Hydraulic balance control method and system for superplastic forming machine

Abstract

This application relates to a hydraulic balance control method and system for a superplastic forming machine. Based on the cavity surface parameters of the superplastic forming mold, a preset pressure parameter prediction model is used to determine a hydraulic extrusion pressure p that matches the cavity surface parameters s. A compensation coefficient α is configured for the hydraulic extrusion pressure p: Px = α*p, to achieve hydraulic balance compensation. A corresponding pressure curve P(t) is generated based on the hydraulic extrusion pressure p. The pressure curve P(t) is configured in the hydraulic system controller of the superplastic forming machine, and the working pressure output of the hydraulic system is controlled with reference to the pressure curve P(t). By determining the hydraulic extrusion pressure p that matches the cavity surface parameters s(x) with reference to the cavity surface parameters of the superplastic forming mold, and simultaneously performing output compensation control, hydraulic compensation can be achieved, solving the hydraulic lag problem of traditional presses and improving sensitivity through hydraulic compensation.

Description

Technical Field

[0001] This disclosure relates to the field of aviation facility technology, and in particular to a hydraulic balance control method, system and electronic equipment for a superplastic forming machine. Background Technology

[0002] Superplastic forming technology is widely used in aerospace, automotive, and other demanding industrial fields. It can be used to manufacture complex thin-walled structures and lightweight parts, characterized by high precision and high strength. The advantages of superplastic forming machines include the ability to produce complex shapes, reduced material waste, and increased production efficiency. Superplastic forming processes can be categorized by the forming medium, including pneumatic forming, hydroforming, dieless forming, and dieless drawing, among others.

[0003] Superplastic forming machines are mainly used for superplastic forming / diffusion bonding processes of titanium alloy parts. They can also perform hot forming and hot straightening of titanium alloy materials. The main components include the main body of the equipment, upper heating platform, lower heating platform, heat insulation door, heating system, cooling system, hydraulic system, pneumatic electronic equipment, and electrical control system.

[0004] As attached Figure 1 The superplastic forming machine shown adopts a frame-type structure bed, mainly including: frame structure bed, hydraulic cylinder, slide block, and transfer platform. The hydraulic cylinder uses a multi-cylinder structure to improve the lateral rigidity of the thermoforming machine and resist the lateral forces generated during thermoforming. The main cylinder body is made of 35# forging, and the plunger rod and piston head are integral parts to avoid the danger caused by the piston head falling off. The plunger rod surface is hardened. Driven by the hydraulic cylinder, the upper slide block is pushed downwards, thereby applying hydraulic thrust to the mold and superplastic forming the material.

[0005] In the superplastic molding process, the stability of the hydraulic (or pneumatic) system has a significant impact on the forming of aerospace components. Therefore, to improve the rigidity of the superplastic molding machine during hot operation and reduce the lateral displacement of the equipment slide caused by the lateral force of thermoforming, the stability of the overall structure must be ensured. Since the hydraulic cylinder seals have high elasticity, the hydraulic cylinders themselves cannot guarantee the straightness of the slide movement. Therefore, each slide is equipped with four guide rods, each with a rack-like surface that meshes with gears fixed inside the upper crossbeam to ensure stable slide movement.

[0006] However, positioning and supporting the slider with guide rods is merely an external condition for superplastic molding. If the hydraulic thrust applied to the mold is unbalanced, it may lead to significant differences in phase structure and uneven texture in the superplastic molded components within the mold, as shown in the attached figure. Figure 2The phase comparison diagram shown shows the normal phase spectrum on the left and the phase disorder spectrum caused by hydraulic imbalance on the right. Existing superplastic molding equipment generally uses a uniform downward pressing method to achieve optimal working conditions. However, for aerospace components, their ductility in the mold is not uniform because aerospace components are almost entirely composed of non-uniform sheet metal or tubular structures, making it difficult to control the pressure using hydraulic uniform speed.

[0007] In addition, when the hydraulic pressure of a traditional superplastic forming machine is increased, there is a lag in the pressurization due to the machine assembly problem (hydraulic control time, oil circuit response time, etc.). The response is delayed, the sensitivity is not high, and it does not respond in time.

[0008] Therefore, it is necessary to optimize the hydraulic control scheme for aerospace components during the superplastic forming process and make appropriate adjustments. Summary of the Invention

[0009] To address the aforementioned issues, this application proposes a hydraulic balance control method, system, and electronic equipment for a superplastic forming machine.

