A robotic additive and subtractive collaborative manufacturing method and system for component processing

Abstract

This invention discloses a robotic additive / subtractive collaborative manufacturing method and system for component processing. The method includes: real-time acquisition of processing status data during component processing; calculation of additive / subtractive weights based on the processing status data; and performing additive or subtractive operations based on the additive / subtractive weights; setting a processing strategy control model and determining whether a new processing strategy needs to be executed based on the processing status data; if so, controlling the robot to process the component according to the new processing strategy; constructing a thermal input path map and a stress field vector map during processing; fusing the two maps to generate a processing risk map; and adjusting the processing path of the robot based on the processing risk map.

Description

Technical Field

[0001] This invention belongs to the field of robot control technology, and more specifically, relates to a robot additive and subtractive collaborative manufacturing method and system for component processing. Background Technology

[0002] Currently, the demand for manufacturing large and complex components is surging in fields such as aerospace and energy equipment, and traditional single processes are no longer sufficient to meet the manufacturing requirements of high precision, high efficiency, and high performance. Additive manufacturing technologies (such as laser wire feeding and arc deposition) have broken through the design limitations of complex structures through discrete layering, but in practical applications, they still face problems such as residual stress accumulation and insufficient forming accuracy.

[0003] Subtractive machining technologies (such as robotic milling and ultrasonic / electrical discharge machining) improve surface quality through stiffness enhancement models and trajectory optimization, but existing systems still rely on offline programming and lack a closed-loop compensation mechanism based on real-time detection, resulting in insufficient precision in machining allowance control.

[0004] Therefore, a technical solution is urgently needed to solve the above technical problems. Summary of the Invention

[0005] To address the above technical problems, this invention proposes a robotic additive and subtractive material collaborative manufacturing method for component processing, comprising:

[0006] Real-time acquisition of processing status data during component processing; calculation of additive / subtractive material weights based on the processing status data; and performance of additive or subtractive material operations based on the additive / subtractive material weights.

[0007] Set up a processing strategy control model, and determine whether a new processing strategy needs to be executed based on the processing status data. If so, control the robot to process the component according to the new processing strategy.

[0008] A thermal input path map and a stress field vector map are constructed during processing. The two maps are then merged to generate a processing risk map. The robot adjusts the processing path based on the processing risk map.

[0009] Furthermore, the calculation of additive / subtractive manufacturing weights includes:

[0010]

[0011] Where W is the additive / subtractive weight, α is the volume weight, and R 余量 R represents the remaining unprocessed volume of the target processing area of ​​the component. 目标 Let T be the volume of the target processing area of ​​the component, β be the weight of heat accumulation, and T be the volume of the target processing area of ​​the component. 热累积 T represents the heat accumulation in the target processing area of ​​the component. 阈值 This represents the threshold for heat accumulation.

[0012] If the additive / subtractive weight W is greater than the additive / subtractive weight threshold, then an additive operation is performed; otherwise, a subtractive operation is performed.

[0013] Furthermore, the processing strategy control model includes: fusing multi-source data in the processing state data using a Kalman filter, inputting the fused multi-source data into an LSTM-RNN neural network to predict residual stress deviation during processing, and executing a new processing strategy when the residual stress deviation exceeds a preset deviation threshold.

[0014] Furthermore, the processing strategy control model includes:

[0015] Calculate the thermal-stress response factor:

[0016]

[0017] Among them, Ψ i (t) represents the thermal-stress response factor of the i-th machining trajectory point in the target machining area of ​​the component at time t. Let T′ be the residual stress at the i-th machining trajectory point in the target machining area of ​​the component at time t. i (t) represents the temperature of the i-th processing trajectory point in the target processing area of ​​the component at time t;

[0018] When the thermal-stress response factor Ψ i (t) When the preset response threshold is exceeded, a new processing strategy is executed.

[0019] Furthermore, the new processing strategy includes: adjusting the laser power, initiating ultrasonic-assisted processing, or pausing wire feeding for a certain period of time to achieve thermal interruption.

