A method for bending forming of molybdenum-rhenium alloy pipe material with dynamically regulated parameters and related device
By combining multi-segment circular arc fitting and simulation models with springback prediction models, a dynamic control method was developed to solve the accuracy and consistency problems of molybdenum-rhenium alloy tubes in complex shape forming, achieving high-precision and flexible bending forming, which is suitable for aerospace, nuclear energy and high-end medical device fields.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
- Filing Date
- 2026-04-30
- Publication Date
- 2026-06-09
AI Technical Summary
Molybdenum-rhenium alloy pipes have poor plasticity, high deformation resistance, and significant springback effect at room temperature. Traditional cold bending processes are prone to cracking and cannot guarantee precision. Existing hot bending technology has high mold costs and poor flexibility, making it difficult to achieve high-precision and flexible complex shape forming. Furthermore, heating and bending control are independent, making it impossible to compensate for forming deviations in real time.
The pipe material is decomposed by using a multi-segment circular arc fitting function, the mapping relationship between geometric features and bending process parameters is established, a simulation model is constructed for parameter correction, dynamic adjustment is carried out by combining springback prediction model and observation model, and springback compensation mold is used for shaping correction to achieve precise control of the bending process.
It significantly improves the accuracy and stability of bending and forming of molybdenum-rhenium alloy tubes, reduces the scrap rate, enhances the versatility and practicality of the process, adapts to target tubes with different geometric characteristics, and achieves efficient and precise bending and forming.
Smart Images
Figure CN122164785A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of alloy processing, specifically a method and related apparatus for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters. Background Technology
[0002] Molybdenum-rhenium alloys play an irreplaceable role in aerospace, nuclear energy, and high-end medical devices due to their excellent high-temperature strength, corrosion resistance, and stable physicochemical properties. However, molybdenum-rhenium alloy tubes exhibit poor plasticity at room temperature, high deformation resistance, and a significant springback effect, making them prone to cracking and inconsistent with precision using traditional cold bending processes. This poses a significant challenge to the precision forming of complex-shaped tubes. Existing hot bending technologies suffer from drawbacks such as high mold costs and poor flexibility, and lack effective real-time compensation methods for post-forming springback, resulting in low precision and poor consistency of the manufactured components, severely restricting the application of molybdenum-rhenium alloy tubes in complex flow channels and piping systems. Therefore, there is an urgent need to develop a process method that can achieve high-precision, flexible, and complex spatial shape forming. Furthermore, while some heat-assisted bending methods exist in existing technologies, heating and bending control are often independent, making it difficult to dynamically and precisely control the forming process in a closed loop, and unable to compensate for forming deviations caused by fluctuations in material properties and changes in friction conditions in real time. In particular, for spatial free bending and forming, how to predict and control springback to achieve precise forming of the target axis is a technical problem that urgently needs to be solved. Summary of the Invention
[0003] This application addresses the technical problem that existing forming processes cannot compensate in real time for forming deviations caused by factors such as fluctuations in material properties and changes in friction conditions. It provides a method and related apparatus for dynamically controlling parameters in bending and forming molybdenum-rhenium alloy tubes. The forming process provided in this application integrates heating, dynamic bending, and springback compensation to achieve precise control of the bending process.
[0004] To achieve the above objectives, this application adopts the following technical solution: The first aspect of this application provides a method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters, comprising the following steps: Obtain the axial spatial coordinates of the target pipe, decompose the target pipe into multiple arc segments based on the multi-segment arc fitting function, and establish a preliminary mapping relationship between geometric features and bending process parameters based on the geometric features of each arc segment. A bending forming simulation model is constructed, which includes the target pipe, feeding mechanism, guide roller and springback compensation die. Simulation data including forming trajectory, curvature and springback data are obtained through the bending forming simulation model. The preliminary mapping relationship is corrected based on the simulation data to obtain the processing parameters. A springback prediction model is constructed based on simulation data; a kinematic model and an observation model of the target pipe are constructed based on the corrected preliminary mapping relationship. The heated target pipe is bent and shaped using the aforementioned processing parameters; during the processing, the actual axis coordinates of the pipe are acquired in real time and compared with the predicted trajectory output by the kinematic model. If there is a deviation, the processing angle or feed rate is dynamically adjusted through the observation model and the springback prediction model. The bent and shaped pipe is fed into a springback compensation mold for shaping. The springback compensation mold corrects the target pipe according to the springback pre-compensation amount output by the springback prediction model.
