the position of the spot, thereby achieving automatic calibration of the light-water coupling. This includes:

[0018] Adjust the motorized deflector to its initial position;

[0019] The electric deflector is controlled to move continuously in a preset step size, and image change data of the nozzle is collected;

[0020] The mapping relationship between the image change data and the preset step size is determined based on a preset algorithm;

[0021] The electric deflector is adjusted according to the mapping relationship, the spot detection result, and the nozzle detection result to change the optical path of the laser so that the spot is aligned with the image of the nozzle.

[0022] Optionally, the coaxial monocular vision detection module includes an auxiliary light source, an adjustable lens barrel, and a monocular CCD camera. The monocular CCD camera is connected to the adjustable lens barrel. The auxiliary light source and the laser beam are on the same optical axis to illuminate the light spot. The step of acquiring the relative position image of the light spot and the nozzle through the coaxial monocular vision detection module includes:

[0023] By adjusting the focal length of the adjustable lens barrel, the imaging plane of the monocular CCD camera is made to coincide with the plane where the nozzle is located;

[0024] The auxiliary light source is used for illumination, and the relative position image of the light spot and the nozzle is acquired by the monocular CCD camera.

[0025] Optionally, the step of converting the relative position image to obtain a temporary image includes:

[0026] The segmentation threshold of the relative position image is determined by an image processing algorithm;

[0027] The relative position image is segmented according to the segmentation threshold to obtain the temporary image.

[0028] Optionally, the step of performing circle detection on the edge features of the light spot to obtain the light spot detection result includes:

[0029] All pixels in the edge features of the light spot are counted, and a preset number of the pixels are selected for random sampling consistency detection to obtain the edge pixel set;

[0030] The set of edge pixels is fitted to obtain a target fitted circle, and the target fitted circle is used as the spot detection result.

[0031] Optionally, fitting the set of edge pixels to obtain the target fitted circle includes:

[0032] A preset number of pixels from the set of edge pixels are selected for fitting to obtain a current fitted circle, and the number of edge points contained in the current fitted circle is taken as the number of interior points.

[0033] Repeat the above steps. When the number of interior points of the current fitted circle is higher than the number of interior points of the fitted circle in the previous iteration, and the radius of the current fitted circle meets the preset radius range, the current fitted circle is used as a temporary fitted circle, or until the preset number of iterations is reached, the current fitted circle is used as the target fitted circle.

[0034] Optionally, the motorized optical path calibration module further includes a motion controller connected to the motorized deflector; adjusting the motorized deflector according to the mapping relationship, the spot detection result, and the nozzle detection result to align the spot with the nozzle image includes:

[0035] Based on the mapping relationship, the spot detection result, and the nozzle detection result, the execution command is determined by the motion controller;

[0036] According to the execution command, the electric deflector is adjusted to deflect so that the light spot is aligned with the image of the nozzle.

[0037] Optionally, the segmentation threshold includes a first segmentation threshold and a second segmentation threshold; the step of performing region segmentation on the relative position image according to the segmentation threshold to obtain the temporary image includes:

[0038] The relative position image is processed based on the first segmentation threshold and the second segmentation threshold to obtain the temporary image;

[0039] Wherein, the first segmentation threshold is used to segment the high-brightness grayscale area and the medium-brightness grayscale area in the relative position image; the second segmentation threshold is used to segment the medium-brightness grayscale area and the low-brightness grayscale area in the relative position image.

[0040] Optionally, the temporary image includes a spot image; after converting the relative position image to obtain the temporary image, the process further includes:

[0041] The light spot image is subjected to median filtering, and an opening operation is performed on the filtered image according to the first preset circular convolution kernel to obtain a temporary light spot image;

[0042] The temporary spot image is closed by performing a closing operation on the second preset circular convolution kernel to obtain the processed spot image.

[0043] The beneficial effects of the water-guided laser optical-water coupling automatic calibration method of the present invention are:

[0044] When the laser collimator receives the laser beam, it first acquires an image of the relative position between the laser beam spot and the nozzle using a coaxial monocular vision detection module. This process involves capturing images in real time with a camera and generating initial data to lay the foundation for subsequent processing. The acquired relative position image is then transformed to obtain a temporary image. This process aims to improve the accuracy of subsequent steps (such as edge detection), reduce the impact of background noise, and thus extract key features more effectively.

[0045] Edge detection is performed on a temporary image to extract edge features of the light spot and nozzle. This process employs edge detection algorithms (such as the Canny operator) to identify obvious boundaries in the image, especially the contours of the light spot and nozzle. Accurate extraction of edge features ensures the reliability of subsequent feature recognition and circle detection, laying the foundation for precise localization of the light spot.

[0046] Subsequently, circle detection is performed on the extracted spot edge features to obtain the spot detection result. This is typically achieved using a parameterized equation for a circle and corresponding algorithms (such as Hough transform). The spot detection result from this process provides an accurate spot position for the calibration process, ensuring that the laser beam can be effectively coupled with the water jet.

[0047] Next, an improved Hough gradient circular transform is used to detect the nozzle's edge features to obtain the nozzle detection results. This step ensures that the nozzle's position and shape are accurately identified and located. Therefore, the accuracy of nozzle detection is enhanced, especially against complex backgrounds, ensuring correct nozzle positioning and helping to balance the relationship between the laser spot and the nozzle.

[0048] Finally, based on the light spot detection results and nozzle detection results, the motorized optical path calibration module automatically adjusts the light spot to achieve automatic calibration of the light-water coupling. By automatically adjusting the light spot position, errors that may be caused by manual adjustment are eliminated, improving calibration efficiency and stability while reducing the consumption of human resources.