[0020] Furthermore, constructing the heat input path diagram during processing includes:

[0021] Nodes are processing trajectory points, edges are heat conduction channels between the i-th and j-th processing trajectory points, and the edge weight w′ between the i-th and j-th processing trajectory points is... ij for:

[0022]

[0023] Among them, T′ j Let T′ be the temperature of the j-th machining trajectory point in the target machining area of ​​the component. i Let d be the temperature of the i-th machining trajectory point in the target machining area of ​​the component. ij Let be the distance between the i-th processing trajectory point and the j-th processing trajectory point.

[0024] Furthermore, the vector diagram of the stress field during processing includes:

[0025] Nodes are machining trajectory points, and edges are stress transmission channels between the i-th and j-th machining trajectory points. Each node is associated with a stress vector.

[0026]

[0027] in, Let i be the stress vector of the i-th machining trajectory point. The maximum principal stress at the i-th machining trajectory point, It is the unit vector of the direction of the maximum principal stress at the i-th machining trajectory point.

[0028] The edge weight w′ between the i-th processing trajectory point and the j-th processing trajectory point ij for:

[0029]

[0030] in, Let be the stress vector of the j-th machining trajectory point.

[0031] Furthermore, the two graphs are merged to generate a processing risk map, including:

[0032] Nodes are processing trajectory points, and edges represent the adjacency relationships between nodes. The target processing area of ​​the component is divided into a regular grid. If the i-th processing trajectory point and the j-th processing trajectory point are adjacent grid points, then the i-th processing trajectory point and the j-th processing trajectory point are adjacent and are connected.

[0033] Define the fusion function for the nodes of the heat input path map and the nodes of the stress field vector map, and calculate the fusion value:

[0034]

[0035] Where, Φ i Let ω1 be the fused value of the i-th processing trajectory point, and let ω1 be the weight of the temperature gradient. ω1 represents the temperature gradient at the i-th processing trajectory point, and ω2 represents the weight of the stress vector.

[0036] Based on the fusion value and stress vector of each node, calculate the edge weight w″′ between the i-th processing trajectory point and the j-th processing trajectory point. ij :

[0037]

[0038] Where λ is the weight of the difference in fusion values, Φ j Let μ be the fusion value of the j-th processing trajectory point, and μ be the weight of the difference in stress vectors.

[0039] Furthermore, the robot adjusts the processing path based on the processing risk map, including:

[0040] The shortest path in the risk map is found using A* search or Dijkstra's algorithm. This path is then used as the path with the lowest risk. The robot is then controlled to complete the processing of the target processing area of ​​the component by following the processing trajectory points corresponding to the path with the lowest risk.

[0041] This invention also proposes a robotic additive and subtractive manufacturing system for component processing, comprising:

[0042] The additive / subtractive manufacturing control module is used to collect processing status data during component processing in real time, calculate the additive / subtractive manufacturing weight based on the processing status data, and perform additive or subtractive manufacturing operations based on the additive / subtractive manufacturing weight.

[0043] The processing strategy control module is used to set the processing strategy control model and determine whether a new processing strategy needs to be executed based on the processing status data. If so, it controls the robot to process the component according to the new processing strategy.

[0044] The processing path adjustment module is used to construct a thermal input path map and a stress field vector map during processing, merge the two maps to generate a processing risk map, and the robot adjusts the processing path according to the processing risk map.

[0045] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art:

[0046] The technical solution of this invention can precisely control the additive and subtractive modules to perform additive and subtractive processes, thereby improving processing accuracy. In addition, it can control the robot to avoid risk areas and select the optimal processing path during processing, thereby improving processing efficiency. Attached Figure Description

[0047] Figure 1 This is a flowchart of the method in Embodiment 1 of the present invention;

[0048] Figure 2 This is a system structure diagram of Embodiment 2 of the present invention;

[0049] Figure 3 This is the first schematic diagram of the component processing system;

[0050] Figure 4 This is the second schematic diagram of the component processing system. Detailed Implementation

[0051] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0052] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0053] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and by calling data stored in the storage medium.

