Intelligent closed-loop processing method and system for internal defects of castings using X-ray flaw detection

Abstract

This application belongs to the field of casting product quality inspection, and specifically discloses an intelligent closed-loop processing method and system for internal defects in casting X-ray flaw detection. The method includes: planning a filming path, and performing multi-angle flaw detection on the casting according to the filming path to obtain multi-angle flaw detection images; using the multi-angle flaw detection images to mark the defect information of the casting on the three-dimensional model of the casting; repairing the casting by welding based on the defect information; and re-performing multi-angle flaw detection on the repaired casting according to the filming path to obtain multi-angle flaw detection images to determine whether the repair is qualified: if qualified, the processing is terminated; if unqualified, the repair and flaw detection steps are re-executed on the repaired casting based on the newly acquired multi-angle flaw detection images. This application realizes an intelligent closed-loop processing process for flaw detection, inspection, marking, repair, and re-flaw detection of castings, effectively ensuring the reliability and safety of castings.

Description

Technical Field

[0001] The present application belongs to the technical field of casting product quality inspection, and more specifically, relates to an intelligent closed-loop processing method and system for internal defects of castings by X-ray flaw detection. Background Art

[0002] Light alloys such as titanium and aluminum have excellent properties such as low density, high specific strength, and strong corrosion resistance, and are widely used in aerospace, weaponry, and other fields. As the demand for lightweight, integrated, and high-quality parts continues to increase, castings such as casings and cabins are developing towards more complex structures, such as large wall thickness differences, multiple intersecting structures, multiple rings, curved surfaces, blind holes, and complex internal cavities. This makes internal quality control more difficult and non-destructive detection of internal defects such as loose holes and inclusions more difficult. The existing detection methods mainly include "X-ray inspection 2D imaging + manual visual experience film evaluation + manual trial and error 3D positioning", which have problems such as missed and false detection of defect identification, and low-quality and inefficient defect positioning marking and repair. These have become the main bottlenecks hindering the urgent realization of intelligent, efficient, and high-quality mass production of high-end equipment. Summary of the Invention

[0003] In response to the defects of the existing technology, the purpose of this application is to provide an intelligent closed-loop processing method and system for internal defects in casting X-ray flaw detection, aiming to solve the problems of defect identification prone to missed detection and false detection, and low quality and efficiency of defect positioning, marking and repair in existing X-ray detection methods.

[0004] To achieve the above objectives, the present application provides an intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection, comprising the following steps:

[0005] S1 plans a filming path, and performs multi-angle flaw detection on the casting according to the filming path to obtain multi-angle flaw detection images;

[0006] S2 marks defect information of the casting on a three-dimensional model of the casting using the multi-angle flaw detection image;

[0007] S3 repairs the casting by welding according to the defect information;

[0008] In step S4, the repaired casting is subjected to multi-angle flaw detection again according to the filming path to obtain multi-angle flaw detection images to determine whether the repair is qualified: if qualified, the processing is terminated; if unqualified, steps S2-S4 are re-executed on the repaired casting according to the multi-angle flaw detection images obtained in step S4 until the repair is qualified.

[0009] This application realizes an intelligent closed-loop process of flaw detection, testing, marking, repair, and re-flaw detection of castings, effectively ensuring the reliability and safety of castings.

[0010] Furthermore, in step S1, the method for planning the filming path includes the following steps:

[0011] S101 establishes a virtual flaw detection platform and a three-dimensional model of the casting, and establishes an enveloping cylinder containing the three-dimensional model of the casting;

[0012] S102: obtaining a line connecting the quality control points on the three-dimensional model of the casting and the corresponding contour points on the center line of the virtual flaw detection platform; and obtaining an intersection point between the line and the enveloping cylinder;

[0013] S103 takes the intersection as a starting point, traverses the surface of the casting three-dimensional model, searches for remaining path points at preset intervals, and generates the filming path based on all the searched path points.