[0049] Therefore, the automatic calibration method for water-guided laser optical-water coupling of the present invention can achieve efficient and accurate automatic calibration in complex environments, improving the stability and processing accuracy of the optical-water coupling system. The use of automation technology not only improves processing efficiency but also reduces dependence on operator skill levels, providing higher consistency and repeatability, thus making the water-guided laser processing process more reliable and efficient. Attached Figure Description

[0050] Figure 1 This is one of the flowcharts of an automatic calibration method for water-guided laser optical-water coupling according to an embodiment of the present invention;

[0051] Figure 2 This is an embodiment of the water-guided laser optical-water coupling automatic calibration system of the present invention;

[0052] Figure 3 This is a schematic diagram of the relative position image according to an embodiment of the present invention;

[0053] Figure 4 This is a schematic diagram of a temporary image according to an embodiment of the present invention;

[0054] Figure 5 This is a schematic diagram of the automatic coupling of a water-guided laser spot into a water jet according to an embodiment of the present invention;

[0055] Figure 6 This is a schematic diagram of the optical path of the water-guided laser optical-water coupling automatic calibration system according to an embodiment of the present invention;

[0056] Figure 7 This is a schematic diagram of the processed light spot image according to an embodiment of the present invention;

[0057] Figure 8 This is the second schematic diagram of the automatic calibration method for water-guided laser optical-water coupling according to an embodiment of the present invention.

[0058] Explanation of reference numerals in the attached figures:

[0059] 1-Laser collimator, 101-Laser input QBH interface, 2-Variable aperture, 3-Electrically powered optical path calibration module, 301-Electrically powered deflector, 302-Reflector, 303-Dichromatic mirror, 4-Coaxial monocular vision inspection module, 401-Auxiliary light source, 402-Adjustable lens barrel, 403-Monocular CCD camera, 5-Focusing lens, 6-Coupled cavity. Detailed Implementation

[0060] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0061] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to"; the term "based on" means "at least partially based on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; and the term "optionally" means "optional embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first," "second," etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0062] The names of messages or information exchanged between the various devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0063] like Figure 1 As shown in the figure, an automatic calibration method for water-guided laser optical-water coupling provided by an embodiment of the present invention is applied to a water-guided laser optical-water coupling automatic calibration system. The water-guided laser optical-water coupling automatic calibration system includes a laser collimator 1, a coaxial monocular vision detection module 4, an electric optical path calibration module 3, and a coupling cavity 6 equipped with a nozzle. The water-guided laser optical-water coupling automatic calibration method includes:

[0064] Step S100: When the laser collimator 1 receives the laser beam, the coaxial monocular vision detection module 4 acquires an image of the relative position of the light spot generated by the laser beam and the nozzle, and converts the relative position image to obtain a temporary image.

[0065] Specifically, such as Figure 2 The diagram shows the structure of a water-guided laser optical-water coupling automatic calibration system, including a laser collimator 1 for receiving laser beams via a laser input QBH interface 101. A variable aperture 2 is immediately following the laser collimator to adjust the size of the laser spot entering the optical path. The motorized optical path calibration module 3 includes: a motorized deflector 301 for adjusting the laser direction for precise optical path calibration; a reflector 302 for reflecting the laser beam to ensure correct propagation; and a dichroic mirror 303 for separating lasers of different wavelengths, improving system flexibility and functionality. The coaxial monocular vision inspection module 4 includes: an auxiliary light source 401 for providing additional illumination to enhance visual inspection; an adjustable lens barrel 402 for adjusting the focal length by changing its distance from the CCD camera 403, maintaining image clarity at different working distances, allowing adjustment at different viewing distances to obtain a clear image; and a monocular CCD camera 403 for capturing images of the laser spot for real-time monitoring. Focusing lens 5 is used to focus the laser beam, ensuring that the laser beam has a precise focus within the target area. Coupled cavity 6 ultimately combines the laser and imaging system to form a complete optical path system.

[0066] The laser collimator 1 receives the laser beam through the laser input QBH interface 101 and sends it to the variable aperture (2). After adjustment, the beam is then transmitted to the motorized optical path calibration module 3. The motorized deflector 301, reflector 302, and dichroic mirror 303 in the motorized optical path calibration module 3 jointly adjust and calibrate the optical path of the laser beam. The calibrated laser beam is then transmitted to the coaxial monocular vision detection module 4, where it is illuminated by an auxiliary light source 401 and focused onto the monocular CCD camera 403 via an adjustable lens barrel 402. Finally, the focusing lens 5 and the coupling cavity 6 ensure that the laser beam is correctly focused and coupled.

[0067] Furthermore, the coaxial settings for the water-guided laser optical-water coupling automatic calibration system include:

[0068] The laser collimator receives the laser beam, which continues to propagate along the same optical axis after passing through a variable aperture. The electric optical path calibration module 3 then adjusts the beam to maintain alignment along the same optical axis. The auxiliary light source 401 is typically designed along the path of the laser beam to illuminate the laser spot. When this light source is aligned with the laser beam, it provides a clear view. The adjustable lens barrel 402 allows light to pass directly from the auxiliary light source to the industrial monocular CCD camera 403, ensuring distortion-free imaging. The monocular CCD camera 403's optical path is coaxial with other components, ensuring that the captured image originates directly from the same laser beam.

[0069] When the laser collimator 1 receives the laser beam, a coaxial monocular vision inspection module 4, equipped with a camera and a suitable light source, captures an image of the relative position between the laser spot and the nozzle in real time. This capture process ensures that the latest image data is obtained in the laser processing environment; the image mode is typically a grayscale image, for example... Figure 3 The diagram shows a relative position image. The acquired image resolution is 2448×2048, and the acquisition frequency is 15fps. This ensures high resolution and real-time performance of the light spot and nozzle image acquisition, achieving micron-level positioning of the autocollimation system.

[0070] If relative motion exists during the acquisition process (e.g., slight vibration of a machine tool), image stabilization technology can be used to correct the image. This technology can reduce blurring caused by motion and improve image clarity.

[0071] Transformations are typically performed on the acquired relative position images, including image enhancement (improving image visibility by adjusting contrast and brightness to ensure edge features are more prominent) and binarization (facilitating edge detection and feature extraction).

