Hydraulic manipulator modeling method and system integrating physical model and data drive

Abstract

The present invention belongs to the field of hydraulic manipulator modeling and provides a method and system for modeling a hydraulic manipulator arm that integrates physical models and data-driven models. The method for modeling a hydraulic manipulator arm that integrates physical models and data-driven models includes virtually decomposing the hydraulic manipulator arm into multiple independent sub-models to decouple the closed-chain structure between the joints and the connecting rods; constructing a hydraulic drive system model for each sub-model, which is then combined with the corresponding sub-model to form a corresponding subsystem; using an embedded neural network model to learn the dynamic characteristics of the hydraulic manipulator arm under different working conditions, and then dynamically compensating each subsystem; combining the dynamic compensation of the subsystem and its corresponding embedded neural network model to construct a dynamic model of the hydraulic manipulator arm. This method can improve the modeling accuracy of the hydraulic manipulator arm and speed up its response speed.

Description

Technical Field

[0001] The present invention belongs to the field of hydraulic mechanical arm modeling, and in particular relates to a hydraulic mechanical arm modeling method and system integrating physical modeling with data driving. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] A hydraulic manipulator is an automated device that relies on hydraulic drive. Composed of multiple connecting rods, joints, and hydraulic actuators, it can perform complex spatial motion and precise tasks. Compared to electric manipulators, hydraulic manipulators have a higher load capacity and fewer electrical components, making them suitable for heavy loads and harsh operating environments. Hydraulic systems are also well-suited for high-risk operating environments, such as those with explosive gases and underwater, due to their ease of achieving explosion-proof and waterproof designs. Currently, hydraulic robots have become a vital tool in coal mining, nuclear power plant maintenance, distribution network inspection, and underwater operations, playing a significant role in reducing operational risks, improving efficiency, lowering costs, and enhancing equipment stability.

[0004] However, the linear hydraulic cylinder and the arm's connecting rods form a closed-loop structure, resulting in a coupling effect between the linear actuator's output force and the multi-link mechanism. This coupling makes precise positioning and motion control of the end-of-arm challenging. Furthermore, hydraulic systems often exhibit significant nonlinear characteristics, such as pressure fluctuations and hysteresis, further complicating the development of a precise control model for hydraulic manipulators. Traditional modeling and control methods for motor-driven manipulators struggle to effectively address the complex dynamics of hydraulic manipulators.

[0005] However, the linear hydraulic cylinders and arm joints of a hydraulic manipulator form a closed-loop structure, resulting in a coupling effect between the output force of the linear actuator and the multi-link mechanism of the arm. This coupling characteristic poses challenges in precise positioning and motion control of the manipulator. Furthermore, hydraulic systems often exhibit significant nonlinear characteristics, such as pressure fluctuations and hysteresis, which further complicate the development of accurate and stable control models. Traditional modeling and control methods for motor-driven manipulators struggle to effectively address the complex dynamic characteristics of hydraulic manipulators. Summary of the Invention

[0006] To address the above technical issues, the present invention provides a hydraulic robotic arm modeling method and system that integrates physical models and data-driven approaches. This hybrid modeling framework, combined with physical and data-driven approaches, enables the establishment of precise dynamic models to improve the accuracy and stability of hydraulically driven robotic arms in specialized tasks.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A first aspect of the present invention provides a hydraulic manipulator modeling method that integrates physical models and data-driven models.

[0009] In one or more embodiments, a method for modeling a hydraulic mechanical arm that integrates a physical model and data-driven operation is provided, including:

[0010] The hydraulic manipulator is virtually decomposed into multiple independent sub-models to decouple the closed chain structure between joints and connecting rods;

[0011] Construct a hydraulic drive system model for each sub-model, and then combine it with the corresponding sub-model to form the corresponding sub-system;

[0012] An embedded neural network model is used to learn the dynamic characteristics of the hydraulic manipulator under different working conditions, and then dynamically compensate each subsystem;

[0013] The dynamic compensation of the subsystems and their corresponding embedded neural network models are combined to construct a dynamic model of the hydraulic manipulator.

[0014] A second aspect of the present invention provides a hydraulic manipulator modeling system that integrates physical models and data-driven models.

