Digital twin modeling method of hydraulic forming equipment and consistency optimization method of digital twin modeling method

Abstract

The invention relates to a digital twin modeling method and consistency optimization method of hydraulic forming equipment, and the method comprises the steps: building a digital twin model of the hydraulic forming equipment which comprises terminal forming equipment, a hydraulic driving system and a controller, the digital twin model comprises a multi-body dynamics simulation unit, a hydraulic system simulation unit and a control system simulation unit; operating data of the hydraulic driving system and the terminal forming equipment are acquired through the data acquisition system, and the operating data are input into the hydraulic system simulation unit and the control system simulation unit; the control system simulation unit generates a simulation control signal by adopting feedback control logic based on the operation data and sends the simulation control signal to the controller and the hydraulic system simulation unit; the hydraulic system simulation unit generates a simulation driving signal according to the operation data and the simulation control signal and sends the simulation driving signal to the multi-body dynamics simulation unit, and the multi-body dynamics simulation unit displays the motion condition of the terminal forming equipment based on the simulation driving signal.

Description

Technical Field

[0001] The present application relates to the field of equipment monitoring, and in particular to a digital twin modeling method of hydraulic forming equipment and a consistency optimization method thereof. Background Art

[0002] Hydroforming equipment, a core component of precision manufacturing, is facing increasing demand for integrated forming of high-strength, lightweight materials such as high-strength steel, high-strength aluminum alloys, and titanium alloys. This has led to a gradual increase in the tonnage and force required for these equipment, resulting in the emergence of large-scale equipment ranging from thousands to tens of thousands of tons. These equipment are subject to alternating forces and thermal loads during operation, leading to performance degradation and an increased risk of failure. Therefore, effective online monitoring and fault prediction of hydroforming equipment to ensure stable operation has become a pressing issue.

[0003] Traditional monitoring methods rely on pressure / displacement sensor networks to collect data, building a state analysis of the equipment based on this massive amount of sensor data. Displacement, pressure, and acoustic emission signals are the primary characteristic parameters used to monitor hydraulic system operation. However, state analysis based on signal characteristics inherently has a lag. Furthermore, some hidden faults, such as seal wear, are difficult to effectively capture with sensor data. Furthermore, data-driven monitoring models rely on data quality and quantity, which presents certain limitations. When model performance degrades, equipment parameter adjustment relies on the engineer's experience, resulting in long parameter optimization cycles and difficulty achieving real-time performance calibration. Simulation modeling of hydraulic forming equipment can identify operational issues in real time, but there was a lack of effective and accurate methods for simulation modeling of hydraulic forming equipment. Summary of the Invention

[0004] The present invention provides a digital twin modeling method for hydraulic forming equipment and a consistency optimization method thereof to solve the problem that there is currently a lack of methods that can effectively and accurately simulate and model hydraulic forming equipment.

[0005] In a first aspect, the present invention provides a digital twin modeling method for hydroforming equipment, comprising:

[0006] Constructing a digital twin model of hydroforming equipment, the hydroforming equipment comprising a terminal forming device, a hydraulic drive system, and a controller, the controller being configured to control the hydraulic drive system, and the hydraulic drive system being configured to drive the terminal forming device to move, the digital twin model comprising a multi-body dynamics simulation unit, a hydraulic system simulation unit, and a control system simulation unit for respectively simulating the terminal forming device, the hydraulic drive system, and the controller;

[0007] Collecting the operating data of the hydraulic drive system and the terminal forming device through a data acquisition system, and inputting the operating data into the hydraulic system simulation unit and the control system simulation unit;

[0008] The control system simulation unit generates a simulation control signal using feedback control logic based on the operating data and sends the simulation control signal to the controller and the hydraulic system simulation unit;

[0009] The hydraulic system simulation unit generates a simulation drive signal according to the operating data and the simulation control signal and sends the simulation drive signal to the multi-body dynamics simulation unit. The multi-body dynamics simulation unit displays the movement of the terminal forming device based on the simulation drive signal.

[0010] In a second aspect, the present invention provides a method for optimizing the consistency of a digital twin model, which is used to optimize the digital twin modeling of hydroforming equipment, comprising:

[0011] Obtaining a digital twin model of the hydroforming equipment by the digital twin modeling method of the hydroforming equipment described in the first aspect;

[0012] Performing a Sobol global parameter sensitivity analysis on the digital twin model to obtain highly sensitive internal parameters of the digital twin model;

[0013] The highly sensitive internal parameters are iteratively optimized using a damped least squares algorithm until the estimation error of the digital twin model is less than a target threshold.