[0072] After completing the above processing, the generated temporary image is as follows: Figure 4 As shown, this is a schematic diagram of the temporary image (binarized segmentation result), which is used for subsequent edge detection and feature extraction steps. This temporary image will serve as input for subsequent algorithm analysis, ensuring the accuracy of subsequent processing.

[0073] By accurately acquiring relative position images, the entire water-guided laser processing system becomes more stable during automatic calibration. Optimized initial data input reduces calibration errors caused by data discrepancies, improving the overall stability of the system. Furthermore, automated image acquisition and processing significantly reduces the time and labor intensity required for manual calibration, enhancing the automation level and consistency of the processing.

[0074] Step S200: Perform edge detection on the temporary image to extract edge features, including spot edge features and nozzle edge features.

[0075] Specifically, firstly, the temporary image generated in step S100 is used as input data. This image has been preprocessed to have high clarity and low noise levels, providing a reliable basis for edge detection.

[0076] Choose a suitable edge detection algorithm, such as the Canny operator, Sobel operator, or Laplacian operator. For example, the Canny operator can be chosen, as it has strong noise suppression and edge detection capabilities. After edge detection, the edge features of the light spot and nozzle are extracted and output as a binary image for subsequent feature recognition and location localization.

[0077] By employing a highly efficient edge detection algorithm, the edges of the light spot and nozzle can be automatically identified in complex backgrounds, ensuring the accuracy of the extracted features. Furthermore, the multiple steps in the edge detection process (such as thresholding and non-maximum suppression) effectively reduce false alarms and missed detections, resulting in more precise extraction of the light spot and nozzle edges, which is crucial for subsequent calibration. Accurate edge feature extraction provides reliable data for subsequent feature recognition and circle detection, ensuring effective alignment between the light spot and nozzle, thereby improving the overall performance of the water-guided laser coupling.

[0078] By using automated edge detection algorithms, the time spent on manual inspection is eliminated, improving the efficiency of the entire calibration process and enabling the system to quickly adapt to changes in the production environment. Simultaneously, automated edge detection technology reduces reliance on operator skill levels, ensuring that even non-professionals can effectively complete calibration, thus enhancing system consistency and operability.

[0079] Step S300: Perform circle detection on the edge features of the light spot to obtain the light spot detection result.

[0080] Specifically, a suitable circle detection algorithm, such as RCD (Randomized Circle Detection), is used to detect the position of the light spot. This algorithm is widely used for circle detection processing in images due to its efficiency and adaptability.

[0081] The automated circle detection process reduces human intervention and adjustment time, making the optical-water coupling calibration process faster and more efficient. This improves the overall operational efficiency of the production line.

[0082] Step S400: Based on the improved Hough gradient circular transform, the nozzle edge features are used for detection to obtain the nozzle detection result.

[0083] Specifically, the improved Hough gradient circle transform is an enhanced method of the traditional Hough transform, designed to improve the efficiency and accuracy of circle detection. This method combines the advantages of edge detection and Hough transform, and performs better in high-noise or complex backgrounds.

[0084] The improved Hough gradient circle transform process typically includes: gradient calculation: calculating the gradient of the edge intensity map to obtain the direction and intensity of the edge information; circle accumulation: establishing an accumulator while recording possible combinations of center coordinates and radii; and optimizing the accumulator update process by incorporating edge gradient information to improve detection accuracy. Finally, the detected nozzle result is output, including the nozzle's center coordinates and radius information. These parameters can be used for subsequent control and adjustment.

[0085] The improved Hough gradient circular transform, combining edge features and gradient information, can more accurately identify the circular characteristics of nozzles, thereby improving detection accuracy. This process is highly adaptable to noise and background interference, maintaining good detection performance even in complex environments, thus enhancing system reliability.

[0086] Furthermore, by combining the advantages of edge detection and Hough transform, unnecessary computation is reduced, and the overall detection speed is improved, providing support for real-time or online detection. The improved algorithm maintains high efficiency and adaptability in the detection of nozzles of different sizes and shapes, and has good results for the rapid detection of new nozzles and adaptation to new environments.

[0087] Step S500: Based on the spot detection result and the nozzle detection result, the optical path of the laser beam is changed by the electric optical path calibration module 3 to adjust the position of the spot, so as to realize the automatic calibration of the light-water coupling.

[0088] Specifically, after acquiring the positions of the beam spot and the nozzle, the relative positional deviation between the center of the beam spot and the center of the nozzle is calculated. This can usually be achieved through simple geometric calculations (such as Euclidean distance measurement). The purpose of this step is to determine the specific direction and distance the beam needs to be offset to ensure optimal coupling between the two.

[0089] The calculated deviation value is input into the motorized optical path calibration module 3. This module may include a stepper motor, servo motor, or other drive device, responsible for adjusting the angle and position of the optical path system (such as a mirror or lens). Based on the deviation value, the motorized calibration module is controlled to make precise adjustments and corrects the position in real time based on feedback information, ensuring fast and accurate calibration.

[0090] After the adjustment is completed, the optical-water coupling state can be verified, which can be achieved by monitoring parameters such as coupling efficiency in real time.

[0091] Based on precise spot and nozzle detection results, highly accurate light-water coupling can be achieved, significantly improving the efficiency and quality of laser processing. This process reduces manual intervention through automatic calibration, increasing the degree of automation and minimizing errors caused by human operation, thereby enhancing the overall stability of the system. Simultaneously, real-time deviation calculation and immediate adjustments enable the system to quickly adapt to dynamically changing working environments, improving overall production efficiency.

[0092] The automated adjustment function of the electric optical path calibration module 3 simplifies the operation process, making it easy for even untrained operators to manage and adjust the system, thereby reducing the skill requirements for operation.

[0093] In this embodiment, when the laser collimator receives the laser beam, it first acquires an image of the relative position between the laser beam spot and the nozzle using the coaxial monocular vision detection module 4. This process involves capturing images in real time with a camera and generating initial data to lay the foundation for subsequent processing. The acquired relative position image is then converted to obtain a temporary image. This process aims to improve the accuracy of subsequent steps (such as edge detection), reduce the impact of background noise, and thus extract key features more effectively.

