Mechanical arm digital twinning system for deep space exploration

Abstract

The invention discloses a mechanical arm digital twinning system for deep space exploration, and relates to the technical field of digital twinning simulation. The mechanical arm comprises a physical layer, a data acquisition and transmission layer, a digital twin model layer and an application layer, the physical layer comprises a mechanical arm body and a sensor network, and the sensor network is used for acquiring operation state information of the mechanical arm body; the data acquisition and transmission layer comprises data acquisition equipment and a data transmission network, wherein the data acquisition equipment is respectively connected with the sensor network and the data transmission network. According to the invention, the physical layer, the data acquisition and transmission layer, the digital twinborn model layer and the application layer of the mechanical arm are constructed, so that the actual mechanical arm body can be guided to perform related actions through virtual simulation data, and virtual and real body configuration comparison can be completed through a visual interface; and the digital twinning requirements of various spacecraft operations in the future deep space exploration field are met.

Description

Technical Field

[0001] The present invention relates to the field of BB technology, and in particular to a digital twin system of a robotic arm for deep space exploration. Background Art

[0002] Digital twin technology is a technology that interacts with the actual system in real time through digital models. Through digital twin technology, a virtual model that is highly consistent with the real robot arm can be built and simulated and optimized in a virtual environment. This technology can provide a highly controllable environment, allowing engineers and researchers to test and optimize the robot arm safely, economically and efficiently.

[0003] The existing digital twin system is not accurate and intelligent enough in terms of robotic arm twin control, and cannot achieve a high degree of restoration of its motion state, nor is it easy to perform friendly human-computer interaction control, and does not have intelligent motion control functions based on the arm's historical data and operating status. Based on the deep space exploration mission scenario, the present invention can overcome these defects by building a specific system architecture and using relevant algorithms, achieving more accurate control, higher intelligence, and better human-computer interaction effects.

[0004] To this end, we propose a digital twin system of a robotic arm for deep space exploration. Summary of the invention

[0005] The purpose of the present invention is to provide a digital twin system of a robotic arm for deep space exploration to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: A digital twin system of a manipulator for deep space exploration, comprising a physical layer, a data acquisition and transmission layer, a digital twin model layer and an application layer, wherein the physical layer comprises a manipulator body and a sensor network, wherein the sensor network is used to collect operating status information of the manipulator body;

[0007] The data acquisition and transmission layer includes a data acquisition device and a data transmission network, wherein the data acquisition device is connected to the sensor network and the data transmission network respectively, and the data acquisition device is used to convert the operating status information collected by the sensor network into an electrical signal and transmit it to the data transmission network for storage;

[0008] The digital twin model layer includes a geometric model construction module, a physical model construction module and a model calibration and verification module. The geometric model construction module is used to create a high-precision geometric model of the robotic arm body. The physical model construction module is used to build a physical model of the robotic arm body based on the geometric model in combination with the dynamics, kinematics principles and material properties of the robotic arm body. The model calibration and verification module is used to perform precision calibration on the constructed geometric model and physical model according to the actual operating status data of the robotic arm obtained by the data acquisition and transmission layer.

[0009] The application layer is specifically a visualization module, which is connected to the data acquisition and transmission layer and the digital twin model layer, and is used to receive the operating status information of the robotic arm body and display the motion trajectory, workspace range and currently executed task information of the robotic arm body in real time.

[0010] Furthermore, the sensor network is installed on the robot body, and the sensor network includes joint position sensors, force sensors, vision sensors, and speed sensors.

[0011] Furthermore, the data acquisition device is used to condition, sample and digitize the analog signals collected by the sensor network to convert them into a digital format suitable for network transmission. The data acquisition device is specifically configured as an integrated data acquisition card, and the data acquisition device is equipped with a redundant power supply module.

[0012] Furthermore, the data transmission network uses a standard network transmission protocol to transmit the collected data from the physical layer to the digital twin model layer.

[0013] Furthermore, the geometric model and the physical model are deeply connected through multi-dimensional and multi-level data interaction links and adaptation interfaces to realize digital twin control, as follows:

[0014] The physical layer collects the current joint angle, angular velocity, force magnitude and direction, and real-time spatial posture operation data of the physical model, and transmits it to the digital twin model layer where the geometric model is located through the data acquisition and transmission layer in accordance with the defined data format and transmission protocol, so that the geometric model reproduces the current morphological position of the physical model in space.

[0015] Furthermore, the modeling deduction and twin simulation in the model calibration and verification module are implemented using Solidworks and Matlab Simulink platforms, as follows:

[0016] (1) Constructing the model assembly: Using Solidworks to design the robot arm assembly;

[0017] (2) Generate geometric model URDF file;

[0018] (3) Specific methods for building twin models;

[0019] (4) Construction of twin control interface.