[0010] This application proposes a hydraulic balance control method for a superplastic forming machine, comprising the following steps:

[0011] Obtain the cavity surface parameters s(x) of the superplastic forming mold;

[0012] Based on the cavity surface parameters s(x) of the superplastic forming mold, a preset pressure parameter prediction model is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x);

[0013] A compensation coefficient α is configured for the hydraulic extrusion pressure p:

[0014] Px = α*p,

[0015] Where α is the compensation coefficient, used to compensate for the lag pressure caused by the system when the superplastic forming machine outputs hydraulic pressure, so as to achieve hydraulic balance compensation; Px is the compensated hydraulic value;

[0016] Based on Px, the corresponding pressure curve P(t) is generated;

[0017] The pressure curve P(t) is configured in the hydraulic system controller of the superplastic forming machine, and the working pressure output of the hydraulic system is controlled with reference to the pressure curve P(t).

[0018] As an optional embodiment of this application, optionally, obtaining the cavity surface parameters s(x) of the superplastic forming mold includes:

[0019] An ultrasonic scanning system was used to scan the cavity structure of the superplastic forming mold to obtain three-dimensional ultrasonic data of the superplastic forming mold;

[0020] The three-dimensional ultrasonic data of the superplastic forming mold is transmitted to the host server of the superplastic forming equipment, and the three-dimensional ultrasonic data of the superplastic forming mold is preprocessed.

[0021] After preprocessing, the three-dimensional ultrasound data is imported into a simulation system pre-deployed on the host server for three-dimensional simulation modeling to obtain the corresponding cavity three-dimensional model.

[0022] Set reference coordinates, generate a cross-sectional view of the cavity 3D model, and construct the cavity surface parameters s(x) of the cross-sectional view based on the cross-sectional area of ​​the cross-sectional view.

[0023] As an optional embodiment of this application, the method for generating the pressure parameter prediction model may include:

[0024] 3.1 Data Collection and Preprocessing

[0025] Collect a dataset S suitable for the task, including: the historical cross-sectional area function of the superplastic forming die: s n (x), and the historical hydraulic extrusion pressure output by the superplastic forming machine used: p n ,

[0026] S={(s 1 (x), p 1 ), (s 2 (x), p 2 )......(s n (x), p n )},

[0027] Among them, (s 1 (x), p 1 ), (s 2 (x), p 2 )......(s n (x), p n ), which represent the cross-sectional area of ​​the superplastic forming molds of different types by the same superplastic forming machine, and the output hydraulic extrusion pressure;

[0028] The dataset S is preprocessed, including data augmentation, normalization, and standardization operations, to improve the generalization ability of the model.

[0029] 3.2. Model Design

[0030] Choose the CNN model architecture: ResNet;

[0031] Adjust the model parameters according to the task requirements, including the number of convolutional layers, the size of the convolutional kernel, and the size of the pooling layer.

[0032] 3.3. Loss Function and Optimizer Selection

[0033] Choose a loss function that suits the task requirements, such as cross-entropy loss function for classification tasks and mean squared error loss function for regression tasks.

[0034] Choose an appropriate optimizer, such as stochastic gradient descent (SGD) or Adam, and set the learning rate;

[0035] 3.4. Training Process

[0036] The dataset is divided into a training set and a validation set for training and validating the model;

[0037] Initialize model parameters;

[0038] The training loop includes steps such as forward propagation, loss calculation, backpropagation, and parameter update.

[0039] After each training cycle, the model's performance is evaluated using the validation set, and the best model is saved.

[0040] 3.5. Verification and Testing

[0041] Use a validation set to validate the model and ensure that it performs well on unseen data.

[0042] Use the test set to test the model and evaluate its generalization ability;

[0043] 3.6. Parameter Adjustment and Improvement

[0044] Based on the validation and testing results, adjust the model parameters and optimizer parameters to improve the model's performance;

[0045] 3.7. Deployment and Application

[0046] The trained model is deployed to the host server, such as an image classifier or object detector.

[0047] The model is fine-tuned based on the actual application scenario to improve its practicality;

[0048] 3.8. Monitoring and Maintenance

[0049] Monitor the performance of the model to ensure it remains stable over a long period of time;

[0050] The model should be updated and maintained regularly to adapt to new data distributions and task requirements.

