Visual positioning method for component machining area considering size deformation

Through simulation, component deformation information is obtained, auxiliary positioning areas are determined and point cloud data is converted, which solves the problem of insufficient positioning accuracy of processing areas caused by component size deformation in the prior art, and achieves higher positioning accuracy and quality consistency in processing areas.

CN119048443APending Publication Date: 2024-11-29WUHAN UNIV OF TECH

Patent Information

Application Number
CN202411079575.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The dimensional deformation of the components during filling and solidification cooling processes has not been effectively considered in the prior art, resulting in poor positioning accuracy of the processing area and unable to meet the processing requirements.

Method used

Through the filling and solidification cooling process of simulation components, component deformation information is obtained, auxiliary positioning area and its corresponding point cloud data are determined, and the initial flying point cloud data is converted into intermediate flying point cloud data, thereby measuring point cloud from the measurement point cloud Target point cloud data is extracted from the data to determine the processing area.

Benefits of technology

It effectively reduces the introduction of point clouds in non-processing areas, improves the positioning accuracy of the processing area, and ensures the consistency and accuracy of processing quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048443A_ABST
    Figure CN119048443A_ABST
Patent Text Reader

Abstract

The invention relates to a component machining area visual positioning method considering size deformation, and belongs to the technical field of component machining, and the method comprises the steps: determining a local flash area and corresponding initial flash point cloud data according to standard component information; simulating the mold filling and solidification cooling process of the component according to the standard component information to obtain component deformation information, and determining an auxiliary positioning area and positioning point cloud data corresponding to the auxiliary positioning area based on the component deformation information; and the positioning point cloud data and the measurement point cloud data are registered to obtain a target transformation matrix, the initial flash point cloud data are converted based on the target transformation matrix, target point cloud data are extracted from the measurement point cloud data, and a processing area is determined based on the target point cloud data. According to the method, the target point cloud data are extracted from the local flash area where flash possibly occurs in the measurement point cloud by means of the auxiliary positioning area, introduction of point clouds in a non-machining area is reduced, and the machining area positioning accuracy is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of component processing, and in particular to a component processing area visual positioning method taking into account dimensional deformation. Background Art

[0002] Precision machining of complex components such as aircraft engine blades and automotive components is crucial to ensure the performance and reliability of the final product. Taking complex automotive components as an example, the flywheel housing has a complex structure and large size. After casting, it is inevitable that flash of different sizes and shapes will be produced at the mold parting. At present, domestic automotive parts manufacturing companies generally adopt manual operation, relying on manual visual identification of flash and manual processing to remove it. The processing environment is full of metal dust and the workload is large. The workers are tired and the processing efficiency is not high. The processing quality and consistency cannot be guaranteed. Although dedicated CNC machine tools can provide higher processing accuracy and stable milling quality, they are not flexible enough when handling large and complex components, and the high processing cost makes it difficult for small and medium-sized enterprises to afford it. Robot milling has been successfully applied in many fields such as aerospace, rail transportation, etc. It is a feasible solution to apply robots to milling flash of automobile engine flywheel housings. The use of robot automated processing has great advantages in saving labor, improving efficiency and improving processing quality.

[0003] Obtaining the position of the processing area is a prerequisite for processing. The manual operation method relies on visual identification of the flash area. In order to replace manual operation with sensors to determine the flash area, the invention patent with application number 202210952988.6 discloses a method and device for automatically removing component flash. This method accurately determines the flash area by analyzing the component image. However, the flash detection accuracy of this method is highly dependent on image quality and may be affected by light or camera quality. In response to the problems caused by the above-mentioned two-dimensional machine vision guidance technology, three-dimensional machine vision technology can obtain morphological information such as the depth of the object surface, and can realize object recognition and positioning. In actual production, some environmental interference can be avoided. The invention patent with application number 202311036938.4 discloses a real-time full-coverage polishing path planning method based on point cloud. The flash area determination of this method is to align the discrete standard point cloud and the measured point cloud of the CAD model using point cloud registration technology, retrieve the registration error of each pair of registration points through the error search algorithm, and extract the point cloud greater than the threshold as the non-overlapping part, which is the processing area.