[0014] In a third aspect, the present invention provides a hydroforming system comprising:

[0015] Hydroforming equipment and electronic equipment, wherein the electronic equipment is used to execute the digital twin modeling method and consistency optimization method of the hydroforming equipment described in the first aspect.

[0016] Compared with related technologies, the present invention divides hydraulic forming equipment into three parts (terminal forming equipment, hydraulic drive system and controller), models each part separately to obtain three simulation units (multi-body dynamics simulation unit, hydraulic system simulation unit and control system simulation unit), and clarifies the collaborative relationship between the three simulation units, thereby forming a digital twin model of the hydraulic forming equipment as a whole, providing a new digital twin modeling method for hydraulic forming equipment.

[0017] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of the digital twin modeling method for hydroforming equipment provided in this embodiment;

[0019] Figure 2 is an architectural diagram of the hydroforming equipment and its digital twin model in this embodiment;

[0020] Figure 3 is a flow chart of the consistency optimization method of the digital twin model in this embodiment;

[0021] Figure 4 This is a flow chart of the sobol sensitivity analysis method in this embodiment.

[0022] Figure 5 is a flow chart of the damped least squares algorithm in this embodiment. DETAILED DESCRIPTION

[0023] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0024] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (simulation units) is not limited to the listed steps or modules (simulation units), but may include unlisted steps or modules (simulation units), or may include other steps or modules (simulation units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Generally, the character " / " indicates that the related objects are in an "or" relationship. The terms "first," "second," "third," etc. used in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0025] In this embodiment, a digital twin modeling method for hydroforming equipment is provided. Figure 1is a flow chart of the digital twin modeling method for the hydroforming equipment provided in this embodiment, such as Figure 1 As shown, the process includes step S110, step S120, step S130 and step S140.

[0026] Step S110: construct a digital twin model of the hydroforming equipment. Figure 2 The hydraulic forming equipment includes terminal forming equipment, a hydraulic drive system and a controller. The controller is used to control the hydraulic drive system, and the hydraulic drive system is used to drive the terminal forming equipment to move. The digital twin model includes a multi-body dynamics simulation unit, a hydraulic system simulation unit and a control system simulation unit that simulate the terminal forming equipment, the hydraulic drive system and the controller respectively.

[0027] The final forming equipment is the terminal device that performs hydraulic operations. It mainly includes the final hydraulic cylinder, hydraulic mold, and supporting mechanical components. The hydraulic mold is divided into a movable mold and a static mold. The movable mold rotates at the output end of the final hydraulic cylinder. The final hydraulic cylinder drives the movable mold to move the movable mold toward or away from each other. Other mechanical components mainly include the base and column guide rails, which are used to limit the movement trajectory of the movable mold.

[0028] The hydraulic drive system provides oil to the terminal hydraulic cylinder and mainly includes the motor, hydraulic pump, accumulator, oil tank, pipeline, etc. Valves include proportional valves, motor reversing valves, check valves, relief valves, etc.

[0029] The motor controls the hydraulic pump to supply oil to the terminal hydraulic cylinder, while the accumulator recovers oil from the terminal hydraulic cylinder. The hydraulic pump, terminal hydraulic cylinder, and accumulator form an oil supply circuit. The accumulator ensures the stability of the oil supply circuit. The oil supply circuit is equipped with a proportional valve, a check valve, and a relief valve. The proportional valve controls the oil flow in the oil supply circuit, specifically the oil flow between the rod chamber and the rodless chamber in the terminal hydraulic cylinder. The relief valve ensures that the oil pressure in the oil supply circuit is below a safe threshold. The reversing valve enables the change of operating conditions between the stroke and return strokes.

[0030] The controller primarily provides control signals to the hydraulic drive system. These signals primarily include the proportional valve opening signal and the motor speed signal, which are used to control the proportional valve opening and motor speed, respectively. When the proportional valve opening and motor speed change, the motion state of the terminal hydraulic cylinder also changes accordingly.