[0005] Furthermore, the multi-segment circular arc fitting function is as follows:
[0006] in, Let i be the spatial coordinates of the axis of the i-th sampling point of the target pipe. Let R be the spatial coordinates of the center of the sphere of the fitted arc of segment j. j Let be the radius of the fitted arc of the j-th segment.
[0007] Furthermore, the preliminary mapping relationship between the geometric features and bending process parameters includes: Mapping relationship of guide roller deflection angle: i j =k 1 ·arctan(1 / R j )+k 2 ·α j Where, θ j R is the deflection angle of the guide roller. j Let α be the fitted radius of the j-th arc segment. j Let be the bending angle of the j-th segment, and k1 and k2 be the experimental fitting coefficients; Mapping relationship of guide roller tilt angle: j =k 3 ·β j in, j is the tilt angle of the guide roller, β j Let be the spatial twist angle of the j-th segment, and k3 be the fitting coefficient; Feed rate mapping relationship: v j =k 4 / R j +k 5·T j Among them, v j For feed rate, T j K is the heating temperature, and k4 and k5 are the fitting coefficients.
[0008] Furthermore, the rebound prediction model is as follows: Δα pred,j =σ(W out ·[R j ,T j ,v j ,E,α j ] T +b out ) Where, Δα pred,j Let W be the predicted rebound angle for the j-th segment, σ() be the Sigmoid activation function, and W be the predicted rebound angle for the j-th segment. out R is the weight matrix of the output layer of the neural network. j T is the bending radius. j v is the heating temperature. j Let E be the feed rate, E be the material's elastic modulus, and α be the feed rate. j For the bending angle, b out This is the bias term for the output layer of the neural network.
[0009] Furthermore, the dynamic adjustment of the processing angle during the bending forming process satisfies: i j ′=θ j +k 6 ·(α target,j α meas,j )+k 7 ·Da pred,j Where, θ j θ' represents the corrected deflection angle of the guide roller in the j-th segment. j Let α be the initial deflection angle of the j-th guide roller. target,j Let α be the bending angle of the j-th target segment. meas,j The actual measured bending angle of segment j is Δα. pred,j To predict the rebound angle, k6 and k7 are control coefficients.
[0010] Furthermore, the springback compensation mold is corrected using the pre-compensation amount obtained from the springback prediction model, and the correction formula is as follows: R die,j =R target,j (1+β Δα pred,j / 90 ) Among them, R die,j R is the actual radius of curvature of the j-th mold cavity. target,j Let β be the target radius of curvature of the j-th pipe segment, β be the springback compensation coefficient, and Δα be the radius of curvature. pred,j Predict the rebound angle for segment j.
[0011] Furthermore, the heating temperature of the target pipe is 300~600℃.
[0012] A second aspect of this application provides a molybdenum-rhenium alloy tube bending forming system with dynamically adjustable parameters, comprising: The geometry fitting module is used to obtain the axial spatial coordinates of the target pipe. Based on the multi-segment arc fitting function, the target pipe is decomposed into multiple arc segments. According to the geometric features of each arc segment, a preliminary mapping relationship between the geometric features and the bending process parameters is established. The simulation correction module is used to construct a bending forming simulation model that includes the target pipe, feeding mechanism, guide roller and springback compensation mold. The simulation data including forming trajectory, curvature and springback data are obtained through the bending forming simulation model. The initial mapping relationship is corrected based on the simulation data to obtain the processing parameters. The model building module is used to build a springback prediction model based on simulation data; and to build a kinematic model and observation model of the target pipe based on the corrected preliminary mapping relationship. The forming module is used to bend and form the heated target pipe using the processing parameters. During the processing, the actual axis coordinates of the pipe are acquired in real time and compared with the predicted trajectory output by the kinematic model. If there is a deviation, the processing angle or feed speed is dynamically adjusted through the observation model and the springback prediction model. The springback shaping module is used to feed the bent and shaped pipe into the springback compensation mold for shaping. The springback compensation mold corrects the target pipe according to the springback pre-compensation amount output by the springback prediction model.