[0004] However, the component will deform during the filling and solidification cooling process, which may easily lead to a large dimensional deviation between the component and its CAD model. The use of the registration error search algorithm is likely to introduce more non-processing area point clouds, resulting in poor positioning accuracy of the processing area in the component to be processed, thus failing to meet the relevant processing requirements. Summary of the invention

[0005] In view of this, it is necessary to provide a component processing area visual positioning method that takes into account dimensional deformation, so as to solve the problem in the prior art that the component deformation factor is not taken into account, resulting in poor positioning accuracy of the processing area in the component to be processed.

[0006] In order to solve the above problems, the present application provides a component processing area visual positioning method considering dimensional deformation, including: Determine the local flash area and its corresponding initial flash point cloud data according to the standard component information; Simulating the filling and solidification cooling process of the component according to the standard component information to obtain the component deformation information, and determining the auxiliary positioning area and its corresponding positioning point cloud data based on the component deformation information; The positioning point cloud data is aligned with the measurement point cloud data to obtain a target transformation matrix, the initial fly point cloud data is converted into intermediate fly point cloud data based on the target transformation matrix, target point cloud data is extracted from the measurement point cloud data based on the intermediate fly point cloud data, and a processing area is determined based on the target point cloud data.

[0007] In some possible implementations, the component deformation information includes component deformation amount information, the standard component information includes standard component feature point information, and the auxiliary positioning area is determined according to the component deformation amount information and the standard component feature point information.

[0008] In some possible implementations, the local flash area is a three-dimensional space with a standard component parting line as a guide line.

[0009] In some possible implementations, the measured point cloud data is point cloud data acquired by a single scan, the local flash area includes a plurality of flash sub-areas, the initial flash point cloud data includes point cloud data corresponding to the plurality of flash sub-areas, the auxiliary positioning area includes a plurality of positioning sub-areas, the positioning point cloud data includes point cloud data corresponding to the plurality of positioning sub-areas, and the positioning sub-areas correspond one-to-one to the flash sub-areas; The positioning point cloud data is registered with the measurement point cloud data to obtain a target transformation matrix, including: The point cloud data corresponding to the plurality of positioning sub-areas are respectively registered with the measured point cloud data to obtain initial transformation matrices and evaluation indicators corresponding to the plurality of positioning sub-areas; A target positioning sub-region with the best evaluation index is selected from the plurality of positioning sub-regions, a target flying edge sub-region and a target transformation matrix corresponding to the target positioning sub-region are determined, and point cloud data corresponding to the target flying edge sub-region is used as updated initial flying edge point cloud data.

[0010] In some possible implementations, the point cloud data corresponding to the plurality of positioning sub-areas are respectively registered with the measured point cloud data to obtain initial transformation matrices corresponding to the plurality of positioning sub-areas, including: Roughly registering the point cloud data corresponding to the plurality of positioning sub-areas with the measured point cloud data to obtain initial transformation matrices corresponding to the plurality of positioning sub-areas; Determining a target transformation matrix corresponding to the target positioning sub-region includes: Based on the initial transformation matrix corresponding to the target positioning sub-region, the point cloud data corresponding to the target positioning sub-region is precisely aligned with the measured point cloud data to obtain a target transformation matrix.

[0011] In some possible implementations, the coarse registration uses a random sampling consensus algorithm.

[0012] In some possible implementations, the precise registration uses an iterative closest point algorithm.

[0013] In some possible implementations, extracting target point cloud data from the measured point cloud data based on the intermediate flash point cloud data includes: Determine the convex hull of the intermediate flash point cloud data; Points within the convex hull from the measured point cloud data are extracted to obtain target point cloud data.

