A high-precision plasma cutting method and system in a radioactive environment

Abstract

The present invention discloses a high-precision plasma cutting method and system in a radioactive environment, which relates to the technical field of nuclear industry decommissioning. The method includes collecting two-dimensional images of a target workpiece and performing stitching processing to obtain a two-dimensional stitched image, performing target recognition on the two-dimensional stitched image to obtain the positioning data of the target workpiece; collecting three-dimensional point cloud data of the target workpiece, performing stitching processing on the three-dimensional point cloud data to obtain the cutting boundary of the target workpiece; obtaining the optimal cutting trajectory of the target workpiece based on the positioning data and cutting boundary of the target workpiece, and using a plasma cutting tool head to cut the target workpiece according to the optimal cutting trajectory of the target workpiece. The present invention adopts high-precision image and point cloud data processing technologies, combined with an advanced template matching algorithm, to generate an optimal cutting path for various complex-structured objects to be cut, thereby improving the cutting efficiency and quality.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear industry decommissioning, and particularly to a high-precision plasma cutting method and system in a radioactive environment. Background Art

[0002] The decommissioning of nuclear facilities is an important task in the nuclear energy industry. Its core goal is to safely and efficiently demolish and disassemble various equipment, components, and pipelines within nuclear facilities. This process is of crucial significance for reducing the generation of radioactive waste and ensuring environmental safety. However, there are several defects in the cutting and disassembly methods in the existing technology for nuclear facility decommissioning:

[0003] The structures of the objects to be cut in nuclear facilities are complex and diverse, different from the regular-structured objects common in the industrial field. This makes it difficult for traditional plasma cutting technologies to adapt, and problems such as unreasonable cutting paths often occur.

[0004] Since the nuclear facility decommissioning sites are usually radioactive, the cutting operations need to be carried out remotely, which increases the complexity of the operation. Especially under the requirement of maintaining an appropriate distance (5 - 8 mm) between the cutting torch and the cutting surface, remote control becomes more difficult.

[0005] Traditional plasma jets are mostly transferred arcs, which may lead to a reduction in cutting efficiency and accuracy during remote operation. Summary of the Invention

[0006] In view of the problems existing in the existing high-precision plasma cutting methods in a radioactive environment, the present invention is proposed.

[0007] Therefore, the problem to be solved by the present invention is how to achieve safe, efficient, and precise cutting and disassembly of decommissioned nuclear facilities.

[0008] To solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, an embodiment of the present invention provides a high-precision plasma cutting method in a radioactive environment, which includes collecting two-dimensional images of a target workpiece and performing stitching processing to obtain a two-dimensional stitched image, performing target recognition on the two-dimensional stitched image to obtain the positioning data of the target workpiece; collecting three-dimensional point cloud data of the target workpiece, performing stitching processing on the three-dimensional point cloud data to obtain the cutting boundary of the target workpiece; obtaining the optimal cutting trajectory of the target workpiece based on the positioning data and the cutting boundary of the target workpiece, and using a plasma cutting tool head to cut the target workpiece according to the optimal cutting trajectory of the target workpiece.

[0010] As a preferred embodiment of the high-precision plasma cutting method in the radioactive environment of the present invention, the following steps are included: collecting a two-dimensional image of the target workpiece and performing preprocessing, performing ORB image stitching on the preprocessed two-dimensional image based on the ROI region to obtain a two-dimensional stitched image; converting the two-dimensional stitched image from the RGB color space to the HSV color space, which is expressed as:

[0011] ,

[0012] where R represents red, G represents green, B represents blue, H represents hue, S represents saturation, V represents brightness, max represents the maximum gray value among the red, green, and blue color channels in the RGB image, and min represents the minimum gray value among the red, green, and blue color channels in the image; further performing threshold segmentation based on hue to extract the two-dimensional contour of the target workpiece; using the workpiece shape in the DXF file as a template, and matching the extracted two-dimensional contour of the target workpiece with the template to obtain the target workpiece positioning data.

[0013] As a preferred embodiment of the high-precision plasma cutting method in the radioactive environment of the present invention, the following step is included: the matching is performed based on the halcon image processing library for template matching.