[0013] A third aspect of this application provides a computer device, including: a processor and a computer-readable storage medium; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program that, when executed by the processor, implements the method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters as described above.
[0014] A fourth aspect of this application provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed as described above for a method of bending and forming molybdenum-rhenium alloy tubing with dynamically adjustable parameters.
[0015] Compared with the prior art, this application has the following beneficial effects: The method provided in this application decomposes the target pipe through multi-segment circular arc fitting and establishes a preliminary mapping relationship between geometric features and bending process parameters, avoiding the shortcomings of traditional process parameter setting being blind and poorly adapted to the pipe's geometric features. It corrects the mapping relationship using a simulation model containing fully formed components and constructs a springback prediction model, overcoming the shortcomings of existing simulations being disconnected from actual forming and unable to predict springback and forming deviations in advance. By constructing a kinematic and observation model, the actual axial coordinates of the pipe are compared with the predicted trajectory in real time during processing. The processing angle or feed rate is dynamically adjusted by combining the observation model and the springback prediction model, achieving real-time compensation for forming deviations caused by sudden factors such as material performance fluctuations and changes in friction conditions. Furthermore, a springback compensation mold is used for shaping correction, further offsetting springback errors. This significantly improves the accuracy and stability of molybdenum-rhenium alloy pipe bending forming, reduces the scrap rate, and adapts to target pipes with different geometric features, enhancing the versatility and practicality of the process. This provides a reliable technical solution for the efficient and precise bending forming of molybdenum-rhenium alloy pipes. Attached Figure Description
[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 This is a schematic diagram of the alloy tube bending and forming process with dynamically adjustable parameters in the embodiments of this application; Figure 2 This is a cross-sectional structural diagram of the guide roller device in the embodiments of this application; Figure 3 This is a schematic diagram of the alloy tube bending and forming system with dynamically adjustable parameters in an embodiment of this application; Figure 4 This is an internal structural diagram of the computer device in the embodiments of this application; The components include: 1. Feeding mechanism; 2. Guide roller; 3. Heating zone; 4. Springback compensation mold. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0019] Molybdenum-rhenium alloys play an irreplaceable role in aerospace, nuclear energy, and high-end medical devices due to their excellent high-temperature strength, corrosion resistance, and stable physicochemical properties. However, molybdenum-rhenium alloy pipes exhibit poor plasticity at room temperature, high deformation resistance, and a significant springback effect. Traditional cold bending processes are prone to cracking and cannot guarantee precision, posing a significant challenge to the precision forming of complex-shaped pipes.
[0020] Existing hot bending technologies suffer from drawbacks such as high mold costs and poor flexibility. Furthermore, they lack effective real-time compensation methods for springback after forming, resulting in low precision and poor consistency of the manufactured components, severely restricting the application of molybdenum-rhenium alloy tubing in complex flow channels and piping systems. In addition, in existing heat-assisted bending methods, heating and bending control are independent, making it difficult to dynamically and precisely regulate the forming process in a closed loop, and unable to compensate for forming deviations caused by fluctuations in material properties and changes in friction conditions in real time. For spatial free bending forming, springback prediction and control, as well as precise forming along the target axis, remain pressing technical challenges that need to be addressed.