[0020] Furthermore, Solidworks was used to design the robot arm assembly, as follows:

[0021] (71) First, in the top-down design stage, the overall structure and structural strength distribution of the robot arm are planned, and the layout of each joint of the robot arm, the shape of the connecting rod and the top-level framework of the end effector are designed;

[0022] (72) Then switch to the bottom-up design stage, create the basic components of the robotic arm one by one, and use Solidworks to design the part structure, including the joint housing, connecting rod structure, and sensor structure;

[0023] (73) During the assembly phase, the matching accuracy and motion interference of each component are dynamically verified, and the assembly relationship is corrected in real time.

[0024] Furthermore, the specific method of generating the geometric model URDF file is as follows:

[0025] (81) After completing the construction of the robotic arm assembly in Solidworks, the Solidworks and URDF conversion plug-in or conversion script is used to realize the innovative conversion from Solidworks assembly data to URDF format;

[0026] (82) During the conversion process, for each part and connecting component of the robotic arm, in addition to the conventional geometry, size, and mass attribute information, the functional role, reliability requirements, and environmental adaptability characteristics of each component in deep space exploration are integrated into the URDF file;

[0027] (83) Characterize the flexible connection characteristics between connected parts in the URDF file, including simulating the elastic deformation, damping effect, and connection stiffness at the joints;

[0028] (84) Embed intelligent data tags in the URDF file to automatically update the status information of the corresponding components according to the real-time operation data and simulation results of the robot arm;

[0029] (85) An XML extension-based method is used to add custom elements and attributes in URDF files.

[0030] Furthermore, the specific method of building a twin model is as follows:

[0031] (91) In the Matlab Simulink environment, based on the previously imported robotic arm URDF file, the multi-physics field modeling technology is deeply integrated, and the module library of Simulink is used to build the rigid body dynamics model of the robotic arm. The corresponding physical effect sub-model is constructed for the special environmental factors of deep space exploration. At the same time, the microgravity compensation algorithm is used to compensate and correct the motion deviation of the dynamic model, and the adaptive control algorithm is used to adjust the control parameters in real time, as follows:

[0032] (91.1) The microgravity compensation algorithm is as follows:

[0033] The microgravity compensation algorithm is based on dynamic modeling. The dynamic model of the robotic arm is described as follows:

[0034]

[0035] Where τ is the joint torque, M(q) is the inertia matrix, is the Coriolis force and centrifugal force matrix, G(q) is the gravity compensation term, and F(q) is the friction torque;

[0036] In a microgravity environment, the influence of the gravity compensation term is significantly reduced, and the improved compensation term is expressed as:

[0037] G micro (q) = g micro ·J T (q)m

[0038] In the formula, g micro is the microgravity acceleration, J T is the Jacobian matrix, m is the mass vector of each link of the robot arm;

[0039] (91.2) Adaptive control algorithm, the specific implementation steps are as follows:

[0040] Dynamic modeling: Build a real-time dynamic model of the robot arm to describe the nonlinear relationship between joint torque and angle, velocity, and acceleration;

[0041] Parameter estimation: Estimate model parameters including inertia, friction, and joint stiffness in real time using recursive least squares or gradient descent algorithms;

[0042] Error analysis and feedback: The error function is used to calculate the deviation between the current output and the expected output. The error is defined as: e(t) = x d (t)-x a (t), x d is the expected trajectory, x a is the actual trajectory;

[0043] Control law update: Based on the Lyapunov stability criterion, design the control law: τa =τ n +K e e(t),K e is the error gain matrix, τ n is the nominal value;

[0044] (92) Build an intelligent control architecture based on model predictive control or adaptive control algorithms, tightly coupled with the physical model;

[0045] (93) With the help of Simulink 3D Animation toolbox, the fine geometric model built by SolidWorks is deeply bound to the physical model to render the virtual robotic arm operation scene.

[0046] Furthermore, the specific method of constructing the twin control interface is:

[0047] (101) In the design of twin control interface, multimodal information fusion display is introduced, including position, posture, speed, force, audio, and tactile feedback information;

[0048] (102) Develop an intelligent decision-making support system integrated into the control interface;

[0049] (103) Build adaptive control functions for interfaces to accommodate long-duration missions and high-latency communications for deep space exploration;

[0050] (104) Implementing distributed collaborative control of the interface, allowing multiple operators to access the control interface simultaneously through the network at different locations;

[0051] (105) Establish a multi-level security protection mechanism, including authority authentication and real-time risk assessment of operation commands;

[0052] (106) The system automatically records the operator’s operation history and the robot’s response, analyzes the pros and cons of the operation based on a machine learning algorithm, and provides the operator with suggestions for improving his or her operating skills.