[0014] As a preferred embodiment of the high-precision plasma cutting method in the radioactive environment of the present invention, the following steps are included: collecting three-dimensional point cloud data of the target workpiece and performing preprocessing; performing rough stitching of the point cloud on the preprocessed three-dimensional point cloud data based on the covariance matrix to obtain rough three-dimensional point cloud stitching data; assuming that point cloud and point cloud are a pair of point clouds with an overlapping region, respectively calculating the covariance matrices of point cloud and point cloud :

[0015] ,

[0016] where represents the centroid of point cloud X, represents the centroid of point cloud Y; x i represents the i-th point in point cloud X, y j represents the j-th point in point cloud Y, M x , M y are the covariance matrices of point cloud and point cloud ; assuming that the eigenvectors corresponding to the eigenvalues of Mx are respectively p 1 , p2 , p 3 , M y The eigenvectors corresponding to the eigenvalues are respectively q 1 , q 2 , q 3 ;

[0017] According to the covariance matrix theory, the rigid transformation matrix between point cloud X and point cloud Y is:

[0018] ,

[0019] where R 0 represents the rotation matrix, T 0 represents the translation matrix; the transformation between the two point clouds is obtained

[0020] Based on the iterative closest point algorithm, the point cloud of the three-dimensional point cloud rough stitching data is finely stitched to obtain the three-dimensional point cloud fine stitching data; based on the target workpiece positioning data and the three-dimensional point cloud fine stitching data, the cutting boundary of the target workpiece is obtained.

[0021] As a preferred scheme of the high-precision plasma cutting method in the radioactive environment described in the present invention, wherein: based on the positioning data of the target workpiece and the cutting boundary of the target workpiece, a number of features to be cut are obtained; the starting cutting points and the ending cutting points of each feature to be cut are determined, and each feature to be cut is connected step by step through the cutting points. For a non-terminal feature to be cut, the distance between its ending cutting point and the starting cutting point of the next-level feature to be cut is less than the distance between its ending cutting point and the starting cutting points of other features to be cut, so as to form an optimal cutting trajectory of the target workpiece.

[0022] As a preferred scheme of the high-precision plasma cutting method in the radioactive environment described in the present invention, wherein: the features to be cut include one or more of linear features, arc features, polygon features, and circular features.

[0023] As a preferred scheme of the high-precision plasma cutting method in the radioactive environment described in the present invention, wherein: the data of the optimal cutting trajectory of the target workpiece is DXF file data.

[0024] In a second aspect, an embodiment of the present invention provides a high-precision plasma cutting system in a radioactive environment, which includes: a positioning module for performing target recognition on a two-dimensional spliced image of a target workpiece and splicing processing on three-dimensional point cloud data to obtain positioning data and a cutting boundary of the target workpiece; an optimization module for obtaining an optimal cutting trajectory of the target workpiece according to the positioning data and the cutting boundary of the target workpiece; and a cutting module, where the plasma cutting tool head of the nuclear decommissioning robot cuts the target workpiece according to the optimal cutting trajectory of the target workpiece.

[0025] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the processor executes the computer program, any step of the above-mentioned high-precision plasma cutting method in a radioactive environment is implemented.

[0026] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by a processor, any step of the above-mentioned high-precision plasma cutting method in a radioactive environment is implemented.

[0027] The beneficial effects of the present invention are as follows: By adopting high-precision image and point cloud data processing technologies and combining with an advanced template matching algorithm, the present invention generates an optimal cutting path for various complex-structured objects to be cut, thereby improving cutting efficiency and quality. Using a nuclear decommissioning robot equipped with a plasma cutting tool head and combining precise positioning data, precise control of the cutting tool head is achieved. Even under remote control conditions, an appropriate distance between the cutting torch and the cutting surface can be maintained. It can adapt to nuclear facility decommissioning objects of different shapes and structures, with high adaptability and flexibility. And it reduces the potential impact on the environment, contributing to the environmental friendliness of nuclear facility decommissioning. Description of the Drawings

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0029] Figure 1 is a schematic flowchart of the high-precision plasma cutting method in the radioactive environment described in the embodiment;

[0030] Figure 2 is a schematic diagram of the transformation of each coordinate system in the embodiment;

[0031] Figure 3 is a schematic diagram for determining the starting point of linear feature machining in the embodiment;

[0032] Figure 4 Schematic diagram for determining the starting point of arc feature machining in the embodiment;

