Stress self-adaption multi-point flexible machining tool based on data driving and control method

Abstract

The invention discloses a stress self-adaption multi-point flexible machining tool based on data driving and a control method. The control method comprises the steps that in response to an adsorption machining request instruction, parameters of a to-be-machined curved surface piece are obtained; determining an initial adsorption force value and an initial adsorption point through the configuration feature library based on the geometric features of the to-be-processed curved surface part; generating a first control strategy set based on the initial adsorption force value and the initial adsorption point data; to-be-machined curved surface piece adsorption force data sent by the force sensor is obtained, and the workpiece real-time deformation amount is determined based on the to-be-machined curved surface piece adsorption force data; based on the initial adsorption force value and the initial adsorption point data, a theoretical workpiece deformation amount is obtained through a trained adsorption force control model; and on the basis of the real-time workpiece deformation and the theoretical workpiece deformation, a final adsorption force value is obtained through a PID (Proportion Integration Differentiation) control algorithm. According to the method, self-adaptive control over deformation in the machining process of the curved surface part is achieved, and elastic deformation is effectively prevented and compensated through dynamic coupling cutting force and residual stress.

Description

Technical Field

[0001] This invention discloses a data-driven stress-adaptive multi-point flexible machining tooling and control method, belonging to the field of manufacturing engineering technology. Background Technology

[0002] Curved parts are widely used in aerospace, automotive manufacturing, and other fields due to their excellent aerodynamic properties; however, deformation control during their machining process has always been a technical challenge in the manufacturing industry. During machining, curved parts, due to their low stiffness and susceptibility to deformation, are prone to elastic deformation under cutting forces, leading to a decrease in machining accuracy. To address this issue, multi-point flexible machining fixtures are widely used in the machining of curved parts.

[0003] Currently, there is a certain research foundation in the prediction and control technology of machining deformation of curved parts. CN115422670B proposes a method for predicting machining deformation of curved parts based on spatiotemporal learning of cutting force and clamping force. This method establishes a time-varying correlation model between cutting force and clamping force, and combines it with the geometric parameterized matrix of the part. It achieves machining deformation prediction through a spatiotemporal learning model of convolutional network and recurrent neural network. In terms of flexible clamping technology, CN119442778A introduces an adaptive dynamic optimization method for skin local rigidity based on flexible clamping. This method constructs a skin-flexible tooling finite element model and sets parameters to establish a multi-point flexible clamping stiffness prediction model. It combines neural network and genetic algorithm for multi-objective optimization to obtain the optimal clamping layout that meets the constraints.

[0004] However, existing positioning technologies for machining curved parts still have the following problems: the adsorption force is constantly distributed, and there is no compensation mechanism when the residual stress is released and deformation is caused; the passive positioning system lacks dynamic coupling modeling of cutting force and residual stress; compensation is delayed after deformation occurs, and the loss of accuracy is irreversible. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention proposes a data-driven stress-adaptive multi-point flexible machining control fixture and method. This invention solves the problems in current curved part machining technologies, such as the inability of the constant distribution of the adsorption force of multi-point flexible machining fixtures to cope with deformation caused by residual stress release, the lack of dynamic coupling modeling of cutting force and residual stress, and the lag in deformation compensation. This invention achieves a significant improvement in the machining accuracy of curved parts, a substantial reduction in clamping preparation time, and a significant reduction in the rate of out-of-tolerance rework.

[0006] According to a first aspect of the present invention, a data-driven stress-adaptive multi-point flexible machining control method is provided, comprising: in response to an adsorption machining request command, acquiring parameters of a surface part to be machined; determining an initial adsorption force value and an initial adsorption point based on the geometric features of the surface part to be machined, using a configuration feature library; generating a first control strategy set based on the initial adsorption force value and initial adsorption point data, wherein the first control strategy set controls a guide rail assembly, a support unit, and an adsorption controller to execute an initial target working position; in response to a command from the guide rail assembly, the support unit, and the adsorption controller to complete the initial target working position, acquiring adsorption force data of the surface part to be machined sent by a force sensor, and determining the real-time deformation of the workpiece based on the adsorption force data of the surface part to be machined; obtaining a theoretical workpiece deformation based on the initial adsorption force value and initial adsorption point data, using a trained adsorption force control model; obtaining a final adsorption force value based on the real-time workpiece deformation and the theoretical workpiece deformation, using a PID control algorithm; and generating a second control strategy set based on the final adsorption force value, wherein the final adsorption force value control strategy set controls the guide rail assembly, the support unit, and the adsorption controller to execute the final target working position.

[0007] Furthermore, in response to the adsorption processing request command, the geometric features of the surface to be processed are obtained. Prior to this, the following steps are also taken: obtaining the training parameters of the surface to be processed, establishing a dynamic cutting force finite element model, an adsorption position prediction model, and initial boundary conditions respectively; and obtaining a trained adsorption force control model based on the training parameters of the surface to be processed, the dynamic cutting force finite element model, the adsorption position prediction model, and the initial boundary conditions.

[0008] Furthermore, based on the training parameters of the machined curved part, the dynamic cutting force finite element model, the adsorption position prediction model, and the initial boundary conditions, a trained adsorption force control model is obtained, including: determining the equivalent cutting force for machining the curved part based on the training parameters of the machined curved part and the dynamic cutting force finite element model; determining the optimal adsorption point layout based on the equivalent cutting force for machining the curved part and the adsorption position prediction model; constructing the adsorption force-deformation response matrix based on the initial boundary conditions, the equivalent cutting force for machining the curved part, and the optimal adsorption point layout; and obtaining the trained adsorption force control model based on the adsorption force-deformation response matrix.