[0031] In summary, this step primarily utilizes digital twin technology to construct a digital twin model of the hydroforming equipment. For example, Unity3D can be used to create a 3D visualization model and information acquisition interface UI, combined with Simulink to build a dynamic simulation model of the forming equipment. This dynamic simulation model is a multi-domain digital twin model that includes a control system simulation unit, a multi-body dynamics simulation unit, and a hydraulic system simulation unit. This allows for real-time simulation of the operating status of the hydroforming equipment. Furthermore, the digital twin model allows for real-time control of the operating status of the hydroforming equipment (described in detail later).

[0032] Step S120: collecting operating data of the hydraulic drive system through the data acquisition system, and inputting the operating data into the hydraulic system simulation unit and the control system simulation unit.

[0033] The data acquisition system includes several pressure sensors and displacement sensors. These pressure sensors are installed inside the terminal hydraulic cylinder, proportional valve, one-way valve, relief valve, and reversing valve, respectively, and are used to obtain pressure data at the corresponding installation locations. Specifically, they obtain pressure data for the rodless and rod-loaded cavities in the terminal hydraulic cylinder, as well as pressure data within each valve. The displacement sensor is installed inside the terminal hydraulic cylinder and is used to obtain displacement and velocity data of the piston within the terminal hydraulic cylinder. Operational data includes pressure data from several pressure sensors, displacement and velocity data from the displacement sensors, and speed signal data from the motor. The pressure data inside the terminal hydraulic cylinder includes pressure data for both the rod-loaded and rodless cavities of the terminal hydraulic cylinder.

[0034] Specifically, the data acquisition system should also include data acquisition cards, communication cables, etc. The data acquisition cards are used to read the operating data and transmit the operating data to the host computer through the communication cables. These operating data include the data detected by each sensor and the speed signal data of the motor. These data acquisition cards are respectively AI receiving cards for pressure / displacement sensors, communication cards for DI / O signals such as reversing valves and hydraulic element switches, and AO output cards for proportional valves. Several data acquisition cards are connected to the host computer through communication cables. The host computer is an electronic device that executes the digital twin modeling method and consistency optimization method of the hydraulic forming equipment in this embodiment.

[0035] In step S130 , the control system simulation unit generates a simulation control signal using feedback control logic based on the operating data and sends the simulation control signal to the controller and the hydraulic system simulation unit.

[0036] In step S140 , the hydraulic system simulation unit generates a simulation drive signal according to the operation data and the simulation control signal and transmits the simulation drive signal to the multi-body dynamics simulation unit. The multi-body dynamics simulation unit displays the movement of the terminal forming device based on the simulation drive signal.

[0037] In the above two steps, the control system simulation unit will generate a simulation control signal based on the operating data of the hydraulic drive system and the terminal forming equipment, and the controller will control the hydraulic drive system through the simulation control signal. Since the simulation control signal is generated based on the feedback control logic (for example, the feedback control logic can adopt PID control logic), the hydraulic forming equipment can be operated in the expected state. At the same time, the simulation control signal will be given to the hydraulic system simulation unit, and the simulation control signal will simulate the operating state of the hydraulic drive system, and provide the simulation drive signal to the multi-body dynamics simulation unit, so that the multi-body dynamics simulation unit can simulate the operating state of the terminal forming equipment, which is convenient for the user to observe the operating status of the simulated terminal forming equipment in real time. The simulation drive signal is specifically the operating index of the terminal hydraulic cylinder in the terminal forming equipment, such as the displacement and speed of the piston in the terminal hydraulic cylinder.

[0038] The specific construction steps of each part of the digital twin model are introduced below.

[0039] Building a digital twin model of hydroforming equipment includes:

[0040] In step S111, a feedback control module is constructed in Simulink to obtain a control system simulation unit. The feedback control module is used to implement feedback regulation and output a simulation control signal according to the difference between the operating data and the target data.

[0041] The simulation control signal includes a valve opening control signal of the proportional valve and a speed control signal of the motor.

[0042] Specifically, the feedback control module includes a motor drive control module (for outputting motor speed control signals) that generates valve-controlled feedback signals, and a proportional valve opening control signal module (for outputting proportional valve opening control signals). The difference between the operating data and the target data includes the displacement, velocity, and pressure of the piston in the terminal hydraulic cylinder of the final forming equipment. Feedback control can be used to regulate the pressure and flow of the hydroforming equipment to correct the piston displacement and velocity curves.