[0051] As an optional embodiment of this application, optionally, based on the cavity surface parameters s(x) of the superplastic forming mold, a preset pressure parameter prediction model is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x), including:

[0052] The host server receives and forwards the cavity surface parameters s(x) to the pressure parameter prediction model;

[0053] The pressure parameter prediction model identifies the cavity surface parameter s(x) and outputs the hydraulic extrusion pressure p of the superplastic forming machine that matches the cavity surface parameter s(x) from the learned parameters.

[0054] The host server receives and forwards the hydraulic extrusion pressure p to the hydraulic system of the superplastic forming machine.

[0055] As an optional embodiment of this application, optionally, a compensation coefficient α is configured for the hydraulic extrusion pressure p, including:

[0056] Based on the cavity surface parameters s(x), find the historical hydraulic extrusion pressure output by the superplastic forming machine: p n ;

[0057] The hydraulic extrusion pressure p output by the pressure parameter prediction model in this instance is compared with the historical hydraulic extrusion pressure: p n By comparing the two pressure values, the difference between them can be determined: δp;

[0058] Based on the difference δp, the compensation coefficient α is determined such that:

[0059] p n =α*p;

[0060] Perform the conversion so that:

[0061] Px = p n ;

[0062] Further conversion makes:

[0063] Px = α*p.

[0064] In another aspect, this application proposes a system for implementing the aforementioned hydraulic balance control method for a superplastic forming machine, comprising:

[0065] The data acquisition module is used to obtain the cavity surface parameters s(x) of the superplastic forming mold;

[0066] The pressure prediction module is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x) of the superplastic forming mold using a preset pressure parameter prediction model.

[0067] A configuration module is used to configure a compensation coefficient α for the hydraulic extrusion pressure p:

[0068] Px = α*p,

[0069] Where α is the compensation coefficient, which is used to compensate for the lag pressure caused by the system when the superplastic forming machine outputs hydraulic pressure, so as to achieve hydraulic balance compensation;

[0070] The curve generation module is used to generate a corresponding pressure curve P(t) based on the hydraulic extrusion pressure p;

[0071] The data interface module is used to configure the pressure curve P(t) into the hydraulic system controller of the superplastic forming machine, and control the working pressure output of the hydraulic system with reference to the pressure curve P(t).

[0072] In another aspect, this application also proposes an electronic device comprising:

[0073] processor;

[0074] Memory used to store processor-executable instructions;

[0075] The processor is configured to implement the hydraulic balance control method for a superplastic forming machine when executing the executable instructions.

[0076] Technical effects of the present invention:

[0077] This application determines a hydraulic extrusion pressure p that matches the cavity surface parameters s of the superplastic forming mold using a preset pressure parameter prediction model; it configures a compensation coefficient α for the hydraulic extrusion pressure p: Px = α*p, to achieve hydraulic balance compensation; it generates a corresponding pressure curve P(t) based on the hydraulic extrusion pressure p; and it configures the pressure curve P(t) into the hydraulic system controller of the superplastic forming machine, controlling the working pressure output of the hydraulic system with reference to the pressure curve P(t). By determining the hydraulic extrusion pressure p that matches the cavity surface parameters s(x) of the superplastic forming mold with reference to the cavity surface parameters, and simultaneously performing output compensation control, hydraulic compensation can be achieved, solving the hydraulic lag problem of traditional presses and improving sensitivity through hydraulic compensation.

[0078] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0079] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this disclosure together with the specification and serve to explain the principles of this disclosure.

[0080] Figure 1 The diagram shows the main structure of the superplastic molding machine tool used in this invention.

[0081] Figure 2 The diagram shows a comparison of phase distortion caused by hydraulic imbalance (the right side shows the non-uniform phase).