[0033] Figure 5 Schematic diagram for determining the starting point of polygon feature machining in the embodiment;

[0034] Figure 6 Schematic diagram for determining the starting point of circular feature machining in the embodiment;

[0035] Figure 7 Schematic diagram of the machining optimization algorithm flow in the embodiment;

[0036] Figure 8 Code structure diagram of the DXF file;

[0037] Figure 9 Schematic diagram of the process for redrawing the pattern after reading the DXF file in the embodiment. Specific implementation manners

[0038] To make the above objects, features, and advantages of the present invention more obvious and understandable, the specific implementation manners of the present invention will be described in detail below with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0039] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0040] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an individual or alternative embodiment that excludes other embodiments.

[0041] Embodiment 1

[0042] This embodiment provides a high-precision plasma cutting method in a radioactive environment, which is realized based on a nuclear decommissioning robot equipped with a plasma cutting tool head.

[0043] The nuclear decommissioning robot is equipped with a six-axis robotic arm, and a plasma cutting tool head is installed at the end of the six-axis robotic arm. The nuclear decommissioning robot described in this embodiment also comes with a two-dimensional camera and a three-dimensional camera, which are used to collect the two-dimensional image of the target workpiece and the three-dimensional point cloud data of the target workpiece respectively. The two-dimensional image can obtain better results in workpiece target recognition than the three-dimensional point cloud, while the three-dimensional point cloud processing can obtain the height information of the workpiece, obtain a high-precision cutting trajectory, effectively ensure the distance between the plasma cutting head and the surface of the cutting workpiece, improve the cutting quality and prevent the plasma cutting head from being welded to the surface of the cutting workpiece due to insufficient cutting distance.

[0044] Refer to Figures 1 to 8 , which is the first embodiment of the present invention. This embodiment provides a high-precision plasma cutting method in a radioactive environment, including:

[0045] S1: Collect the two-dimensional image of the target workpiece and perform stitching processing to obtain a two-dimensional stitched image, and perform target recognition on the two-dimensional stitched image to obtain the target workpiece positioning data.

[0046] In this embodiment, camera calibration and eye-in-hand calibration are performed. Obtain the transformation matrix from the camera coordinate system to the calibration board coordinate system, and the transformation matrix between the camera coordinate system and the robot base coordinate system;

[0047] Eye-in-Hand calibration (calibration of the Eye-in-Hand vision system) aims to solve the rigid transformation relationship between the camera coordinate system and the robot tool coordinate system.

[0048] As Figure 2 shown, use camera to represent the camera coordinate system at the end of the robotic arm, tool to represent the robot tool coordinate system, base to represent the robot base coordinate system, and object to represent the calibration board coordinate system. Among them, the robot base coordinate system is a rectangular coordinate system fixed on the robot installation base, which is used to describe the movement of the robot body;

[0049] When the robot is at position 1, the relationship between the robot tool coordinate system tool1 and the robot base coordinate system is expressed as:

[0050] ,

[0051] The relationship between the robot tool coordinate system tool1 and the camera coordinate system camera1 is expressed as:

[0052] ,

[0053] The camera coordinate system camera1 and the calibration board coordinate system object satisfy the following formula:

[0054] ,

[0055] Combining the above three equations gives:

[0056] ,

[0057] After moving to position 2, we get:

[0058] ,

[0059] Combining the above two equations gives:

[0060] ,

[0061] where represents the transformation relationship from the camera coordinate system to the robot tool coordinate system, represents the transformation relationship from the robot base coordinate system to the calibration plate coordinate system, represents the transformation relationship from the robot base coordinate system to the robot tool coordinate system, represents the transformation relationship from the camera coordinate system to the calibration plate coordinate system. represents the transformation relationship from the robot base coordinate system to the robot tool coordinate system when the robot is at position 1, represents the transformation relationship from the robot base coordinate system to the robot tool coordinate system when the robot is at position 2, represents the transformation relationship from the camera coordinate system to the calibration plate coordinate system when the robot is at position 1, represents the transformation relationship from the camera coordinate system to the calibration plate coordinate system when the robot is at position 2.

[0062] In the above equation, only is the unknown. Therefore, the solution of the hand-eye calibration can be transformed into solving the linear equation system AX = BX, and solving this linear equation system can obtain the hand-eye calibration result.