[0014] Furthermore, in step S102, the quality control points include multiple quality control points at locations with large wall thickness differences, multiple cross structures, sharp corners, sharp edges, and blind holes. In step S103, each quality control point is used as a starting point, and the remaining path points on the three-dimensional model of the casting are traversed and searched at preset intervals to generate multiple initial filming paths; the shortest path among the initial paths is selected as the filming path.

[0015] Furthermore, in step S103, the preset interval satisfies the following conditions:

[0016] d(P1,P2)=r*min(|θ1-θ2|,2π-|θ1-θ2|)+|z1-z2|

[0017] Among them, d(P1,P2) represents the distance between the previous point P1 and the next point P2, r is the radius of the enveloping cylinder, θ1 is the angular coordinate of point P1 in the cylindrical coordinate system, θ2 is the angular coordinate of point P2 in the cylindrical coordinate system, z1 is the height coordinate of point P1 in the cylindrical coordinate system, and z2 is the height coordinate of point P2 in the cylindrical coordinate system.

[0018] Furthermore, in step S2, the specific steps of marking defect information of the casting on the three-dimensional model of the casting using the multi-angle flaw detection image include:

[0019] S201 obtains two-dimensional coordinates of a defect from the multi-angle flaw detection image, and converts the two-dimensional coordinates of the defect into three-dimensional coordinates;

[0020] S202 takes the ray source as the starting point and the defect contour point as the end point, and obtains the intersection points of the ray between the starting point and the end point and each triangular facet on the casting model;

[0021] S203 draws a polyhedron that can contain all the intersection points on the triangular facets, and intersects all the polyhedrons to obtain a defective polyhedron;

[0022] S204 obtains the vector corresponding to the center of gravity of the defect polyhedron and the vector corresponding to the closest distance between the center of gravity and the casting model surface, uses all vectors to project the defect polyhedron onto the casting model, and forms a defect outline; and performs laser marking along the defect outline.

[0023] Furthermore, in step S204, when laser marking is performed based on the defect contour, the closest distance between the center of gravity and the surface of the casting model is used as the marking depth.

[0024] According to a second aspect of the present application, there is further provided a system for implementing the intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection as described in any of the above items, the system comprising a casting conveying unit, a casting flaw detection module, a defect marking module, and a repair welding module, wherein the casting flaw detection module, the defect marking module, and the repair welding module are sequentially connected through the casting conveying unit to form an intelligent closed-loop circulation processing system, wherein:

[0025] The casting conveying unit is used to transport the castings to the workstations of the casting flaw detection module, the defect marking module and the repair welding module in sequence;

[0026] The casting flaw detection module is used to plan a filming path, and perform multi-angle flaw detection on the casting and the casting repaired by welding according to the filming path, obtain corresponding multi-angle flaw detection images, and transmit the corresponding multi-angle flaw detection images to the defect marking module;

[0027] The defect marking module is used to mark the defect position of the casting on the three-dimensional model of the casting using the received multi-angle flaw detection image, and transmit the marking information to the repair welding module;

[0028] The repair welding module is used to perform repair welding on the casting or the casting after repair welding using the received marking information.

[0029] Furthermore, the defect marking module includes:

[0030] A coordinate conversion unit, configured to obtain two-dimensional coordinates of a defect from the received multi-angle flaw detection image and convert the two-dimensional coordinates of the defect into three-dimensional coordinates;

[0031] The ray intersection unit is used to obtain the intersection points of the ray between the starting point and the end point and each triangular facet on the casting model, with the ray source as the starting point and the defect contour point as the end point;

[0032] Defect location determination unit, used to draw a polyhedron that can contain all intersection points on the triangles;

[0033] A polyhedron intersection unit, configured to intersect all the polyhedrons to obtain a defective polyhedron;

[0034] The defect laser marking unit is used to obtain the vector corresponding to the center of gravity of the defect polyhedron and the vector corresponding to the closest distance between the center of gravity and the surface of the casting model, and use all vectors to project the defect polyhedron onto the casting model to form a defect outline; it is also used to perform laser marking along the defect outline.

[0035] According to a third aspect of the present application, a computer-readable storage medium is further provided, wherein the computer-readable storage medium stores a computer program. When the computer program runs on a processor, the processor executes any of the above-described intelligent closed-loop processing methods.