[0053] The present invention has at least the following beneficial effects:

[0054] The present invention completes the construction of the physical layer, data acquisition and transmission layer, digital twin model layer, and application layer of the robotic arm. It can use virtual simulation data to guide the actual robotic arm body to perform related actions, and can complete the comparison of virtual and real body configurations through a visual interface, thereby meeting the digital twin requirements of various spacecraft operations in the field of future deep space exploration.

[0055] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 Schematic diagram of the overall architecture of the digital twin system in an embodiment of the present invention;

[0057] Figure 2 It is a schematic diagram of an assembly for building a robot arm body in an embodiment of the present invention;

[0058] Figure 3 A schematic diagram of the structure of a geometric model in an embodiment of the present invention;

[0059] Figure 4 A schematic diagram of generating a model URDF file in an embodiment of the present invention;

[0060] Figure 5 A schematic diagram of the coordinate system construction and model correction of the geometric model in an embodiment of the present invention;

[0061] Figure 6 A schematic diagram of generating a twin model of a UR5 robotic arm in an embodiment of the present invention;

[0062] Figure 7 This is a schematic diagram of a simulink simulation model of a UR5 robotic arm twin model in an embodiment of the present invention;

[0063] Figure 8 Schematic diagram of the control principle of the UR5 robot arm input controller in an embodiment of the present invention;

[0064] Fig. 9 Schematic diagram of the control principle of the UR5 robot arm actuator in an embodiment of the present invention;

[0065] Fig.10 Schematic diagram of the control principle of the UR5 robot arm output controller in an embodiment of the present invention;

[0066] Fig.11 This is a schematic diagram of the UR5 robotic arm twin control interface based on matlab in an embodiment of the present invention;

[0067] Fig.12 This is a schematic diagram of the digital twin comparison implementation of the UR5 robotic arm in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0069] See also Figure 1-Figure 12, the present invention provides a technical solution: a digital twin system of a robotic arm for deep space exploration, comprising a physical layer, a data acquisition and transmission layer, a digital twin model layer and an application layer, the physical layer comprising a robotic arm body and a sensor network, wherein the sensor network is used to collect operating status information of the robotic arm body;

[0070] The data acquisition and transmission layer includes data acquisition equipment and data transmission network, where the data acquisition equipment is connected to the sensor network and the data transmission network respectively. The data acquisition equipment is used to convert the operating status information collected by the sensor network into electrical signals and transmit them to the data transmission network for storage. The data transmission network uses wired (such as Ethernet) to transmit the collected data from the physical layer to the digital twin model layer;

[0071] The digital twin model layer includes a geometric model construction module, a physical model construction module, and a model calibration and verification module. The geometric model construction module is used to create a high-precision geometric model of the robot body. The physical model construction module is used to build a physical model of the robot body based on the geometric model, combined with the dynamics, kinematics principles and material properties of the robot body. The model calibration and verification module is used to calibrate the constructed geometric model and physical model with the actual operating status data of the robot obtained by the data acquisition and transmission layer to ensure that the model output results are highly consistent with the operating characteristics of the real physical system.

[0072] The application layer is specifically a visualization module, which is connected to the data acquisition and transmission layer and the digital twin model layer. The visualization module provides users with an intuitive and friendly human-computer interaction interface. The interface can display the real-time collection of physical parameters such as the position, speed, acceleration, force, etc. of each joint of the robotic arm, and synchronously update the display in the digital twin model to display the motion trajectory, workspace range and currently executed task information of the robotic arm. It also conducts real-time evaluation of the operating status of the robotic arm, such as whether it is within the normal working range, whether there is abnormal vibration or overload, etc., and promptly issues alarm information.

[0073] According to the technical solution of this embodiment, the sensor network is installed on the robot body. The sensor network includes joint position sensors, force sensors, visual sensors, and speed sensors, which are used to collect physical parameters such as position, speed, acceleration, force, etc. of the operating state of the robot body. The data acquisition equipment is used to condition, sample and digitize the analog signals collected by the sensor network to convert them into a digital format suitable for network transmission. The data acquisition equipment is specifically configured as a multi-channel, high-precision integrated data acquisition card, which has a powerful signal conditioning function module and can accurately remove noise interference, compensate for signal attenuation, and ensure the purity and integrity of the original signal for different types of analog signals transmitted from the sensor network, such as the weak voltage signal of the pressure sensor, the millivolt fluctuation signal of the acceleration sensor, and the analog signal corresponding to the resistance change of the strain gauge.

[0074] The digital processing unit has a built-in high-speed and high-precision analog-to-digital converter (ADC) with a conversion accuracy of up to 24 bits or even higher, achieving seamless, low-error conversion of analog signals to digital signals. The converted data is packaged and encapsulated in accordance with standard network transmission protocols, such as PROFINET, ETHERNET / IP protocol for industrial Ethernet, or Wi-Fi 6 standard protocol for wireless transmission, so as to be efficiently and stably transmitted to the data transmission network, supporting real-time, large-capacity data transmission requirements, meeting the rapid flow of massive operating status data of deep space exploration robotic arms, and ensuring high-quality supply of data sources for the entire digital twin system.