[0043] Step S112: Based on the principle diagram of the hydraulic drive system, a hydraulic system simulation unit is established using Simscape.

[0044] Specifically, the components that require simulation modeling include hydraulic pumps, terminal hydraulic cylinders, pipelines, accumulators, proportional valves, relief valves, check valves, and oil tanks. Fluid transmission between hydraulic components is simulated through pipelines and connectors, and pressure / displacement sensor models are integrated to enable real-time monitoring.

[0045] In step S113, the assembly model is converted into an XML file using the Simscape Multibody Link model conversion plug-in, based on the size, structure, and shape of each component in the terminal forming device, as well as the physical constraints between these components. The conversion command is then run in MATLAB or Simulink, which recognizes the XML file and converts it into an SLX program file. The physical constraints of the terminal forming device and the world space coordinate system are configured in the SLX program file. The kinematic constraints between the components are then linked using at least one of the Prismatic Joint, Revolute Joint, and Cylindrical Joint constraint modules in Simulink, resulting in a multibody dynamics simulation unit. The XML file includes the dimensional parameters of the 3D models of each component in the terminal forming device. These components include the terminal hydraulic cylinder, base, upper slide (upper mold), lower slide (lower mold), column guide rails, and the dimensional parameters of the piston rod length, cylinder bore diameter, piston, and seal within the terminal hydraulic cylinder. The kinematic constraints between these components and within the terminal hydraulic cylinder, as well as the spatial gravity constraints, are also included.

[0046] Step S114: The multibody dynamics simulation unit is coupled to the simulation drive signal through the Translational Multibody Interface (TMI) module. This coupling enables the multibody dynamics simulation unit to recognize the simulation drive signal and perform motion simulation of the terminal forming device based on the simulation drive signal.

[0047] In summary, in the entire digital twin model, the input parameters of the hydraulic system simulation unit are first defined based on the control logic and the obtained control parameters of the control system simulation unit. The input parameters include the proportional valve port opening control voltage signal, the motor drive speed signal, and the displacement curve feedback control signal obtained through the sensor data and the displacement correction logic control module. The hydraulic system simulation unit drives the multi-body dynamics simulation unit of the hydraulic forming equipment according to the input control parameters.

[0048] The following is an example explanation of the signal transmission between the various simulation units and the hydroforming equipment in the digital twin model.

[0049] First, the real-time pressure and displacement data collected by the sensor are transmitted to the Simulink-realtime control system simulation unit and the hydraulic system simulation unit through the PCI bus and the data acquisition card.

[0050] Then, the control instructions output by the Simulink control system simulation unit are transmitted back to the controller of the hydroforming equipment to execute the control logic, and the proportional valve port opening voltage control signal and the motor speed signal output by the control system simulation unit are input to the hydraulic system simulation unit. The hydraulic system simulation unit obtains the hydraulic drive signal and inputs it to the multi-body dynamics simulation unit to complete the hydraulically driven dynamic motion, realizing real-time linkage between the hydroforming equipment and the hydraulic system simulation unit and the multi-body dynamics simulation unit.

[0051] Finally, the motion state of the multibody dynamics simulation unit is displayed using a Unity3D 3D visualization model. This Unity3D 3D visualization model uses the UDP protocol to implement data exchange between the Simulink control system simulation unit and the Unity3D monitoring interface, establishing a host computer human-computer interaction interface. A UDP communication module is embedded in Unity3D. A C# script is used to define multiple threads to receive Simulink's unit8 byte vectors and dispatch them to the main thread. This thread parses the string data and uses Mathf.Lerp to calculate the interpolated position. This drives the update of the Unity piston scene position, integrating data acquisition, virtual-reality interaction, remote operation, and real-time monitoring to achieve visual monitoring of operational status.