[0009] Furthermore, initial boundary conditions are established based on the residual stress distribution of the curved part during forming, including: establishing a multi-physics coupling model of the curved part forming process, simulating the material removal process by removing elements layer by layer, applying cutting thermal loads, and obtaining the residual stress distribution of the curved part after forming; and establishing initial constraint conditions based on the residual stress distribution.

[0010] Furthermore, based on the training parameters for machining curved parts and the finite element model of dynamic cutting force, the equivalent cutting force for machining curved parts is determined, including: based on the training parameters for machining curved parts and the finite element model of dynamic cutting force, the equivalent cutting force for machining curved parts is obtained through Equation 1:

[0011]

[0012] Wherein: F c The main cutting force, C Fc a is the cutting force coefficient. p To measure the amount of cuts made by the back of the blade, x Fc The depth of cut is the index, f is the feed per revolution, and y is the feed rate. Fc Where z is the feed rate exponent, v is the cutting speed, and z is the feed rate exponent. Fc K is the cutting speed exponent. Fc This is the working condition correction factor.

[0013] According to a second aspect of the present invention, a data-driven stress-adaptive multi-point flexible machining fixture is provided for implementing the stress-adaptive multi-point flexible machining control method described in the first aspect. The fixture includes: a fixture frame having a guide rail assembly; a support unit comprising multiple support units arranged at intervals and connected to the guide rail assembly; and a suction cup assembly comprising a suction cup head, a suction cup head support, and a suction cup component. A first end of the suction cup head support is connected to the execution end of the support unit, a first end of the suction cup head is magnetically connected to a second end of the suction cup head support, and the suction cup component is connected to the second end of the suction cup head.

[0014] Furthermore, the suction cup assembly includes: a suction cup body, which is connected to the second end of the suction cup rotating head; a fan-shaped fish bionic suction cup structure, which includes multiple fan-shaped fish bionic suction cup structures, which are spaced apart circumferentially along the suction cup body, and a first vacuum groove is provided between two adjacent fan-shaped fish bionic suction cup structures; the fan-shaped fish bionic suction cup structure includes multiple bionic fish fins, which are spaced apart radially, and a second vacuum groove is provided between any two adjacent bionic fish fins; the bionic fish fins include multiple protrusions, which are spaced apart circumferentially along the suction cup body.

[0015] Furthermore, the suction cup assembly also includes a force sensor, which is connected to the suction cup body. The force sensor is spaced apart from multiple fan-shaped fish-inspired suction cup structures and is used to acquire the adsorption force data of the curved surface to be processed.

[0016] Furthermore, the suction cup assembly is made of polyurethane material, and the suction cup head has an epitaxial unit that cooperates with the suction cup assembly. The epitaxial unit is made of polytetrafluoroethylene material.

[0017] According to a third aspect of the present invention, a terminal is provided, comprising:

[0018] One or more processors;

[0019] Memory for storing the one or more processor-executable instructions;

[0020] Wherein, the one or more processors are configured as follows:

[0021] The method described in the second aspect of the embodiments of the present invention is performed.

[0022] The beneficial effects of this invention are as follows:

[0023] This invention provides a data-driven stress-adaptive multi-point flexible machining fixture and control method, which realizes adaptive control of deformation during the machining of curved parts. By dynamically coupling cutting force and residual stress, it effectively prevents and compensates for elastic deformation, significantly improving machining accuracy and product consistency to meet the stringent standards of high-precision curved parts. It also significantly shortens clamping and process preparation time to improve production efficiency, and significantly reduces product rework rate to optimize resource utilization. Furthermore, it achieves adaptive pose adjustment of the multi-point flexible machining fixture through a biomimetic rotating adsorption device, improving process flexibility and overcoming the limitations of traditional fixed fixtures. It is suitable for complex curved parts and provides an innovative technical path that integrates dynamic modeling and biomimetic equipment, enhancing system robustness and stability.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating a data-driven stress-adaptive multi-point flexible machining control method according to an exemplary embodiment.

[0026] Figure 2 This is a schematic diagram illustrating dynamic cutting force modeling in a data-driven stress-adaptive multi-point flexible machining control method according to an exemplary embodiment.

[0027] Figure 3 This is a schematic diagram illustrating the adsorption point layout generation in a data-driven stress-adaptive multi-point flexible processing control method according to an exemplary embodiment.

[0028] Figure 4 This is a schematic diagram of residual stress in a data-driven stress-adaptive multi-point flexible machining control method according to an exemplary embodiment.

[0029] Figure 5This is a structural diagram illustrating a first embodiment of a data-driven stress-adaptive multi-point flexible machining control fixture according to an exemplary embodiment.

[0030] Figure 6 This is a structural diagram of a first embodiment of a suction cup assembly in a data-driven stress-adaptive multi-point flexible machining control tooling, according to an exemplary embodiment.