[0075] At the same time, the data acquisition equipment is equipped with a redundant power supply module. Even in the complex and changeable deep space environment, when encountering abnormal conditions such as power fluctuations and short interruptions, it can still operate stably and prevent data loss. It also has its own intelligent self-check program to periodically perform functional checks on each acquisition channel and processing unit. Once a fault is detected, an alarm message is immediately sent to the ground control center through an independent backup communication link to ensure the reliability of the equipment itself and lay the foundation for the continuity of the robotic arm status monitoring.

[0076] Furthermore, the data transmission network uses standard network transmission protocols to transmit the collected data from the physical layer to the digital twin model layer.

[0077] For the technical solution of this embodiment, the geometric model is a simulation model constructed by three-dimensional modeling software (Solidworks or 3Dmax), and the physical model is a UR5 robotic arm. The simulation model and the UR5 robotic arm are jointly subjected to virtual reality twin simulation, and the outputted posture and position data of the robotic arm end are compared. Specifically, the geometric model and the physical model are deeply connected through multi-dimensional and multi-level data interaction links and adapter interfaces to achieve precise digital twin control. At the data interaction level, a real-time two-way data channel is constructed. On the one hand, various sensors densely distributed on the physical model (UR5 robotic arm), such as high-precision encoders at the joints, force sensors and posture sensors on the end effector, continuously transmit the actual physical parameters of the robotic arm at the moment, including joint rotation angle, angular velocity, force magnitude and direction, and quaternion information of real-time spatial posture, etc., through the data acquisition and transmission layer, in accordance with the strictly defined data format and transmission protocol, and are transmitted at high speed to the digital twin model layer where the geometric model is located; these actual operation data become the key driving force for driving the geometric model to synchronize the physical entity state in real time, ensuring that the geometric model can reproduce the current morphological position of the physical robotic arm in space exactly;

[0078] For the technical solution of this embodiment, the modeling deduction and twin simulation in the model calibration and verification module are implemented using Solidworks and Matlab Simulink platforms, as follows:

[0079] (1) Constructing the model assembly: Using Solidworks to design the robot arm assembly;

[0080] The model assembly is constructed by using the powerful parametric design function of Solidworks to start an innovative top-down and bottom-up hybrid design mode to fully carve the robot arm assembly.

[0081] First, in the top-down design stage, according to the macro requirements and complex operation processes of deep space exploration missions, the overall structure and key performance indicators of the robotic arm are accurately planned, such as planning a flexible working envelope space that can adapt to different celestial surface sampling and complex equipment installation tasks, as well as the structural strength distribution required to resist deep space radiation and micrometeor impacts. In this way, the top-level framework of the layout of each joint of the robotic arm, the shape of the connecting rod and the adaptation form of the end effector are outlined to ensure that the design of each component is closely centered on the mission core from the beginning;

[0082] Then we switched to the bottom-up design process and created the basic parts of the robotic arm one by one. We used Solidworks' advanced surface modeling and solid modeling technology to design the part structure in strict accordance with the cutting-edge achievements of material science, such as using a new lightweight and high-strength alloy to create the joint shell, and combined with the topology optimization algorithm to create an internal hollowed-out connecting rod structure with excellent mechanical properties. We also embedded intelligent sensor microstructures inside the parts, enabling them to sense stress, temperature, strain and other parameters in situ, laying the groundwork for subsequent real-time monitoring and health management.

[0083] In the assembly process, the traditional static assembly concept is abandoned, and a dynamic assembly verification mechanism based on kinematics and dynamics virtual prototype technology is introduced; the full life cycle movement process of the robotic arm under various typical working conditions in deep space is simulated, from the violent vibration impact in the launch phase, to the microgravity attitude adjustment during orbital operation, to the operating forces on the surfaces of different celestial bodies after landing, the matching accuracy and motion interference of each component are dynamically verified, and the assembly relationship is corrected in real time to ensure that the assembly has gone through many tests in the virtual environment. The final geometric model is like a precise projection of the real robotic arm in the digital world, laying a solid foundation for the subsequent in-depth application of the twin model, and realizing an innovative construction paradigm that is deeply in line with the stringent requirements of deep space exploration from the design source;

[0084] (2) Generate the geometric model URDF file. The specific method is as follows:

[0085] First, after completing the detailed construction of the robotic arm assembly in Solidworks, the Solidworks and URDF conversion plug-ins or customized conversion scripts developed by ourselves are used to realize the innovative conversion from Solidworks assembly data to URDF format. This conversion process is not a simple data format switch, but fully considers the unique needs of deep space exploration scenarios, and deeply optimizes the data and expands the information.

