Intelligent thin-wall component shape correcting method and system based on digital elevation technology

Abstract

The invention discloses a thin-wall component intelligent shape correction method and system based on a digital elevation technology. The method comprises the following steps: obtaining three-dimensional shape data of a thin-wall component to be corrected, and establishing a digital elevation model; comparing the digital elevation model with a target configuration, and determining point location information and shape correction quantity information of each shape correction part; using a preset neural network model to determine the shaping process parameters and the predicted shaping time of each shaping part; obtaining a laser shape correction sequence decision scheme by using the mixed integer programming-based laser shape correction sequence decision model; generating a robot motion path planning scheme by using a preset algorithm according to the point position information of each sizing part and the laser sizing sequence decision scheme; and controlling the robot to move according to the robot motion path planning scheme and the shaping process parameters so as to complete laser heating shaping of the thin-wall component to be shaped. According to the scheme, the sizing efficiency and quality can be improved, and the intelligence and automation degree of sizing of the large thin-wall component is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of metal component forming, and in particular to an intelligent shape correction method and system for thin-walled components based on digital elevation technology. Background Art

[0002] In recent years, the aerospace field has developed rapidly, especially the output value of the civil aviation industry and the market size of aviation equipment have shown a significant growth trend. With the continuous advancement of technology, the demand for large thin-walled components in the aerospace manufacturing industry is increasing. As the key load-bearing components of aerospace equipment, large thin-walled components directly affect the performance and safety of aerospace equipment. Large thin-walled components will inevitably have springback after creep aging forming, which results in poor forming accuracy of parts. Commonly used methods such as bending method, mold compensation method, and stretch bending method are used to solve the correction parameters by analytical and numerical calculation to predict the springback, so as to achieve the purpose of reducing springback and improving forming accuracy. However, the calculation of the compensation value is based on certain assumptions, and there are errors in the calculation results. Therefore, the shape correction work after creep aging forming of thin-walled components is indispensable.

[0003] Laser profiling technology has high energy density and low pollution, and can be used in the intelligent profiling process of large thin-walled components in the aerospace field. However, the existing technology combines laser heating with other profiling processes for profiling, and is unable to perform task planning and path planning for the profiling target, which hinders the application of laser profiling technology in the intelligent profiling process of large thin-walled components in the aerospace field. Summary of the invention

[0004] In order to solve the technical problem that the existing laser shaping process of large thin-walled components cannot perform task planning and path planning for the shaping target, an embodiment of the present invention provides a thin-walled component intelligent shaping method and system based on digital elevation technology.

[0005] The technical solution of the embodiment of the present invention is achieved as follows: The embodiment of the present invention provides a thin-walled component intelligent shape correction method based on digital elevation technology, the method comprising: collecting the profile data of the thin-walled component to be corrected to obtain three-dimensional shape data; using the three-dimensional shape data to establish a digital elevation model of the thin-walled component, and comparing the digital elevation model with the target configuration of the thin-walled component to determine the point information of each correction part of the thin-walled component and the corresponding correction amount information; according to the point information and the correction amount information, using a preset neural network model, determining the correction process parameters of each correction part and predicting the correction time; According to the position information of each shaping part and the predicted shaping time, a laser shaping sequence decision plan is obtained by using a laser shaping sequence decision model based on mixed integer programming; according to the position information of each shaping part and the laser shaping sequence decision plan, a robot motion path planning plan is generated by using a preset algorithm; the robot is equipped with a laser heater for emitting laser to heat and shape the thin-walled component to be shaped; according to the robot motion path planning plan and the shaping process parameters, the robot is controlled to move to complete the laser heating shaping of the thin-walled component to be shaped.

[0006] In one embodiment, after controlling the movement of the robot according to the robot motion path planning scheme and the shaping process parameters, the method also includes: collecting the profile data of the thin-walled component after laser shaping to obtain three-dimensional morphology data; judging whether the thin-walled component is consistent with the target configuration according to the three-dimensional morphology data; if the thin-walled component is consistent with the target configuration, the shaping is completed; if the thin-walled component is inconsistent with the target configuration, the robot motion path planning scheme and the shaping process parameters are calculated again, and the robot movement is controlled according to the robot motion path planning scheme and the shaping process parameters to complete the laser heating shaping of the thin-walled component to be shaped until the thin-walled component is consistent with the target configuration.