[0052] The above summarizes the overall process of the digital twin modeling method for hydroforming equipment. It is used to construct a digital twin model of hydroforming equipment. The hydroforming equipment includes a terminal forming device, a hydraulic drive system, and a controller. The digital twin model comprises a multibody dynamics simulation unit, a hydraulic system simulation unit, and a control system simulation unit, which respectively simulate the terminal forming device, the hydraulic drive system, and the controller. In the digital twin model, operating data from the hydraulic drive system and the terminal forming device is collected via a data acquisition system and input into the hydraulic system simulation unit and the control system simulation unit. The control system simulation unit then uses feedback control logic based on the operating data to generate simulated control signals and transmits them to the controller and the hydraulic system simulation unit. The hydraulic system simulation unit then generates simulated drive signals based on the operating data and the simulated control signals and transmits them to the multibody dynamics simulation unit. The multibody dynamics simulation unit then displays the motion of the terminal forming device based on the simulated drive signals. Therefore, this embodiment provides a new digital twin modeling method for hydraulic forming equipment, which divides the hydraulic forming equipment into three parts (terminal forming equipment, hydraulic drive system and controller), and models each part separately to obtain three simulation units (multi-body dynamics simulation unit, hydraulic system simulation unit and control system simulation unit), and clarifies the collaborative relationship between the three simulation units, thereby forming a digital twin model of the hydraulic forming equipment as a whole.

[0053] At the same time, since digital twin technology can simulate small structures in hydraulic forming equipment, such as sealing rings, the digital twin modeling method of hydraulic forming equipment provided in this embodiment can also timely discover some invisible faults in hydraulic forming equipment.

[0054] It should be noted that in order for the digital twin model to accurately simulate the hydroforming equipment, the parameters of the digital twin model can be optimized during the modeling process.

[0055] Therefore, in this embodiment, referring to Figure 3 , also provides a consistency optimization method for a digital twin model, which is used to optimize the digital twin modeling of hydroforming equipment, including:

[0056] Step S210: Obtain a digital twin model of the hydroforming equipment through the digital twin modeling method of the hydroforming equipment in this embodiment.

[0057] Step S220: Perform a Sobol global parameter sensitivity analysis on the digital twin model to obtain a highly sensitive internal parameter set of the digital twin model.

[0058] Reference Figure 4 Specifically, the internal parameters β0 of each digital twin model in the hydroforming equipment can be defined, and the upper and lower limits β of the iterative optimization of the internal parameters can be set through the sobol global parameter sensitivity analysis. min ={β 1m ,...,β jm ,...β Nm} and β max ={β 1M ,...,β jM ,...β NM}, and generate a 2N-dimensional extended parameter space β min ={β 1m ,...,β jm ,...β Nm ,β (N+1)m ,...,β 2Nm} and β max ={β 1M ,...,β jM ,...β NM ,β (N+1)M ,...,β 2NM}, the number of samples is α, the extended parameter space will be used to filter out the sample matrix R, split R and transform it, the first N columns of matrix R are set to matrix A, the last N columns are set to B, and the α*N mixing matrix AB is generated by cross permutation i , that is, replace the i-th column of matrix A with the i-th column of matrix B, and get A, B, AB1, AB2, ..., ABN There are N+2 matrices in total, and finally we get (N+2)*α sets of input data and the corresponding Y value matrix [Y A Y B Y AB1 Y AB2 ······Y ABN ], calculate the first-order influence index S and total effect index ST of the internal parameters of each digital twin model, and determine the highly sensitive internal parameter set β by selecting the top-ranked internal parameters from the internal parameters of each digital twin model based on the values ​​of the first-order influence index and the total effect index. The number of highly sensitive internal parameter sets n is determined by the accuracy level of the digital twin model and the hardware resources used for calculation, and is generally [20% to 100%] of the number of internal parameters. Several internal parameters include piston area, pump displacement, oil viscosity, actuator gain, etc. Selecting a highly sensitive internal parameter set from these parameters for optimization can achieve parameter correction of the coupling between component-level parameters and overall machine performance.

[0059] Step S230: Iteratively optimize the highly sensitive internal parameter set using a damped least squares algorithm until the estimation error of the digital twin model is less than the target threshold. Specifically, it includes:

[0060] A multi-parameter collaborative optimization model is established based on the damped least squares method. The optimization object of the multi-parameter collaborative optimization model is a highly sensitive internal parameter set, and the optimization goal of the multi-parameter collaborative optimization model is to minimize the square of the norm of the objective function:

[0061]

[0062] f i (β) = A obs,i (β)-B vir,i (β)

[0063] Among them, f(β) is the objective function, f i (β) is the objective function value at time i, β is the highly sensitive internal parameter set, A obs,i (β) is the actual value of the physical output at time i, B vir,i (β) is the simulation value of the simulation output at time i. The observed parameters in the output include the rod chamber pressure, rodless chamber pressure and piston displacement of the terminal hydraulic cylinder and the main circuit pressure.