[0082] Figure 3 The diagram shown is a schematic representation of the implementation process of the present invention;

[0083] Figure 4 The diagram shown is a schematic diagram of the cavity surface curve of the mold of the present invention;

[0084] Figure 5 The diagram shown is a schematic representation of the pressure curve of the present invention;

[0085] Figure 6 The diagram shown is a schematic representation of the system of the present invention;

[0086] Figure 7 The diagram shows an application schematic of the electronic device of the present invention. Detailed Implementation

[0087] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0088] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0089] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0090] Example 1

[0091] like Figure 3 As shown, this application proposes a hydraulic balance control method for a superplastic forming machine, comprising the following steps:

[0092] S1. Obtain the cavity surface parameters s(x) of the superplastic forming mold;

[0093] S2. Based on the cavity surface parameters s(x) of the superplastic forming mold, a preset pressure parameter prediction model is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x);

[0094] S3. Configure a compensation coefficient α for the hydraulic extrusion pressure p:

[0095] Px = α*p;

[0096] Where α is the compensation coefficient, used to compensate for the lag pressure caused by the system when the superplastic forming machine outputs hydraulic pressure, so as to achieve hydraulic balance compensation; Px is the compensated hydraulic value;

[0097] S4. Based on Px, generate the corresponding pressure curve P(t); let P(t) = β*Px, where β is a manual control coefficient set by the administrator;

[0098] S5. Configure the pressure curve P(t) into the hydraulic system controller of the superplastic forming machine, and control the working pressure output of the hydraulic system with reference to the pressure curve P(t).

[0099] The implementation of this method will be further described below in conjunction with the system.

[0100] like Figure 3 As shown, in the superplastic forming process, a superplastic forming mold is placed in the superplastic forming machine, and the corresponding aerospace component will be formed in the superplastic forming mold. Therefore, the specific process of superplastic forming mainly takes place in the cavity of the superplastic forming mold.

[0101] The hydraulic pressure applied by the superplastic molding machine to the superplastic molding die is also related to the forming cross-section of the superplastic molding die. Because the cavity cross-section of the superplastic molding die may be regular or irregular, the applied hydraulic pressure and the forming force on the aerospace component blank within the die cavity will differ. For regular die shapes, such as symmetrical or cylindrical / cubic-shaped aerospace components, the die cavity has a uniform spatial curved surface, thus allowing for hydraulic control. However, for asymmetrical structures, the die cavity will produce a non-uniform cavity surface, leading to hydraulic imbalance and causing internal phase misalignment in the molded component due to uneven pressure.

[0102] Therefore, this solution adopts a hydraulic balance control method, which combines the cavity surface structure of the mold to control the corresponding hydraulic pressure output, thereby achieving hydraulic balance control.

[0103] This solution involves scanning and simulating the cavity surface of a superplastic molding die, generating corresponding cavity surface parameters, and then controlling the hydraulic extrusion pressure accordingly. Hydraulic balance is achieved through dynamic compensation of the hydraulic extrusion pressure. The hydraulic system controller regulates the hydraulic output according to the pressure curve, ensuring a hydraulic output that matches the cavity structure and preventing phase differences caused by significant phase misalignment in the die's forming components due to hydraulic imbalance.

[0104] For complex surfaces, the balance between cross-section s and pressure can be referenced in the design of this scheme; this scheme is preferred for components with a single surface or no more than three surfaces.

[0105] As an optional embodiment of this application, optionally, obtaining the cavity surface parameters s(x) of the superplastic forming mold includes:

[0106] An ultrasonic scanning system was used to scan the cavity structure of the superplastic forming mold to obtain three-dimensional ultrasonic data of the superplastic forming mold;

[0107] The three-dimensional ultrasonic data of the superplastic forming mold is transmitted to the host server of the superplastic forming equipment, and the three-dimensional ultrasonic data of the superplastic forming mold is preprocessed.

[0108] After preprocessing, the three-dimensional ultrasound data is imported into a simulation system pre-deployed on the host server for three-dimensional simulation modeling to obtain the corresponding cavity three-dimensional model.

[0109] Set reference coordinates, generate a cross-sectional view of the cavity 3D model, and construct the cavity surface parameters s(x) of the cross-sectional view based on the cross-sectional area of ​​the cross-sectional view.

[0110] Combined with appendix Figure 6 As shown, the cavity structure of a mold can be scanned using 3D ultrasonic scanning technology to obtain 3D ultrasonic data of the mold cavity. 3D ultrasonic scanning can obtain the cavity structure of the mold, and combined with a simulation system, 3D modeling can be performed using the 3D ultrasonic data to generate a corresponding virtual mold model. The simulation system deployed on the host server performs 3D modeling on the 3D ultrasonic data to obtain the corresponding 3D cavity model. After the host server receives the 3D ultrasonic data, it can perform preprocessing, such as filling in missing 3D data or removing 3D data from abnormal areas.