[0014] The present application also provides a component processing area visual positioning device taking into account dimensional deformation, comprising: A local flash area determination unit is used to determine the local flash area and its corresponding initial flash point cloud data according to standard component information; The auxiliary positioning area determination unit simulates the filling and solidification cooling process of the component according to the standard component information to obtain the component deformation information, and determines the auxiliary positioning area and its corresponding positioning point cloud data based on the component deformation information; A point cloud registration unit is configured to register the positioning point cloud data with the measurement point cloud data to obtain a target transformation matrix, and is configured to convert the initial flying edge point cloud data into intermediate flying edge point cloud data based on the target transformation matrix; The processing area determination unit extracts target point cloud data from the measured point cloud data based on the intermediate flash point cloud data, and determines the processing area based on the target point cloud data.

[0015] The present application also provides an electronic device, including a memory and a processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the above-mentioned method for visual positioning of the component processing area considering dimensional deformation.

[0016] The beneficial effect of the present application is that the visual positioning method of the component processing area taking into account dimensional deformation provided in the present application maps the local flash area of ​​the standard component where flash may appear to the measured point cloud data of the component to be processed with the help of the auxiliary positioning area with small deformation, and then extracts the target point cloud data in the local flash area of ​​the measured point cloud data to determine the processing area, which effectively reduces the introduction of point clouds in non-processing areas and improves the positioning accuracy of the processing area. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of an embodiment of a method for visually locating a component processing area taking into account size deformation provided in the present application; Figure 2 Schematic diagram of the local flash area provided for this application; Figure 3 A schematic diagram of the deformation of the upper surface of the flywheel housing provided in this application; Figure 4 A schematic diagram of the intrinsic shape feature points on the upper surface of the flywheel housing provided in this application; Figure 5 A schematic diagram of the auxiliary positioning area provided for this application; Figure 6 A schematic diagram of the relative positions of the positioning sub-region and the flash sub-region provided in this application; Figure 7 For this application Figure 1 A schematic flow chart of an embodiment of step S103; Figure 8 For this application Figure 1 A schematic flow chart of an embodiment of step S104; Fig. 9 A schematic diagram of point clouds of two positioning sub-areas and their corresponding fin sub-areas provided in this application; Fig.10 A schematic diagram of a target point cloud within a convex hull in the measurement point cloud data provided by this application; Fig.11 A schematic diagram of an embodiment of a visual positioning device for component processing area considering dimensional deformation provided in this application Fig.12 A schematic diagram of the structure of an embodiment of an electronic device provided in this application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0019] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowcharts, or may remove one or more operations from the flowcharts, under the guidance of the content of this application. Some of the block diagrams shown in the accompanying drawings are functional entities, and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.

[0020] The descriptions of "first", "second", etc. involved in the embodiments of the present application are only used to describe the implicit purpose, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist, for example: A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone.

[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] The present application provides a method for visual positioning of a component processing area taking into account dimensional deformation, which is described below.

[0023] Figure 1 A schematic flow chart of an embodiment of a method for visually locating a component processing area considering size deformation provided in the present application is shown in FIG. Figure 1 As shown in the figure, the visual positioning method of the component processing area considering the size deformation includes: S101, determining a local flash area and its corresponding initial flash point cloud data according to standard component information; It should be noted that the local flash area is the area where the component may have flash, which is known after the casting process is determined. In this embodiment, the flywheel housing component is taken as an example for explanation. The area where the component may have flash is the parting of the casting mold. The mold parting surface is on the upper part of the component. The local flash area is a three-dimensional space with the parting line as the guide line. The local flash area is as follows: Figure 2 As shown in the figure, the definition method is: the distance from the flash edge to the component body is set to , the distance in the reverse direction is set to , the vertical distance upward of the flash edge is set to , the downward distance is set to The size of the local flash area needs to be set in consideration of the deformation of the component, the accuracy of the registration algorithm, and the extension of the flash. In this embodiment, and All are set to 3mm. Set to 10mm, Set to 2mm.