[0031] Figure 7 This is a structural diagram of a second embodiment of a suction cup assembly in a data-driven stress-adaptive multi-point flexible machining control fixture, according to an exemplary embodiment. Detailed Implementation

[0032] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] In the description of this invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0034] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0035] like Figure 1 As shown in the exemplary embodiment, a data-driven stress-adaptive multi-point flexible machining control method includes:

[0036] Step S10: In response to the adsorption processing request command, obtain the parameters of the surface part to be processed, wherein...

[0037] Before acquiring the geometric features of the surface to be processed in response to the adsorption processing request command, the process also includes: acquiring the training parameters of the surface to be processed, establishing a dynamic cutting force finite element model, an adsorption position prediction model, and initial boundary conditions, and obtaining a trained adsorption force control model based on the training parameters of the surface to be processed, the dynamic cutting force finite element model, the adsorption position prediction model, and the initial boundary conditions. The specific steps are as follows:

[0038] Step S101: First, establish a dynamic cutting force finite element model, then import it into the finite element analysis software, and set the material properties, boundary conditions, and mesh generation parameters, such as... Figure 2 As shown, the instantaneous cutting force at each cutting position is calculated by simulating the contact process between the tool and the workpiece. Finally, a cutting force distribution cloud map of the entire machining process is generated, providing a basis for the subsequent layout of the adsorption positions.

[0039] The equivalent cutting force distribution is calculated using analytical mechanics. The formula for calculating the cutting force is:

[0040]

[0041] Wherein: F c The main cutting force, C Fc a is the cutting force coefficient. p To measure the amount of cuts made by the back of the blade, x Fc The depth of cut is the index, f is the feed per revolution, and y is the feed rate. Fc Where z is the feed rate exponent, v is the cutting speed, and z is the feed rate exponent. Fc K is the cutting speed exponent. Fc This is the working condition correction factor.

[0042] When building the model, the curved part is discretized into a finite element mesh, and the cutting force effect is calculated for each mesh node.

[0043] In one exemplary embodiment, in this step, the dynamic cutting force finite element model considers cutting parameters, tool geometry, and material properties, and calculates the equivalent cutting force distribution through numerical simulation. Unlike analytical mechanical methods, the numerical simulation method used in this embodiment is more suitable for handling curved surfaces with complex geometries.

[0044] In practice, a tool-workpiece contact model is first established, and the material properties are described using the Johnson-Cook constitutive model. The model parameters are determined based on the material properties of the workpiece.

[0045] Numerical simulation is used to obtain the stress, strain, and temperature field distributions during the cutting process, and then the equivalent cutting force acting on the workpiece can be calculated. Numerical simulation can more accurately reflect the nonlinear effects and thermo-mechanical coupling effects during the cutting process, and is particularly suitable for machining curved parts made of difficult-to-machine materials.

[0046] Step S102 introduces the adsorption site prediction model, the details of which are as follows:

[0047] like Figure 3 As shown, in this step, a cutting force-deformation field finite element database is first established. This database contains deformation response data of curved parts under different cutting forces. In practice, finite element software is used to construct a model of the curved part, the calculated cutting force is applied, and the deformation of the curved part during the machining process is simulated and analyzed.

[0048] To obtain comprehensive deformation field data, an orthogonal experimental scheme was designed to systematically vary the magnitude, location, and direction of the cutting force. For each set of working conditions, key indicators such as the maximum deformation, deformation distribution, and stress distribution of the curved part were recorded.

[0049] Based on the constructed finite element database, a machine learning algorithm is used to fit the mapping relationship between the cutting force distribution and the optimal adsorption position. Specifically, a deep neural network architecture is adopted, with the input layer containing features of the cutting force magnitude, direction, and position of action, and the output layer being a multi-dimensional vector of the adsorption point coordinates and the recommended adsorption force value.

[0050] The neural network structure is designed as follows: the input layer has 9 nodes (including the three directional components of the cutting force, the three-dimensional coordinates of the point of application, and the three-dimensional vector of the tool feed direction), the hidden layer adopts a 4-layer structure with 64, 128, 128, and 64 nodes respectively, the activation function is ReLU, and the number of nodes in the output layer is 3 times the number of adsorption points (the three-dimensional coordinates of each adsorption point).

[0051] During training, 80% of the data was used as the training set and 20% as the validation set. The Adam optimizer was used with a learning rate of 0.001, a batch size of 64, and 500 training iterations. The loss function was defined as the mean square error between the predicted adsorption point location and the ideal adsorption point location. A stiffness constraint penalty term was also introduced to ensure that the generated adsorption point layout met the overall stiffness requirements.

[0052] After training, the model can output a set of spatial coordinates of adsorption points that satisfy stiffness constraints based on the input cutting force distribution. For typical aerospace curved parts, the adsorption points generated by the model are usually distributed in the deformation-sensitive areas of the workpiece, forming an optimal adsorption point layout.

[0053] The multi-point flexible processing fixture receives a set of spatial coordinates and generates an adsorption position path planning instruction; the pose adjustment robot or five-axis machine tool drives the remora-like vacuum suction cup to rotate to the target angle.

[0054] Step S103, establish initial boundary conditions, the details of which are as follows:

[0055] In this step, the forming process of the curved part is simulated using multiphysics coupled finite element method, such as... Figure 4As shown, the residual stress gradient distribution in the thickness direction is extracted as the initial constraint condition for adsorption force distribution.

[0056] First, a multiphysics coupling model of the forming process of curved parts is established. For milled curved parts, the coupling effect of the three fields of thermo-mechanical-phase transition is considered.