[0086] During the conversion process, for each part and connection of the robotic arm, in addition to conventional information such as geometry, size, and mass attributes, the functional role, reliability requirements, and environmental adaptability characteristics of each component in deep space exploration are integrated into the URDF file; for example, for key joint components, not only conventional information such as its rotation range and moment of inertia is recorded, but also special information such as the lubrication characteristics of the component in a high vacuum environment, radiation damage resistance index, and performance attenuation coefficient of the material under extreme temperatures are added; at the same time, a unique deep space exploration mission label is assigned to each component to clarify its usage status and importance level in different mission stages (such as sampling, detection, maintenance, etc.);

[0087] In addition, the connection relationship of the manipulator is innovatively and optimally described; multi-physics field coupling information is introduced to accurately describe the flexible connection characteristics between the connected parts in the URDF file, such as simulating the elastic deformation and damping effect at the joints, so as to better reflect the connection behavior under the complex force field in space; and according to different mission scenarios, the connection parameters such as stiffness and damping coefficient are adaptively adjusted, so that the URDF file can dynamically reflect the changes in the connection performance of the manipulator in different deep space environments;

[0088] Intelligent data tags can also be embedded in URDF files. These tags can automatically update the status information of corresponding components based on the real-time operation data and simulation results of the robot arm. For example, when the simulated robot arm is performing a high-load sampling task, the force at the joint exceeds the set threshold. The corresponding joint part in the URDF file will automatically update its load-bearing capacity tag, so that the subsequent digital twin model and analysis software can quickly perceive and make corresponding decisions, such as triggering fault warnings, adjusting operation strategies, etc.

[0089] Furthermore, an XML-based extension method is used to add custom elements and attributes to the URDF file to achieve the description of the non-traditional structure and function of the robotic arm. For example, for new detection equipment that may be carried, custom elements are used in the URDF file to describe its detection range, accuracy, energy requirements, and the collaborative relationship with other parts of the robotic arm. These custom elements can also be dynamically updated through external scripts to ensure that the URDF file can flexibly adapt to the evolving deep space exploration technology and mission requirements.

[0090] The URDF file generated in this way will become a comprehensive, dynamic description file rich in deep space exploration information, providing richer, more accurate and forward-looking information support for subsequent simulation and control operations on platforms such as Matlab, greatly improving the performance and adaptability of the digital twin system;

[0091] (3) The specific method of building the twin model is:

[0092] In the Matlab Simulink environment, based on the previously imported robotic arm URDF file, the multi-physics field modeling technology is deeply integrated; using the rich module library of Simulink, not only the rigid body dynamics model of the robotic arm is built to accurately simulate the kinematic relationship of the joints and the force transmission path, but also the corresponding physical effect sub-model is built for the special environmental factors of deep space exploration, such as microgravity field, high and low temperature radiation heat exchange, and changes in material properties in a vacuum environment. For example, the microgravity compensation algorithm is written through a custom S-Function module and embedded in the core loop of the dynamics model to correct the motion deviation caused by the lack of gravity in real time; the heat conduction finite element module is used to simulate the distribution of heat in the robotic arm structure and the heat dissipation process, and the closed-loop thermal control strategy modeling is realized in combination with the temperature sensor feedback to ensure that the model can truthfully reflect the evolution of the physical performance of the robotic arm in the extreme environment of deep space, as follows:

[0093] It should be noted that the microgravity compensation algorithm is based on dynamic modeling, and is mainly adjusted to reduce the weakening of the gravity compensation term in a microgravity environment. The dynamic model of the robotic arm is described as follows:

[0094]

[0095] Where τ is the joint torque, M(q) is the inertia matrix, is the Coriolis force and centrifugal force matrix, G(q) is the gravity compensation term, and F(q) is the friction torque.

[0096] In a microgravity environment, the influence of the gravity compensation term is significantly reduced, and the improved compensation term can be expressed as:

[0097] G micro (q) = g micro ·J T (q)m

[0098] In the formula, g micro is the microgravity acceleration, J T is the Jacobian matrix, and m is the mass vector of each link of the robotic arm.

[0099] The specific implementation of the algorithm includes:

[0100] State acquisition: real-time acquisition of the angle, angular velocity, acceleration, and external force information of the robot arm joints;

[0101] Parameter adjustment: Set g according to the microgravity conditions of the deep space environment micro ;

[0102] Compensation calculation: Calculate the compensation torque of the joint based on the Jacobian matrix;

[0103] Dynamic correction: adjust the dynamic model, remove the original gravity compensation term, and add the microgravity correction term;

[0104] Real-time control: Combined with the prediction module, the control input is dynamically adjusted to ensure the precise trajectory of the robot arm.