[0024] It should also be noted that the local flash area is expressed in a point cloud data structure, that is, the space is made into a CAD model, and samples are taken from the model surface to obtain the corresponding point cloud. In this embodiment, the sampling method is uniform sampling, that is, points are uniformly extracted from the three-dimensional surface of the CAD model surface, and the sampling density is set to 5.

[0025] S102, simulating the filling and solidification cooling process of the component according to the standard component information to obtain component deformation information, and determining the auxiliary positioning area and its corresponding positioning point cloud data based on the component deformation information; It should be noted that the selection criteria for the auxiliary positioning area are areas with relatively small deformation of the component and rich feature information. The deformation information of the component is obtained through casting simulation, and the area with rich feature information refers to an area containing more feature points. In this embodiment, the simulation software uses ProCAST, and the standard component information includes casting method, mold material, alloy material, pouring temperature, mold temperature, heat transfer coefficient, boundary conditions, etc. The casting method is low-pressure casting, the mold material is HT13, the alloy material is AlSi7Mg0.3, the pouring temperature is 700°C, the mold preheating temperature is 360°C for the upper mold, 385°C for the side mold, and 465°C for the lower mold. The heat transfer coefficient between the mold and the alloy is 2000 W / (m 2 ∙K), the boundary conditions are air cooling of the mold, reasonable pressure-time parameters, etc. The deformation of the upper surface of the flywheel housing obtained by casting simulation is as follows Figure 3The feature points are the intrinsic shape signature (ISS) feature points of the flywheel housing upper surface point cloud. The flywheel housing upper surface point cloud is obtained by sampling the upper surface of the flywheel housing CAD model. The sampling method is uniform sampling, that is, points are uniformly extracted from the three-dimensional surface of the CAD model surface. The sampling density is set to 5. The intrinsic shape feature points of the flywheel housing upper surface are finally obtained as shown in Figure 4 shown; according to Figure 3 and Figure 4 The final auxiliary positioning area is as follows Figure 5 shown.

[0026] S103, registering the positioning point cloud data with the measurement point cloud data to obtain a target transformation matrix, and converting the initial flying edge point cloud data into intermediate flying edge point cloud data based on the target transformation matrix; It should be noted that the measurement point cloud is obtained by scanning the component using a surface structured light scanner, which belongs to visual positioning.

[0027] S104, extracting target point cloud data from the measured point cloud data based on the intermediate flash point cloud data, and determining a processing area based on the target point cloud data.

[0028] It should be noted that the present application is based on the component measurement point cloud to accurately locate the processing area, and the milling flash work can be guided by point cloud segmentation later.

[0029] Compared with the prior art, the present application uses an auxiliary positioning area with small deformation to map the local flash area of ​​the standard component where flash may appear to the measured point cloud data of the component to be processed, and then extracts the target point cloud data in the local flash area of ​​the measured point cloud data to determine the processing area, effectively reducing the introduction of point clouds in non-processing areas and improving the positioning accuracy of the processing area.

[0030] Considering that when performing point cloud registration in the existing technology, the three-dimensional scanning measurement equipment is limited by the measurement method and the shape of the set of objects to be measured, and can only scan the point cloud data of a limited range of the measured object at a time, which requires multiple scans at multiple perspectives. For large and complex components, two large numbers of measured point clouds are repeatedly spliced ​​into a complete component point cloud, which will introduce splicing errors.

[0031] Therefore, in order to avoid stitching the measured point cloud and introducing stitching errors, in some embodiments, the measured point cloud data is point cloud data obtained by a single scan, and the scanning and detection are performed simultaneously to realize the online autonomous positioning of the processing area. Specifically, the local flash area includes several flash sub-areas, the initial flash point cloud data includes point cloud data corresponding to several flash sub-areas, the auxiliary positioning area includes several positioning sub-areas, the positioning point cloud data includes point cloud data corresponding to several positioning sub-areas, the positioning sub-areas correspond to the flash sub-areas one-to-one, and each positioning sub-area determines the flash sub-area it is responsible for; when dividing the auxiliary positioning area, the distribution should be as wide as possible. In this embodiment, the auxiliary positioning area includes six areas, three of which include two sub-areas, all of which are intended to complete auxiliary positioning. The relative position relationship between the positioning sub-area and the flash sub-area is as follows: Figure 6 shown.