[0111] By using 3D simulation modeling, a corresponding 3D cavity model can be obtained. After preprocessing the model surface, a smooth cavity model can be obtained.

[0112] For the cavity model, reference coordinates can be set according to the forming direction of the workpiece. The 3D model is cross-sectionally processed to obtain the cavity cross-sectional curve of the 3D cavity model. Using this cross-section as a reference, the cavity surface parameters of this cross-section are generated (using the plug-in or algorithm in the simulation system, the parameters of the cavity cross-section are automatically extracted to construct the corresponding cavity surface parameters s(x), where x is the direction of extrusion forming, and the blank will be formed according to the cross-section of this direction).

[0113] During high-speed forming, the billet is extruded along the cross-section of the cavity. Therefore, based on the shape of the cross-section and the direction of high-speed forming, the pressure on each cross-section is determined to be consistent.

[0114] If the area of ​​a certain cross-section is large, the hydraulic pressure output will be increased accordingly based on the cross-sectional area; if the cross-sectional area is small, the hydraulic pressure output will be decreased accordingly. By controlling the cross-sectional area to be proportional to the output hydraulic pressure, and uniformly controlling the output pressure, the hydraulic extrusion pressure p received by the billet on the cross-section is matched with the corresponding cross-sectional area, achieving balance.

[0115] To overcome the lag in the system's hydraulic output, the aforementioned method of hydraulic compensation using hydraulic extrusion pressure p was adopted.

[0116] like Figure 4 As shown, this scheme also uses a preset pressure parameter prediction model to determine the hydraulic extrusion pressure p that matches the cavity surface parameter s(x);

[0117] A compensation coefficient α is configured for the hydraulic extrusion pressure p:

[0118] Px = α*p;

[0119] Where α is the compensation coefficient, used to compensate for the lag pressure caused by the system when the superplastic forming machine outputs hydraulic pressure, so as to achieve hydraulic balance compensation; Px is the compensated hydraulic value;

[0120] Based on Px, generate the corresponding pressure curve P(t); let P(t) = β*Px, where β is a manual control coefficient set by the administrator;

[0121] The pressure curve P(t) is configured in the hydraulic system controller of the superplastic forming machine, and the working pressure output of the hydraulic system is controlled with reference to the pressure curve P(t).

[0122] like Figure 5 As shown, the corresponding pressure will be output according to the compensated pressure curve P(t). This ensures that the hydraulic pressure on the billet at each extrusion section matches the cross-sectional area within the mold cavity, avoiding pressure imbalance caused by inconsistent cross-sectional areas, which can easily lead to extrusion phase misalignment.

[0123] The compensation coefficient α is for dynamic compensation. At each cross-sectional position, the cross-sectional area and the corresponding hydraulic pressure control will be proportional. After regenerating the cavity surface parameters s(x), the administrator can generate the corresponding control function for the compensation coefficient α based on the cavity surface parameters s(x).

[0124] α = α(t), thereby ensuring that the hydraulic pressure on each section is dynamically adjusted according to the cavity cross section.

[0125] Here, α(t) can be a constant. It is specifically set according to the cavity cross-section s(x).

[0126] As an optional embodiment of this application, the method for generating the pressure parameter prediction model may include:

[0127] 3.1 Data Collection and Preprocessing

[0128] Collect a dataset S suitable for the task, including: the historical cross-sectional area function of the superplastic forming die: s n (x), and the historical hydraulic extrusion pressure output by the superplastic forming machine used: p n ,

[0129] S={(s 1 (x), p 1 ), (s 2 (x), p 2 )......(s n (x), p n )},

[0130] Among them, (s 1 (x), p 1 ), (s 2 (x), p 2 )......(s n (x), p n ), which represent the cross-sectional area of ​​the superplastic forming molds of different types by the same superplastic forming machine, and the output hydraulic extrusion pressure;

[0131] The dataset S is preprocessed, including data augmentation, normalization, and standardization operations, to improve the generalization ability of the model.

[0132] Historical cross-sectional area function of superplastic forming mold: s n (x) can be retrieved by the administrator from the host server. This embodiment does not limit the historical cross-sectional area data for different superplastic forming molds; the administrator can retrieve the corresponding parameters from the host database.