[0063] Before stitching the two-dimensional images of the target workpiece, preprocess the two-dimensional images of the target workpiece, including correction and filtering, to reduce the interference of light and noisy backgrounds and prepare for image stitching, where the correction is based on the transformation matrix.

[0064] After that, perform ORB image stitching on the preprocessed two-dimensional images based on the ROI region to obtain the two-dimensional stitched image.

[0065] Since a single shot by a two-dimensional camera generally cannot obtain a panoramic view of the entire working platform, it can only be achieved through image stitching. By collecting images of the target workpiece at different positions multiple times and then performing image stitching, a panoramic view of the target workpiece can be finally obtained.

[0066] Due to certain feature invariance, the ORB algorithm can identify the same object under the premise of certain illumination changes, translational changes, rotational changes, and scaling changes in the image. The core idea of the algorithm is to use the improved FAST (oriented FAST) algorithm for corner detection on the image pyramid and generate the main direction, so that the feature points have a certain scale invariance. Based on the BRIEF algorithm, the feature points are described to make the feature point descriptors have a certain scale invariance. Finally, the RANSAC (Random Sample Consensus) algorithm is used to purify the feature points, find the matching feature points to achieve image registration, and use weighted fusion to eliminate the stitching gap to achieve image stitching.

[0067] In this embodiment, the two-dimensional stitched image is converted from the RGB color space to the HSV color space, and threshold segmentation based on hue is performed to extract the two-dimensional contour of the target workpiece.

[0068] The images obtained from the camera are all RGB images, and the contour extraction based on the HSV color space requires converting the image from the RGB color space to the HSV color space. First, calculate the maximum and minimum values of the grayscale in the red, green, and blue color channels of the original RGB image, and then obtain the corresponding values of the hue channel, saturation channel, and brightness channel according to the following four formulas to achieve the conversion of the image under the RGB color space to the image under the HSV color space:

[0069] ,

[0070] where R represents red, G represents green, and B represents blue;

[0071] In the formula: if R = max, it means that if (if) R is the largest value among the three channels (R represents red, G represents green, B represents blue, and the largest R means the redder the image), then H (hue) is equal to (G - B) / (max - min).

[0072] H is the hue, which represents the basic attribute of the color and is measured in degrees, ranging from 0° to 360°. Among them, red corresponds to 0°, green corresponds to 120°, and blue corresponds to 240°. The colors on the hue circle are arranged in the order of the spectrum, forming a color wheel.

[0073] S is the saturation, which represents the purity or depth of the color, and the value range is 0% to 100%. The higher the saturation, the more vivid the color; the lower the saturation, the closer the color is to gray.

[0074] V is the brightness, which represents the brightness of the color, and the value range is also 0% to 100%. The higher the brightness, the brighter the color; the lower the brightness, the darker the color.

[0075] After converting the spliced image to the HSV color space, threshold segmentation based on hue can visually distinguish the workpiece from the background, obtaining the two-dimensional contour of the target workpiece.

[0076] Taking the shape of the workpiece in the DXF file as a template, match the extracted two-dimensional contour of the target workpiece with the template to obtain the positioning data of the target workpiece.

[0077] In this embodiment, based on the workpiece contour, template matching of the workpiece and target workpiece positioning can obtain a high matching rate and position accuracy.

[0078] The principle of shape-based template matching is as follows: generate a contour template by extracting the contour features of a known target shape, and then calculate the matching scores for all contours through a corresponding matching function. The one with the highest score is the target workpiece. Each workpiece has a corresponding shape design drawing at the beginning of the design. Based on the design drawing, a DXF file is exported through CAD software, and then reading the DXF file to generate a contour template can achieve a good recognition effect. Since information such as contour features is insensitive to illumination changes, template matching has strong robustness.

[0079] Using the Halcon image processing library as a template matching tool, the matching process of the DXF template based on the Halcon image processing library is as follows:

[0080] Import the DXF model into the DXF file, which is a storage format of CAD files and contains workpiece contour information. This information can be used as a template for the template matching algorithm to prepare for subsequent processing;

[0081] Since the size of the image contour in the DXF file does not match the size of the collected image, it is necessary to adjust the scale of the contour to improve the contour matching rate;

[0082] Read the workpiece contour image obtained from the above steps as the image to be matched;

[0083] Using the imported DXF file as a template, search for the workpiece contour on the working platform read as the image to be matched to obtain the template matching coefficient of the target workpiece and the centroid position of the workpiece, that is, the positioning data of the target workpiece.