[0021] Based on this, such as Figure 1 As shown, this application provides a method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters, including the following steps: S1. Obtain the axial spatial coordinates of the target pipe. Based on the multi-segment arc fitting function, decompose the target pipe into multiple arc segments. Establish a preliminary mapping relationship between geometric features and bending process parameters based on the geometric features of each arc segment.
[0022] Specifically, the geometric characteristics of the target pipe include core geometric parameters such as the radius of each arc, bending angle, and spatial torsion angle. Bending process parameters include guide roller deflection angle, guide roller tilt angle, and feed speed.
[0023] This step employs a multi-segment circular arc fitting model to quantitatively decompose the complex spatial trajectory. The model's function is to break down the axis of the complex spatial pipe into multiple standard circular arcs, achieving a preliminary mapping of geometric features to process parameters. The multi-segment circular arc fitting function is as follows:
[0024] in, Let i be the spatial coordinates of the axis of the i-th sampling point of the target pipe. Let R be the spatial coordinates of the center of the sphere of the fitted arc of segment j. j Let the radius of the fitted arc be the j-th segment. Let be all the sampling points contained in the j-th arc segment.
[0025] Obtain the axial spatial coordinates of the target pipe, substitute the set of coordinate points into a multi-segment circular arc fitting function, and optimize the solution using the least squares method. For each segment of the circular arc, solve for its geometric parameters, including the bending radius R. j Bending angle α j and spatial twist angle β j .
[0026] Furthermore, a preliminary mapping relationship between geometric features and bending process parameters is established based on the geometric features of each arc segment. This preliminary mapping relationship includes: Mapping relationship of guide roller deflection angle: i j =k 1 ·arctan(1 / R j )+k 2 ·α j Where, θ j R is the deflection angle of the guide roller. j Let α be the fitted radius of the j-th arc segment. j Let be the bending angle of the j-th segment, and k1 and k2 be the experimental fitting coefficients; Mapping relationship of guide roller tilt angle: j =k 3 ·β j in, j is the tilt angle of the guide roller, β j Let be the spatial twist angle of the j-th segment, and k3 be the fitting coefficient; Feed rate mapping relationship: v j =k 4 / R j +k 5 ·T j Among them, v j For feed rate, T jK is the heating temperature, and k4 and k5 are the fitting coefficients.
[0027] This step transforms complex spatial trajectories into quantifiable segmented geometric parameters through multi-segment circular arc fitting, and then establishes a direct mapping between geometric parameters and process parameters, providing initial process basis for subsequent bending processing, and realizing the quantitative decomposition and process initialization of complex spatial trajectories.
[0028] S2, construct a bending forming simulation model including the target pipe, feeding mechanism, guide roller and springback compensation mold, obtain simulation data including forming trajectory, curvature and springback data through the bending forming simulation model, and correct the preliminary mapping relationship based on the simulation data to obtain the processing parameters.
[0029] This step uses a thermo-mechanical coupling simulation model to simulate the actual forming process. The model is used to simulate the deformation behavior of molybdenum rhenium alloy tubes during the entire process of heating, bending, and springback, and to correct the initial mapping relationship.
[0030] like Figure 2 As shown, the forming device includes a feeding mechanism 1, a guide roller 2, and a springback suppression mold 4. A heating zone 3 is located at the front end of the guide roller. The guide roller in the heating zone 3 includes a roller shell, inside which a resistance heating element, a temperature sensor, and a heat insulation layer are installed. The guide roller device is coaxially mounted on the moving end of a multi-axis motion platform. The multi-axis motion platform has at least two degrees of freedom: deflection and tilt, which can drive the guide roller to complete deflection and tilting. The front end of the guide roller is the heating zone, which houses the resistance heating element, temperature sensor, and heat insulation layer. The heating zone and the bending forming zone are arranged coaxially to ensure that the pipe is uniformly heated to 300~600℃ before entering the bending zone. The heat insulation layer prevents heat from being conducted to the multi-axis motion platform. The feeding mechanism is used to push the pipe through the guide roller at a uniform speed, achieving continuous feeding. The springback compensation mold is used to shape the bent pipe, and its cavity curvature radius is corrected according to the springback pre-compensation amount output by the springback prediction model.