[0133] The historical hydraulic extrusion pressure output by the superplastic forming machine used: p n Based on historical data, hydraulic control parameters can be obtained from the output control records of the hydraulic system to reflect the hydraulic pressure output in different mold cavities.

[0134] The corresponding hydraulic pressure control parameters can be directly scheduled based on the historical mold cavity structure to determine the aforementioned dataset S.

[0135] The collection of dataset S is specifically completed with the cooperation of the administrator.

[0136] 3.2. Model Design

[0137] Choose the CNN model architecture: ResNet;

[0138] Adjust the model parameters according to the task requirements, including the number of convolutional layers, the size of the convolutional kernel, and the size of the pooling layer.

[0139] The training and learning of the convolutional neural network model will not be described in detail in this embodiment.

[0140] 3.3. Loss Function and Optimizer Selection

[0141] Choose a loss function that suits the task requirements, such as cross-entropy loss function for classification tasks and mean squared error loss function for regression tasks.

[0142] Choose an appropriate optimizer, such as stochastic gradient descent (SGD) or Adam, and set the learning rate;

[0143] 3.4. Training Process

[0144] The dataset is divided into a training set and a validation set for training and validating the model;

[0145] Initialize model parameters;

[0146] The training loop includes steps such as forward propagation, loss calculation, backpropagation, and parameter update.

[0147] After each training cycle, the model's performance is evaluated using the validation set, and the best model is saved.

[0148] 3.5. Verification and Testing

[0149] Use a validation set to validate the model and ensure that it performs well on unseen data.

[0150] Use the test set to test the model and evaluate its generalization ability;

[0151] 3.6. Parameter Adjustment and Improvement

[0152] Based on the validation and testing results, adjust the model parameters and optimizer parameters to improve the model's performance;

[0153] 3.7. Deployment and Application

[0154] The trained model is deployed to the host server, such as an image classifier or object detector.

[0155] The model is fine-tuned based on the actual application scenario to improve its practicality;

[0156] 3.8. Monitoring and Maintenance

[0157] Monitor the performance of the model to ensure it remains stable over a long period of time;

[0158] The model should be updated and maintained regularly to adapt to new data distributions and task requirements.

[0159] As an optional embodiment of this application, optionally, based on the cavity surface parameters s(x) of the superplastic forming mold, a preset pressure parameter prediction model is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x), including:

[0160] The host server receives and forwards the cavity surface parameters s(x) to the pressure parameter prediction model;

[0161] The pressure parameter prediction model identifies the cavity surface parameter s(x) and outputs the hydraulic extrusion pressure p of the superplastic forming machine that matches the cavity surface parameter s(x) from the learned parameters.

[0162] The host server receives and forwards the hydraulic extrusion pressure p to the hydraulic system of the superplastic forming machine.

[0163] As an optional embodiment of this application, optionally, a compensation coefficient α is configured for the hydraulic extrusion pressure p, including:

[0164] Based on the cavity surface parameters s(x), find the historical hydraulic extrusion pressure output by the superplastic forming machine: p n ;

[0165] The hydraulic extrusion pressure p output by the pressure parameter prediction model in this instance is compared with the historical hydraulic extrusion pressure: p n By comparing the two pressure values, the difference between them can be determined: δp;

[0166] Based on the difference δp, the compensation coefficient α is determined such that:

[0167] p n =α*p;

[0168] Perform the conversion so that:

[0169] Px = p n ;

[0170] Further conversion makes:

[0171] Px = α*p.

[0172] Based on Px, generate the corresponding pressure curve P(t); let P(t) = β*Px, where β is a manual control coefficient set by the administrator;

[0173] The pressure curve P(t) is configured in the hydraulic system controller of the superplastic forming machine, and the working pressure output of the hydraulic system is controlled with reference to the pressure curve P(t).

[0174] The training, learning, and deployment of the above models can be understood in conjunction with CNN models.

[0175] Obviously, those skilled in the art should understand that implementing all or part of the processes in the above embodiments can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the control embodiments described above. Those skilled in the art will understand that implementing all or part of the processes in the above embodiments can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the control embodiments described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0176] Example 2

[0177] like Figure 6 As shown, based on the implementation principle of Embodiment 1, this application, in another aspect, proposes a system for implementing the hydraulic balance control method of the superplastic forming machine, comprising:

[0178] The data acquisition module is used to obtain the cavity surface parameters s(x) of the superplastic forming mold;

[0179] The pressure prediction module is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x) of the superplastic forming mold using a preset pressure parameter prediction model.