[0007] In one embodiment, according to the point information of each alignment part and the predicted alignment time, a laser alignment sequence decision scheme is obtained by using a laser alignment sequence decision model based on mixed integer programming, including: The laser correction sequence decision model based on mixed integer programming includes an optimization target; the calculation formula of the optimization target is: in, is the total time of laser calibration, For robots to carry laser heaters from point Solstice exercise time, , They are all mission point numbers. m is the total number of mission points; For mission points The proofreading time, is a decision variable, expressing whether the planned path starts from the task point Move to the mission point , whose expression is: .

[0008] In one embodiment, according to the point information of each alignment part and the predicted alignment time, a laser alignment sequence decision scheme is obtained by using a laser alignment sequence decision model based on mixed integer programming, including: The laser correction sequence decision model based on mixed integer programming includes a task planning non-subloop constraint equation; the calculation formula of the task planning non-subloop constraint equation is: in, is a decision variable, expressing whether the planned path starts from the task point Move to the mission point , whose expression is: m The total number of mission points.

[0009] In one embodiment, according to the point information of each alignment part and the predicted alignment time, a laser alignment sequence decision scheme is obtained by using a laser alignment sequence decision model based on mixed integer programming, including: The laser correction sequence decision model based on mixed integer programming includes a motion time calculation model; the calculation formula of the motion time calculation model is: in, For robots to carry laser heaters from task points To the mission point exercise time, and The laser heater is at the calibration task point. and mission points The absolute coordinates of .

[0010] In one embodiment, according to the point information of each calibration part and the laser calibration sequence decision plan, a robot motion path planning plan is generated using a preset algorithm, including: The preset algorithm includes a laser heater collision avoidance constraint equation; the calculation formula of the laser heater collision avoidance constraint equation is: in, For laser heater at the calibration task point The height of the position at For thin-walled components at the correction task point The height of the location, The maximum distance between the laser heater and the component plane while ensuring the correction effect. for The safety distance in the direction to prevent laser collision.

[0011] An embodiment of the present invention also provides an intelligent shaping system for thin-walled components based on digital elevation technology, the system comprising a laser heater, a robot, a three-dimensional laser scanner, a dynamic tracker, a tooling and a centralized processing workstation; the laser heater is used to emit laser to heat the thin-walled component to be shaped; the three-dimensional laser scanner is used to obtain surface data of the thin-walled component to be shaped; the robot is used to control the movement of the laser heater and the three-dimensional laser scanner; the dynamic tracker is used to assist the three-dimensional laser scanner in spatial positioning to complete data acquisition; the tooling is used to support or hold the thin-walled component; the centralized processing workstation is used to execute the steps of the above-mentioned method.

[0012] In one embodiment, the robot includes a first robot and a second robot; the first robot is equipped with the laser heater and is used to control the movement of the laser heater; the second robot is equipped with the three-dimensional laser scanner and is used to control the movement of the three-dimensional laser scanner.

[0013] In one embodiment, the tooling is a flexible dot matrix tooling.

[0014] An embodiment of the present invention further provides a storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0015] This embodiment has the following beneficial effects: This embodiment realizes intelligent decision-making of laser shaping process through neural network algorithm, and intelligently generates laser shaping process plan for large thin-walled components for different shaping tasks with the goal of optimizing shaping quality.

[0016] This embodiment establishes a digital elevation model that reflects the spatial position of thin-walled components based on the measurement data of a three-dimensional laser scanner and digital elevation technology. At the same time, mixed integer programming and a preset algorithm are used to obtain the optimal task sequence of the correction process and the robot correction path to avoid collisions between the robot and the thin-walled components during movement, thereby improving the correction efficiency and intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a process of an intelligent shape correction method for thin-walled components based on digital elevation technology according to an embodiment of the present invention; Figure 2 A schematic diagram of the structure of an application device of the method according to an embodiment of the present invention; Figure 3 A schematic diagram of a model architecture of an intelligent shape correction method according to an embodiment of the present invention; Figure 4 A schematic diagram of the application process of the intelligent shape correction method according to an embodiment of the present invention; Figure 5 1 is a diagram showing the internal structure of a computer device according to an embodiment of the present invention.

[0018] Description of Reference Numerals 1-Laser heater; 2-First robot; 3-First truss; 4-3D laser scanner; 5-Second robot; 6-Second truss; 7-Dynamic tracker; 8-Tooling; 9-Centralized processing workstation. DETAILED DESCRIPTION

[0019] The present invention will be described in further detail below with reference to the accompanying drawings and embodiments.