[0031] Specifically, using ABAQUS finite element software, a bending forming simulation model was established, including the target pipe, feeding mechanism, guide rollers, and springback compensation die. This bending forming simulation model is a thermo-mechanical coupled finite element model. Different bending radii R were set in the bending forming simulation model. j Bending angle α j Heating temperature T j and feed rate v j The combination of these parameters yields simulation data such as axis coordinates, springback angle, and curvature distribution. The deviation between the simulation results and the target trajectory is calculated, and the initial mapping relationship is corrected to obtain the machining process parameters. The deviation calculation formula is: =
[0032] in, e j The deviation between the simulation result of segment j and the target trajectory is... , , Let J be the coordinates of the j-th axis segment after simulation. , , Let be the coordinates of the target axis of segment j.
[0033] The least squares method is used to iteratively adjust the fitting coefficients k1, k2, k3, k4, and k5 in the initial mapping relationship to reduce the total deviation. S e j Minimize. Substitute the optimized coefficients into the initial mapping relationship to obtain high-precision machining process parameters. Collect all simulation data to construct a finite element parameter database that can be queried.
[0034] This step uses thermo-mechanical coupling simulation to simulate the actual heating and bending process, and uses batch simulation data to correct the initial process mapping relationship, effectively improving the accuracy of the processing parameters and providing precise parameter support for actual bending processing.
[0035] S3, construct a springback prediction model based on simulation data; construct a kinematic model and observation model of the target pipe based on the corrected preliminary mapping relationship; Specifically, the springback prediction model is built upon a deep neural network model and trained using batch simulation data from a bending forming simulation model. The springback prediction model is as follows: Δα pred,j =σ(W out ·[R j ,T j ,v j ,E,α j ] T +b out ) Where, Δα pred,j Let W be the predicted rebound angle for the j-th segment, σ() be the Sigmoid activation function, and W be the predicted rebound angle for the j-th segment. out Let R be the weight matrix of the output layer of the neural network. j ,T j ,v j ,E,α j ] T To output the feature vector (R) j T is the bending radius.j v is the heating temperature. j Let E be the feed rate, E be the material's elastic modulus, and α be the feed rate. j (for the bending angle), b out This is the bias term for the output layer of the neural network.
[0036] Specifically, based on the corrected preliminary mapping relationship, a kinematic model and an observation model of the target pipe are constructed. Specifically, based on the corrected preliminary mapping relationship, the corrected guide roller angle θ is obtained. j Inclination angle j Feed rate v j Bending radius R j Bending angle α j The kinematic model of the target pipe is trained, and the specific kinematic model is as follows: + ·N +
[0037] =
[0038] =1 / R j =
[0039] Where, N, The curves are respectively at The principal and secondary normal vectors of a point are oriented by the tilt angle of the guide roller. j The decision is made to jointly define the bending plane; for Internal feed rate For time feed time; Instantaneous curvature; for The increase in the central angle generated within.
[0040] Predicted pipe axis coordinates (x) output by the kinematic model pred,j y pred,j , z pred,j Predicting the bending angle α pred,j The predicted rebound angle Δα output by the rebound prediction model pred,j The actual axis coordinates (x) collected by the real-time detection unit meas,j y meas,j , z meas,j ), bending angle α meas,jThe observation model of the target pipe is trained to calculate forming deviations and output process parameter adjustment instructions. The specific adjustment method is as follows: =[ ] = α meas,j -(α pred,j+ Da pred,j ) This step combines the corrected process mapping with rebound prediction to construct a dual model system of trajectory prediction and deviation observation, providing a computational basis and judgment criteria for subsequent real-time closed-loop control.