[0180] A configuration module is used to configure a compensation coefficient α for the hydraulic extrusion pressure p:

[0181] Px = α*p,

[0182] Where α is the compensation coefficient, which is used to compensate for the lag pressure caused by the system when the superplastic forming machine outputs hydraulic pressure, so as to achieve hydraulic balance compensation;

[0183] The curve generation module is used to generate a corresponding pressure curve P(t) based on the hydraulic extrusion pressure p;

[0184] The data interface module is used to configure the pressure curve P(t) into the hydraulic system controller of the superplastic forming machine, and control the working pressure output of the hydraulic system with reference to the pressure curve P(t).

[0185] Please refer to Example 1 for the functions and specific interaction processes of the above modules.

[0186] The modules or steps of the present invention described above can be implemented using a general-purpose computing system. They can be centralized on a single computing system or distributed across a network of multiple computing systems. Optionally, they can be implemented using program code executable by a computing system, thereby storing them in a storage system for execution by the computing system, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps into a single integrated circuit module. Thus, the present invention is not limited to any specific hardware and software combination.

[0187] Example 3

[0188] like Figure 7 As shown, further, in another aspect, this application also proposes an electronic device, comprising:

[0189] processor;

[0190] Memory used to store processor-executable instructions;

[0191] The processor is configured to implement the hydraulic balance control method and system for a superplastic forming machine when executing the executable instructions.

[0192] This disclosure discloses an electronic device including a processor and a memory for storing processor-executable instructions. The processor is configured to implement any of the preceding descriptions of a superplastic forming machine hydraulic balancing control method and system when executing the executable instructions.

[0193] It should be noted here that the number of processors can be one or more. Furthermore, the electronic device in this embodiment may also include an input system and an output system. The processor, memory, input system, and output system can be connected via a bus or other means, without specific limitations herein.

[0194] As a computer-readable storage medium, the memory can be used to store software programs, computer-executable programs, and various modules, such as the program or module corresponding to the hydraulic balance control method and system for a superplastic forming machine according to embodiments of this disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0195] The input system can be used to receive input digital numbers or signals. These signals can be key signals related to user settings and function control of the device / terminal / server. The output system can include display devices such as screens.

[0196] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A hydraulic balance control method for a superplastic forming machine, characterized in that, Includes the following steps: Obtain the cavity surface parameters s(x) of the superplastic forming mold; Based on the cavity surface parameters s(x) of the superplastic forming mold, a preset pressure parameter prediction model is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x); A compensation coefficient α is configured for the hydraulic extrusion pressure p: Px=α p, Where α is the compensation coefficient, used to compensate for the lag pressure caused by the system when the superplastic forming machine outputs hydraulic pressure, so as to achieve hydraulic balance compensation; Px is the compensated hydraulic value; Based on Px, the corresponding pressure curve P(t) is generated; The pressure curve P(t) is configured in the hydraulic system controller of the superplastic forming machine, and the working pressure output of the hydraulic system is controlled with reference to the pressure curve P(t).

2. The hydraulic balance control method for a superplastic forming machine according to claim 1, characterized in that, Obtain the cavity surface parameters s(x) of the superplastic forming mold, including: An ultrasonic scanning system was used to scan the cavity structure of the superplastic forming mold to obtain three-dimensional ultrasonic data of the superplastic forming mold; The three-dimensional ultrasonic data of the superplastic forming mold is transmitted to the host server of the superplastic forming equipment, and the three-dimensional ultrasonic data of the superplastic forming mold is preprocessed. After preprocessing, the three-dimensional ultrasound data is imported into a simulation system pre-deployed on the host server for three-dimensional simulation modeling to obtain the corresponding cavity three-dimensional model. Set reference coordinates, generate a cross-sectional view of the cavity 3D model, and construct the cavity surface parameters s(x) of the cross-sectional view based on the cross-sectional area of ​​the cross-sectional view.

3. The hydraulic balance control method for a superplastic forming machine according to claim 2, characterized in that, The method for generating the pressure parameter prediction model includes: 3.