[0094] Edge detection is performed on a temporary image to extract edge features of the light spot and nozzle. This process employs edge detection algorithms (such as the Canny operator) to identify obvious boundaries in the image, especially the contours of the light spot and nozzle. Accurate extraction of edge features ensures the reliability of subsequent feature recognition and circle detection, laying the foundation for precise localization of the light spot.

[0095] Subsequently, circle detection is performed on the extracted spot edge features to obtain the spot detection result. This is typically achieved using a parameterized equation for a circle and corresponding algorithms (such as Hough transform). The spot detection result from this process provides an accurate spot position for the calibration process, ensuring that the laser beam can be effectively coupled with the water jet.

[0096] Next, an improved Hough gradient circular transform is used to detect the nozzle's edge features to obtain the nozzle detection results. This step ensures that the nozzle's position and shape are accurately identified and located. Therefore, the accuracy of nozzle detection is enhanced, especially against complex backgrounds, ensuring correct nozzle positioning and helping to balance the relationship between the laser spot and the nozzle.

[0097] Finally, based on the light spot detection results and nozzle detection results, the motorized optical path calibration module 3 automatically adjusts the light spot to achieve automatic calibration of the light-water coupling. By automatically adjusting the light spot position, errors that may be caused by manual adjustment are eliminated, improving calibration efficiency and stability while reducing the consumption of human resources.

[0098] Therefore, the automatic calibration method for water-guided laser optical-water coupling of the present invention can achieve efficient and accurate automatic calibration in complex environments, improving the stability and processing accuracy of the optical-water coupling system. The use of automation technology not only improves processing efficiency but also reduces dependence on operator skill levels, providing higher consistency and repeatability, thus making the water-guided laser processing process more reliable and efficient.

[0099] Optionally, the step of detecting nozzles based on the improved Hough gradient circular transform according to the nozzle edge features to obtain nozzle detection results includes:

[0100] The gradient information of each edge point in the nozzle edge feature is determined, and a parameter space is constructed based on the gradient information; the gradient information includes the gradient magnitude and gradient direction.

[0101] Multiple candidate circle centers are determined based on the gradient magnitude and gradient direction of each edge point, and voting is performed on each candidate circle center in the parameter space to generate multiple temporary candidate circle centers;

[0102] The corresponding candidate circle is determined based on the temporary candidate circle center and the preset radius parameter;

[0103] The overlap of each candidate circle is detected based on the nozzle edge features, and the candidate circle with the highest overlap is taken as the nozzle detection result.

[0104] Specifically, nozzle detection uses an improved Hough gradient circular transform. The traditional Hough gradient circular transform traverses all edges, calculates the pixel gradient direction at each edge point, and forms intersections in space; these intersections are considered candidate circle centers. Simultaneously, the gradient directions of the intersections are accumulated as votes; the more votes, the greater the likelihood that the intersection is considered the optimal circle center. After all edge points have been processed, some points in the Hough space will have a high number of votes. These high-vote points are considered potential circle centers. By performing local maxima detection on these vote points, the optimal circle center location and corresponding radius can be found.

[0105] However, due to background noise interference in the nozzle edge features (nozzle edge detection results) that cannot be completely eliminated, these background noise edges also participate in the Hough gradient circle transform, interfering with the voting results and causing bias in the voting results of candidate circles. To solve this problem, based on the candidate circle results (candidate circles) obtained from the traditional Hough gradient circle transform, it is necessary to calculate the overlap degree between the edge of the candidate circle and the nozzle edge detection results (nozzle edge features). The candidate circle with the highest overlap degree will be identified as the best circle and used as the final detection result feedback. Figure 5 The diagram shows the automatic coupling of a water-guided laser spot into a water jet. Figure 5 The image before the automatic calibration of the motorized deflector contains nozzle detection results.

[0106] Optionally, the electric optical path calibration module 3 includes an electric deflector 301. The step of changing the optical path of the laser to adjust the position of the laser spot based on the spot detection result and the nozzle detection result, thereby achieving automatic calibration of the light-water coupling, includes:

[0107] Adjust the electric deflector 301 to the initial position, control the electric deflector 301 to move continuously in a preset step size, and collect image change data of the nozzle;

[0108] The mapping relationship between the image change data and the preset step size is determined based on a preset algorithm;

[0109] The electric deflector 301 is adjusted according to the mapping relationship, the spot detection result, and the nozzle detection result to change the optical path of the laser so that the spot is aligned with the image of the nozzle.

[0110] Optionally, the motorized optical path calibration module 3 further includes a motion controller connected to the motorized deflector. The step of adjusting the motorized deflector 301 according to the mapping relationship, the light spot detection result, and the nozzle detection result to align the light spot with the nozzle image includes:

[0111] Based on the mapping relationship, the spot detection result, and the nozzle detection result, the execution command is determined by the motion controller;

[0112] According to the execution command, the electric deflector 301 is adjusted to deflect so that the light spot is aligned with the image of the nozzle.

[0113] Specifically, such as Figure 2As shown, the laser collimator includes an integrated beam coupling device, an autocollimating lens assembly, and a laser input QBH interface 101 that can be directly connected to an optical fiber. The integrated beam coupling device is primarily responsible for effectively coupling the laser beam from the laser source to subsequent optical systems, ensuring efficient light transmission. The output of the integrated beam coupling device is connected to the autocollimating lens assembly. In its design, the integrated coupling device ensures that the beam is transmitted to subsequent optical components at the appropriate angle and size. The autocollimating lens assembly is used to correct and adjust the path of the laser beam, ensuring straight-line transmission in space and maintaining optimal focusing and divergence characteristics. The input of the autocollimating lens assembly receives the beam from the integrated beam coupling device and performs further collimation processing. The output of the autocollimating lens assembly should be connected to the laser input QBH interface 101 that can be directly connected to an optical fiber to ensure efficient beam transmission to the fiber. The laser input QBH interface 101 is a standardized interface that allows efficient laser transmission through optical fibers, enabling connections with other optical or laser systems. The QBH interface's structural design allows it to directly receive the beam from the autocollimating lens assembly, ensuring seamless integration. In many systems, the QBH interface may also include mechanical and optical alignment mechanisms to reduce light loss during connection and ensure efficient laser beam transmission. For example... Figure 6 The diagram shows the optical path of the water-guided laser optical-water coupling automatic calibration system.