[0041] S4, the heated target pipe is bent and shaped using the processing parameters; during the processing, the actual axis coordinates of the pipe are acquired in real time and compared with the predicted trajectory output by the kinematic model. If there is a deviation, the processing angle or feed speed is dynamically adjusted through the observation model and the springback prediction model.
[0042] Specifically, when the target tube is a molybdenum-rhenium alloy tube, the heating temperature before bending is 300℃~600℃. A heating zone is located at the front end of the guide roller, containing a built-in resistance heating element, temperature sensor, and insulation layer. The heating zone is coaxially arranged with the bending zone. The guide roller is mounted on a multi-axis motion platform, enabling coordinated control of both deflection and tilt.
[0043] In some embodiments of this application, the dynamic adjustment of the processing angle during the bending forming process satisfies: i j ′=θ j +k 6 · +k 7 ·Da pred,j +K p
[0044] Where, θ j θ' represents the corrected deflection angle of the guide roller in the j-th segment. j Let j be the initial deflection angle of the guide roller segment. This represents the deviation between the spatial position of the pipe tip actually measured by the sensor and the theoretical position predicted by the kinematic model at the j-th processing moment. α represents the deviation between the pipe bending angle actually measured by the sensor at the j-th processing moment and the total bending angle expected by the system.meas,j The actual measured bending angle of segment j is Δα. pred,j To predict the rebound angle, K p Here, k6 and k7 are the control gain matrix and the control coefficients.
[0045] The feeding mechanism propels the tube through the guide rollers at a uniform speed according to the feed rate specified in the processing parameters. The multi-axis motion platform drives the guide rollers to complete deflection and tilting actions according to the processing parameters. Real-time acquisition of actual forming data and comparison with the predicted trajectory result in deviations. When deviations occur, the guide roller deflection angle is corrected in real time according to the aforementioned adjustment formula, achieving dynamic closed-loop control of the bending process. The observation model is responsible for calculating the forming deviation, and the springback prediction model is responsible for providing springback pre-compensation. Together, they provide a basis for the dynamic adjustment of process parameters.
[0046] This step combines online detection with model calculation to compensate for forming errors caused by material fluctuations, friction changes, and temperature fluctuations in real time, ensuring that the bending trajectory continuously matches the design target and significantly improving the bending forming accuracy of molybdenum rhenium alloy pipes.
[0047] S5, the bent and shaped pipe is sent into the springback compensation mold for shaping. The springback compensation mold corrects the target pipe according to the springback pre-compensation amount output by the springback prediction model.
[0048] The bent pipe is fed into a springback compensation mold for shaping; the springback compensation mold is corrected by the pre-compensation amount obtained by the springback prediction model.
[0049] Specifically, the springback compensation mold is corrected using the pre-compensation amount obtained from the springback prediction model. The correction formula is as follows: R die,j =R target,j (1+β Δα pred,j / 90 ) Among them, R die,j R is the actual radius of curvature of the j-th mold cavity. target,j Let be the target radius of curvature of the j-th pipe segment, β be the springback compensation coefficient, typically 0.8~1.2, and Δα be the radius of curvature. pred,j Predict the rebound angle for segment j.
[0050] The bent pipe is immediately fed into a modified springback compensation mold. The mold applies uniform constraint to the formed part to complete the shaping process, suppress the springback deformation of the pipe, and ensure that the final formed size of the pipe meets the design requirements.
[0051] This step uses springback prediction and pre-correction of the mold cavity, combined with online dynamic control, to achieve full-process springback control during the bending and shaping processes, completely solving the problems of large springback and low forming accuracy in molybdenum-rhenium alloy tubes.