[0036] According to a fourth aspect of the present application, a computer program product is also provided. When the computer program product runs on a processor, the processor executes any of the above-mentioned intelligent closed-loop processing methods.

[0037] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0038] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the existing technologies:

[0039] (1) The intelligent closed-loop processing method provided by the present application sequentially associates flaw detection, defect marking, and repair by welding of castings, uses multi-angle flaw detection images to mark defect information of castings on a three-dimensional model of castings, and then repairs the castings by welding based on the marked defect information. The repaired castings are re-tested by multi-angle flaw detection according to the filming path to determine whether the repair is qualified. If the castings are unqualified, the defects can be re-marked and repaired based on the new multi-angle flaw detection images, thereby realizing an intelligent closed-loop process of flaw detection, inspection, marking, repair, and re-flaw detection of castings, effectively ensuring the reliability and safety of castings.

[0040] (2) The filming path planning method provided in this application can realize all-round and complete detection of casting defects, obtain comprehensive and complete defect images, and facilitate subsequent efficient marking and efficient repair welding.

[0041] (3) The closed-loop processing system provided in this application connects the casting flaw detection station, defect marking station and welding repair station through a casting transport unit. The casting transport unit enables the casting to be automatically transported to the next station after completing the corresponding process at the current station, realizing unmanned processing of the entire process.

[0042] (4) This application realizes the fully automated operation of casting film path planning, intelligent film evaluation, three-dimensional positioning, laser marking and welding repair, which reduces the scrap rate of castings and improves the efficiency of casting flaw detection and repair work. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of an intelligent closed-loop processing method for internal defects in casting X-ray flaw detection provided by an embodiment of the present application;

[0044] Figure 2 This is a flowchart of a method for planning a filming path provided in an embodiment of the present application;

[0045] Figure 3 1 is a flow chart of a method for marking defect information of a casting on a three-dimensional model of a casting provided in an embodiment of the present application;

[0046] Figure 4 This is a schematic diagram of three-dimensional positioning of casting defects provided in an embodiment of the present application;

[0047] Figure 5 This is a schematic diagram of the processing area planning of the intelligent closed-loop processing system for internal defects of castings by X-ray flaw detection provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0049] The term "and / or" as used herein describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. The symbol " / " as used herein indicates that the related objects are in an "or" relationship, for example, A / B means either A or B.

[0050] The terms "first" and "second" in this specification and claims are used to distinguish different objects rather than to describe a specific order of objects. For example, "first response message" and "second response message" are used to distinguish different response messages rather than to describe a specific order of response messages.

[0051] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0052] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more, for example, multiple processing units means two or more processing units, etc.; multiple elements means two or more elements, etc.

[0053] Next, the technical solutions provided in the embodiments of this application are introduced.

[0054] This embodiment provides an intelligent closed-loop processing method for internal defects in castings inspected by X-ray inspection. During processing, the working area involved in this method is divided into a production area, a finished product area, a casting inspection area, a defect marking area, and a repair welding area. A casting conveying unit, such as an automated conveyor, is used to sequentially connect the casting inspection area, the defect marking area, and the repair welding area to form a closed loop. A robotic arm is provided at a workstation in each area to automatically transport castings, so that the castings can automatically cycle between the casting inspection area, the defect marking area, and the repair welding area in sequence, and can be automatically transported to the workstation to perform work in the corresponding area.

[0055] like Figure 1 The figure shows a flow chart of the intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection, which specifically includes the following steps:

[0056] S1 plans a filming path and performs multi-angle flaw detection on the casting according to the filming path, obtaining multi-angle flaw detection images. Specifically, the casting is placed in the casting flaw detection area, and X-ray flaw detection equipment is used to inspect key quality control points of the casting, generating a set of DR (digital radiography) flaw detection images. The flaw detection equipment is closely linked to the intelligent film evaluation system, and the generated flaw detection images are then transmitted to the intelligent film evaluation system in real time. The intelligent film evaluation system then selects defects in the flaw detection images.