[0032] Correspondingly, such as Figure 7 As shown, in step S103, the positioning point cloud data is registered with the measurement point cloud data to obtain a target transformation matrix, including: S701, registering the point cloud data corresponding to the plurality of positioning sub-areas with the measured point cloud data, and obtaining initial transformation matrices and evaluation indicators corresponding to the plurality of positioning sub-areas; It should be noted that the point cloud corresponding to the registration sub-region With measured point cloud Finally, the mean square error (RSME) of the matching points between the two point clouds is used as the evaluation index. The smaller the value, the better the registration result. The formula is as follows:

[0033] In the formula, Point cloud corresponding to the localization sub-region The point in Is the measured point cloud The point in It is to point After matrix transformation, the point cloud is measured After mid-range transformation The closest point.

[0034] S702, selecting a target positioning sub-region with the best evaluation index from a plurality of positioning sub-regions, determining a target flying edge sub-region and a target transformation matrix corresponding to the target positioning sub-region, and using point cloud data corresponding to the target flying edge sub-region as updated initial flying edge point cloud data.

[0035] Furthermore, in order to improve the accuracy of point cloud registration, in some embodiments, the registration is divided into two stages. The first stage is the coarse registration result of the point cloud corresponding to each positioning sub-region and the measured point cloud, and the second stage is the fine registration result of the point cloud corresponding to the optimal positioning sub-region and the measured point cloud. Specifically, step S701 includes: coarsely aligning the point cloud data corresponding to several positioning sub-regions with the measured point cloud data, respectively, to obtain the initial transformation matrices corresponding to the several positioning sub-regions.

[0036] It should be noted that the rough registration of the measured point cloud with the point cloud corresponding to each positioning sub-region is performed by calculating the fast point feature histogram (FPFH) features of the measured point cloud and the point cloud corresponding to each positioning sub-region, and using the random sampling consistency algorithm (RANdom SAmple Consensus, RANSAC) to align the measured point cloud with the point cloud corresponding to each positioning sub-region to obtain the initial transformation matrix of each rough registration.

[0037] Correspondingly, determining the target transformation matrix corresponding to the target positioning sub-region in step S702 includes: based on the initial transformation matrix corresponding to the target positioning sub-region, accurately aligning the point cloud data corresponding to the target positioning sub-region with the measured point cloud data to obtain the target transformation matrix.

[0038] It should be noted that the precise registration uses the iterative closest point (ICP) algorithm.

[0039] In order to better extract the target point cloud data, in some embodiments, such as Figure 8 As shown, step S104 includes: S801, determining the convex hull of the middle flying edge point cloud data; S802: extract points in the convex hull from the measured point cloud data to obtain target point cloud data.

[0040] It should be noted that Fig. 9 As shown in the figure, the point cloud diagram of two positioning sub-areas and their corresponding flying edge sub-areas is taken as an example. The target point cloud in the convex hull of the measured point cloud data is as follows: Fig.10 shown.

[0041] In order to better implement a component processing area visual positioning method considering size deformation in an embodiment of the present application, based on a component processing area visual positioning method considering size deformation, correspondingly, Fig.11 As shown, the embodiment of the present application also provides a component processing area visual positioning device 1100 considering size deformation, including: A local flash area determining unit 1101 is used to determine the local flash area and its corresponding initial flash point cloud data according to the standard component information; The auxiliary positioning region determining unit 1102 simulates the filling and solidification cooling process of the component according to the standard component information to obtain the component deformation information, and determines the auxiliary positioning region and its corresponding positioning point cloud data based on the component deformation information; The point cloud registration unit 1103 registers the positioning point cloud data with the measurement point cloud data to obtain a target transformation matrix, which is used to convert the initial flying edge point cloud data into intermediate flying edge point cloud data based on the target transformation matrix; The processing area determining unit 1104 extracts target point cloud data from the measured point cloud data based on the intermediate flash point cloud data, and determines the processing area based on the target point cloud data.