[0114] like Figure 2 As shown, the motorized optical path calibration module 3 also includes a reflector 302, a dichroic mirror 303, and a motion controller. The motorized deflector 301 is used to adjust the direction of the light beam, precisely pointing it towards the nozzle, thus adjusting the relative position of the light spot and the nozzle. The motorized deflector 301 is directly connected to the motion controller to receive control commands. When the motion controller issues a command, the motorized deflector deflects at a set angle to change the propagation direction of the light beam. That is, the motorized deflector 301 can deflect according to the motion controller's commands, adjusting the relative position of the light spot and the nozzle to complete optical path auto-alignment. The reflector 302 is used to perform a first 90° bend on the light beam and guide it into the dichroic mirror. The reflector 302 is connected to the output end of the motorized deflector 301. After passing through the motorized deflector, the light beam first reaches the reflector and is reflected to the dichroic mirror 303. The dichroic mirror 303 is used to perform specific optical processing on the light beam (such as phase modulation, dispersion, etc.) and achieve a second 90° bend. Dichroic mirror 303 is placed opposite reflector 302 to receive the light beam from the reflector. The reflector is designed to ensure that the light beam is smoothly deflected after passing through dichroic mirror 303, maintaining the quality and consistency of the beam. A motion controller controls the movement of the motorized deflector to ensure precise alignment between the light beam and the nozzle. The motion controller is connected to motorized deflector 301 and sends control signals for deflection adjustment.

[0115] Specifically, heat is generated during laser processing, causing thermal deformation of optical components. Furthermore, replacing components in the water-guided processing system causes positional changes in the Z-axis direction. Therefore, the adjustable lens barrel 402 needs adjustment to ensure that the focal plane of the camera (monocular CCD camera 403) is always located on the plane where the nozzle and laser spot are located, thus achieving clear imaging. This results in a change in the mapping relationship between the image pixels acquired by the camera and the step size of the motorized deflector 301 during each processing step. Therefore, the motorized deflector 301 or its corresponding motor needs to be initialized. Then, the motorized deflector 301 or the motor is controlled to move continuously at a preset step size, and image change data of the nozzle is acquired; the mapping relationship between the image change data and the preset step size is determined based on a preset algorithm; and the motorized deflector 301 is adjusted by combining the spot detection results and the nozzle detection results to align the image of the spot with the nozzle.

[0116] In some embodiments, by controlling the motor to move continuously 8 times, each time moving 50 steps, the pixel changes (image change data) of the nozzle in the X and Y directions are detected. A preset algorithm, such as the least squares method, is used to fit the mapping relationship between the motor step size and the pixels. Finally, as... Figure 5 As shown, by adjusting the electric deflector 301, the light spot is moved and aligned with the nozzle, thereby realizing the self-alignment function of the water-guided laser processing optical path.

[0117] Optionally, such as Figure 2 As shown, the coaxial monocular vision detection module 4 includes an auxiliary light source 401, an adjustable lens barrel 402, and a monocular CCD camera 403. The monocular CCD camera 403 is connected to the adjustable lens barrel 402. The auxiliary light source 401 is on the same optical axis as the laser beam and is used to illuminate the light spot. The step of acquiring the relative position image of the light spot and the nozzle through the coaxial monocular vision detection module 4 includes:

[0118] By adjusting the focal length of the adjustable lens barrel 402, the imaging plane of the monocular CCD camera 403 is made to coincide with the plane where the nozzle is located;

[0119] The auxiliary light source 401 is used for illumination, and the relative position image of the light spot and the nozzle is acquired by the monocular CCD camera 403.

[0120] Specifically, by adjusting the focal length of the adjustable lens barrel 402, the imaging plane of the monocular CCD camera 403 is ensured to perfectly coincide with the plane where the nozzle is located. This precise alignment provides high-quality images, enabling the system to accurately capture the relative position of the light spot and the nozzle, thereby improving the accuracy and reliability of the measurement.

[0121] The auxiliary light source 401 provides sufficient illumination to the field of view, enabling the monocular CCD camera 403 to acquire images with adequate brightness and contrast. Furthermore, using the auxiliary light source 401 for illumination, instead of a traditional ring light source, effectively reduces shadow and reflection problems caused by space constraints or improper light source placement. This flexible light source selection ensures uniform illumination conditions, significantly improving image contrast and sharpness, and making the light spot and nozzle features more distinct. The use of the monocular CCD camera 403 makes the image acquisition process efficient and real-time, enabling rapid acquisition of images showing the relative positions of the light spot and nozzle. Such real-time feedback is crucial for dynamic adjustment and control systems, enabling faster responses.

[0122] Choosing the coaxial monocular vision inspection module 4 simplifies the system design, especially in space-constrained environments. The integration of the entire module not only saves space but also reduces interference between components, improving system stability and ease of use.

[0123] By automating the processing of images showing the relative positions of the laser spot and nozzle, the results can be used for subsequent control and calibration tasks, improving the automation level of the entire laser processing system. Such advanced detection systems can reduce human intervention and increase work efficiency.

[0124] Optionally, the step of converting the relative position image to obtain a temporary image includes:

[0125] The segmentation threshold of the relative position image is determined by an image processing algorithm;

[0126] The relative position image is segmented according to the segmentation threshold to obtain the temporary image.