[0054] Storage media can include random access memory (RAM) or read-only memory (ROM). Storage media can be used to store instructions, programs, code, code sets, or instructions.

[0055] The display screen is used to show the user interface of each application.

[0056] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.

[0057] Example 1

[0058] like Figure 1 This embodiment proposes a robotic additive and subtractive manufacturing method for component processing, used to control the following component processing system:

[0059] like Figure 3 and 4 As shown, the component processing system includes: an additive manufacturing module employing a robotic arm and a positioner working in tandem. The robotic arm's end effector integrates a high-precision laser-arc composite wire feeding mechanism, using TC4 titanium alloy wire with a diameter of 1.2mm. The robotic arm carries a laser / arc additive welding terminal and integrates a vision sensor. The two-axis flip-over positioner has a diameter of 2000mm and a load capacity of 2000kg. The subtractive manufacturing module is a fixed gantry structure, with two sets of X-axis and Z-axis mounted on the gantry. One set is used for electrical discharge machining (EDM), and the other for ultrasonic milling. The two sets are installed back-to-back to facilitate different servo controls. The Y-axis is located below the gantry and is used for workpiece movement and servo linkage control. For five-axis linkage machining requirements, a dual-axis rotary table can be arranged on the Y-axis to achieve linkage machining.

[0060] The sensing module includes a distributed infrared thermometer (temperature range 100℃-1500℃), a laser vibrometer (accuracy ±0.1μm), and a high-speed camera for molten pool topography (frame rate 2000fps). Each sensor moves synchronously with the robotic arm via a rigid support.

[0061] The electrical structure includes: the main control unit adopts the KUKA KRC4 (extd) control system, with hard disk, optical drive, floppy drive, printer interface, I / O signals, multiple bus interfaces, and remote diagnostics; the KCP has teaching, programming, and safety protection functions; the control system has absolute position memory and soft PLC (optional) functions.

[0062] The robotic additive and subtractive manufacturing method for component (workpiece) processing in this embodiment is integrated into the main control unit. The method specifically includes:

[0063] Step 101: Collect processing status data of the component during processing in real time; calculate the additive / subtractive weight based on the processing status data; and control the additive module to perform additive operation or the subtractive module to perform subtractive operation based on the additive / subtractive weight.

[0064] Specifically, calculating the additive / subtractive manufacturing weights includes:

[0065]

[0066] Where W is the additive / subtractive weight, α is the volume weight, and R 余量 R represents the remaining unprocessed volume of the target processing area of ​​the component. 目标 Let T be the volume of the target processing area of ​​the component, β be the weight of heat accumulation, and T be the volume of the target processing area of ​​the component. 热累积 T represents the heat accumulation in the target processing area of ​​the component. 阈值 For the heat accumulation threshold, the sum of α and β is 1. If we are more concerned with R... 余量 If so, α can be increased; if more attention is paid to T... 热累积 If so, then increase β;

[0067] If the additive / subtractive weight W is greater than the additive / subtractive weight threshold, then an additive operation is performed; otherwise, a subtractive operation is performed.

[0068] Step 102: Set up the processing strategy control model, and determine whether a new processing strategy needs to be executed based on the processing status data. If so, control the robot to process the component according to the new processing strategy.

[0069] Specifically, the processing strategy control model includes: fusing multi-source data in the processing state data using a Kalman filter, inputting the fused multi-source data into an LSTM-RNN neural network to predict residual stress deviation during processing, and executing a new processing strategy when the residual stress deviation exceeds a preset deviation threshold.

[0070] Preferably, the Kalman filter integrates three types of sensor data (processing status data) in a recursive manner: ① an infrared thermometer provides the heat flux and time-varying thermal gradient distribution at the molten pool boundary; ② a vision module provides the edge changes and offset trajectory of the molten pool morphology; ③ a laser vibrometer provides the high-frequency vibration response and surface micro-deformation. After the three sources of data are fused by the collaborative filter, they are input into the LSTM-RNN neural network to predict the residual stress deviation during processing, with a prediction residual >0.95.