[0057] During the simulation, for milled curved parts, the material removal process is simulated by removing elements layer by layer, while a cutting thermal load is applied.

[0058] The residual stress distribution of the curved part after forming is obtained through simulation calculation. The focus is on the residual stress gradient distribution in the thickness direction, and the residual stress values ​​of the surface layer, intermediate layer and bottom layer are extracted to construct a three-dimensional residual stress field.

[0059] Based on the extracted residual stress distribution, initial constraints for adsorption force distribution are established. Specifically, the residual stress field is converted into an equivalent external force field, and the required equilibrium force at different adsorption points is calculated to counteract the deformation trend caused by residual stress. A higher initial adsorption force is set for the residual tensile stress region, and a lower initial adsorption force is set for the residual compressive stress region.

[0060] In this way, the established initial boundary conditions can effectively compensate for the residual stress generated during the forming process of curved parts, providing a basic reference value for subsequent adsorption force control.

[0061] Step S104: Based on the training parameters of the machined curved surface part, the dynamic cutting force finite element model, the adsorption position prediction model, and the initial boundary conditions, the trained adsorption force control model is obtained. Details are as follows:

[0062] Based on the training parameters for machining curved parts and the dynamic cutting force finite element model, the equivalent cutting force for machining curved parts is determined.

[0063] Based on the equivalent cutting force and adsorption location prediction model for machining curved parts, the optimal adsorption point layout is determined.

[0064] Based on the initial boundary conditions, the equivalent cutting force for machining curved parts, and the optimal adsorption point layout, an adsorption force-deformation response matrix is ​​constructed.

[0065] Based on the adsorption force-deformation response matrix, a well-trained adsorption force control model is obtained.

[0066] In one exemplary embodiment, in this step, the workpiece deformation response under different combinations of adsorption forces is first parameterized and simulated. A finite element model of the curved part-multi-point flexible machining fixture system is established, and different magnitudes of adsorption forces are applied at the determined optimal adsorption point positions to simulate and analyze the workpiece deformation response.

[0067] To comprehensively obtain data on the relationship between adsorption force and deformation, a parametric simulation scheme was designed. For n adsorption points, the adsorption force at each point was set to m levels (typically 5 levels, representing 20%, 40%, 60%, 80%, and 100% of the maximum adsorption force), generating a total of m... n Adsorption force combinations were considered. Given the large number of combinations, an orthogonal experimental method was employed to reduce the number of simulation conditions.

[0068] For each combination of adsorption forces, a calculated equivalent cutting force is applied, and the deformation at key locations on the workpiece is recorded. In this way, an adsorption force-deformation response matrix R is constructed, where the matrix element Rij represents the deformation at the j-th monitoring point under the i-th combination of adsorption forces.

[0069] Based on the constructed response matrix, an adsorption force control model is trained. An optimization algorithm is used to solve for the dynamic adjustment strategy, and the objective function is defined as:

[0070] minJ = ||DD target || 2 +λ·||F|| 2 (2)

[0071] Where: minJ is the objective function to be minimized, D is the actual deformation vector of the workpiece, and D target Let F be the target deformation vector, F be the adsorption force vector, and λ be the regularization coefficient, which is used to balance the relationship between deformation control and adsorption force consumption.

[0072] To solve this optimization problem, a gradient descent method combined with the Lagrange multiplier method is used to iteratively calculate the optimal adsorption force distribution scheme. To improve the solution efficiency, a response surface methodology is introduced to establish an approximate analytical relationship between adsorption force and deformation, thereby accelerating the optimization process.

[0073] The trained adsorption force control model can calculate the optimal adsorption force required at each adsorption position based on real-time cutting force and workpiece condition, thus achieving dynamic adjustment of the adsorption force. The model's output adsorption force adjustment strategy includes: the magnitude of the adsorption force at each adsorption point, the adjustment sequence, and the adjustment rate, ensuring that workpiece deformation is always controlled within the allowable range during the cutting process.

[0074] In an exemplary embodiment, in this step, the workpiece deformation response under different combinations of adsorption forces is parameterized and simulated to construct an adsorption force-deformation response matrix, and a dynamic adjustment strategy is solved by an optimization algorithm.

[0075] Unlike the gradient descent and Lagrange multiplier methods used in previous examples, this embodiment employs a genetic algorithm to solve for the optimal adsorption force allocation scheme. The genetic algorithm has global search capabilities, effectively avoiding getting trapped in local optima.

[0076] In practice, the adsorption force allocation problem is encoded as chromosomes, with each gene representing the adsorption force value at an adsorption point. The population size is set to 50-100, the crossover probability is set to 0.8, and the mutation probability is set to 0.1. The fitness function is defined as the negative value of the workpiece deformation; that is, the smaller the deformation, the higher the fitness.

[0077] Through selection, crossover, and mutation operations, the algorithm iteratively evolves for 100-200 generations to obtain the optimal adsorption force allocation scheme. To improve algorithm efficiency, an elite retention strategy and an adaptive mutation rate are introduced to accelerate the convergence process. Genetic algorithms have better robustness in handling high-dimensional nonlinear optimization problems, and are particularly suitable for positioning systems of complex curved surfaces with a large number of adsorption points (>10).