[0105] At the same time, an intelligent control architecture based on model predictive control (MPC) or adaptive control algorithm is built, which is tightly coupled with the physical model. This control architecture generates control sequences based on real-time optimization of mission objectives, continuously compares the model prediction output with the actual response of the physical model, and dynamically adjusts the control parameters, giving the twin model the ability to autonomously adapt to complex working conditions and uncertain interference, achieving a leap from simple mechanical motion reproduction to intelligent decision-making and execution of complex tasks, greatly improving the performance and reliability of the robotic arm throughout the life cycle of deep space exploration missions.

[0106] It should be noted that the adaptive control algorithm monitors the dynamic behavior of the robot arm in real time, adjusts the control parameters according to the task objectives and environmental changes, and solves the uncertainty problem under complex working conditions. The specific implementation steps are as follows:

[0107] Dynamic modeling: Build a real-time dynamic model of the robotic arm to describe the nonlinear relationship between joint torque and angle, velocity, and acceleration.

[0108] Parameter estimation: Use recursive least squares (RLS) or gradient descent algorithms to estimate model parameters in real time, including inertia, friction, and joint stiffness.

[0109] Error analysis and feedback: The error function is used to calculate the deviation between the current output and the expected output. The error is defined as: e(t) = x d (t)-x a (t), x d is the expected trajectory, x a The actual trajectory.

[0110] Control law update: Based on the Lyapunov stability criterion, design the control law: τ a =τ n +K e e(t),K e is the error gain matrix, τ n is the nominal value;

[0111] In addition, to achieve high-fidelity visual twin display, the fine geometric model built by SolidWorks is deeply bound to the physical model with the help of Simulink 3D Animation toolbox, rendering a realistic virtual robotic arm operation scene, supporting immersive interactive viewing. Operators can observe the stress and strain of the robotic arm structure and the joint drive details from any angle, providing an intuitive basis for troubleshooting and performance tuning, so that the model construction results can fully serve the complex operation process control of deep space exploration;

[0112] (4) Twin control interface construction, the specific method is as follows:

[0113] In the design of the twin control interface, multimodal information fusion display is introduced; in addition to the traditional graphical interface displaying the status information of the robot arm (such as position, posture, speed, force, etc.), it will also integrate information such as audio and tactile feedback; for example, when the robot arm approaches the limit of the operating range or a potential fault occurs, the operator is prompted through specific sound signals and tactile vibrations, so that the operator can perceive the operating status of the robot arm through hearing and touch in addition to vision, thereby enhancing situational awareness;

[0114] At the same time, an intelligent decision-making support system is developed and integrated into the control interface; the system can automatically recommend the best operation strategy and control parameters based on the current mission objectives and the real-time status of the robotic arm; for example, when the robotic arm is required to grasp an irregular deep-space object, the system will automatically plan the optimal motion trajectory and grasping posture based on the shape, position and current position of the object, and visualize it on the interface. The operator can choose to accept the suggestion or make adjustments based on his or her own experience;

[0115] In order to adapt to the long-term mission and high-latency communication characteristics of deep space exploration, the adaptive control function of the interface is constructed; when the communication delay with the actual robotic arm is high, the interface can predict the movement trajectory and state of the robotic arm during the delay period based on the current control command and the known robotic arm dynamics model, so that the operator can make adjustments in advance to avoid operational errors caused by communication delays;

[0116] In addition, the distributed collaborative control of the interface is realized; multiple operators are allowed to access the control interface at the same time through the network at different locations to jointly complete complex deep space exploration tasks; each operator is responsible for different operations, and the interface can clearly divide their respective operating permissions and task scopes, and synchronize the operating information between different operators in real time to ensure the smoothness and safety of collaborative operations;

[0117] In terms of the security of the control interface, a multi-level security protection mechanism is set up; in addition to conventional authority authentication, real-time risk assessment of operation commands will be performed. For high-risk operations that may cause damage to the robot arm or mission failure, a warning window will pop up and force the operator to confirm or provide a higher level of authority authentication to ensure the safety and reliability of the operation;

[0118] Finally, a machine learning-driven operation record and learning function is added to the interface; the system automatically records the operator's operation history and the robot arm's response, analyzes the pros and cons of the operation through a machine learning algorithm, and provides the operator with suggestions for improving their operating skills. At the same time, it continuously optimizes its own operation recommendation algorithm to achieve continuous improvement in human-machine collaboration, allowing the operator and the twin control interface to grow together and better serve deep space exploration missions.

[0119] For the technical solution of this embodiment, the system automatically records the operator's operation history and the response of the robot arm, uses an algorithm architecture that combines deep reinforcement learning with supervised learning to analyze the pros and cons of the operation, and provides operators with suggestions for improving their operating skills. Reinforcement learning continuously optimizes the operation strategy through interaction with the environment, and supervised learning uses historical data to provide clear feedback and improvement directions for the operation. Compared with a single reinforcement learning method, this combined strategy can converge faster and make up for the shortcomings of the early model through supervised learning when the amount of data is small.