[0084] Output the matching area and matching score for subsequent use.

[0085] S2: Collect the three-dimensional point cloud data of the target workpiece, perform splicing processing on the three-dimensional point cloud data, and obtain the cutting boundary of the target workpiece therefrom.

[0086] Collect the three-dimensional point cloud data of the target workpiece and perform preprocessing.

[0087] After calibrating the hand-eye of the 3D camera, it is necessary to filter the acquired point cloud to reduce the subsequent stitching calculation amount. Due to the acquisition method and the influence of the external environment, there are a large number of error information such as noise points, outliers, and holes in the directly acquired point cloud data. If these noise points are not processed, it will directly affect the subsequent point cloud registration result and cause the algorithm to fall into a local optimal solution. As the first step of point cloud preprocessing, point cloud filtering is to remove the above noise points so that the subsequent point cloud processing can be carried out better. Since the point cloud collected by the 3D camera carried by the nuclear decommissioning robot belongs to ordered data, Gaussian filtering is used to process the collected point cloud.

[0088] Based on the covariance matrix, rough stitching of the preprocessed 3D point cloud data is performed to obtain the rough stitching data of the 3D point cloud.

[0089] The rough stitching method of the point cloud based on the covariance matrix can stitch the point clouds to be stitched together. Although the accuracy is not high, it reduces the calculation amount for the subsequent fine stitching of the point cloud and can effectively prevent the fine stitching of the point cloud from falling into a local optimal solution.

[0090] The rough stitching of the point cloud is a method of transforming two point clouds with the same local features into the same global coordinate system under the premise of low accuracy. The purpose is to obtain a better initial iteration value for the subsequent fine stitching. According to the theoretical description of the covariance matrix, a point cloud can be described by the covariance matrix, and the eigenvalues and eigenvectors of the covariance matrix can be used to characterize the features of the point cloud. The matrix properties are used to process the point cloud to obtain the transformation matrix between the two point clouds. The basic principle of the rough stitching of the point cloud based on the covariance matrix is: calculate the covariance matrix representing the two point clouds according to the centroid positions of the two point clouds, and then calculate the rigid transformation matrix between the two point clouds according to the eigenvalues and eigenvectors of the covariance matrix to achieve the rough stitching of the point cloud.

[0091] The rough stitching of the point cloud based on the covariance matrix can be calculated according to the following steps:

[0092] Let the point cloud and the point cloud be a pair of point clouds with an overlapping area, and calculate the covariance matrices of the point cloud and the point cloud respectively:

[0093] ,

[0094] where, represents the centroid of the point cloud X, represents the centroid of the point cloud Y. , The x and y in () = 1~m) refers to which point.

[0095] To obtain the transformation matrix between two point clouds, it is necessary to find M x and M y eigenvalues. Assume M x the eigenvectors corresponding to the eigenvalues are respectively p 1 , p 2 , p 3 , M y the eigenvectors corresponding to the eigenvalues are respectively q 1 , q 2 , q 3 ,

[0096] According to the covariance matrix theory, the rigid transformation matrix between point cloud X and point cloud Y is:

[0097] ,

[0098] Based on the iterative closest point algorithm, fine stitching of the three-dimensional point cloud for the rough stitching data of the three-dimensional point cloud is performed to obtain the fine stitching data of the three-dimensional point cloud.

[0099] Generally, the accuracy of the obtained rough stitching data of the three-dimensional point cloud cannot meet the requirements of cutting, and fine stitching is still required to meet the accuracy requirements. The point cloud fine stitching method adopted in this embodiment is the iterative closest point algorithm (ICP). The main idea of the ICP algorithm is to calculate the optimal rigid transformation matrix between the original point cloud and the point cloud to be stitched through the objective function to achieve point cloud stitching. Based on the least squares method, iteration is finally achieved by calculating the error function value. Generally, the distance between points, the distance from a point to a line, and the distance from a point to a tangent plane can be used to implement the objective function.