[0064] The iterative formula for the norm square of the objective function is:

[0065]

[0066]

[0067] βk+1 =β k -α(B vir T τ+μ k (β k -β initial ))

[0068] λ=μ k ||β k -β initial || 2

[0069] β k+1 =β k -α(B vir T τ+μ k (β k -β initial ))

[0070]

[0071] Among them, β k and β k+1 are the kth and k+1th generation high-sensitivity internal parameter sets, β initial is the initial high-sensitivity internal parameter set, λ is the dynamic damping factor, α is the learning rate, μ k is a fixed damping factor, A obs is the actual value matrix of the physical output, B vir is the simulation value matrix of the simulation output. In the matrix, P a 、P b , P and X m They represent the actual rod cavity pressure, rodless cavity pressure, main circuit pressure and piston displacement in the hydroforming equipment, respectively. aT 、P bT 、P T and X mT The ij subscripts of the observed parameters in each output indicate that the observed parameter in the output belongs to time i and sensor or measurement position j.

[0072] It should be noted that, unlike the traditional damped least squares method which only uses fixed damping, the damped least squares method in this embodiment introduces an adaptive regularization term λ=μ k ||β k -β0|| 2, with better dynamic balance model accuracy and parameter stability. The process involves matrix operations, gradient descent iterations, and convergence analysis. Since the sensor data contains n time points, the objective function f(β) is a vector of length n f(β)=[f1(β),f2(β),......,f n (β)] T , each element represents the error at the corresponding time point. i (β) = A obs,i (β)-B vir,i (β), and then the norm square of the objective function needs to be minimized.

[0073] Reference Figure 5 , the overall process of the damped least squares method is:

[0074] The objective function is solved by the gradient descent method. At the kth iteration, the current Jacobian matrix J(β k ) and the residual vector R = A obs -B vir β k , update the parameter vector β k+1 =β k -α(B vir T τ+μ k (β k -β0)).

[0075] Where α is the learning rate, which is different from the traditional Δβ k The update of β is dynamically adjusted to ensure the convergence efficiency. When the step size does not meet the conditions, update β k+1 Prepare for the next iteration, but the current iteration still uses β k , when the step size ||Δβ k ||≤ε2(||Δβ k ||+ε2) satisfies or gradient ||g|| ∞ ≤ε1, the optimization is terminated. The iterative process will calculate the gain ratio ρ. When ρ>0, the current Hessian matrix and gradient are determined. When the gradient ||g|| ∞ ≤ε1, end the current iteration, if the gradient threshold is not met, update and reduce μ k Use the Gauss-Newton method to perform new iterations and accelerate convergence. If ρ≤0, update and increase μ k The system is stable by approximating the gradient descent. When the i-th iteration is completed, the current optimal parameter set will be obtained. The internal parameters of the multi-body dynamics simulation unit, hydraulic system simulation unit, and control system simulation unit of the twin model are substituted to optimize and update the digital twin model.

[0076] This embodiment also provides a hydraulic forming system, which includes hydraulic forming equipment and electronic equipment. The electronic equipment is used to execute the digital twin modeling method for the hydraulic forming equipment and the consistency optimization method of the digital twin model provided in this embodiment. In this hydraulic forming system, the electronic equipment serves as the host computer of the hydraulic forming equipment. The data collected by various sensors in the hydraulic forming equipment is uploaded to the electronic equipment. The electronic equipment obtains a digital twin model by executing the digital twin modeling method for the hydraulic forming equipment, optimizes the parameters of the digital twin model, and finally monitors the hydraulic forming equipment in real time. It should be noted that monitoring refers to simulating the operation process of the hydraulic forming equipment through the digital twin model, so that operational problems of the forming equipment can be discovered in a timely manner.

[0077] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0078] Obviously, the accompanying drawings are merely examples or embodiments of the present application. A person skilled in the art can also apply the present application to other similar situations based on these drawings without inventive effort. Furthermore, it is understandable that, although the work involved in this development process may be complex and lengthy, certain design, manufacturing, or production changes based on the technical content disclosed in this application are merely routine technical means for a person skilled in the art and should not be considered to constitute a deficiency in the disclosure of the present application.