[0078] Step S20: Based on the geometric features of the curved surface part to be processed, determine the initial adsorption force value and the initial adsorption point through the configuration feature library;

[0079] Step S30: Based on the initial adsorption force value and initial adsorption point data, a first control strategy set is generated. The first control strategy set controls the guide rail assembly, support unit and adsorption controller to execute the initial target working position.

[0080] Step S40: In response to the command of the guide rail assembly, support unit and adsorption controller to complete the initial target working position, acquire the adsorption force data of the curved surface to be processed sent by the force sensor, and determine the real-time deformation of the workpiece based on the adsorption force data of the curved surface to be processed.

[0081] Step S50: Based on the initial adsorption force value and initial adsorption point data, the theoretical workpiece deformation is obtained through the trained adsorption force control model.

[0082] Step S60: Based on the real-time deformation of the workpiece and the theoretical deformation of the workpiece, the final adsorption force value is obtained through a PID control algorithm;

[0083] A PID control algorithm is used to dynamically adjust the adsorption force data of the curved surface to be processed at each adsorption point. The PID controller parameters are set as follows: proportional coefficient Kp = 0.8-1.2, integral coefficient Ki = 0.3-0.5, derivative coefficient Kd = 0.1-0.2, and sampling period T = 10-50ms.

[0084] During the control process, when the deformation in a local area exceeds a preset threshold, a collaborative re-optimization calculation of the adsorption position and adsorption force is automatically triggered. The re-optimization process includes: re-evaluating the current cutting state, updating the deformation prediction model, calculating a new optimal adsorption point layout and adsorption force distribution scheme, and smoothly transitioning to the new control strategy to ensure the continuity and stability of the machining process.

[0085] Step S70: Based on the final adsorption force value, a second control strategy set is generated. The final adsorption force value control strategy set controls the guide rail assembly, support unit and adsorption controller to execute the final target working position.

[0086] In one exemplary embodiment, the deformation of the workpiece is monitored in real time by a force sensor, the feedback data is compared with the output of the prediction model, and the vacuum adsorption force value of each adsorption point is dynamically adjusted by a fuzzy PID control algorithm.

[0087] Unlike the traditional PID control algorithm used in Example 1, this example uses a fuzzy PID control algorithm, which can adaptively adjust the control parameters according to the deformation error and its rate of change, thereby improving the system response speed and stability.

[0088] The input variables of the fuzzy PID controller are the deformation error e and the error change rate ec, and the output variable is the PID parameter adjustment ΔK. p ΔK i and ΔK d The fuzzy rule base contains 49 IF-THEN rules, covering control strategies under various operating conditions.

[0089] By employing fuzzy inference and defuzzification, the optimal PID parameters for the current operating conditions are calculated, enabling online adaptive adjustment of the control parameters. Compared to the fixed-parameter PID control in Example 1, fuzzy PID control exhibits better adaptability and robustness when facing disturbances such as changes in workpiece material properties and cutting parameters.

[0090] Furthermore, this embodiment introduces a feedforward compensation mechanism into the closed-loop control, which predicts the future deformation trend based on the cutting trajectory and adjusts the adsorption force distribution in advance to achieve preventive control of deformation and further improve machining accuracy.

[0091] like Figures 4-7 As shown in the exemplary embodiment, a stress-adaptive multi-point flexible machining control fixture includes: a fixture frame 10, support units 20, and a suction cup assembly 30. The fixture frame 10 has a guide rail assembly 40. Multiple support units 20 are spaced apart and connected to the guide rail assembly 40. The suction cup assembly 30 includes a suction cup head 302, a suction cup head support 301, and a suction cup assembly. The first end of the suction cup head support 301 is connected to the actuating end of the support unit 20. The first end of the suction cup head 302 is magnetically connected to the second end of the suction cup head support 301. The suction cup assembly is connected to the second end of the suction cup head 302. The suction cup head 302 allows the suction cup assembly to rotate flexibly within a 45° range in all directions.

[0092] The aforementioned tooling frame 10 and support unit 20 are described in detail in Chinese invention patent application number CN202410407681.7, entitled "A Vacuum Adsorption Multi-point Flexible Support Tooling and Its Positioning Accuracy Control Method". The execution end of the support unit 20 is the ball joint column in the patent, and the first end of the suction cup rotating head support is installed on the ball joint column.

[0093] In this embodiment, the guide rail assembly of the tooling frame, together with multiple spaced and connected support units, provides a stable and flexibly adjustable basic support structure for the device, facilitating adjustments to the support position according to processing requirements. The unique design of the suction cup assembly is particularly crucial; the suction cup head and its support are connected via a strong magnet. Combined with the suction cup head's ability to rotate flexibly within a 45° range in all directions, this significantly enhances the tooling's flexibility and adaptability, allowing for precise fitting of various complex curved surfaces and effectively overcoming the limitations of traditional fixed tooling. Simultaneously, the multi-point distributed support units and the flexibly rotating suction cup assembly work together to apply suction force more evenly, reducing workpiece deformation and contributing to improved processing accuracy and stability. This makes it suitable for processing various complex curved surfaces, significantly enhancing process flexibility and practicality.