[0020] The embodiment of the present invention provides a thin-walled component intelligent shape correction method based on digital elevation technology, such as Figure 1 As shown, the method includes: Step 101: collecting profile data of the thin-walled component to be shaped to obtain three-dimensional shape data; Step 102: using the three-dimensional shape data to establish a digital elevation model of the thin-walled component, and comparing the digital elevation model with the target configuration of the thin-walled component to determine the point information of each correction part of the thin-walled component and the corresponding correction amount information; Step 103: determining the shaping process parameters of each shaping part and predicting the shaping time according to the point information and the shaping amount information using a preset neural network model; Step 104: according to the position information of each calibration part and the predicted calibration time, a laser calibration sequence decision plan is obtained by using a laser calibration sequence decision model based on mixed integer programming; Step 105: Generate a robot motion path planning scheme using a preset algorithm according to the position information of each shaping part and the laser shaping sequence decision scheme; the robot is equipped with a laser heater for emitting laser to heat and shape the thin-walled component to be shaped; Step 106: According to the robot motion path planning scheme and the shaping process parameters, the robot is controlled to move to complete the laser heating shaping of the thin-walled component to be shaped.

[0021] This embodiment adopts laser shaping technology. Laser shaping technology is a new type of flexible shaping process method. The laser generates a laser beam of a certain intensity and scans the area to be shaped on the workpiece in a specific path. Under the thermal effect of the laser, the temperature of the area rises rapidly, increasing the plastic deformation capacity of the material in the area and reducing its yield strength, promoting the work of elastic internal energy, correcting the processing deformation of the workpiece, and improving the shape accuracy of the deformed workpiece.

[0022] Compared with other shaping technologies, laser shaping technology has high energy density and low pollution. The shaping ability and shaping accuracy of the workpiece can be controlled by adjusting the laser beam quality, action time, scanning path and other parameters. It is particularly suitable for the shaping of complex large-scale integral structural parts in aerospace that are difficult to achieve using conventional methods. In addition, the laser has excellent spatial control characteristics and time control characteristics, high control accuracy, and can easily realize the flexibility, automation and intelligence of shaping processing. Therefore, this embodiment uses laser to shape large thin-walled components, which can improve the shaping accuracy.

[0023] In addition, this embodiment also uses digital elevation technology and artificial intelligence technology to intelligently generate laser correction solutions (laser correction process parameters, laser spot scanning path, robot motion path, correction task planning, laser beam start and stop, etc.) based on the measurement results of large thin-walled components, further enhancing the efficiency and quality of laser correction.

[0024] Digital elevation technology is based on the collection and processing of elevation data. It generates elevation matrix or point cloud data through mathematical methods (such as interpolation) and graphical methods (such as point data and line data) to construct a digital elevation model.

[0025] Since a large thin-walled component may have multiple areas that need to be shaped during one forming process, this embodiment will perform intelligent task planning for these shaping tasks while considering the shaping quality and shaping efficiency. At the same time, the spatial position of the robot to the large thin-walled component to be shaped during the movement process will also be considered to prevent the robot or the laser heater from colliding with the thin-walled component. The focus of this embodiment is to realize the automation and intelligence of the detection, decision-making, and execution of the laser shaping process. Through the combination of artificial intelligence and numerical optimization, based on the reconstruction of three-dimensional space with digital elevation technology, the shaping process parameters and the shaping motion path are intelligently planned to reduce the quality loss of laser shaping caused by human factors.

[0026] The present embodiment will be described in detail below.

[0027] Specifically, see Figure 2 , Figure 2 It is a structural schematic diagram of an application device of the intelligent shape correction method according to an embodiment of the present invention. Figure 2In the figure, the laser heater 1 is used to emit laser to heat the thin-walled component to be shaped, the first robot 2 is used to carry the laser heater for movement, the first truss 3 is used to carry the first robot for movement, the three-dimensional laser scanner 4 is used to obtain surface data of the thin-walled component to be measured, the second robot 5 is used for the three-dimensional laser scanner movement, the second truss 6 is used to carry the second robot for movement, the dynamic tracker 7 is used to assist the three-dimensional laser scanner data acquisition system to perform spatial positioning to complete data acquisition, the tooling 8 is used to support or hold the thin-walled component, and the centralized processing workstation 9 is used to analyze data and issue relevant control instructions.