[0042] The device 1100 for visually positioning a component processing area considering dimensional deformation provided in the above embodiment can implement the technical solution described in the embodiment of the method for visually positioning a component processing area considering dimensional deformation. The specific implementation principles of the above units can refer to the corresponding contents in the embodiment of the method for visually positioning a component processing area considering dimensional deformation, which will not be repeated here.

[0043] like Fig.12 As shown, the present application also provides an electronic device 1200. The electronic device 1200 includes a processor 1201, a memory 1202 and a display 1203. Fig.12 Only some components of the electronic device 1200 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0044] In some embodiments, the memory 1202 may be an internal storage unit of the electronic device 1200, such as a hard disk or memory of the electronic device 1200. In other embodiments, the memory 1202 may also be an external storage device of the electronic device 1200, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 1200.

[0045] Furthermore, the memory 1202 may include both an internal storage unit of the electronic device 1200 and an external storage device. The memory 1202 is used to store application software installed in the electronic device 1200 and various data.

[0046] In some embodiments, the processor 1201 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 1202, such as the component processing area visual positioning method considering dimensional deformation in the present application.

[0047] In some embodiments, the display 1203 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 1203 is used to display information on the electronic device 1200 and to display a visual user interface. The components 1201-1203 of the electronic device 1200 communicate with each other via a system bus.

[0048] In some embodiments of the present application, when the processor 1201 executes the component processing area visual positioning program considering size deformation in the memory 1202, the following steps may be implemented: Determine the local flash area and its corresponding initial flash point cloud data according to the standard component information; The filling and solidification cooling process of the component is simulated according to the standard component information to obtain the component deformation information, and the auxiliary positioning area and its corresponding positioning point cloud data are determined based on the component deformation information; The positioning point cloud data is registered with the measurement point cloud data to obtain a target transformation matrix, and the initial flying edge point cloud data is converted into intermediate flying edge point cloud data based on the target transformation matrix; Target point cloud data are extracted from the measured point cloud data based on the intermediate flash point cloud data, and the processing area is determined based on the target point cloud data.

[0049] It should be understood that: when the processor 1201 executes the component processing area visual positioning program considering dimensional deformation in the memory 1202, in addition to the above functions, other functions can also be realized. For details, please refer to the description of the corresponding method embodiment above.

[0050] Furthermore, the embodiment of the present application does not specifically limit the type of the electronic device 1200 mentioned, and the electronic device 1200 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present application, the electronic device 1200 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0051] The above is a detailed introduction to a method for visual positioning of a component processing area that takes into account dimensional deformation provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0052] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.

Claims

1. A visual positioning method for component processing area considering dimensional deformation, characterized in that: include: Determine the local flash area and its corresponding initial flash point cloud data according to standard component information; Simulating the filling and solidification cooling process of the component according to the standard component information to obtain the component deformation information, and determining the auxiliary positioning area and its corresponding positioning point cloud data based on the component deformation information; The positioning point cloud data is registered with the measurement point cloud data to obtain a target transformation matrix, and the initial flying edge point cloud data is converted into intermediate flying edge point cloud data based on the target transformation matrix; Target point cloud data is extracted from the measured point cloud data based on the intermediate flash point cloud data, and a processing area is determined based on the target point cloud data.

2. The component processing area visual positioning method considering dimensional deformation according to claim 1 is characterized in that: The component deformation information includes component deformation amount information, the standard component information includes standard component feature point information, and the auxiliary positioning area is determined according to the component deformation amount information and the standard component feature point information.