[0100] The process of using the ICP algorithm to stitch point clouds includes three steps:

[0101] Search for the corresponding point relationship of the overlapping positions in the original point cloud and the point cloud to be stitched;

[0102] Remove the wrong matching point pairs;

[0103] Solve the rigid transformation matrix of the two point clouds and implement iteration.

[0104] Obtain the cutting boundary of the target workpiece based on the target workpiece positioning data and the three-dimensional point cloud precise stitching data, including: obtaining the point cloud outer contour of the upper surface of the stitched workpiece to get the surface outer contour. After extracting all the contour points of the upper surface point cloud of the workpiece, use the target workpiece positioning data to mark the upper surface point cloud of a single workpiece, and then segment the outer contour of the upper surface of a single workpiece. Perform scaling processing based on the centroid of the point cloud on the outer contour of the upper surface point cloud of a single workpiece to obtain the cutting boundary of the target workpiece.

[0105] S3: Obtain the optimal cutting trajectory of the target workpiece according to the target workpiece positioning data and the cutting boundary of the target workpiece, and transmit the data of the optimal cutting trajectory of the target workpiece to the nuclear decommissioning robot through TCP / IP communication.

[0106] Obtain several cutting features to be cut according to the target workpiece positioning data and the cutting boundary of the target workpiece, determine the starting cutting point and the ending cutting point of each cutting feature to be cut. Then connect each cutting feature to be cut level by level through the cutting points. For a certain non-final cutting feature to be cut, the distance between its ending cutting point and the starting cutting point of the next-level cutting feature is less than the distance between its ending cutting point and the starting cutting points of other cutting features to be cut, and then form the optimal cutting trajectory of the target workpiece.

[0107] The cutting features on the plane can generally be divided into closed features and open features. The closed features are connected end to end, and the cutting starting point and the cutting ending point of the feature are at the same point; the open features have different starting and ending points, and the cutting starting point and the cutting ending point are not the same point.

[0108] The cutting features to be cut can be linear features, arc features, polygon features, and circular features.

[0109] For the cutting of a linear feature as Figure 3 shown, both ends of the line can be used as the cutting starting point of the feature. By the distances d 0 , d 1 from the position P of the cutting tool head to both ends of the line respectively, determine the point Q 1 with the shorter distance as the starting point, and the other point Q 0 as the ending point.

[0110] For the cutting of an arc segment feature as Figure 4 shown, similar to the linear feature, compare the distances between point P and the two endpoints of the arc, and select the point with the shorter distance as the cutting starting point.

[0111] The cutting path of the polygon is as Figure 5As shown, a polygon is a graphical feature composed of multiple line segments connected end to end. For the cutting of this feature, the intersection point of two selected line segments is chosen as the starting and ending points of the cutting trajectory. The polygon shown in the figure is a regular pentagon, and this feature has a total of 5 corner points. By comparing the distances from the previous cutting end point to these 5 corner points, the corner point with the shortest distance is selected. Q 4 This is the starting point for the cutting of this feature, and the end point coincides with this point.

[0112] Such as Figure 6 As shown in the circular feature, this feature is determined by the center and radius of the circle. For this feature, connect the starting position P of the cutting tool head and the center O of the circle, and use the intersection point of this line segment and the circle Q 0 As the starting and ending points of the cutting of this feature.

[0113] Due to the limitations of the cutting environment in a radioactive environment, the method of manually controlling the robot for cutting is usually adopted. However, due to other factors such as the robot's arm span, a complete cutting process usually includes multiple cutting steps.

[0114] The overall process of the processing optimization algorithm in this embodiment is as shown in Figure 7 As shown, taking the current position of the cutting tool head as the starting position of the overall cutting path, set the end point of the first feature as the origin O(0, 0), then assign O to P, and compare the distances from the end point P of the previous feature to each end point of the remaining single feature respectively. For an open feature, set the point with the shorter distance as the starting point and the other point as the end point. For a closed feature, set the determined feature points as both the starting and ending points at the same time. Compare the distances from point P to the starting points of all the remaining features, select the route with the shortest distance as the next processing route, and at the same time update the cutting end point of the connected feature to the new P point, and iterate to obtain the final path.

[0115] In this embodiment, the optimal output result of the cutting trajectory of the target workpiece is a DXF file optimized by the algorithm.