[0094] Furthermore, the suction cup assembly includes: a suction cup body 303 and a fan-shaped fish bionic suction cup structure. The suction cup body 303 is connected to the second end of the suction cup rotating head 302. The fan-shaped fish bionic suction cup structure includes multiple fan-shaped fish bionic suction cup structures, which are spaced apart circumferentially along the suction cup body. A first vacuum groove 307 is provided between two adjacent fan-shaped fish bionic suction cup structures. The fan-shaped fish bionic suction cup structure includes multiple bionic fish fins 304, which are spaced apart radially. A second vacuum groove is provided between any two adjacent bionic fish fins 304. The bionic fish fins 304 include multiple protrusions 305, which are spaced apart circumferentially along the suction cup body 303.

[0095] In this embodiment, the suction cup body is combined with multiple fan-shaped fish-inspired suction cup structures arranged circumferentially. The first vacuum groove between adjacent fan-shaped fish-inspired suction cup structures and the second vacuum groove between multiple radially spaced bionic fish fins in each structure can form a multi-layered vacuum adsorption area, which greatly improves the adsorption sealing and stability. The bionic fish fin design imitates the shape of fish fins and can flexibly fit the complex surface of curved parts, enhancing the adaptability to the workpiece. Combined with the vacuum groove structure, it can not only evenly disperse the adsorption force to reduce workpiece deformation, but also adapt to the processing requirements of curved surfaces with different curvatures, further improving the flexibility of the tooling and the reliability of processing.

[0096] Multiple protrusions spaced circumferentially along the suction cup body on the biomimetic fish fin further optimize the suction performance of the suction cup assembly. These protrusions enhance the contact tightness between the biomimetic fish fin and the surface of the workpiece to be processed. Especially when dealing with surfaces with slight undulations or unevenness, the protrusions can fill gaps through adaptive deformation, improving the sealing effect and thus enhancing the stability of vacuum adsorption. At the same time, the spaced protrusions can disperse the adsorption force, avoiding excessive local adsorption force that could cause workpiece deformation. Combined with the previous vacuum groove structure, this forms a more reasonable force distribution pattern, making the suction cup assembly more adaptable when conforming to complex curved surfaces. This further improves the tooling's adaptability to different working conditions and the reliability of the processing.

[0097] In this embodiment, the suction cup assembly further includes a force sensor 306, which is connected to the suction cup body 303. The force sensor 306 is spaced apart from multiple fan-shaped fish bionic suction cup structures. The force sensor 306 is used to acquire the adsorption force data of the curved surface to be processed.

[0098] Force sensor 306 is connected to the suction cup body and spaced apart from multiple fan-shaped fish-inspired suction cup structures. It can acquire the adsorption force data of the curved surface to be processed in real time and accurately, providing crucial feedback for the adaptive control of the entire processing device. Based on this real-time adsorption force data, the system can promptly sense the force changes of the workpiece during the adsorption process. Combined with the aforementioned characteristics of flexible rotation of the suction cup components and biomimetic structure fit, it can further achieve dynamic adjustment of the adsorption force, ensuring that the adsorption force is always within a reasonable range. This avoids workpiece displacement due to insufficient adsorption force and prevents workpiece deformation due to excessive adsorption force, thereby improving processing stability and further ensuring processing accuracy, effectively enhancing the flexibility and intelligence of the entire tooling.

[0099] In one exemplary embodiment, the suction cup assembly is made of polyurethane, and the suction cup rotor 302 has an extension unit that cooperates with the suction cup assembly. The extension unit is made of polytetrafluoroethylene (PTFE). The polyurethane material of the suction cup assembly, with its excellent elasticity, wear resistance, and sealing properties, allows it to closely adhere to the surface of the curved workpiece to be processed, enhancing the adsorption effect while reducing wear and scratches on the workpiece surface. Meanwhile, the PTFE material of the extension unit of the suction cup rotor, with its excellent corrosion resistance, low coefficient of friction, and high-temperature resistance, reduces frictional resistance during relative movement when used with the suction cup assembly, improving rotational flexibility and service life. It also adapts to various working conditions in the processing environment. The rational selection and synergistic effect of these two materials further optimize the performance of the suction cup assembly and enhance the practicality and reliability of the tooling.

[0100] This application provides a structural block diagram of a terminal, which can be the terminal described in the above embodiments. The terminal can be a portable mobile terminal, such as a smartphone or tablet computer. The terminal may also be referred to as user equipment, portable terminal, or other names.

[0101] Typically, a terminal includes a processor and memory.

[0102] The processor may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor may also include a main processor and coprocessors. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0103] The memory may include one or more computer-readable storage media, which may be tangible and non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory are used to store at least one instruction, which is executed by a processor to implement a data-driven stress-adaptive multi-point flexible fabrication control method provided in this application.

[0104] In some embodiments, the terminal may also optionally include: a peripheral device interface and at least one peripheral device. Specifically, the peripheral device includes at least one of: a radio frequency circuit, a touch display screen, a camera, an audio circuit, a positioning component, and a power supply.