3. The component processing area visual positioning method considering dimensional deformation according to claim 1 is characterized in that: The local flash area is a three-dimensional space with the standard component parting line as the guide line.

4. The component processing area visual positioning method considering dimensional deformation according to claim 1 is characterized in that: The measured point cloud data is point cloud data acquired by a single scan, the local flash area includes a plurality of flash sub-areas, the initial flash point cloud data includes point cloud data corresponding to the plurality of flash sub-areas, the auxiliary positioning area includes a plurality of positioning sub-areas, the positioning point cloud data includes point cloud data corresponding to the plurality of positioning sub-areas, and the positioning sub-areas correspond to the flash sub-areas one by one; The positioning point cloud data is registered with the measurement point cloud data to obtain a target transformation matrix, including: The point cloud data corresponding to the plurality of positioning sub-areas are respectively registered with the measured point cloud data to obtain initial transformation matrices and evaluation indicators corresponding to the plurality of positioning sub-areas; A target positioning sub-region with the best evaluation index is selected from the plurality of positioning sub-regions, a target flying edge sub-region and a target transformation matrix corresponding to the target positioning sub-region are determined, and point cloud data corresponding to the target flying edge sub-region is used as updated initial flying edge point cloud data.

5. The component processing area visual positioning method considering dimensional deformation according to claim 4 is characterized in that: The point cloud data corresponding to the plurality of positioning sub-areas are respectively registered with the measured point cloud data to obtain initial transformation matrices corresponding to the plurality of positioning sub-areas, including: Roughly registering the point cloud data corresponding to the plurality of positioning sub-areas with the measured point cloud data to obtain initial transformation matrices corresponding to the plurality of positioning sub-areas; Determining a target transformation matrix corresponding to the target positioning sub-region includes: Based on the initial transformation matrix corresponding to the target positioning sub-region, the point cloud data corresponding to the target positioning sub-region is precisely aligned with the measured point cloud data to obtain a target transformation matrix.

6. The component processing area visual positioning method considering dimensional deformation according to claim 5 is characterized in that: The coarse registration uses a random sampling consensus algorithm.

7. The component processing area visual positioning method considering dimensional deformation according to claim 5 is characterized in that: The precise registration adopts an iterative closest point algorithm.

8. The component processing area visual positioning method considering dimensional deformation according to claim 1 is characterized in that: Extracting target point cloud data from the measured point cloud data based on the intermediate flash point cloud data includes: Determine the convex hull of the intermediate flash point cloud data; Points within the convex hull from the measured point cloud data are extracted to obtain target point cloud data.

9. A visual positioning device for component processing area taking into account dimensional deformation, characterized in that: include: A local flash area determination unit is used to determine the local flash area and its corresponding initial flash point cloud data according to standard component information; The auxiliary positioning area determination unit simulates the filling and solidification cooling process of the component according to the standard component information to obtain the component deformation information, and determines the auxiliary positioning area and its corresponding positioning point cloud data based on the component deformation information; A point cloud registration unit is configured to register the positioning point cloud data with the measurement point cloud data to obtain a target transformation matrix, and is configured to convert the initial flying edge point cloud data into intermediate flying edge point cloud data based on the target transformation matrix; The processing area determination unit extracts target point cloud data from the measured point cloud data based on the intermediate flash point cloud data, and determines the processing area based on the target point cloud data.

10. An electronic device, characterized in that: including memory and processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the method for visually locating a component processing area taking into account dimensional deformation as described in any one of claims 1 to 8 above.

Citation Information

Patent Citations

  • Method and device for automatically removing casting flash based on precise edge positioning

    CN115035137A

  • Real-time full-coverage polishing path planning method based on point cloud

    CN117011471A

Cited By

  • Machining correction method and equipment and storage medium

    CN119991666A

  • Steering knuckle flash full-automatic grinding method and system based on 3D vision

    CN120734399A

  • A method and system for automatic robot following, identification, and edge scraping control of non-ferrous metal ingots.

    CN123060680A