[0057] like Figure 2 As shown, the method for planning a filming path includes the following steps:

[0058] S101 establishes a virtual flaw detection platform and a three-dimensional model of the casting, and establishes an enveloping cylinder containing the three-dimensional model of the casting.

[0059] Establish an image coordinate system: take the center of the imaging plate model in the virtual flaw detection platform as the origin, the x-axis is in the horizontal direction, rightward is positive, and the y-axis is in the vertical direction, upward is positive.

[0060] Establish a world coordinate system: take the center of the imaging plate model as the origin, the y-axis is parallel to the x-axis of the image coordinate system, and the z-axis is parallel to the y-axis of the image coordinate system. The x-axis of the world coordinate system can be determined according to the right-hand rule of the coordinate system.

[0061] Project all vertices of the casting's 3D model onto a plane along the z-axis of the world coordinate system. On this projection plane, with the casting's center as the origin, find the smallest circular region encompassing all projected points and determine the radius r of this circular region. Using this circular region as the base, create an enveloping cylinder encompassing the casting's 3D model.

[0062] S102 obtains a line connecting the quality control points on the three-dimensional model of the casting and the corresponding contour points on the center line of the virtual flaw detection platform; and obtains an intersection point of the line and the enveloping cylinder.

[0063] Specifically, quality control points include locations with large wall thickness differences, multiple intersections, sharp corners, sharp edges, and blind holes. These areas are prone to defects and require special attention during filming. The quality control points for these areas can be manually compiled based on relevant quality system documentation to identify the quality characteristics and dominant factors that require special control in key links and areas. The three-dimensional coordinates of each quality control point can then be determined based on the world coordinate system.

[0064] Select a point on the centerline of the imaging platform model whose height matches that of a quality control point. Connect this point to the quality control point at the corresponding height. Extend a ray outward from this point, which intersects the enveloping cylinder of the casting model. For other key quality control points on the casting, use this step to determine all intersections, as well as the angle and height of each intersection on the enveloping cylinder.

[0065] S103 traverses the surface of the 3D casting model, starting from the intersection point. It searches for additional path points at preset intervals and generates a radiographic path based on all found path points. Specifically, an intersection point is selected as the starting point, and the imaging platform is rotated and moved up and down at preset intervals to comprehensively capture flaw detection images at different locations on the casting model, achieving a complete inspection of the casting model surface.

[0066] Specifically, the preset interval meets the following conditions:

[0067] d(P1,P2)=r*min(|θ1-θ2|,2π-|θ1-θ2|)+|z1-z2| (1)

[0069] Among them, d(P1,P2) represents the distance between the previous point P1 and the next point P2, r is the radius of the enveloping cylinder, θ1 is the angular coordinate of point P1 in the cylindrical coordinate system, θ2 is the angular coordinate of point P2 in the cylindrical coordinate system, z1 is the height coordinate of point P1 in the cylindrical coordinate system, and z2 is the height coordinate of point P2 in the cylindrical coordinate system.

[0070] In a preferred embodiment, in the aforementioned step S103, each quality control point can be used as a starting point, and the remaining path points on the three-dimensional model of the casting can be traversed multiple times at preset intervals to generate multiple initial filming paths using the set of path points searched each time; then, the shortest path among the initial paths can be compared and selected as the filming path.

[0071] During actual flaw detection, the imaging plate is rotated and moved up and down so that the center of the ray source is aligned with each intersection of the envelope cylindrical surface in sequence according to the filming path, and the corresponding flaw detection image of the angle is automatically generated.

[0072] S2 uses multi-angle flaw detection images to mark casting defect information on a 3D model of the casting. Specifically, the 2D position of the defect in the flaw detection image is correlated with the 3D position of the defect in the actual casting. Laser marking equipment is then used to mark the location, size, and depth of the defect in the casting.