[0120] The specific steps of the algorithm include:

[0121] First, the system collects the operating status of the robot arm (such as joint position, speed, force, etc.) and the operator's control input in real time, denoises and normalizes the data, and extracts key features such as task completion and response time. Subsequently, the system analyzes the historical operation data through a supervised learning model to explore the patterns of successful and failed operations, providing basic support for improving operation skills. At the same time, in the reinforcement learning stage, the operation strategy is optimized through a deep Q network (DQN), and the operation success rate and efficiency are used as reward signals to continuously improve the control strategy. Finally, the system combines the historical experience of supervised learning with the real-time optimization of reinforcement learning through a hybrid decision-making mechanism to generate targeted operation suggestions. The feedback results are presented in an intuitive way, including specific contents such as the direction of improving operation skills, suggestions for reducing invalid operations, and force input optimization.

[0122] Next, the digital twin simulation verification of the robotic arm is carried out:

[0123] The digital twin simulation verification of the robotic arm is mainly implemented using the matlab simulink platform, which mainly includes building a model assembly, generating a model URDF file, building a twin model, and a twin control interface. Finally, the simulation model will be combined with the actual UR5 robotic arm for virtual reality twin simulation to compare the output of the robotic arm end posture and related position data, as follows:

[0124] (1) Constructing the model assembly specifically involves using Solidworks to build the assembly of the robot body, and assembling the assembly to form a geometric model, such as Figure 2 and Figure 3 As shown;

[0125] (2) Generate a geometric model URDF file, such as Figure 4 and Figure 5 As shown;

[0126] (3) Specific methods for building twin models:

[0127] like Figures 6 to 10 As shown, open matlab, install matlab R2021b, install the robot toolbox (MatlabToolbox), add the path of the ur5.urdf file to the matlab path, and enter the command: smimport('ur5_urdf.urdf') to import the system;

[0128] (4) Fig.11 As shown in the figure, the twin control interface sends the relevant parameters required by the UR5 robotic arm by setting the relevant parameters, and displays the relevant parameters fed back by the UR5 robotic arm and supports the relevant parameters to be transmitted to the control box of the robotic arm through Ethernet to complete the control of the robotic arm.

[0129] Robotic arm digital twin demonstration and verification:

[0130] Table 1 Twin simulation parameter information of UR5 robot arm

[0131]

[0132] Fig.12 This is a schematic diagram for the digital twin comparison of the UR5 robotic arm. By completing the construction of the physical layer, data acquisition and transmission layer, digital twin model layer, and application layer of the robotic arm, the actual robotic arm body can be guided to perform related actions through virtual simulation data, and the virtual and real body configuration comparison can be completed through a visual interface to meet the digital twin needs of various spacecraft operations in the field of future deep space exploration.

[0133] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0134] For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. When an element is referred to as being "assembled on", "installed on", "fixed on" or "set on" another element, it can be directly on the other element or there can also be a centered element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be a centered element at the same time. The terms "vertical", "horizontal", "up", "down", "left", "right" and similar expressions used herein are only for illustrative purposes and are not intended to be the only implementation method.

[0135] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0136] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

Claims

1. A digital twin system of a robotic arm for deep space exploration, comprising a physical layer, a data acquisition and transmission layer, a digital twin model layer and an application layer, characterized in that: The physical layer includes a robot body and a sensor network, wherein the sensor network is used to collect operating status information of the robot body; The data acquisition and transmission layer includes a data acquisition device and a data transmission network, wherein the data acquisition device is connected to the sensor network and the data transmission network respectively, and the data acquisition device is used to convert the operating status information collected by the sensor network into an electrical signal and transmit it to the data transmission network for storage; The digital twin model layer includes a geometric model construction module, a physical model construction module and a model calibration and verification module. The geometric model construction module is used to create a high-precision geometric model of the robotic arm body. The physical model construction module is used to build a physical model of the robotic arm body based on the geometric model in combination with the dynamics, kinematics principles and material properties of the robotic arm body. The model calibration and verification module is used to perform precision calibration on the constructed geometric model and physical model according to the actual operating status data of the robotic arm obtained by the data acquisition and transmission layer. The application layer is specifically a visualization module, which is connected to the data acquisition and transmission layer and the digital twin model layer, and is used to receive the operating status information of the robotic arm body and display the motion trajectory, workspace range and currently executed task information of the robotic arm body in real time.

2. The digital twin system of a robotic arm for deep space exploration according to claim 1, characterized in that: The sensor network is installed on the robot body, and the sensor network includes joint position sensors, force sensors, vision sensors, and speed sensors.