[0071] Specifically, the processing strategy control model includes:

[0072] Calculate the thermal-stress response factor:

[0073]

[0074] Among them, Ψ i (t) represents the thermal-stress response factor of the i-th machining trajectory point in the target machining area of ​​the component at time t. Let T′ be the residual stress at the i-th machining trajectory point in the target machining area of ​​the component at time t. i (t) represents the temperature of the i-th processing trajectory point in the target processing area of ​​the component at time t;

[0075] When the thermal-stress response factor Ψ i (t) When the preset response threshold is exceeded, a new processing strategy is executed.

[0076] Specifically, the new processing strategy includes: adjusting the laser power, initiating ultrasonic-assisted processing, or pausing wire feeding for a certain period of time to achieve thermal interruption.

[0077] Step 103: Construct a thermal input path map and a stress field vector map during processing, merge the two maps to generate a processing risk map, and adjust the processing path according to the processing risk map.

[0078] Specifically, constructing the heat input path diagram during processing includes:

[0079] Nodes are processing trajectory points, edges are heat conduction channels between the i-th and j-th processing trajectory points, and the edge weight w′ between the i-th and j-th processing trajectory points is... ij for:

[0080]

[0081] Among them, T′ j Let T′ be the temperature of the j-th machining trajectory point in the target machining area of ​​the component. i Let d be the temperature of the i-th machining trajectory point in the target machining area of ​​the component. ij Let be the distance between the i-th processing trajectory point and the j-th processing trajectory point.

[0082] Specifically, the stress field vector diagram during construction includes:

[0083] Nodes are machining trajectory points, and edges are stress transmission channels between the i-th and j-th machining trajectory points. Each node is associated with a stress vector.

[0084]

[0085] in, Let i be the stress vector of the i-th machining trajectory point. The maximum principal stress at the i-th machining trajectory point, It is the unit vector of the direction of the maximum principal stress at the i-th machining trajectory point.

[0086] The edge weight w′ between the i-th processing trajectory point and the j-th processing trajectory point ij for:

[0087]

[0088] in, Let be the stress vector of the j-th machining trajectory point.

[0089] Specifically, merging the two graphs to generate a processing risk map includes:

[0090] Nodes are processing trajectory points, and edges represent the adjacency relationships between nodes. The target processing area of ​​the component is divided into a regular grid. If the i-th processing trajectory point and the j-th processing trajectory point are adjacent grid points, then the i-th processing trajectory point and the j-th processing trajectory point are adjacent and are connected.

[0091] Define the fusion function for the nodes of the heat input path map and the nodes of the stress field vector map, and calculate the fusion value:

[0092]

[0093] Where, φ i Let ω1 be the fused value of the i-th processing trajectory point, and let ω1 be the weight of the temperature gradient. ω1 represents the temperature gradient at the i-th processing trajectory point, and ω2 represents the weight of the stress vector.

[0094] Based on the fusion value and stress vector of each node, calculate the edge weight w″′ between the i-th processing trajectory point and the j-th processing trajectory point. ij :

[0095]

[0096] Where λ is the weight of the difference in fusion values, Φ j Let μ be the fusion value of the j-th processing trajectory point, and μ be the weight of the difference in stress vectors.

[0097] Specifically, the robot adjusts the processing path based on the processing risk map, including:

[0098] The shortest path in the risk map is found using A* search or Dijkstra's algorithm. This path is then used as the path with the lowest risk. The robot is then controlled to complete the processing of the target processing area of ​​the component by following the processing trajectory points corresponding to the path with the lowest risk.

[0099] Example 2

[0100] like Figure 2 As shown, this embodiment proposes a robotic additive and subtractive manufacturing system for component processing, including:

[0101] The additive / subtractive manufacturing control module is used to collect processing status data during component processing in real time, calculate the additive / subtractive manufacturing weight based on the processing status data, and perform additive or subtractive manufacturing operations based on the additive / subtractive manufacturing weight.