1. Data Collection and Preprocessing Collect a dataset S suitable for the task, including: the historical cross-sectional area function of the superplastic forming die: s n (x), and the historical hydraulic extrusion pressure output by the superplastic forming machine used: p n , S={(s 1 (x),p 1 ),(s 2 (x),p 2 )......(s n (x),p n )}, Among them, (s) 1 (x), p 1 (s) 2 (x), p 2 )......(s n (x), p n ), which represent the cross-sectional area of ​​the superplastic forming molds of different types by the same superplastic forming machine, and the output hydraulic extrusion pressure; The dataset S is preprocessed, including data augmentation, normalization, and standardization operations, to improve the generalization ability of the model. 3.

2. Model Design Choose the CNN model architecture: ResNet; Adjust the model parameters according to the task requirements, including the number of convolutional layers, the size of the convolutional kernel, and the size of the pooling layer. 3.

3. Loss Function and Optimizer Selection Based on the task requirements, select a loss function suitable for the task. Among them, the cross-entropy loss function is used for classification tasks, and the mean squared error loss function is used for regression tasks. Choose an appropriate optimizer and set the learning rate; 3.

4. Training Process The dataset is divided into a training set and a validation set for training and validating the model; Initialize model parameters; The training loop is executed, including forward propagation, loss calculation, backpropagation, and parameter update steps; After each training cycle, the model's performance is evaluated using the validation set, and the best model is saved. 3.

5. Verification and Testing Use a validation set to validate the model and ensure that it performs well on unseen data. Use the test set to test the model and evaluate its generalization ability; 3.

6. Parameter Adjustment and Improvement Based on the validation and testing results, adjust the model parameters and optimizer parameters to improve the model's performance; 3.

7. Deployment and Application Deploy the trained model to the host server; The model is fine-tuned based on the actual application scenario to improve its practicality; 3.

8. Monitoring and Maintenance Monitor the performance of the model to ensure it remains stable over a long period of time; The model should be updated and maintained regularly to adapt to new data distributions and task requirements.

4. The hydraulic balance control method for a superplastic forming machine according to claim 3, characterized in that, Based on the cavity surface parameters s(x) of the superplastic forming mold, a preset pressure parameter prediction model is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x), including: The host server receives and forwards the cavity surface parameters s(x) to the pressure parameter prediction model; The pressure parameter prediction model identifies the cavity surface parameter s(x) and outputs the hydraulic extrusion pressure p of the superplastic forming machine that matches the cavity surface parameter s(x) from the learned parameters. The host server receives and forwards the hydraulic extrusion pressure p to the hydraulic system of the superplastic forming machine.

5. The hydraulic balance control method for a superplastic forming machine according to claim 1, characterized in that, A compensation coefficient α is configured for the hydraulic extrusion pressure p, including: Based on the cavity surface parameter s(x), find the historical hydraulic extrusion pressure output by the superplastic forming machine: p n ; The hydraulic extrusion pressure p output by the pressure parameter prediction model in this instance is compared with the historical hydraulic extrusion pressure: p n By comparing the two pressure values, the difference between them can be determined: δp; Based on the difference δp, the compensation coefficient α is determined such that: p n =α p; Perform the conversion so that: Px=p n Px represents the compensated hydraulic pressure value. Further conversion makes: Px=α p.

6. A system for implementing the hydraulic balance control method for a superplastic forming machine according to any one of claims 1-5, characterized in that, include: The data acquisition module is used to obtain the cavity surface parameters s(x) of the superplastic forming mold; The pressure prediction module is used to determine the hydraulic extrusion pressure p that matches the cavity surface parameters s(x) based on the cavity surface parameters s(x) of the superplastic forming mold using a preset pressure parameter prediction model; A configuration module is used to configure a compensation coefficient α for the hydraulic extrusion pressure p: Px=α p, Where α is the compensation coefficient, which is used to compensate for the lag pressure caused by the system when the superplastic forming machine outputs hydraulic pressure, so as to achieve hydraulic balance compensation; The curve generation module is used to generate the corresponding pressure curve P(t) based on the compensated hydraulic value Px. The data interface module is used to configure the pressure curve P(t) into the hydraulic system controller of the superplastic forming machine, and control the working pressure output of the hydraulic system with reference to the pressure curve P(t).

7. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the hydraulic balance control method for a superplastic forming machine according to any one of claims 1-5 when executing the executable instructions.

Images