[0015] In one or more embodiments, a hydraulic manipulator arm modeling system that integrates physical models and data-driven models includes:

[0016] A hydraulic manipulator virtual decomposition module is used to virtually decompose the hydraulic manipulator into multiple independent sub-models to decouple the closed chain structure between the joints and the connecting rods;

[0017] A hydraulic drive system model building module is used to build a hydraulic drive system model for each sub-model, and then combine it with the corresponding sub-model to form a corresponding subsystem;

[0018] The subsystem dynamic compensation module uses an embedded neural network model to learn the dynamic characteristics of the hydraulic manipulator under different working conditions, and then dynamically compensates each subsystem;

[0019] The dynamic model construction module is used to combine the dynamic compensation of the subsystem and its corresponding embedded neural network model to construct the dynamic model of the hydraulic manipulator.

[0020] A third aspect of the present invention provides a computer-readable storage medium.

[0021] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the above-mentioned method for modeling a hydraulic mechanical arm that integrates a physical model and data-driven operation.

[0022] A fourth aspect of the present invention provides an electronic device.

[0023] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the above-mentioned method for modeling a hydraulic mechanical arm that integrates a physical model and data-driven modeling are implemented.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] (1) The present invention designs a physical-data hybrid dynamics model of the robotic arm by combining virtual decomposition with an embedded neural network. The robotic arm joints are decoupled by virtual decomposition, and the complex mechanical system is divided into multiple simple subsystems. Considering the hydraulic drive model, a complete dynamic model is established for each subsystem, which greatly reduces the complexity of the robotic arm modeling.

[0026] (2) The physical equation embedded neural network proposed in this paper combines the learning ability of neural networks with the dynamic characteristics of differential equations. By embedding a physical dynamic system in a neural network and using inverse dynamics equations to construct a specialized neural network to explicitly encode physical knowledge, the network can not only learn the static characteristics of the data, but also capture and simulate the dynamic changes of the data. In a complex operating environment, it effectively ensures that the dynamics of the robot arm are continuously updated and iterated, and the compensation model is adjusted to adapt to the ever-changing external conditions, thereby improving operating efficiency and safety.

[0027] (3) The physics-data-driven hybrid dynamics model proposed in this invention is reversible and computationally efficient, and can be applied to inverse dynamics algorithms such as feedforward control strategies and feedback linearization control strategies, effectively improving the control performance of the robotic arm operating in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0029] Figure 1 1 is a flow chart of a method for modeling a hydraulic mechanical arm that integrates a physical model and data-driven operation according to an embodiment of the present invention;

[0030] Figure 2 is a virtual exploded structural diagram of a swing hydraulic cylinder driving joint according to an embodiment of the present invention;

[0031] Figure 3 is a virtual exploded structural diagram of a linear hydraulic cylinder driven joint according to an embodiment of the present invention;

[0032] Figure 4 is a schematic diagram of an electronic device according to an embodiment of the present invention;

[0033] Figure 5 This is a structural diagram of an embedded physical information neural network according to an embodiment of the present invention;

[0034] Figure 6 is a flow chart of physical-data driven hybrid modeling according to an embodiment of the present invention;

[0035] Figure 7 It is a structural diagram of a hydraulic manipulator modeling system that integrates physical models and data-driven methods according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0037] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0038] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0039] The existing technology provides a virtual decomposition control method for a flexible hydraulic manipulator that takes nonlinear deformation into account. This method can achieve decoupling of the closed-chain structure of the hydraulic manipulator joints and realize virtual decomposition control of multi-module subsystems. The effect of virtual decomposition depends on parameters such as mass, center of mass, and inertia tensor matrix in dynamics. However, most of these parameters are calculated from computer-aided programs and have significant deviations from the actual manipulator connecting rod and hydraulic cylinder parameters. Although adaptive algorithms are currently available to adjust these parameters, the accurate estimation and real-time updating of these parameters in a dynamically changing environment remains a challenge, making it difficult to meet the requirements for accurate dynamic modeling of hydraulic manipulators with strong nonlinearity and complex coupling characteristics.

[0040] Prior art also offers an adaptive neural network control method for hydraulic manipulators. This method uses a neural network to approximate the uncertainties in the modeling of the hydraulic manipulator and dynamically adjusts the system's control parameters through an adaptive algorithm. However, overfitting the network to the manipulator model training data prevents effective generalization to uncollected data. More importantly, the generated model lacks physical consistency and interpretability, complicating its use for purposes other than simulation (i.e., control and identification).