[0052] In one embodiment of this application, such as Figure 3 As shown, a molybdenum-rhenium alloy tube bending forming system with dynamically adjustable parameters is provided, comprising: The geometry fitting module is used to obtain the axial spatial coordinates of the target pipe. Based on the multi-segment arc fitting function, the target pipe is decomposed into multiple arc segments. According to the geometric features of each arc segment, a preliminary mapping relationship between the geometric features and the bending process parameters is established. The simulation correction module is used to construct a bending forming simulation model that includes the target pipe, feeding mechanism, guide roller and springback compensation mold. The simulation data including forming trajectory, curvature and springback data are obtained through the bending forming simulation model. The initial mapping relationship is corrected based on the simulation data to obtain the processing parameters. The model building module is used to build a springback prediction model based on simulation data; and to build a kinematic model and observation model of the target pipe based on the corrected preliminary mapping relationship. The forming module is used to bend and form the heated target pipe using the processing parameters. During the processing, the actual axis coordinates of the pipe are acquired in real time and compared with the predicted trajectory output by the kinematic model. If there is a deviation, the processing angle or feed speed is dynamically adjusted through the observation model and the springback prediction model. The springback shaping module is used to feed the bent and shaped pipe into the springback compensation mold for shaping. The springback compensation mold corrects the target pipe according to the springback pre-compensation amount output by the springback prediction model.
[0053] Specific limitations regarding the bending and forming system for molybdenum-rhenium alloy tubes with dynamically adjustable parameters can be found in the limitations of the bending and forming method for molybdenum-rhenium alloy tubes with dynamically adjustable parameters described above. The corresponding technical effects can be obtained equivalently and will not be repeated here. Each module in the aforementioned bending and forming system for molybdenum-rhenium alloy tubes with dynamically adjustable parameters can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.
[0054] Figure 4 An internal structural diagram of a computer device is shown in one embodiment. This computer device may specifically be a terminal or a server. Figure 4As shown, the computer device includes a processor, memory, network interface, display, camera, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When executed by the processor, the computer program implements a method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters. The display screen can be an LCD screen or an e-ink display screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.
[0055] As will be understood by those skilled in the art, computer equipment Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computing devices may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.
[0056] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.
[0057] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.
[0058] In summary, the embodiments of this application provide a method, system, computer equipment, and storage medium for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters.
[0059] The various embodiments in this specification are described in a progressive manner. For directly identical or similar parts of the embodiments, refer to each other. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.
[0060] The embodiments described above are merely preferred embodiments of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various improvements and substitutions without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application. Therefore, the scope of protection of this patent application should be determined by the scope of the claims.
Claims
1. A method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters, characterized in that, Includes the following steps: Obtain the axial spatial coordinates of the target pipe, decompose the target pipe into multiple arc segments based on the multi-segment arc fitting function, and establish a preliminary mapping relationship between geometric features and bending process parameters based on the geometric features of each arc segment. A bending forming simulation model is constructed, which includes the target pipe, feeding mechanism, guide roller and springback compensation die. Simulation data including forming trajectory, curvature and springback data are obtained through the bending forming simulation model. The preliminary mapping relationship is corrected based on the simulation data to obtain the processing parameters. A springback prediction model is constructed based on simulation data; a kinematic model and an observation model of the target pipe are constructed based on the corrected preliminary mapping relationship. The heated target pipe is bent and shaped using the aforementioned processing parameters; during the processing, the actual axis coordinates of the pipe are acquired in real time and compared with the predicted trajectory output by the kinematic model. If there is a deviation, the processing angle or feed rate is dynamically adjusted through the observation model and the springback prediction model. The bent and shaped pipe is fed into a springback compensation mold for shaping. The springback compensation mold corrects the target pipe according to the springback pre-compensation amount output by the springback prediction model.
2. The method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters according to claim 1, characterized in that, The multi-segment circular arc fitting function is as follows: in, Let i be the spatial coordinates of the axis of the i-th sampling point of the target pipe. Let R be the spatial coordinates of the center of the sphere of the fitted arc of segment j. j Let be the radius of the fitted arc of the j-th segment.