[0028] Also, see Figure 3 The model architecture of the intelligent shaping method of this embodiment includes the following modules: an intelligent process decision module, a digital elevation model of thin-walled components, an intelligent motion path planning module, a laser shaping process plan, an intelligent shaping sequence decision module, a shaping motion path planning plan and a laser shaping execution module.

[0029] Based on the above application device and model architecture, see Figure 4 The intelligent calibration method of this embodiment includes the following contents: S0: Place the thin-walled component on the tooling and clamp it; S1: Measure the three-dimensional shape of the target thin-walled component by a three-dimensional laser scanner, and transmit the acquired three-dimensional shape data to a centralized processing server; S2: The centralized processing server analyzes the three-dimensional data, divides the grid according to the process accuracy, establishes a digital elevation model reflecting the three-dimensional coordinates of the thin-walled component space, and compares it with the target configuration to obtain the point information of each part to be calibrated and the corresponding calibration quantity information; S3: The centralized processing server transmits the point information of each part to be shaped and the corresponding shaping amount information of the thin-walled component to the laser shaping process neural network, and obtains the shaping process parameters of each shaping part and the predicted shaping time; S4: The centralized processing server transmits the position information of each part to be shaped by the thin-walled component and the predicted shaping time to the laser shaping sequence decision model based on mixed integer programming, and generates a laser shaping sequence decision plan; S5: The centralized processing server generates a motion path planning scheme for the first robot based on the position information of each part to be shaped by the thin-walled component and the laser shaping sequence decision scheme in combination with the A* algorithm; S6: The centralized processing server transmits the shaping process parameters of each shaping part and the motion path planning scheme of the first robot to the first robot. The first robot carries a laser heater and performs laser heating shaping on each to-be-shaped target according to the instruction with the target configuration as the shaping target. S7: The three-dimensional laser scanner measures the three-dimensional shape of the target thin-walled component after shape correction, and transmits the acquired three-dimensional shape data to the centralized processing server; S8: Determine whether the part to be calibrated is calibrated to the target configuration. If so, complete the calibration. If not, return to step S2.

[0030] This embodiment uses a digital elevation model based on digital elevation technology to reflect the spatial position of the thin-walled component to be shaped, combined with an intelligent algorithm, to achieve automatic planning of the movement path of the robot carrying the laser heater between multiple different shaped task targets. This embodiment includes the following technical points: 1. Optimization of laser shaping process parameters: Based on the positioning information and correction requirement information of each target correction area of ​​thin-walled components, a neural network model of laser correction process was constructed. The model takes the structural parameters and correction requirement of large thin-walled components as input variables, and the output variables include key process parameters such as temperature and duration during the correction process. In actual application, the geometric dimensions, material properties and correction requirement data obtained through detection are input into the trained laser correction process neural network model to obtain the corresponding laser correction temperature and duration process parameters.

[0031] 2. Calibration task planning and robot motion path acquisition: According to the point information of each part to be shaped of the thin-walled component and the predicted shaping time, the mixed integer programming method is used to establish a laser shaping task sequence decision model. This model adds constraints such as process and robot motion to the mixed integer programming model in the form of mathematical equations, takes minimizing the overall shaping time as the optimization goal, and uses the A* algorithm to optimize and solve the optimal shaping task sequence and its robot motion path. In this application scenario, the A* algorithm is used to determine the optimal shaping task sequence and the best motion path for the robot when performing these tasks. In this way, we can generate a decision plan for the laser shaping sequence, which includes shaping task planning and robot motion path.

[0032] 3. Obtaining the start and stop of the laser beam: According to the laser calibration sequence decision plan, when the robot follows the predetermined motion trajectory and arrives at the calibration area, the laser beam is activated. After the calibration operation is completed (i.e., after the predetermined calibration time T), the laser beam is immediately turned off and the robot immediately leaves the calibration area.

[0033] In addition, the following calculation formula is applied in this embodiment: Digital elevation model formula expression: Digital Elevation Model (DEM) is a digital simulation of the ground terrain (i.e., a digital expression of the terrain surface morphology) achieved through limited terrain elevation data. It is a physical ground model that represents the ground elevation in the form of a set of ordered numerical arrays: is the position information of the terrain feature point in the plane, Reflects the point elevation information.