[0073] like Figure 3 As shown, the specific steps of marking defect information of a casting on a three-dimensional casting model using multi-angle flaw detection images include:

[0074] S201 obtains the two-dimensional coordinates of the defect from the multi-angle flaw detection image and converts the two-dimensional coordinates of the defect into three-dimensional coordinates; specifically, after planning the filming path of the casting according to the key quality control points of the casting, the automatic detection system generates a multi-angle flaw detection image of the casting, and transmits the flaw detection image to the intelligent film evaluation system, locates the two-dimensional coordinates of the defect in the flaw detection image based on the image coordinate system, and converts the two-dimensional coordinates of the defect contour point in the image coordinate system into the three-dimensional coordinates in the world coordinate system.

[0075] S202 takes the ray source as the starting point and the defect contour point as the end point, and obtains the intersection points of the ray between the starting point and the end point and each triangular facet on the casting model; that is, the center of the ray source is taken as the starting point and a series of defect contour points as the end point, and obtains the intersection points of a series of rays formed by the connection between the starting point and the end point and the triangular facets of the casting model file in the STL format.

[0076] S203 draws a polyhedron that can contain all the intersection points on the triangular facets, and obtains a defective polyhedron by intersecting all the polyhedrons; the defective polyhedron corresponds to a preliminary defect position.

[0077] S204 obtains the vector corresponding to the center of gravity of the defect polyhedron and the vector corresponding to the closest distance between the center of gravity and the surface of the casting model. The marking depth is the closest distance between the center of gravity and the surface of the casting model. All vectors are used to project the defect polyhedron onto the casting model to form a defect outline. Laser marking is performed along the defect outline.

[0078] Specifically, based on the obtained defective polyhedron, visual positioning is used to calculate the coordinates of the center of gravity of the polyhedron and the closest distance between the center of gravity and the model surface, as well as the vectors corresponding to the aforementioned center of gravity and the closest distance between the center of gravity and the model surface, so as to achieve the effect of using the visual system to locate the casting and determine the laser marking position.

[0079] More specifically, the laser parameters are set, including laser power, marking speed, marking profile, and marking depth. The laser marking machine, based on pre-set parameters, precisely controls the laser beam to mark the surface of the casting, leaving information such as the defect profile and depth on the casting surface. A vision system is used to recheck the marking results to ensure they meet the requirements.

[0080] S3 repairs the casting by welding based on the defect information.

[0081] Specifically, the casting is transported to the repair welding area. After the casting is removed, a solvent is first used to remove grease, oxides, and other contaminants from the surface of the light alloy casting. Next, a welding wire of the appropriate alloy is selected, using argon as the shielding gas. Based on information such as the defect profile and depth on the casting surface, the welding robot gradually fills and repairs the internal defects of the light alloy casting during the welding process. Finally, the welded casting is allowed to cool naturally, and tools are used to remove welding slag and other residues.

[0082] In step S4, the repaired casting is re-tested with multi-angle flaw detection according to the filming path to obtain multi-angle flaw detection images to determine whether the repair is qualified: if qualified, the processing is terminated; if unqualified, steps S2-S4 are re-executed on the repaired casting according to the multi-angle flaw detection images obtained in step S4 until the repair is qualified.

[0083] Specifically, the casting is transported back to the casting flaw detection area to check whether the internal defects have been completely repaired. If they have been repaired, the casting is transported to the finished product area. If they have not been repaired, the casting is transported to the defect marking area and the repair welding area in sequence until the internal defects of the casting are completely repaired.

[0084] The above-mentioned embodiment realizes the intelligent closed-loop process of flaw detection, testing, marking, repair and re-flaw detection of castings, effectively ensuring the reliability and safety of castings.

[0085] In another embodiment, a system is provided for implementing the intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection as described in any of the previous embodiments. The system includes a casting conveying unit, a casting flaw detection module, a defect marking module and a repair welding module. The casting flaw detection module, the defect marking module and the repair welding module are connected in sequence through the casting conveying unit to form an intelligent closed-loop circulation processing system.

[0086] Among them, the casting conveying unit is an automated conveyor (such as a roller conveyor), which is equipped with a flat-bottomed plastic box for holding castings. The automated conveyor can transport the castings to the workstations of the casting flaw detection module, defect marking module and welding repair module in sequence according to the preset conveying path, and transport the castings at the corresponding workstations through the set robotic arms.