[0041] This paper aims to propose a hybrid modeling framework that combines physics and data-driven to solve this problem, and to establish an accurate dynamic model to improve the accuracy and stability of the hydraulically driven robotic arm in special operating tasks.

[0042] This paper provides a high-precision modeling method for a hydraulic manipulator arm that integrates physical models with data-driven approaches. This method uses a virtual segmentation method to reduce the dimensionality of a multi-degree-of-freedom manipulator system. To address the impact of unknown parameters on system modeling, such as valve deadband, nonlinear friction, and oil viscosity, a neural network incorporating physical information is used to estimate system states and encode characteristic variables, achieving dynamic nonlinear model compensation. Ultimately, this method achieves high-precision modeling of a multi-degree-of-freedom hydraulic manipulator arm.

[0043] Figure 1 FIG. 1 is a flow chart of a method for modeling a hydraulic mechanical arm that integrates a physical model and data-driven operation in an embodiment of the present invention. Figure 1 The hydraulic mechanical arm modeling method of the embodiment shown in FIG. 1 that integrates the physical model and data-driven modeling may include:

[0044] S101, the hydraulic manipulator is virtually decomposed into multiple independent sub-models to decouple the closed chain structure between the joints and the connecting rods.

[0045] In step S101, virtual decomposition theory is used to perform joint decoupling for the hydraulic manipulator, and different types of virtual cutting points are designed for the swing hydraulic cylinder driven joints and the linear hydraulic cylinder driven joints respectively.

[0046] Among them, a virtual split is added to the rotary joint driven by the swing hydraulic cylinder to decompose it into two independent links, and a coordinate system is added to the end of each link close to the base of the robotic arm, such as Figure 2 shown.

[0047] Coordinate system The generalized velocity at can be obtained by forward iteration of the velocity of the previous part of the virtual split link, then the driving joint Department The generalized speed is:

[0048]

[0049] In the formula is the angular velocity of active joint j, Represents the coordinate system Relative to the coordinate system The transformation matrix, whose function is to transform the coordinate system The generalized force / velocity vectors in the coordinate system are converted to The equivalent force vector in , The bit is a mapping matrix that maps joint angular velocity to generalized velocity.

[0050] Generalized velocity and Substituting into the formula, we can get the force required for each member, and further the internal force relationship of all members of the structure can be obtained as follows:

[0051]

[0052] in Represents the coordinate system The force received by the lower link, Represents the force on the end of the connecting rod, the matrix Represents the transformation matrix representing coordinate system T relative to coordinate system B.

[0053] The required output force of the hydraulic system is: ;in is the output force of the hydraulic cylinder corresponding to the j-th joint.

[0054] For the variable triangle closed chain structure driven by the linear hydraulic cylinder, two virtual divisions are used, such as Figure 3 As shown in the figure, the closed chain structure is first cut into an open chain, and then virtual cutting points are added to the connection between the hydraulic cylinder and the joint, and the cylinder and the piston rod, respectively, to obtain four relatively independent connecting rods.

[0055] In the closed chain structure, the relationship between the joint angle displacement and the linear hydraulic cylinder displacement is as follows:

[0056]

[0057] in and is the length of two adjacent links of the robotic arm, is the effective length of the hydraulic linear actuator at zero piston stroke, is the joint position variable of the j-th joint of the robot arm, is the initial angle value of the j-th joint of the robot arm, 、 is the intrinsic value of the j-th joint of the robot arm.

[0058] The generalized velocity vector in the j-th hydraulic joint can be written as follows:

[0059]

[0060] Where: mapping matrix 、 ; Represents the coordinate system The generalized velocity vector under ; is the connecting rod displacement speed.

[0061] The generalized force relationship in the j-th hydraulic joint is as follows:

[0062]

[0063] Where: is the internal force between the open chain j1 and the open chain j2; α1, α2 are proportional distribution factors, and α1 + α2 = 1; where represents the generalized force received by the end of the connecting rod, Indicates the force acting on the end of the robotic arm. Indicates the force acting on the end of the robotic arm.

[0064] In this embodiment, there are three passive joints and two active joints in the closed chain structure, and the output force required by the hydraulic cylinder is: .

[0065] S102: construct a hydraulic drive system model for each sub-model, and then combine it with the corresponding sub-model to form a corresponding sub-system.