[0034] Calibration task planning: (1) Optimization objectives: in, is the total time of laser calibration, For robots to carry laser heaters from point Solstice exercise time, , They are all mission point numbers. m is the total number of mission points; For point The residence time (calibration time), Is a decision variable, expressing whether the planned path starts from point Exercise to , which is expressed as: ; (2) Task planning without sub-loop constraint equation: ; (3) The robot carries the laser heater from point Solstice Exercise time: and The laser heater is at the calibration task point. and Point The absolute coordinates of (4) Laser heater collision avoidance constraint equation: in, For laser heater at the calibration task point The height of the position at For the calibration task point The height of the component at the location, The maximum distance between the laser heater and the component plane while ensuring the correction effect. for The safety distance in the direction to prevent laser collision.

[0035] This embodiment is based on the collection of thin-walled component profile data by a three-dimensional laser measuring instrument, the collection data is transmitted to a centralized processing workstation, and a digital elevation model of the thin-walled component is generated using digital elevation technology. In addition, the system generates the shaping process parameters of each shaping task through a neural network, and generates shaping action decisions that meet the shaping requirements and equipment motion constraints with the goal of minimizing the shaping time, automatically completing the entire shaping process.

[0036] Compared with the prior art, this embodiment has the following differences: 1) The shape correction object and shape correction process are different. This application uses laser heating process to correct the shape of thin-walled components; 2) The number of calibration tasks is different. This application can automatically plan the execution order of multiple tasks according to the relevant parameters of the calibration tasks; 3) The decision-making methods for process parameters and task planning are different. This application uses neural network and mixed integer programming methods to find the best correction process and task planning scheme; 4) The robot's automatic path planning method is different. The path planning of this application is developed based on digital elevation technology.

[0037] In order to implement the method of the embodiment of the present invention, the embodiment of the present invention also provides an intelligent shaping system for thin-walled components based on digital elevation technology, including: a laser heater, a robot, a three-dimensional laser scanner, a dynamic tracker, a tooling and a centralized processing workstation; the laser heater is used to emit laser to heat the thin-walled component to be shaped; the three-dimensional laser scanner is used to obtain surface data of the thin-walled component to be shaped; the robot is used to control the movement of the laser heater and the three-dimensional laser scanner; the dynamic tracker is used to assist the three-dimensional laser scanner in spatial positioning to complete data acquisition; the tooling is used to support or hold the thin-walled component; the centralized processing workstation is used to execute the steps of the above-mentioned method.

[0038] In one embodiment, the robot includes a first robot and a second robot; the first robot is equipped with the laser heater and is used to control the movement of the laser heater; the second robot is equipped with the three-dimensional laser scanner and is used to control the movement of the three-dimensional laser scanner.

[0039] In one embodiment, the tooling is a flexible dot matrix tooling.

[0040] The above-mentioned system provided in this embodiment belongs to the same concept as the above-mentioned method embodiment. The specific implementation process thereof is detailed in the method embodiment and will not be repeated here.

[0041] In order to implement the method of the embodiment of the present invention, the embodiment of the present invention also provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of the above method.

[0042] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiment of the present invention, the embodiment of the present invention further provides an electronic device (computer device). Specifically, in one embodiment, the computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, the method of any one of the above embodiments is implemented. The display screen A04 of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0043] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0044] The device provided by the embodiment of the present invention includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the method of any one of the above embodiments is implemented.

[0045] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0046] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0047] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0049] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0050] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0051] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0052] It can be understood that the memory of the embodiment of the present invention can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAMbus random access memory (DRRAM, Direct Rambus Random Access Memory).The memories described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memories.

[0053] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0054] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. An intelligent shape correction method for thin-walled components based on digital elevation technology, characterized in that: The method comprises: Collect the profile data of the thin-walled component to be shaped and obtain three-dimensional shape data; Using the three-dimensional shape data to establish a digital elevation model of the thin-walled component, and comparing the digital elevation model with the target configuration of the thin-walled component to determine the point information of each correction part of the thin-walled component and the corresponding correction amount information; According to the point information and the correction amount information, a preset neural network model is used to determine the correction process parameters of each correction part and predict the correction time; According to the point information of each calibration part and the predicted calibration time, a laser calibration sequence decision plan is obtained by using a laser calibration sequence decision model based on mixed integer programming; According to the point information of each shaping part and the laser shaping sequence decision plan, a robot motion path planning plan is generated by using a preset algorithm; the robot is equipped with a laser heater for emitting laser to heat and shape the thin-walled component to be shaped; According to the robot motion path planning scheme and the shaping process parameters, the robot is controlled to move so as to complete the laser heating shaping of the thin-walled component to be shaped.