[0116] The motion path of the robotic arm holding the cutting tool needs to be planned by the user. By generating discrete spatial target points that the robotic arm can recognize, the end of the robotic arm can be made to move along a specified path during cutting. Therefore, the planning of the cutting trajectory requires generating DXF read data through modeling. The DXF (AutoCAD Drawing Exchange Format) file is a vector drawing file format. It is an intermediate format for data interaction between various CAD software for planar drawing. It uses ASCII code for storage. Therefore, secondary development of the original drawing can be achieved only by parsing the information in the DXF file. The encoding of the DXF file consists of pairs of group codes and group values. By observing, it can be found that a DXF file generally consists of 7 encoding segments, namely the HEADER segment, the CLASSES segment, the TABLES segment, the BLOCKS segment, the ENTITIES segment, the OBJECTS segment, and the THUMBNAILIMAGE segment.

[0117] Each DXF file is led by a group code 0 and SECTION to introduce each segment. Then, it is followed by a group code 2 and the name of each segment. Each segment represents different feature types in the drawing. The end of a segment is represented by a group code 0 and ENDSEC. When all the segment codes representing features are ended, the end of the entire file is represented by a group code 0 and EOF. The code structure of the DXF file can be represented by Figure 8 as shown. The entire file can be read using high-level languages such as C++. By locating the positions of each segment and reading and parsing the content in the segment, the required information can be obtained for the subsequent reconstruction and secondary development of the drawing.

[0118] After reading the DXF file using a high-level programming language, the encoded data behind the graphics is obtained. Then, the pattern is redrawn according to the entity segment code read. The specific process is as Figure 9 shown, where LINE represents a straight line, CIRCLE represents a circle, ARC represents an arc, and ELLIPSE represents a compound line.

[0119] The six-axis robotic arm of the nuclear decommissioning robot moves according to the optimal cutting trajectory of the target workpiece, so that the plasma cutting tool head cuts the target workpiece according to the optimal cutting trajectory of the target workpiece.

[0120] In summary, by adopting high-precision image and point cloud data processing technologies and combining with advanced template matching algorithms, the present invention can generate optimal cutting paths for various complex-structured objects to be cut, thereby improving the cutting efficiency and quality. By using a nuclear decommissioning robot equipped with a plasma cutting tool head and combining precise positioning data, precise control of the cutting tool head is achieved. Even under remote operation conditions, an appropriate distance between the cutting torch and the surface to be cut can be maintained. The design and control strategy of the plasma cutting tool head are optimized for remote operation, ensuring the stability and consistency of the plasma jet and improving the cutting accuracy and efficiency. It can adapt to nuclear facility decommissioning objects with different shapes and structures, having high adaptability and flexibility. By reducing the time for personnel to be directly exposed to the radioactive environment, the present invention significantly improves the operation safety. Through precise cutting path planning, it helps to reduce unnecessary material waste, conforms to the principle of waste minimization, and the precise cutting technology reduces the potential impact on the environment, contributing to the environmental friendliness of nuclear facility decommissioning.

[0121] Embodiment 2

[0122] Referring to Figure 1 , on the basis of the first embodiment, the present embodiment further provides a high-precision plasma cutting system in a radioactive environment, including:

[0123] A positioning module, configured to perform target recognition on a two-dimensional spliced image of a target workpiece and splicing processing on three-dimensional point cloud data to obtain positioning data and a cutting boundary of the target workpiece;

[0124] An optimization module, configured to obtain an optimal cutting trajectory of the target workpiece according to the positioning data and the cutting boundary of the target workpiece;

[0125] A cutting module, where the plasma cutting tool head of the nuclear decommissioning robot cuts the target workpiece according to the optimal cutting trajectory of the target workpiece.

[0126] The present embodiment also provides a computer device applicable to the high-precision plasma cutting method in a radioactive environment, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the high-precision plasma cutting method in a radioactive environment as proposed in the above embodiment.

[0127] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0128] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the high-precision plasma cutting method in a radioactive environment as proposed in the above embodiment.