[0066] The flow equation of the hydraulic servo valve is:

[0067]

[0068]

[0069] in: is relative to the valve core displacement flow gain; , and , are the pressure and flow of the rodless chamber and the rod chamber of the hydraulic cylinder respectively; is the oil supply pressure, is the oil return pressure; The selection function is defined.

[0070] During operation, the characteristics of the hydraulic oil remain unchanged, and the pressure in each chamber of the linear hydraulic cylinder is equal. The dynamic equation of pressure-flow in the two chambers can be described as:

[0071]

[0072]

[0073] Where: is the elastic modulus of the oil; is the leakage coefficient; is the displacement speed of the hydraulic cylinder; 、 They represent the volume of the rod cavity and the volume of the rodless cavity of the hydraulic linear cylinder respectively; It is the piston area of the rod cavity and the piston area of the rodless cavity of the hydraulic linear cylinder.

[0074] Substituting the servo valve flow equation into the hydraulic system physical model can be expressed by the pressure of the two chambers:

[0075]

[0076]

[0077]

[0078]

[0079] Where: is the extension and retraction speed of the hydraulic cylinder; is the servo valve voltage gain, ; The volume of the two chambers of the hydraulic cylinder is , .

[0080] Output driving force of the linear hydraulic cylinder of the jth joint of the robot arm for:

[0081]

[0082] Linear hydraulic cylinder output force The relationship with the output torque is:

[0083]

[0084] in is the length of the linear hydraulic cylinder Joint position variable for the jth joint The differential of

[0085] The swing hydraulic cylinder of the jth joint of the robot arm has an output torque of Related to displacement as follows:

[0086]

[0087] Where: is the displacement of the swing hydraulic cylinder of the jth joint; For the j The true torque of each joint, They represent the first variable of cylinder pressure and the second variable of cylinder pressure respectively.

[0088] S103, using an embedded neural network model to learn the dynamic characteristics of the hydraulic manipulator under different working conditions, and then dynamically compensate each subsystem.

[0089] In order to compensate for the unknown friction force and system modeling errors in the physical model, this embodiment uses an embedded neural network model to dynamically compensate each subsystem.

[0090]

[0091] in is a vector composed of a set of nonlinear basis functions, which is a known physical nonlinear unit; Respectively represent the joint position variable, velocity variable, first cylinder pressure variable and second cylinder pressure variable of the j-th joint collected, Functions represent a series of known mathematical relationships, consisting of squares, radicals, various types of quadratic operations, etc. They are used as custom layers to simulate the basic mathematical combinations of physical nonlinear elements; is the neuron weight coefficient in the neural network; As a hidden bias term, it corresponds to the nonlinear friction of the system.

[0092] Linear friction torque The following friction model is used:

[0093]

[0094] in represents the friction torque of the j-th joint; is the viscous friction coefficient of the jth joint; is the Coulomb friction coefficient of the jth joint; Contains the additional offset of the jth joint caused by the asymmetric Coulomb friction coefficient and sensor noise.

[0095] The specific form of the neural network compensation model can be obtained, such as Figure 5 As shown, its expression is:

[0096]

[0097] Where P represents the number of joint parameters; Represents the weight coefficient between nonlinear mapping functions; Represents the overall nonlinear mapping function; 、 、 Represent the joint variables after nonlinear mathematical transformation The corresponding weight coefficients in the polynomial; Represents joint variables The weight coefficient of Represents the joint velocity variable The weight coefficient of and Indicates the weight coefficient corresponding to the hydraulic cylinder pressure; Indicates the coefficient of viscous friction in the hydraulic system; represents the Coulomb friction coefficient; represents the position noise coefficient; the subscript j represents the j-th joint.

[0098] In order to improve the performance of the neural network, a custom loss function is designed that takes into account both neuron parameters and the physical weights of the system, as shown in the following formula:

[0099]

[0100] in, is the loss function of the embedded neural network model; is the total number of joint points; For the j The true torque of each joint; For the j Predicted torques for each joint; is the corresponding polynomial weight coefficient; is a physical nonlinear function, Represents the collected j The first half is the mean square error between the predicted torque and the actual torque, and the second half is the physical formula related to the robot arm.

[0101] S104, combining the dynamic compensation of the subsystem and its corresponding embedded neural network model to construct a dynamic model of the hydraulic manipulator.