[0087] The casting flaw detection module is used to plan the filming path and perform multi-angle flaw detection on castings and castings repaired by welding according to the filming path, obtain corresponding multi-angle flaw detection images, and transmit the corresponding multi-angle flaw detection images to the defect marking module;

[0088] The defect marking module is used to mark the defect position of the casting on the three-dimensional model of the casting using the received multi-angle flaw detection images, and transmit the marking information to the repair welding module;

[0089] The defect marking module also includes:

[0090] A coordinate conversion unit, configured to obtain two-dimensional coordinates of a defect from the received multi-angle flaw detection image and convert the two-dimensional coordinates of the defect into three-dimensional coordinates;

[0091] The ray intersection unit is used to obtain the intersection points of the ray between the starting point and the end point and each triangular facet on the casting model, with the ray source as the starting point and the defect contour point as the end point;

[0092] Defect location determination unit, used to draw a polyhedron that can contain all intersection points on the triangles;

[0093] A polyhedron intersection unit, configured to intersect all the polyhedrons to obtain a defective polyhedron;

[0094] The defect laser marking unit is used to obtain the vector corresponding to the center of gravity of the defect polyhedron and the vector corresponding to the closest distance between the center of gravity and the surface of the casting model, and use all vectors to project the defect polyhedron onto the casting model to form a defect outline; it is also used to perform laser marking along the defect outline.

[0095] The repair welding module is used to repair the casting or the casting after repair welding by using the received marking information, and mainly includes a laser marking machine.

[0096] The system workflow is as follows Figure 5 As shown: (1) the production area produces blank castings; (2) the blank castings are transported to the casting flaw detection area by a roller conveyor for X-ray flaw detection; (3) the defective blank castings are then sent to the defect marking area by a roller conveyor, the defective area is marked by a laser marking machine, and the non-defective castings are sent to the finished product area; (4) the marked defective blank castings are sent to the welding repair area by a roller conveyor, and the defective area is repaired by welding using a welding robot according to the flaw detection image; (5) the welded repaired parts are then returned to the casting flaw detection area for flaw detection again. If the inspection is qualified, the repaired castings are sent to the finished product area. If the inspection is unqualified, the unqualified castings are sent to the defect marking area again for marking using a new flaw detection image, and then transported to the welding repair area for repair welding according to the new marking information. After welding is completed, flaw detection is performed again until the defects are repaired.

[0097] It is understandable that the detailed functional implementation of each of the above units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0098] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method and will not be repeated here.

[0099] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0100] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0101] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0102] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0103] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0104] It will be understood that the various numerical numbers involved in the embodiments of the present application are merely distinctions for the convenience of description and are not intended to limit the scope of the embodiments of the present application.

[0105] It is easy for those skilled in the art to understand that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. An intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection, characterized in that: The following steps are involved: S1 plans the filming path according to the following method: S101 establishes a virtual flaw detection platform and a three-dimensional model of the casting, and establishes an enveloping cylinder containing the three-dimensional model of the casting; S102: obtaining a line connecting the quality control points on the three-dimensional model of the casting and the corresponding contour points on the center line of the virtual flaw detection platform; and obtaining an intersection point between the line and the enveloping cylinder; S103 takes the intersection as a starting point, traverses the surface of the casting three-dimensional model, searches for remaining path points at preset intervals, and generates the filming path based on all the searched path points; wherein the preset intervals meet the following conditions: in, Indicates the previous point P 1 and the next point P 2, r is the radius of the enveloping cylinder, θ1 is the point P 1 is the angular coordinate of the cylindrical coordinate system, θ2 is the angle of the point P 2 Angular coordinates in the cylindrical coordinate system, z1 is the point P 1 is the height coordinate of the cylindrical coordinate system, z2 is the point P 2Height coordinate in cylindrical coordinate system; and performing multi-angle flaw detection on the casting according to the filming path to obtain multi-angle flaw detection images; S2 marks defect information of the casting on a three-dimensional model of the casting using the multi-angle flaw detection image; S3 repairs the casting by welding according to the defect information; In step S4, the repaired casting is subjected to multi-angle flaw detection again according to the filming path to obtain multi-angle flaw detection images to determine whether the repair is qualified: if qualified, the processing is terminated; if unqualified, steps S2-S4 are re-executed on the repaired casting according to the multi-angle flaw detection images obtained in step S4 until the repair is qualified.