[0102] Specifically, calculating the additive / subtractive manufacturing weights includes:

[0103]

[0104] Where W is the additive / subtractive weight, α is the volume weight, and R 余量 R represents the remaining unprocessed volume of the target processing area of ​​the component. 目标 Let T be the volume of the target processing area of ​​the component, β be the weight of heat accumulation, and T be the volume of the target processing area of ​​the component. 热累积 T represents the heat accumulation in the target processing area of ​​the component. 阈值 This represents the threshold for heat accumulation.

[0105] If the additive / subtractive weight W is greater than the additive / subtractive weight threshold, then an additive operation is performed; otherwise, a subtractive operation is performed.

[0106] The processing strategy control module is used to set the processing strategy control model and determine whether a new processing strategy needs to be executed based on the processing status data. If so, it controls the robot to process the component according to the new processing strategy.

[0107] Specifically, the processing strategy control model includes: fusing multi-source data in the processing state data using a Kalman filter, inputting the fused multi-source data into an LSTM-RNN neural network to predict residual stress deviation during processing, and executing a new processing strategy when the residual stress deviation exceeds a preset deviation threshold.

[0108] Preferably, the Kalman filter integrates three types of sensor data in a recursive manner: ① an infrared thermometer provides the heat flux and time-varying thermal gradient distribution at the molten pool boundary; ② a vision module provides the edge changes and offset trajectory of the molten pool morphology; ③ a laser vibrometer provides the high-frequency vibration response and surface micro-deformation. The three data sources are fused by a collaborative filter and then input into an LSTM-RNN neural network to predict residual stress deviations during processing, with a prediction residual >0.95.

[0109] Specifically, the processing strategy control model includes:

[0110] Calculate the thermal-stress response factor:

[0111]

[0112] Among them, Ψ i (t) represents the thermal-stress response factor of the i-th machining trajectory point in the target machining area of ​​the component at time t. Let T′ be the residual stress at the i-th machining trajectory point in the target machining area of ​​the component at time t. i (t) represents the temperature of the i-th processing trajectory point in the target processing area of ​​the component at time t;

[0113] When the thermal-stress response factor Ψ i (t) When the preset response threshold is exceeded, a new processing strategy is executed.

[0114] Specifically, the new processing strategy includes: adjusting the laser power, initiating ultrasonic-assisted processing, or pausing wire feeding for a certain period of time to achieve thermal interruption.

[0115] The processing path adjustment module is used to construct a thermal input path map and a stress field vector map during processing, merge the two maps to generate a processing risk map, and the robot adjusts the processing path according to the processing risk map.

[0116] Specifically, constructing the heat input path diagram during processing includes:

[0117] Nodes are processing trajectory points, edges are heat conduction channels between the i-th and j-th processing trajectory points, and the edge weight w′ between the i-th and j-th processing trajectory points is... ij for:

[0118]

[0119] Among them, T′ j Let T′ be the temperature of the j-th machining trajectory point in the target machining area of ​​the component. i Let d be the temperature of the i-th machining trajectory point in the target machining area of ​​the component. ij Let be the distance between the i-th processing trajectory point and the j-th processing trajectory point.

[0120] Specifically, the stress field vector diagram during construction includes:

[0121] Nodes are machining trajectory points, and edges are stress transmission channels between the i-th and j-th machining trajectory points. Each node is associated with a stress vector.

[0122]

[0123] in, Let i be the stress vector of the i-th machining trajectory point. The maximum principal stress at the i-th machining trajectory point, It is the unit vector of the direction of the maximum principal stress at the i-th machining trajectory point.

[0124] The edge weight w′ between the i-th processing trajectory point and the j-th processing trajectory point ij for:

[0125]

[0126] in, Let be the stress vector of the j-th machining trajectory point.