[0129] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. Technical details not described in detail in this embodiment can be referred to in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0130] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A high-precision plasma cutting method in a radioactive environment, characterized in that: including Collecting two-dimensional images of the target workpiece and performing stitching processing to obtain a two-dimensional stitched image, performing target recognition on the two-dimensional stitched image, and obtaining the positioning data of the target workpiece; Collecting three-dimensional point cloud data of the target workpiece, performing stitching processing on the three-dimensional point cloud data, and obtaining the cutting boundary of the target workpiece; Obtaining the optimal cutting trajectory of the target workpiece based on the positioning data and cutting boundary of the target workpiece, and using a plasma cutting tool head to cut the target workpiece according to the optimal cutting trajectory of the target workpiece; Obtaining a number of features to be cut based on the positioning data of the target workpiece and the cutting boundary of the target workpiece; Determining the starting cutting point and ending cutting point of each feature to be cut, connecting each feature to be cut step by step through the cutting points. For a non-final feature to be cut, the distance between its ending cutting point and the starting cutting point of the next-level feature to be cut is less than the distance between its ending cutting point and the starting cutting points of other features to be cut, forming the optimal cutting trajectory of the target workpiece.

2. The high-precision plasma cutting method in a radioactive environment according to claim 1, characterized in that: Collecting the two-dimensional image of the target workpiece and performing preprocessing, performing ORB image stitching on the preprocessed two-dimensional image based on the ROI region, and obtaining a two-dimensional stitched image; Converting the two-dimensional stitched image from the RGB color space to the HSV color space, expressed as: wherein, R represents red, G represents green, B represents blue, H represents hue, S represents saturation, V represents brightness, max represents the maximum gray value in the red, green, and blue color channels of the RGB image, and min represents the minimum gray value in the red, green, and blue color channels of the image; Further performing threshold segmentation based on hue to extract the two-dimensional contour of the target workpiece; Taking the workpiece shape in the DXF file as a template, matching the extracted two-dimensional contour of the target workpiece with the template, and obtaining the target workpiece positioning data.

3. The high-precision plasma cutting method in a radioactive environment according to claim 2, wherein: The matching is based on template matching using the halcon image processing library.

4. The high-precision plasma cutting method in a radioactive environment according to claim 3, wherein: Collecting the three-dimensional point cloud data of the target workpiece and performing preprocessing; Performing rough stitching of the point cloud on the preprocessed three-dimensional point cloud data based on the covariance matrix to obtain rough stitched three-dimensional point cloud data; Suppose point cloud and point cloud are a pair of point clouds with overlapping regions. Calculate the covariance matrices of point cloud and point cloud respectively: where x c represents the centroid of point cloud X, and y c represents the centroid of point cloud Y, xi i represents the i-th point in point cloud X, and yj j represents the j-th point in point cloud Y, M x and M y are the covariance matrices of point cloud and point cloud ; Suppose the eigenvectors corresponding to the eigenvalues of Mx are p1, p2, p3, and M y The eigenvectors corresponding to the eigenvalues are q1, q2, q3; According to the covariance matrix theory, the rigid transformation matrix of point cloud X and point cloud Y is: wherein, R0 represents the rotation matrix and T0 represents the translation matrix; Performing fine stitching of the point cloud on the rough stitched three-dimensional point cloud data based on the iterative closest point algorithm to obtain fine stitched three-dimensional point cloud data; Obtaining the cutting boundary of the target workpiece based on the target workpiece positioning data and the fine stitched three-dimensional point cloud data.

5. The high-precision plasma cutting method in a radioactive environment according to claim 4, characterized in that: The features to be cut include one or more of a straight line feature, an arc feature, a polygon feature, and a circular feature.

6. The high-precision plasma cutting method in a radioactive environment according to claim 5, characterized in that: The data of the optimal cutting trajectory of the target workpiece is DXF file data.

7. A high-precision plasma cutting system in a radioactive environment, based on the high-precision plasma cutting method in a radioactive environment according to any one of claims 1 to 6, characterized in that: including A positioning module for performing target recognition on the two-dimensional stitched image of the target workpiece and performing stitching processing on the three-dimensional point cloud data to obtain the positioning data and cutting boundary of the target workpiece; An optimization module for obtaining the optimal cutting trajectory of the target workpiece according to the positioning data and cutting boundary of the target workpiece; A cutting module, and the plasma cutting tool head of the nuclear decommissioning robot cuts the target workpiece according to the optimal cutting trajectory of the target workpiece.

Images