Claims

1. A digital twin modeling method for hydroforming equipment, characterized in that: include: Constructing a digital twin model of hydroforming equipment, the hydroforming equipment comprising a terminal forming device, a hydraulic drive system, and a controller, the controller being configured to control the hydraulic drive system, and the hydraulic drive system being configured to drive the terminal forming device to move, the digital twin model comprising a multi-body dynamics simulation unit, a hydraulic system simulation unit, and a control system simulation unit for respectively simulating the terminal forming device, the hydraulic drive system, and the controller; Collecting the operating data of the hydraulic drive system and the terminal forming device through a data acquisition system, and inputting the operating data into the hydraulic system simulation unit and the control system simulation unit; The control system simulation unit generates a simulation control signal using feedback control logic based on the operating data and sends the simulation control signal to the controller and the hydraulic system simulation unit; The hydraulic system simulation unit generates a simulation drive signal according to the operating data and the simulation control signal and sends the simulation drive signal to the multi-body dynamics simulation unit. The multi-body dynamics simulation unit displays the movement of the terminal forming device based on the simulation drive signal.

2. The digital twin modeling method for hydroforming equipment according to claim 1, characterized in that: The terminal forming device includes a terminal hydraulic cylinder, and the hydraulic drive system includes a motor, a hydraulic pump, and an accumulator. The motor is used to control the hydraulic pump to supply oil to the terminal hydraulic cylinder, and the accumulator recovers oil from the terminal hydraulic cylinder. An oil supply circuit is formed between the hydraulic pump, the terminal hydraulic cylinder, and the accumulator, and a proportional valve, a relief valve, and a reversing valve are installed in the oil supply circuit. The proportional valve is used to control the oil flow rate of the oil supply circuit, the relief valve is used to ensure that the oil pressure of the oil supply circuit is lower than the safety threshold, and the reversing valve is used to achieve the change of the working conditions of the stroke and return; The data acquisition system includes a plurality of pressure sensors and displacement sensors. The pressure sensors are respectively installed inside the terminal hydraulic cylinder, the proportional valve, the one-way valve, the relief valve, and the reversing valve and are used to obtain pressure data at the corresponding installation positions. The displacement sensor is installed inside the terminal hydraulic cylinder and is used to obtain displacement and speed data of the piston in the terminal hydraulic cylinder. The operation data includes pressure data of the pressure sensors, displacement and speed data of the displacement sensors, and speed signal data of the motor.

3. The digital twin modeling method for hydroforming equipment according to claim 2, characterized in that: The pressure data inside the terminal hydraulic cylinder includes pressure data of the rod chamber and the rodless chamber of the terminal hydraulic cylinder.

4. The digital twin modeling method for hydroforming equipment according to claim 1, characterized in that: The construction of the digital twin model of the hydroforming equipment includes: Building a feedback control module in Simulink to obtain the control system simulation unit, wherein the feedback control module is used to implement feedback control and output the simulation control signal according to the difference between the operating data and the target data; According to the principle diagram of the hydraulic drive system, Simscape is used to establish the simulation model of each hydraulic unit in the hydraulic drive system, and the hydraulic system simulation model is built according to its series and parallel relationship. According to the size, structure and shape of each component in the terminal forming device and the physical constraint relationship between each component, the assembly model is converted into an XML file using the model conversion plug-in Simscape Multibody Link, the conversion instruction is run through MATLAB or Simulink, the XML file is recognized and converted into an SLX program file, the physical constraint relationship and world space coordinate system of the terminal forming device are configured in the SLX program file, and the motion constraint link between each component is performed using at least one constraint module of Prismatic Joint, Revolute Joint, and Cylindrical Joint in Simulink to obtain the multi-body dynamics simulation unit; The coupling between the multi-body dynamics simulation unit and the hydraulic system simulation unit is achieved through a Translational Multibody Interface motion interface conversion module.

5. The digital twin modeling method for hydroforming equipment according to claim 2, characterized in that: The simulation control signal includes a valve opening control signal of the proportional valve and a speed control signal of the motor.