[0127] Optionally, the segmentation threshold includes a first segmentation threshold and a second segmentation threshold; the step of performing region segmentation on the relative position image according to the segmentation threshold to obtain the temporary image includes:

[0128] The relative position image is processed based on the first segmentation threshold and the second segmentation threshold to obtain the temporary image;

[0129] Wherein, the first segmentation threshold is used to segment the high-brightness grayscale area and the medium-brightness grayscale area in the relative position image; the second segmentation threshold is used to segment the medium-brightness grayscale area and the low-brightness grayscale area in the relative position image.

[0130] Specifically, due to system space limitations, the camera illumination did not employ a traditional ring light source as in visual systems. Instead, a biased auxiliary light source 401 was chosen for illumination. This resulted in variations in the grayscale distribution in the image depending on the relative positions of the light spot and the nozzle. Therefore, an image processing algorithm, such as Otsu's method, was required to calculate the segmentation threshold in the current image. By iterating through grayscale values ​​from 0 to 255, the grayscale value that maximizes the inter-class variance was selected as the optimal threshold, thereby achieving adaptive image segmentation.

[0131] The formula for calculating the first segmentation threshold t is:

[0132]

[0133] In the formula: q1(t) is the mean value of pixels with gray values ​​less than the threshold t; q2(t) is the mean value of pixels with gray values ​​greater than t. The intra-class variance of pixels with grayscale values ​​less than the threshold t; t represents the intra-class variance of pixels with grayscale values ​​greater than the threshold t.

[0134] Because the light spot is splashed within the high-pressure water chamber, and because dust and other impurities near the nozzle cause noise in the image, the accuracy of spot and nozzle detection is affected. To enhance the image, weaken the background, and reduce the impact of noise, the relative position image is binarized based on a threshold derived from Otsu's method (image processing algorithm) to segment the image of the light spot and nozzle (e.g., ...). Figure 4 (As shown).

[0135]

[0136] Where g(x,y) is the binarized image; ti is the pixel gray value of the relative position image; the second segmentation threshold is 255-t; when segmenting the light spot, T = 255-t, and when segmenting the nozzle, segmentation is based on the first segmentation threshold t.

[0137] In some embodiments, Figure 4 It is based on Figure 3 Obtained by binarization. Figure 3 This is the original grayscale image (relative position image). The original grayscale image can be roughly divided into high-brightness grayscale areas, medium-brightness grayscale areas, and low-brightness grayscale areas based on grayscale values. In the grayscale image, the light spot corresponds to the high-brightness grayscale area, the nozzle is located in the low-brightness grayscale area, and the background noise belongs to the medium-brightness grayscale area. Specifically: High-brightness grayscale area (light spot): In the grayscale image, the grayscale value of the light spot area is relatively high, typically close to 255. Medium-brightness grayscale area (background noise): The grayscale value of the noise area is in the middle, between the light spot and the nozzle. Low-brightness grayscale area (nozzle): The grayscale value of the nozzle area is relatively low, close to 0.

[0138] To distinguish these three grayscale regions, the grayscale values ​​of the entire image need to be divided into three segments, i.e., two segmentation thresholds need to be determined. The grayscale values ​​of the original grayscale image are calculated using the Otsu method to obtain a t value, as shown in the above formula (1). This t value is used as the first segmentation threshold, and 255-t is used as the second segmentation threshold. The thresholds are applied for segmentation: High-brightness grayscale region (spot): Pixels with grayscale values ​​greater than t are marked as "high-brightness grayscale region", i.e., spot region. Medium-brightness grayscale region (background noise): Pixels with grayscale values ​​between t and 255-t are marked as "medium-brightness grayscale region", i.e., background noise region. Low-brightness grayscale region (nozzle): Pixels with grayscale values ​​less than 255-t are marked as "low-brightness grayscale region", i.e., nozzle region.

[0139] By applying these segmentation thresholds, high-brightness grayscale areas (light spots), medium-brightness grayscale areas (background noise), and low-brightness grayscale areas (nozzles) can be effectively distinguished, thus achieving region segmentation. Ultimately, the pixel values ​​of high-brightness grayscale areas (light spots) and low-brightness grayscale areas (nozzles) will be set to 0, appearing as black in the image, while the pixel values ​​of medium-brightness grayscale areas (background noise) will be set to 255. Figure 4 A schematic diagram of the temporary image shown.

[0140] Optionally, the step of performing circle detection on the edge features of the light spot to obtain the light spot detection result includes:

[0141] All pixels in the edge features of the light spot are counted, and a preset number of the pixels are selected for random sampling consistency detection to obtain the edge pixel set;

[0142] The set of edge pixels is fitted to obtain a target fitted circle, and the target fitted circle is used as the spot detection result.

[0143] Optionally, fitting the set of edge pixels to obtain the target fitted circle includes:

[0144] A preset number of pixels from the set of edge pixels are selected for fitting to obtain a current fitted circle, and the number of edge points contained in the current fitted circle is taken as the number of interior points.

[0145] Repeat the above steps. When the number of interior points of the current fitted circle is higher than the number of interior points of the fitted circle in the previous iteration, and the radius of the current fitted circle meets the preset radius range, the current fitted circle is used as a temporary fitted circle, or until the preset number of iterations is reached, the current fitted circle is used as the target fitted circle.

[0146] In some embodiments, slight unevenness in the edge features of the light spot remains after image preprocessing and cannot be eliminated. Therefore, RCD (Random Circle Detection) is used as the main method for light spot circle detection. During the detection process, a predetermined number of pixels (e.g., 90%) from the edge of the light spot are selected for detection, and the number of iterations is set to 700 (a predetermined number of iterations). A reasonable circle radius range is 95 to 500 pixels (a predetermined radius range). In each iteration, a predetermined number of edge points, typically 3, are randomly selected for circle fitting, and the number of edge points contained within the fitted circle is calculated, i.e., the number of interior points. If the number of interior points in this iteration is greater than the number of interior points in the fitted circle of the previous iteration, and the radius is within the predetermined radius range, then the fitted circle of this iteration is stored as a temporary fitted circle. This process is repeated until the predetermined number of iterations is reached. The finally stored temporary fitted circle is used as the target fitted circle, i.e., the detection result is fed back. The light spot detection result is shown below. Figure 5 The image before automatic calibration of the motorized deflector contains the spot detection results.