[0105] Peripheral device interfaces can be used to connect at least one I / O (Input / Output) related peripheral device to the processor and memory. In some embodiments, the processor, memory, and peripheral device interface are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor, memory, and peripheral device interface can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0106] Radio frequency (RF) circuits are used to receive and transmit RF signals, also known as electromagnetic signals. RF circuits communicate with communication networks and other communication devices via electromagnetic signals. RF circuits convert electrical signals into electromagnetic signals for transmission, or convert received electromagnetic signals back into electrical signals. Optionally, RF circuits include: antenna systems, RF transceivers, one or more amplifiers, tuners, oscillators, digital signal processors, codec chipsets, user identity module cards, etc. RF circuits can communicate with other terminals through at least one wireless communication protocol. These wireless communication protocols include, but are not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0107] A touchscreen display is used to display a user interface (UI). This UI can include graphics, text, icons, videos, and any combination thereof. The touchscreen display also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to a processor for processing. The touchscreen display is used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one touchscreen display, located on the front panel of the terminal; in other embodiments, there may be at least two touchscreen displays, respectively located on different surfaces of the terminal or in a folded design; in still other embodiments, the touchscreen display may be a flexible display, located on a curved or folded surface of the terminal. Furthermore, the touchscreen display can be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The touchscreen display can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0108] A camera assembly is used to capture images or videos. Optionally, the camera assembly includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is used for video calls or selfies, while the rear-facing camera is used for taking photos or videos. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, and a wide-angle camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, and panoramic shooting and VR (Virtual Reality) shooting by fusion of the main camera and the wide-angle camera. In some embodiments, the camera assembly may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash is a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0109] The audio circuitry provides an audio interface between the user and the terminal. The audio circuitry may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to a processor for processing, or input to radio frequency circuitry for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, positioned at different locations on the terminal. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor or radio frequency circuitry into sound waves. The speaker may be a traditional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuitry may also include a headphone jack.

[0110] The positioning component is used to determine the current geographical location of the terminal to enable navigation or LBS (Location Based Service). The positioning component can be based on the US GPS (Global Positioning System), China's BeiDou system, or Russia's Galileo system.

[0111] The power supply is used to power the various components in the terminal. The power supply can be alternating current (AC), direct current (DC), a disposable battery, or a rechargeable battery. When the power supply includes a rechargeable battery, it can be a wired or wirelessly rechargeable battery. A wired rechargeable battery is charged via a wired connection, while a wirelessly rechargeable battery is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0112] In some embodiments, the terminal further includes one or more sensors. These one or more sensors include, but are not limited to, accelerometers, gyroscopes, magnetic force sensors, fingerprint sensors, optical sensors, and proximity sensors.

[0113] An accelerometer can detect the magnitude of acceleration along the three axes of a coordinate system established by the terminal. For example, an accelerometer can be used to detect the components of gravitational acceleration along the three axes. The processor can then control the touchscreen to display the user interface in either landscape or portrait view based on the gravitational acceleration signals acquired by the accelerometer. Accelerometers can also be used for collecting motion data in games or for other applications.

[0114] The gyroscope sensor can detect the terminal's orientation and rotation angle. It can work in conjunction with an accelerometer to collect the user's 3D (3D) movements on the terminal. Based on the data collected by the gyroscope sensor, the processor can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0115] The adhesion sensor can be installed on the side bezel of the terminal and / or under the touchscreen display. When installed on the side bezel, it can detect the user's grip signal and perform left / right hand recognition or quick operation based on this grip signal. When installed under the touchscreen display, it can control operable controls on the UI interface based on the user's adhesion to the touchscreen display. Operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0116] A fingerprint sensor is used to collect a user's fingerprint to identify the user. Once the user's identity is verified as trusted, the processor authorizes the user to perform sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, making payments, and changing settings. The fingerprint sensor can be located on the front, back, or side of the device. When the device has physical buttons or a manufacturer's logo, the fingerprint sensor can be integrated with those buttons or logos.

[0117] An optical sensor is used to collect ambient light intensity. In one embodiment, the processor can control the display brightness of the touch screen based on the ambient light intensity collected by the optical sensor. Specifically, when the ambient light intensity is high, the display brightness of the touch screen is increased; when the ambient light intensity is low, the display brightness of the touch screen is decreased. In another embodiment, the processor can also dynamically adjust the shooting parameters of the camera assembly based on the ambient light intensity collected by the optical sensor.

[0118] A proximity sensor, also known as a distance sensor, is typically located on the front of a terminal. It is used to detect the distance between the user and the front of the terminal. In one embodiment, when the proximity sensor detects that the distance between the user and the front of the terminal is gradually decreasing, the processor controls the touchscreen display to switch from a screen-on state to a screen-off state; conversely, when the proximity sensor detects that the distance between the user and the front of the terminal is gradually increasing, the processor controls the touchscreen display to switch from a screen-off state to a screen-on state.

[0119] In an exemplary embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements a data-driven stress-adaptive multi-point flexible machining control method as provided in all embodiments of the present application.

[0120] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0121] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0122] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0123] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0124] In an exemplary embodiment, an application product is also provided, including one or more instructions that can be executed by the processor of the aforementioned device to complete the aforementioned data-driven stress-adaptive multi-point flexible machining control method.

[0125] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. It can be applied to various fields suitable for the present invention. Other modifications can be readily made by those skilled in the art. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and examples shown and described herein.

Claims

1. A data-driven stress-adaptive multi-point flexible machining control method, characterized in that, include: In response to the adsorption processing request command, the parameters of the curved surface part to be processed are obtained; Based on the geometric features of the curved surface to be processed, the initial adsorption force value and the initial adsorption point are determined through the configuration feature library; Based on the initial adsorption force value and initial adsorption point data, a first control strategy set is generated, which controls the guide rail assembly, support unit and adsorption controller to execute the initial target working position. In response to the command of the guide rail assembly, the support unit and the adsorption controller to complete the initial target working position, the adsorption force data of the surface part to be processed sent by the force sensor is acquired, and the real-time deformation of the workpiece is determined based on the adsorption force data of the surface part to be processed. Based on the initial adsorption force value and initial adsorption point data, the theoretical workpiece deformation is obtained through the trained adsorption force control model. Based on the real-time deformation of the workpiece and the theoretical deformation of the workpiece, the final adsorption force value is obtained through a PID control algorithm. Based on the final adsorption force value, a second control strategy set is generated, which controls the guide rail assembly, the support unit, and the adsorption controller to execute the final target working position.