6. A digital twin model consistency optimization method for optimizing digital twin modeling of hydroforming equipment, characterized in that: include: The digital twin model of the hydroforming equipment is obtained by the digital twin modeling method of any one of claims 2 to 5, and the internal parameters of the digital twin model of the hydroforming equipment are obtained, wherein the internal parameters include the internal parameters {β1, ..., β j } and the internal parameters of the control system simulation unit {β j ,...β N }, uniformly expressed as β0={β1,...,β j ,...β N }. Perform a sobol global parameter sensitivity analysis on the internal parameter β0 of the digital twin model, set the upper and lower limits of the N-dimensional internal parameters, and generate an extended parameter space. The extended parameter space will be used to screen out the sample matrix R, split R and transform it to obtain the mixing matrix AB i As input, the corresponding Y value can be obtained, and the first-order impact index and the total effect index S, ST are calculated and sorted, and the highly sensitive internal parameter set β of the digital twin model can be obtained; The highly sensitive internal parameter set β is iteratively optimized by a damped least squares algorithm until the estimation error of the digital twin model is less than a target threshold.

7. The consistency optimization method of the digital twin model according to claim 6 is characterized in that: The high-sensitivity internal parameter set β of the digital twin model obtained by performing the sobol global parameter sensitivity analysis on the internal parameters of the digital twin model includes: Define the internal parameters of each digital twin model in the hydroforming equipment, and set the upper and lower limits β of the iterative optimization of the internal parameters through the sobol global parameter sensitivity analysis. min ={β 1m ,...,β jm ,...β Nm } and β max ={β 1M ,...,β jM ,...β NM }, and generate a 2N-dimensional extended parameter space with a sampling number of α. The extended parameter space will be used to screen out the sample matrix R, split R and transform it. The first N columns of the matrix R are set to matrix A, and the last N columns are set to B. The α*N mixing matrix AB is generated by cross permutation. i , that is, replace the i-th column of matrix A with the i-th column of matrix B, and get A, B, AB1, AB2, ..., AB N There are N+2 matrices in total, and finally (N+2)*α groups of input data and corresponding Y values ​​are obtained. The first-order influence index and the total effect index of the internal parameters of each digital twin model are calculated. According to the values ​​of the first-order influence index and the total effect index, the internal parameters with the highest ranking are selected from the internal parameters of each digital twin model to determine the highly sensitive internal parameter set β. The number n of the highly sensitive internal parameter sets is determined comprehensively by the accuracy level of the digital twin model and the level of hardware resources used for calculation.

8. The consistency optimization method of the digital twin model according to claim 7, characterized in that: The iterative optimization of the highly sensitive internal parameter set β by using a damped least squares algorithm includes: A multi-parameter collaborative optimization model is established based on the damped least squares method. The optimization object of the multi-parameter collaborative optimization model is the highly sensitive internal parameter set β. The optimization goal of the multi-parameter collaborative optimization model is to minimize the square of the norm of the objective function: f i (b)=A obs,i (b)-B vir,i (b) Among them, f(β) is the objective function, f i (β) is the objective function value at time i, β is the highly sensitive internal parameter set, A obs,i (β) is the actual value of the physical output at time i, B vir,i (β) is the simulation value of the simulation output at time i. The observation quantity is used to compare the consistency between the output of the established digital twin model and the output of the terminal forming equipment. It can be determined according to the requirements of digital twin modeling and generally may include the rod chamber pressure, rodless chamber pressure and piston displacement of the terminal hydraulic cylinder and the main circuit pressure, etc.

9. The consistency optimization method of the digital twin model according to claim 7, characterized in that: The iterative formula of the norm square of the objective function is: b k+1 =b k -a(B vir T t+m k (b k -b initial )) λ=μ k ||b k -b initial || 2 b k+1 =b k -a(B vir T t+m k (b k -b initial )) Among them, β k and β k+1 are the kth and k+1th generation high-sensitivity internal parameter sets, β initial is the initial high-sensitivity internal parameter set, λ is the dynamic damping factor, α is the learning rate, μ k is a fixed damping factor, A obs is the actual value matrix of the physical output, B vir The simulation value matrix is ​​the simulation output.

10. A hydroforming system, characterized in that: include: hydroforming equipment and electronic equipment; The electronic device is used to execute the digital twin modeling method of the hydraulic forming equipment described in any one of claims 1 to 9 to obtain a digital twin model of the hydraulic forming equipment, and monitor the hydraulic forming equipment through the digital twin model.

Images