[0102] For a given multi-DOF manipulator model, the dynamic equation of the link represented by the j-th joint in its fixed branch coordinate system Aj (i.e., the Newton-Euler equation) can be written as follows:

[0103]

[0104] in , Represent the branched coordinate system Inertia matrix, Coriolis force matrix and gravity matrix, represents the torque required by the robotic arm, are linear velocity and angular velocity vectors respectively.

[0105] The torque required by the j-th joint of the robotic arm Can be driven by hydraulic torque and friction torque and unknown modeling errors. According to the proposed method, the dynamic model of the multi-degree-of-freedom manipulator can be written as follows. Its specific structure is as follows: Figure 6 As shown:

[0106]

[0107] in Expressed in the branched coordinate system Compensation torque in

[0108] Reference Figure 4 , a schematic diagram of an electronic device is given. It should be noted that, Figure 4 The electronic device 400 shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0109] like Figure 4 As shown, electronic device 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to programs stored in read-only memory (ROM) 402 or programs loaded from storage unit 408 into random access memory (RAM) 403. Various programs and data required for system operation are also stored in RAM 403. Central processing unit 401, ROM 402, and RAM 403 are connected to each other via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0110] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 408 including devices such as a hard disk; and a communication section 409 including a network interface card such as a local area network (LAN) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read from the removable media can be installed in the storage section 408 as needed.

[0111] When the central processing unit 401 in the electronic device of this embodiment executes the program, the following is achieved: Figure 1 The steps in the modeling method of a hydraulic manipulator arm that integrates physical models and data are shown.

[0112] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, the computer program including a computer program for executing Figure 1 In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409 and / or installed from the removable medium 411. When the computer program is executed by the central processing unit 401, the various functions defined in the apparatus of the present application are performed.

[0113] in, Figure 1 The computer program instructions corresponding to the method shown can also be stored in a computer readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0114] Figure 7 This is a structural diagram of a hydraulic manipulator modeling system that integrates physical models and data-driven in an embodiment of the present invention. Figure 1 The fusion physical model of corresponds to the data-driven hydraulic manipulator modeling method, such as Figure 7 As shown, the hydraulic manipulator modeling system integrating physical model and data-driven in this embodiment may include:

[0115] A hydraulic manipulator virtual decomposition module 701 is used to virtually decompose the hydraulic manipulator into multiple independent sub-models to decouple the closed chain structure between the joints and the connecting rods;

[0116] A hydraulic drive system model building module 702 is used to build a hydraulic drive system model for each sub-model, and then combine it with the corresponding sub-model to form a corresponding sub-system;

[0117] The subsystem dynamic compensation module 703 is used to use an embedded neural network model to learn the dynamic characteristics of the hydraulic manipulator under different working conditions, and then perform dynamic compensation on each subsystem;

[0118] The dynamic model construction module 704 is used to combine the dynamic compensation of the subsystem and its corresponding embedded neural network model to construct a dynamic model of the hydraulic manipulator.

[0119] It should be noted here that, Figure 7 The fusion physical model in the data-driven hydraulic manipulator modeling system is combined with the various modules in the data-driven hydraulic manipulator modeling system. Figure 1 The fusion physical model in corresponds one to one with each step in the data-driven hydraulic robot arm modeling method, and the specific implementation process is the same, which will not be repeated here.

[0120] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0121] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A hydraulic manipulator modeling method integrating physical model and data drive, characterized in that: include: The hydraulic manipulator is virtually decomposed into multiple independent sub-models to decouple the closed chain structure between joints and connecting rods; The virtual decomposition theory is used to decouple the joints of the hydraulic manipulator, and different types of virtual cutting points are designed for the swing hydraulic cylinder driven joints and the linear hydraulic cylinder driven joints respectively. A virtual split was added to the rotary joint driven by the swing hydraulic cylinder, decomposing it into two independent links. A coordinate system was added to the end of each link close to the base of the robotic arm. For the variable triangular closed chain structure driven by the linear hydraulic cylinder, two virtual splits were applied: first, the closed chain structure was cut into an open chain, and then virtual cutting points were added to the connection between the hydraulic cylinder and the joint, and between the cylinder and the piston rod, respectively, to obtain four independent links. Construct a hydraulic drive system model for each sub-model, and then combine it with the corresponding sub-model to form the corresponding sub-system; The embedded neural network model is used to learn the dynamic characteristics of the hydraulic manipulator under different working conditions, and then dynamically compensate each subsystem; the input of the embedded neural network model is: j The joint position variable, velocity variable, cylinder pressure first variable and cylinder pressure second variable of each joint; the output is: compensation torque; The dynamic compensation of the subsystems and their corresponding embedded neural network models are combined to construct a dynamic model of the hydraulic manipulator; The loss function of the embedded neural network model is: in, is the loss function of the embedded neural network model; is the total number of joint points; For the j The true torque of each joint; For the j Predicted torques for each joint; is the corresponding polynomial weight coefficient; is a physical nonlinear function, Represents the collected j The joint position variable, velocity variable, cylinder pressure first variable and cylinder pressure second variable of each joint.