[0127] Specifically, merging the two graphs to generate a processing risk map includes:

[0128] Nodes are processing trajectory points, and edges represent the adjacency relationships between nodes. The target processing area of ​​the component is divided into a regular grid. If the i-th processing trajectory point and the j-th processing trajectory point are adjacent grid points, then the i-th processing trajectory point and the j-th processing trajectory point are adjacent and are connected.

[0129] Define the fusion function for the nodes of the heat input path map and the nodes of the stress field vector map, and calculate the fusion value:

[0130]

[0131] Where, Φ i Let ω1 be the fused value of the i-th processing trajectory point, and let ω1 be the weight of the temperature gradient. ω1 represents the temperature gradient at the i-th processing trajectory point, and ω2 represents the weight of the stress vector.

[0132] Based on the fusion value and stress vector of each node, calculate the edge weight w″′ between the i-th processing trajectory point and the j-th processing trajectory point. ij :

[0133]

[0134] Where λ is the weight of the difference in fusion values, and φ j Let μ be the fusion value of the j-th processing trajectory point, and μ be the weight of the difference in stress vectors.

[0135] Specifically, the robot adjusts the processing path based on the processing risk map, including:

[0136] The shortest path in the risk map is found using A* search or Dijkstra's algorithm. This path is then used as the path with the lowest risk. The robot is then controlled to complete the processing of the target processing area of ​​the component by following the processing trajectory points corresponding to the path with the lowest risk.

[0137] Example 3

[0138] This invention also proposes a storage medium storing multiple instructions for implementing the aforementioned robotic additive and subtractive manufacturing method for component processing.

[0139] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0140] Optionally, in this embodiment, the storage medium is configured to store program code for performing the method steps of Embodiment 1.

[0141] Example 4

[0142] This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the aforementioned robotic additive and subtractive manufacturing method for component processing.

[0143] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.

[0144] The storage medium can be used to store software programs and modules, such as the robotic additive and subtractive manufacturing method for component processing in this embodiment of the invention. The processor executes the software programs and modules stored in the storage medium to perform various functional applications and data processing, thus realizing the aforementioned robotic additive and subtractive manufacturing method for component processing. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely located relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0145] The processor can execute the method steps of Embodiment 1 by calling the information and application stored in the storage medium through the transmission system.

[0146] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0147] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0148] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0149] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0150] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0151] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0152] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A robot additive-subtractive collaborative manufacturing method for component machining, characterized by, include: Real-time acquisition of processing status data during component processing; calculation of additive / subtractive material weights based on the processing status data; and performance of additive or subtractive material operations based on the additive / subtractive material weights. The calculation of additive / subtractive manufacturing weights includes: in, For additive / subtractive manufacturing weights, For volume weights, This refers to the remaining unprocessed volume within the target processing area of ​​the component. The volume of the target processing area of ​​the component. As a weight for heat accumulation, The amount of heat accumulation in the target processing area of ​​the component. This represents the threshold for heat accumulation. If the additive / subtractive weight is greater than the additive / subtractive weight threshold, then an additive operation is performed, otherwise a subtractive operation is performed; Set up a processing strategy control model, and determine whether a new processing strategy needs to be executed based on the processing status data. If so, control the robot to process the component according to the new processing strategy. A thermal input path map and a stress field vector map are constructed during processing. The two maps are then merged to generate a processing risk map. The robot adjusts the processing path based on the processing risk map.

2. A robotic additive-subtractive manufacturing method for component machining as claimed in claim 1, wherein, The processing strategy control model includes: fusing multi-source data in the processing state data through a Kalman filter, inputting the fused multi-source data into an LSTM-RNN neural network to predict residual stress deviation during processing, and executing a new processing strategy when the residual stress deviation exceeds a preset deviation threshold.

3. The robotic additive-subtractive manufacturing method for component machining as claimed in claim 1, wherein, Processing strategy control models include: Calculate the thermal-stress response factor: in, For time The first target processing area of ​​the time component Thermal-stress response factor of each machining trajectory point For time The first target processing area of ​​the time component Residual stress at each machining trajectory point For time The first target processing area of ​​the time component Temperature at each processing trajectory point; When the thermal-stress response factor A new processing strategy is executed when the thermal-stress response factor exceeds a predetermined response threshold.