2. The thin-walled component intelligent shape correction method based on digital elevation technology according to claim 1 is characterized in that: After controlling the robot to move according to the robot motion path planning scheme and the shaping process parameters, the method further includes: Collect the profile data of the thin-walled component after laser correction to obtain three-dimensional shape data; Determining whether the thin-walled component is consistent with a target configuration according to the three-dimensional shape data; If the thin-walled component is consistent with the target configuration, the shape correction is completed; If the thin-walled component is inconsistent with the target configuration, the robot motion path planning scheme and the shaping process parameters are calculated again, and the robot movement is controlled according to the robot motion path planning scheme and the shaping process parameters to complete the laser heating shaping of the thin-walled component to be shaped until the thin-walled component is consistent with the target configuration.

3. The thin-walled component intelligent shape correction method based on digital elevation technology according to claim 1 is characterized in that: According to the point information of each calibration part and the predicted calibration time, a laser calibration sequence decision model based on mixed integer programming is used to obtain a laser calibration sequence decision plan, including: The laser correction sequence decision model based on mixed integer programming includes an optimization target; the calculation formula of the optimization target is: in, is the total time of laser calibration, For robots to carry laser heaters from point Solstice exercise time, , They are all mission point numbers. m is the total number of mission points; For mission points The proofreading time, is a decision variable, expressing whether the planned path starts from the task point Move to the mission point , whose expression is: 。 4. The thin-walled component intelligent shape correction method based on digital elevation technology according to claim 1 is characterized in that: According to the point information of each calibration part and the predicted calibration time, a laser calibration sequence decision model based on mixed integer programming is used to obtain a laser calibration sequence decision plan, including: The laser correction sequence decision model based on mixed integer programming includes a task planning non-subloop constraint equation; the calculation formula of the task planning non-subloop constraint equation is: in, is a decision variable, expressing whether the planned path starts from the task point Move to the mission point , whose expression is: m The total number of mission points.

5. The thin-walled component intelligent shape correction method based on digital elevation technology according to claim 1 is characterized in that: According to the point information of each calibration part and the predicted calibration time, a laser calibration sequence decision model based on mixed integer programming is used to obtain a laser calibration sequence decision plan, including: The laser correction sequence decision model based on mixed integer programming includes a motion time calculation model; the calculation formula of the motion time calculation model is: in, For robots to carry laser heaters from task points To the mission point exercise time, and The laser heater is at the calibration task point. and mission points The absolute coordinates of .

6. The thin-walled component intelligent shape correction method based on digital elevation technology according to claim 1 is characterized in that: According to the point information of each calibration part and the laser calibration sequence decision plan, a robot motion path planning plan is generated using a preset algorithm, including: The preset algorithm includes a laser heater collision avoidance constraint equation; the calculation formula of the laser heater collision avoidance constraint equation is: in, For laser heater at the calibration task point The height of the position at For thin-walled components at the correction task point The height of the location, The maximum distance between the laser heater and the component plane while ensuring the correction effect. for The safety distance in the direction to prevent laser collision.

7. An intelligent shape correction system for thin-walled components based on digital elevation technology, characterized in that: The system includes a laser heater, a robot, a three-dimensional laser scanner, a dynamic tracker, a tooling and a centralized processing workstation; The laser heater is used to emit laser to heat the thin-walled component to be shaped; The three-dimensional laser scanner is used to obtain surface data of the thin-walled component to be shaped; The robot is used to control the movement of the laser heater and the three-dimensional laser scanner; The dynamic tracker is used to assist the three-dimensional laser scanner in spatial positioning to complete data acquisition; The tooling is used to support or hold thin-walled components; The centralized processing workstation is used to execute the steps of the method according to any one of claims 1 to 6.

8. The thin-walled component intelligent shape correction system based on digital elevation technology according to claim 7 is characterized in that: The robot comprises a first robot and a second robot; The first robot is equipped with the laser heater and is used to control the movement of the laser heater; The second robot is equipped with the three-dimensional laser scanner and is used to control the movement of the three-dimensional laser scanner.

9. The thin-walled component intelligent shape correction system based on digital elevation technology according to claim 7 is characterized in that: The tooling is a flexible dot matrix tooling.

10. A storage medium storing a computer program, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images