2. The method for modeling a hydraulic manipulator arm integrating a physical model and data-driven operation as claimed in claim 1, wherein: The dynamic model of the hydraulic manipulator is expressed as: in , Represent the branched coordinate system Inertia matrix, Coriolis force matrix and gravity matrix, denote the linear velocity and angular velocity vectors respectively, For the j The true torque of each joint, Expressed in the branched coordinate system The compensation torque in .

3. The method for modeling a hydraulic mechanical arm integrating a physical model and data-driven operation as claimed in claim 2, wherein: In the branched coordinate system The expression of the compensation torque in is: Where P represents the number of joint parameters; Represents the weight coefficient between nonlinear mapping functions; Represents the overall nonlinear mapping function; 、 、 Respectively represent the joint position variables of the j-th joint after nonlinear mathematical transformation The corresponding weight coefficients in the polynomial; Represents the joint position variable of the jth joint The weight coefficient of Represents the joint velocity variable of the jth joint The weight coefficient of Indicates the weight coefficient corresponding to the first variable of cylinder pressure; Represents the weight coefficient corresponding to the second variable of cylinder pressure; Indicates the coefficient of viscous friction in the hydraulic system; represents the Coulomb friction coefficient; Represents the position noise factor.

4. A hydraulic manipulator modeling system integrating physical model and data drive, characterized in that: include: A virtual decomposition module for hydraulic manipulators, which is used to virtually decompose the hydraulic manipulator into multiple independent sub-models to decouple the closed-chain structure between joints and connecting rods. The module uses virtual decomposition theory to decouple the joints of the hydraulic manipulator, designing different types of virtual cutting points for the swing hydraulic cylinder-driven joints and the linear hydraulic cylinder-driven joints. A virtual split was added to the rotary joint driven by the swing hydraulic cylinder, decomposing it into two independent links. A coordinate system was added to the end of each link close to the base of the robotic arm. For the variable triangular closed chain structure driven by the linear hydraulic cylinder, two virtual splits were applied: first, the closed chain structure was cut into an open chain, and then virtual cutting points were added to the connection between the hydraulic cylinder and the joint, and between the cylinder and the piston rod, respectively, to obtain four independent links. A hydraulic drive system model building module is used to build a hydraulic drive system model for each sub-model, and then combine it with the corresponding sub-model to form a corresponding subsystem; The subsystem dynamic compensation module is used to learn the dynamic characteristics of the hydraulic manipulator under different working conditions using an embedded neural network model, and then perform dynamic compensation on each subsystem; the embedded neural network model input is: j The joint position variable, velocity variable, cylinder pressure first variable and cylinder pressure second variable of each joint; the output is: compensation torque; A dynamic model building module, which is used to combine the dynamic compensation of the subsystems and their corresponding embedded neural network models to build a dynamic model of the hydraulic manipulator; The loss function of the embedded neural network model is: in, is the loss function of the embedded neural network model; is the total number of joint points; For the j The true torque of each joint; For the j Predicted torques for each joint; is the corresponding polynomial weight coefficient; is a physical nonlinear function, Represents the collected j The joint position variable, velocity variable, cylinder pressure first variable and cylinder pressure second variable of each joint.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for modeling a hydraulic mechanical arm that integrates a physical model and data-driven operation are implemented as described in any one of claims 1 to 3.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for modeling a hydraulic mechanical arm that integrates a physical model and data-driven operation are implemented as described in any one of claims 1 to 3.

Images