3. The method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters according to claim 1, characterized in that, The preliminary mapping relationship between the geometric features and bending process parameters includes: Mapping relationship of guide roller deflection angle: θ j =k 1 arctan(1 / R) j )+k 2 ·α j Where, θ j R is the deflection angle of the guide roller. j Let α be the fitted radius of the j-th arc segment. j Let be the bending angle of the j-th segment, and k1 and k2 be the experimental fitting coefficients; Mapping relationship of guide roller tilt angle: j =k 3 ·β j in, j is the tilt angle of the guide roller, β j Let be the spatial twist angle of the j-th segment, and k3 be the fitting coefficient; Feed rate mapping relationship: v j =k 4 / R j +k 5 ·T j Among them, v j For feed rate, T j K is the heating temperature, and k4 and k5 are the fitting coefficients.
4. The method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters according to claim 1, characterized in that, The rebound prediction model is as follows: Da pred,j =σ(W out ·[R j ,T j ,v j ,E,α j ] T +b out ) Where, Δα pred,j Let W be the predicted rebound angle for the j-th segment, σ() be the Sigmoid activation function, and W be the predicted rebound angle for the j-th segment. out R is the weight matrix of the output layer of the neural network. j T is the bending radius. j v is the heating temperature. j Let E be the feed rate, E be the material's elastic modulus, and α be the feed rate. j For the bending angle, b out This is the bias term for the output layer of the neural network.
5. The method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters according to claim 1, characterized in that, The dynamic adjustment of the processing angle during the bending and forming process satisfies: θ j =θ j +k 6 ·(α target,j α meas,j )+k 7 ·Δα pred,j Where, θ j θ' represents the corrected deflection angle of the guide roller in the j-th segment. j Let α be the initial deflection angle of the j-th guide roller. target,j Let α be the bending angle of the j-th target segment. meas,j The actual measured bending angle of segment j is Δα. pred,j To predict the rebound angle, k6 and k7 are control coefficients.
6. The method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters according to claim 1, characterized in that, The springback compensation mold is corrected using the pre-compensation amount obtained from the springback prediction model, and the correction formula is as follows: R die,j =R target,j (1+b Da pred,j / 90 ) Among them, R die,j R is the actual radius of curvature of the j-th mold cavity. target,j Let β be the target radius of curvature of the j-th pipe segment, β be the springback compensation coefficient, and Δα be the radius of curvature. pred,j Predict the rebound angle for segment j.
7. The method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters according to claim 1, characterized in that, The target pipe is heated to a temperature of 300~600℃.
8. A bending and forming system for molybdenum-rhenium alloy tubes with dynamically adjustable parameters, characterized in that, include: The geometry fitting module is used to obtain the axial spatial coordinates of the target pipe. Based on the multi-segment arc fitting function, the target pipe is decomposed into multiple arc segments. According to the geometric features of each arc segment, a preliminary mapping relationship between the geometric features and the bending process parameters is established. The simulation correction module is used to construct a bending forming simulation model that includes the target pipe, feeding mechanism, guide roller and springback compensation mold. The simulation data including forming trajectory, curvature and springback data are obtained through the bending forming simulation model. The initial mapping relationship is corrected based on the simulation data to obtain the processing parameters. The model building module is used to build a springback prediction model based on simulation data; and to build a kinematic model and observation model of the target pipe based on the corrected preliminary mapping relationship. The forming module is used to bend and form the heated target pipe using the processing parameters. During the processing, the actual axis coordinates of the pipe are acquired in real time and compared with the predicted trajectory output by the kinematic model. If there is a deviation, the processing angle or feed speed is dynamically adjusted through the observation model and the springback prediction model. The springback shaping module is used to feed the bent and shaped pipe into the springback compensation mold for shaping. The springback compensation mold corrects the target pipe according to the springback pre-compensation amount output by the springback prediction model.
9. A computer device, characterized in that, include: Processor and computer-readable storage media; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the method for bending and forming molybdenum-rhenium alloy tubing with dynamically adjustable parameters as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed by the method for bending and forming molybdenum-rhenium alloy tubes with dynamically adjustable parameters as described in any one of claims 1 to 7.