2. The intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection according to claim 1, characterized in that: In step S102, the quality control points include multiple quality control points at locations with large wall thickness differences, multiple intersection structures, sharp corners, sharp edges, and blind holes; in step S103, each quality control point is used as a starting point, and the remaining path points on the three-dimensional model of the casting are traversed and searched at preset intervals to generate multiple initial filming paths; the shortest path among the initial filming paths is selected as the filming path.

3. The intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection according to claim 1, characterized in that: In step S2, the specific steps of marking defect information of the casting on the three-dimensional model of the casting using the multi-angle flaw detection image include: S201 obtains two-dimensional coordinates of a defect from the multi-angle flaw detection image, and converts the two-dimensional coordinates of the defect into three-dimensional coordinates; S202 takes the ray source as the starting point and the defect contour point as the end point, and obtains the intersection points of the ray between the starting point and the end point and each triangular facet on the casting model; S203 draws a polyhedron that can contain all the intersection points on the triangular facets, and intersects all the polyhedrons to obtain a defective polyhedron; S204 obtains the vector corresponding to the center of gravity of the defect polyhedron and the vector corresponding to the closest distance between the center of gravity and the casting model surface, uses all vectors to project the defect polyhedron onto the casting model, and forms a defect outline; and performs laser marking along the defect outline.

4. The intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection according to claim 3, characterized in that: In step S204, when laser marking is performed based on the defect contour, the closest distance between the center of gravity and the surface of the casting model is used as the marking depth.

5. A system for implementing the intelligent closed-loop processing method for internal defects of castings by X-ray flaw detection according to any one of claims 1 to 4, characterized in that: The system includes a casting conveying unit, a casting flaw detection module, a defect marking module and a repair welding module. The casting flaw detection module, the defect marking module and the repair welding module are sequentially connected through the casting conveying unit to form an intelligent closed-loop circulation processing system, wherein: The casting conveying unit is used to transport the castings to the workstations of the casting flaw detection module, the defect marking module and the repair welding module in sequence; The casting flaw detection module is used to plan a filming path, and perform multi-angle flaw detection on the casting or the casting repaired by welding according to the filming path, obtain corresponding multi-angle flaw detection images, and transmit the corresponding multi-angle flaw detection images to the defect marking module; The defect marking module is used to mark the defect position of the casting on the three-dimensional model of the casting using the received multi-angle flaw detection image, and transmit the marking information to the repair welding module; The repair welding module is used to perform repair welding on the casting or the casting after repair welding using the received marking information.

6. The system according to claim 5, wherein: The defect marking module includes: A coordinate conversion unit, configured to obtain two-dimensional coordinates of a defect from the received multi-angle flaw detection image and convert the two-dimensional coordinates of the defect into three-dimensional coordinates; The ray intersection unit is used to obtain the intersection points of the ray between the starting point and the end point and each triangular facet on the casting model, with the ray source as the starting point and the defect contour point as the end point; Defect location determination unit, used to draw a polyhedron that can contain all intersection points on the triangles; A polyhedron intersection unit, configured to intersect all the polyhedrons to obtain a defective polyhedron; The defect laser marking unit is used to obtain the vector corresponding to the center of gravity of the defect polyhedron and the vector corresponding to the closest distance between the center of gravity and the surface of the casting model, and use all vectors to project the defect polyhedron onto the casting model to form a defect outline; it is also used to perform laser marking along the defect outline.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor is enabled to execute the intelligent closed-loop processing method according to any one of claims 1 to 4.

8. A computer program product, characterized in that When the computer program product runs on a processor, the processor is enabled to execute the intelligent closed-loop processing method according to any one of claims 1 to 4.

Images