[0147] Optionally, the temporary image includes a spot image; after converting the relative position image to obtain the temporary image, the process further includes:

[0148] The light spot image is subjected to median filtering, and an opening operation is performed on the filtered image according to the first preset circular convolution kernel to obtain a temporary light spot image;

[0149] The temporary spot image is closed by performing a closing operation on the second preset circular convolution kernel to obtain the processed spot image.

[0150] Specifically, even after binary segmentation, the spot image (the spot image in the temporary image) still suffers from problems such as independent sputtering spots and jagged edges. First, median filtering is applied to the spot image. Median filtering suppresses large noise values ​​by replacing the value of each pixel with the median value of its neighboring pixels. This provides a clean base image for subsequent morphological operations.

[0151] Next, morphological operations are performed. An opening operation is applied to the spot image using a pre-defined circular convolution kernel with a diameter of 25 pixels (e.g., 25 pixels), to eliminate isolated sputtering spots around the spot. Then, a closing operation is performed on the spot image using a second pre-defined circular convolution kernel (e.g., 21 pixels), to close the gaps at the spot's edge, eliminating jaggedness and smoothing the edges. The result of the morphological operations is shown below. Figure 7 The image shown is a schematic diagram of the processed light spot.

[0152] Optionally, edge detection is performed on the temporary image to extract edge features therein, the edge features including spot edge features and nozzle edge features.

[0153] In some embodiments, the Canny operator is used to perform edge detection on the filtered and morphologically processed spot and nozzle images. The Canny operator includes a strong edge threshold, a weak edge threshold, and a Sobel operator. First, the image is scanned using the Sobel operator to calculate the gradient intensity. When the gradient intensity is greater than the strong edge threshold, the region is considered a strong edge; when the gradient intensity is between the strong edge threshold and the weak edge threshold, the region is considered a weak edge. For example, in spot edge feature extraction, the strong edge threshold of the Canny operator is set to 47.5, the weak edge threshold is 20, and the size of the Sobel operator is 3 pixels. In nozzle edge feature extraction, the strong edge threshold of the Canny operator is 47.5, the weak edge threshold is 17.5, and the size of the Sobel operator is also 3 pixels.

[0154] Increasing the strong edge threshold appropriately can improve the sensitivity of detecting sharp edges while ignoring blurred edges caused by image noise, reducing false detections and improving noise resistance. However, an excessively high strong edge threshold may lead to missed detections. Therefore, considering both the spot and nozzle, the strong edge threshold is set to 47.5.

[0155] Appropriately lowering the weak edge threshold can preserve more edge details, making the detected edges more continuous and complete. However, if the weak edge threshold is set too low, it may lead to false detections. Since there are many tiny sputtering particles at the edge of the light spot, these sputtering particles act as noise in the edge detection process. Therefore, the weak edge threshold for the light spot is set to 20 to avoid false detections of sputtered edges, thus affecting the accuracy of edge detection. The nozzle has a regular shape and occupies a large area in the image; appropriately lowering the weak edge threshold to 17.5 can yield more continuous and complete nozzle edges.

[0156] The Sobel operator is used for image smoothing. A larger value results in less noise, but also more blurred edges, and its size must be an odd number greater than 1. This is because the Sobel operator acts as a square window, and the calculation result must be fed back to the center pixel. A center pixel only exists in the window when the side length is an odd number of pixels. After the above region segmentation, most of the background noise in the image is filtered out. Therefore, only the smallest Sobel operator (3 pixels) needs to be used to ensure the sharpest edges, facilitating subsequent detection.

[0157] In some specific embodiments, such as Figure 8 As shown, the automatic calibration method for water-guided laser optical-water coupling includes:

[0158] Grayscale images (relative position images) are acquired using a laser coaxial CCD camera (monocular CCD camera).

[0159] The Otsu method is used to binarize the acquired image, that is, to binarize the image of the relative position to obtain the binary threshold of the image, namely the first segmentation threshold and the second segmentation threshold.

[0160] Binarization segmentation of spot / nozzle images involves segmenting the relative position image using a first segmentation threshold and a second segmentation threshold. Based on the binarization result, spot images and nozzle images are segmented, resulting in a temporary image that includes both spot and nozzle images.

[0161] Light spot image processing: Median filtering to remove noise: Median filtering is applied to the light spot image to remove noise. Morphological processing: Morphological operations are performed on the light spot image to further improve image quality. Edge detection is performed using the Canny operator to extract edge features of the light spot. Finally, the light spot circle is detected based on the random circle detection algorithm to obtain the light spot detection result.

[0162] Nozzle image processing steps: Median filtering to remove noise: Median filtering is applied to the nozzle image to remove noise. Canny edge detection: The Canny operator is applied for edge detection to extract nozzle edge features. Finally, the nozzle circle is detected based on the improved Hough gradient circle transform to obtain the nozzle detection result.

[0163] Calculate the relative height of the light spot / nozzle: Calculate the height of the light spot and the distance between the nozzles based on the nozzle detection results and the light spot detection results.

[0164] Initialization is performed by controlling the corresponding motor (the motor corresponding to the electric deflector). Then, the motor is controlled to move continuously at a preset step size, and image change data of the nozzle is collected. The mapping relationship between the image change data and the preset step size is determined based on the least squares method, that is, the mapping relationship between the motor step size and pixel change is fitted.

[0165] Finally, the electric deflector is adjusted based on the mapping relationship and the distance between the light spot height and the nozzle to align the light spot with the nozzle image, thus achieving automatic calibration of the light-water coupling.