4. The robotic additive-subtractive manufacturing method for component machining according to claim 2 or 3, wherein, The new processing strategies include: adjusting laser power, initiating ultrasonic-assisted processing, or pausing wire feeding for a certain period of time to achieve thermal interruption.

5. The robotic additive-subtractive manufacturing method for component machining as claimed in claim 1, wherein, The heat input path diagram during processing includes: The node is the processing trajectory point, and the edge is the first... The processing trajectory point and the first The heat conduction channel between the processing trajectory points, the first The processing trajectory point and the first Edge weights between processing trajectory points for: in, For the target processing area of ​​the component Temperature at each processing trajectory point For the target processing area of ​​the component Temperature at each processing trajectory point For the first The processing trajectory point and the first The distance between each processing trajectory point.

6. A robotic additive-subtractive manufacturing method for component machining as claimed in claim 5, wherein, The stress field vector diagram during construction includes: The node is the processing trajectory point, and the edge is the first... The processing trajectory point and the first Stress transmission channels between processing trajectory points, with a stress vector associated with each node: in, For the first Stress vector at each machining trajectory point For the first The maximum principal stress at each machining trajectory point For the first The unit vector of the direction of the maximum principal stress at each machining trajectory point; No. The processing trajectory point and the first Edge weights between processing trajectory points for: wherein, is the stress vector for the th machining trajectory point.

7. A robotic additive-subtractive manufacturing method for component machining as claimed in claim 6, wherein, The two graphs are merged to generate a processing risk map, which includes: Nodes represent processing trajectory points, and edges represent the adjacency relationships between nodes. The target processing area of ​​the component is divided into a regular grid. If the... The processing trajectory point and the first If the nth processing trajectory point is an adjacent grid point, then the nth... The processing trajectory point and the first Each processing trajectory point is adjacent; connect them. Define the fusion function for the nodes of the heat input path map and the nodes of the stress field vector map, and calculate the fusion value: in, For the first The fusion value of each processing trajectory point The weights for the temperature gradient, For the first Temperature gradient at each processing trajectory point The weights of the stress vector; Based on the fusion value and stress vector of each node, calculate the first... The processing trajectory point and the first Edge weights between processing trajectory points : in, The weights for the difference in fusion values. For the first The fusion value of each processing trajectory point The weight is the difference in stress vectors.

8. The robotic additive-subtractive manufacturing method for component machining as claimed in claim 1, wherein, The robot adjusts the processing path based on the processing risk map, including: The shortest path in the risk map is found using A* search or Dijkstra's algorithm. This path is then used as the path with the lowest risk. The robot is then controlled to complete the processing of the target processing area of ​​the component by following the processing trajectory points corresponding to the path with the lowest risk.

9. A robot additive-subtractive collaborative manufacturing system for component machining, characterized by, include: The additive / subtractive manufacturing control module is used to collect processing status data during component processing in real time, calculate the additive / subtractive manufacturing weight based on the processing status data, and perform additive or subtractive manufacturing operations based on the additive / subtractive manufacturing weight. The calculation of additive / subtractive manufacturing weights includes: in, For additive / subtractive manufacturing weights, For volume weights, This refers to the remaining unprocessed volume within the target processing area of ​​the component. The volume of the target processing area of ​​the component. As a weight for heat accumulation, The amount of heat accumulation in the target processing area of ​​the component. This represents the threshold for heat accumulation. If the additive / subtractive weight is greater than the additive / subtractive weight threshold, then an additive operation is performed, otherwise a subtractive operation is performed; The processing strategy control module is used to set the processing strategy control model and determine whether a new processing strategy needs to be executed based on the processing status data. If so, it controls the robot to process the component according to the new processing strategy. The processing path adjustment module is used to construct a thermal input path map and a stress field vector map during processing, merge the two maps to generate a processing risk map, and the robot adjusts the processing path according to the processing risk map.

Images