2. The stress-adaptive multi-point flexible machining control method according to claim 1, characterized in that, In response to the adsorption processing request command, the geometric features of the surface to be processed are obtained, and prior to this, the process further includes: Obtain the training parameters for machining curved parts, and establish a dynamic cutting force finite element model, an adsorption position prediction model, and initial boundary conditions respectively; Based on the training parameters of the machined curved surface, the dynamic cutting force finite element model, the adsorption position prediction model, and the initial boundary conditions, a trained adsorption force control model is obtained.

3. The stress-adaptive multi-point flexible machining control method according to claim 2, characterized in that, The trained adsorption force control model, based on the training parameters of the machined curved surface part, the dynamic cutting force finite element model, the adsorption position prediction model, and the initial boundary conditions, includes: Based on the training parameters for machining curved parts and the dynamic cutting force finite element model, the equivalent cutting force for machining curved parts is determined. Based on the equivalent cutting force for machining the curved part and the adsorption position prediction model, the optimal adsorption point layout is determined. Based on the initial boundary conditions, the equivalent cutting force for machining the curved part, and the optimal adsorption point layout, an adsorption force-deformation response matrix is ​​constructed. Based on the adsorption force-deformation response matrix, a trained adsorption force control model is obtained.

4. The stress-adaptive multi-point flexible machining control method according to claim 3, characterized in that, Initial boundary conditions are established based on the residual stress distribution during the forming of curved parts, including: A multi-physics coupling model of the forming process of curved parts is established. The material removal process is simulated by removing elements layer by layer. Cutting thermal load is applied to obtain the residual stress distribution of the curved parts after forming. The initial constraint conditions are established based on the residual stress distribution.

5. The stress-adaptive multi-point flexible machining control method according to claim 3, characterized in that, The determination of the equivalent cutting force for machining the curved surface part based on the training parameters of the machined curved surface part and the dynamic cutting force finite element model includes: Based on the training parameters for machining curved parts and the dynamic cutting force finite element model, the equivalent cutting force for machining curved parts is obtained through formula (1): Wherein: F c The main cutting force, C Fc a is the cutting force coefficient. p To measure the amount of cuts made by the back of the blade, x Fc The depth of cut is the index, f is the feed per revolution, and y is the feed rate. Fc Where z is the feed rate exponent, v is the cutting speed, and z is the feed rate exponent. Fc K is the cutting speed exponent. Fc This is the working condition correction factor.

6. A data-driven stress-adaptive multi-point flexible machining control fixture, used to implement the stress-adaptive multi-point flexible machining control method according to any one of claims 1-5, characterized in that, include: Tooling frame (10), the tooling frame (10) having guide rail assembly (40); Support unit (20), the support unit (20) includes a plurality of them, the plurality of support units (20) are arranged at intervals, and the plurality of support units (20) are respectively connected to the guide rail assembly (40); The suction cup assembly (30) includes a suction cup head (302), a suction cup head support (301), and a suction cup component. The first end of the suction cup head support (301) is connected to the execution end of the support unit (20). The first end of the suction cup head (302) is connected to the second end of the suction cup head support (301) via a strong magnet. The suction cup component is connected to the second end of the suction cup head (302).

7. The data-driven stress-adaptive multi-point flexible machining control fixture according to claim 6, characterized in that, The suction cup assembly includes: The suction cup body (303) is connected to the second end of the suction cup rotating head (302); A fan-shaped fish bionic suction cup structure is provided, comprising multiple fan-shaped fish bionic suction cup structures, which are spaced apart circumferentially along the suction cup body (303). A first vacuum groove (307) is provided between two adjacent fan-shaped fish bionic suction cup structures. The fan-shaped fish bionic suction cup structure includes multiple bionic fish fins (304), which are spaced apart radially. A second vacuum groove is provided between any two adjacent bionic fish fins (304). The bionic fish fins (304) include multiple protrusions (305), which are spaced apart circumferentially along the suction cup body (303).

8. The data-driven stress-adaptive multi-point flexible machining control fixture according to claim 7, characterized in that, The suction cup assembly also includes: Force sensor (306) is connected to suction cup body (303). Force sensor (306) is arranged at intervals with multiple fan-shaped fish bionic suction cup structures. Force sensor (306) is used to acquire adsorption force data of curved surface parts to be processed.

9. The data-driven stress-adaptive multi-point flexible machining control fixture according to any one of claims 6-8, characterized in that, The suction cup assembly is made of polyurethane material, and the suction cup rotating head (302) has an epitaxial unit that cooperates with the suction cup assembly. The epitaxial unit is made of polytetrafluoroethylene material.

10. A terminal, characterized in that, include: One or more processors; Memory for storing the one or more processor-executable instructions; Wherein, the one or more processors are configured as follows: Perform a data-driven stress-adaptive multi-point flexible machining control method as described in any one of claims 1 to 5.

Images