[0166] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for automatic calibration of water guide laser light-water coupling, characterized in that, An automatic calibration system for water-guided laser optical-water coupling is applied. The automatic calibration system includes a laser collimator (1), a coaxial monocular vision inspection module (4), an electric optical path calibration module (3), and a coupling cavity (6) equipped with a nozzle. The automatic calibration method for water-guided laser optical-water coupling includes: When the laser collimator (1) receives the laser beam, The coaxial monocular vision detection module (4) acquires an image of the relative position of the spot generated by the laser beam and the nozzle, and converts the relative position image to obtain a temporary image. Edge detection is performed on the temporary image to extract edge features, including spot edge features and nozzle edge features; The edge features of the light spot are subjected to circle detection to obtain the light spot detection result; Based on the improved Hough gradient circular transform, the nozzle edge features are used for detection to obtain nozzle detection results; Based on the spot detection results and the nozzle detection results, the optical path of the laser beam is changed by the electric optical path calibration module (3) to adjust the position of the spot, so as to realize the automatic calibration of the light-water coupling; The coaxial monocular vision detection module (4) includes an auxiliary light source (401), an adjustable lens barrel (402), and a monocular CCD camera (403). The monocular CCD camera (403) is connected to the adjustable lens barrel (402). The auxiliary light source (401) is on the same optical axis as the laser beam and is used to illuminate the light spot. The step of acquiring the relative position image of the light spot generated by the laser beam and the nozzle through the coaxial monocular vision detection module (4) includes: By adjusting the focal length of the adjustable lens barrel (402), the imaging plane of the monocular CCD camera (403) is made to coincide with the plane where the nozzle is located; Illumination is provided by the auxiliary light source (401), and the relative position image of the light spot and the nozzle is acquired by the monocular CCD camera (403).

2. The water guide laser light-water coupling automatic calibration method according to claim 1, wherein, The step of detecting nozzles based on the improved Hough gradient circular transform according to the nozzle edge features to obtain nozzle detection results includes: The gradient information of each edge point in the nozzle edge feature is determined, and a parameter space is constructed based on the gradient information; the gradient information includes the gradient magnitude and gradient direction. Multiple candidate circle centers are determined based on the gradient magnitude and gradient direction of each edge point, and voting is performed on each candidate circle center in the parameter space to generate multiple temporary candidate circle centers; The corresponding candidate circle is determined based on the temporary candidate circle center and the preset radius parameter; The overlap of each candidate circle is detected based on the nozzle edge features, and the candidate circle with the highest overlap is taken as the nozzle detection result.

3. The water guide laser light-water coupling automatic calibration method of claim 1, wherein, The electric optical path calibration module (3) includes an electric deflector (301). Based on the spot detection result and the nozzle detection result, the electric optical path calibration module (3) changes the optical path of the laser to adjust the position of the spot, so as to achieve automatic calibration of the light-water coupling, including: Adjust the electric deflector (301) to the initial position, and control the electric deflector (301) to move continuously at a preset step size, and collect image change data of the nozzle; The mapping relationship between the image change data and the preset step size is determined based on a preset algorithm; The electric deflector (301) is adjusted according to the mapping relationship, the spot detection result, and the nozzle detection result to change the optical path of the laser so that the spot is aligned with the image of the nozzle.

4. The water guide laser light-water coupling automatic calibration method of claim 1, wherein, The process of converting the relative position image to obtain a temporary image includes: The segmentation threshold of the relative position image is determined by an image processing algorithm; The relative position image is segmented according to the segmentation threshold to obtain the temporary image.

5. The water guide laser light-water coupling automatic calibration method of claim 1, wherein, The step of performing circle detection on the edge features of the light spot to obtain the light spot detection result includes: All pixels in the edge features of the light spot are counted, and a preset number of the pixels are selected for random sampling consistency detection to obtain the edge pixel set; The set of edge pixels is fitted to obtain a target fitted circle, and the target fitted circle is used as the spot detection result.

6. The water guide laser light-water coupling automatic calibration method according to claim 5, wherein, The process of fitting the set of edge pixels to obtain the target fitted circle includes: A preset number of pixels from the set of edge pixels are selected for fitting to obtain a current fitted circle, and the number of edge points contained in the current fitted circle is taken as the number of interior points. The process is repeated. When the number of interior points of the current fitted circle is higher than the number of interior points of the fitted circle in the previous iteration, and the radius of the current fitted circle meets the preset radius range, the current fitted circle is taken as the target fitted circle; or until the preset number of iterations is reached, the current fitted circle is taken as the target fitted circle.

7. The water-guide laser light-water coupling automatic calibration method of claim 3, wherein, The electric optical path calibration module (3) also includes a motion controller connected to the electric deflector. The step of adjusting the electric deflector (301) according to the mapping relationship, the spot detection result, and the nozzle detection result to change the optical path of the laser so that the spot is aligned with the nozzle image includes: Based on the mapping relationship, the spot detection result, and the nozzle detection result, the execution command is determined by the motion controller; According to the execution command, the electric deflector (301) is adjusted to deflect so that the light spot is aligned with the image of the nozzle.

8. The water guide laser light-water coupling automatic calibration method of claim 4, wherein, The segmentation threshold includes a first segmentation threshold and a second segmentation threshold; the step of performing region segmentation on the relative position image according to the segmentation threshold to obtain the temporary image includes: The relative position image is processed based on the first segmentation threshold and the second segmentation threshold to obtain the temporary image; Wherein, the first segmentation threshold is used to segment the high-brightness grayscale area and the medium-brightness grayscale area in the relative position image; the second segmentation threshold is used to segment the medium-brightness grayscale area and the low-brightness grayscale area in the relative position image.

9. The water guide laser light-water coupling automatic calibration method of claim 1, wherein, The temporary image includes a light spot image; after converting the relative position image to obtain the temporary image, the process further includes: The spot image is subjected to median filtering, and an open operation is performed on the filtered image according to a first preset circular convolution kernel to obtain a temporary spot image; A closed operation is performed on the temporary spot image according to a second preset circular convolution kernel to obtain a processed spot image.

Images