3. The digital twin system of a robotic arm for deep space exploration according to claim 2, characterized in that: The data acquisition device is used to condition, sample and digitize the analog signals collected by the sensor network to convert them into a digital format suitable for network transmission. The data acquisition device is specifically configured as an integrated data acquisition card, and the data acquisition device is equipped with a redundant power supply module.

4. The digital twin system of a robotic arm for deep space exploration according to claim 3, characterized in that: The data transmission network uses a standard network transmission protocol to transmit the collected data from the physical layer to the digital twin model layer.

5. The digital twin system of a robotic arm for deep space exploration according to claim 4, characterized in that: The geometric model and the physical model are deeply connected through multi-dimensional and multi-level data interaction links and adaptation interfaces to realize digital twin control, as follows: The physical layer collects the current joint angle, angular velocity, force magnitude and direction, and real-time spatial posture operation data of the physical model, and transmits it to the digital twin model layer where the geometric model is located through the data acquisition and transmission layer in accordance with the defined data format and transmission protocol, so that the geometric model reproduces the current morphological position of the physical model in space.

6. The digital twin system of a robotic arm for deep space exploration according to claim 5, characterized in that: The modeling deduction and twin simulation in the model calibration and verification module are implemented using Solidworks and Matlab Simulink platforms, as follows: (1) Constructing the model assembly: Using Solidworks to design the robot arm assembly; (2) Generate geometric model URDF file; (3) Specific methods for building twin models; (4) Construction of twin control interface.

7. The digital twin system of a robotic arm for deep space exploration according to claim 6, characterized in that: The robot body assembly is designed using Solidworks, as follows: (71) First, in the top-down design stage, the overall structure and structural strength distribution of the robot arm are planned, and the top-level framework of the joint layout, connecting rod shape and end effector of the robot arm are designed; (72) Then switch to the bottom-up design stage, create the basic components of the robotic arm one by one, and use Solidworks to design the part structure, including the joint housing, connecting rod structure, and sensor structure; (73) During the assembly phase, the matching accuracy and motion interference of each component are dynamically verified, and the assembly relationship is corrected in real time.

8. The digital twin system of a robotic arm for deep space exploration according to claim 6, characterized in that: The specific method of generating a geometric model URDF file is as follows: (81) After completing the construction of the robotic arm assembly in Solidworks, the Solidworks and URDF conversion plug-in or conversion script is used to realize the innovative conversion from Solidworks assembly data to URDF format; (82) During the conversion process, for each part and connecting component of the robotic arm, in addition to the conventional geometry, size, and mass attribute information, the functional role, reliability requirements, and environmental adaptability characteristics of each component in deep space exploration are integrated into the URDF file; (83) Characterize the flexible connection characteristics between connected parts in the URDF file, including simulating elastic deformation, damping effect, and connection stiffness at the joints; (84) Embed intelligent data tags in the URDF file to automatically update the status information of the corresponding components according to the real-time operation data and simulation results of the robot arm; (85) An XML extension-based method is used to add custom elements and attributes in URDF files.

9. The digital twin system of a robotic arm for deep space exploration according to claim 8, characterized in that: Specific method of building a twin model: (91) In the Matlab Simu Link environment, based on the previously imported robot URDF file, the multi-physics field modeling technology is deeply integrated, and the module library of Simu Link is used to build the rigid body dynamics model of the robot. The corresponding physical effect sub-model is constructed for the special environmental factors of deep space exploration. At the same time, the microgravity compensation algorithm is used to compensate and correct the motion deviation of the dynamics model, and the adaptive control algorithm is used to adjust the control parameters in real time, as follows: (91.1) The microgravity compensation algorithm is as follows: The microgravity compensation algorithm is based on dynamic modeling. The dynamic model of the robotic arm is described as follows: Where τ is the joint torque, M(q) is the inertia matrix, is the Coriolis force and centrifugal force matrix, G(q) is the gravity compensation term, and F(q) is the friction torque; In a microgravity environment, the influence of the gravity compensation term is significantly reduced, and the improved compensation term is expressed as: G micro (q)=g micro ·J T (q)m In the formula, g micro is the microgravity acceleration, J T is the Jacobian matrix, m is the mass vector of each link of the robot arm; (91.2) Adaptive control algorithm, the specific implementation steps are as follows: Dynamic modeling: Build a real-time dynamic model of the robot arm to describe the nonlinear relationship between joint torque and angle, velocity, and acceleration; Parameter estimation: Estimate model parameters including inertia, friction, and joint stiffness in real time using recursive least squares or gradient descent algorithms; Error analysis and feedback: The error function is used to calculate the deviation between the current output and the expected output. The error is defined as: e(t) = x d (t)-x a (t), x d is the expected trajectory, x a is the actual trajectory; Control law update: Based on the Lyapunov stability criterion, design the control law: τ a =τ n +K e e(t),K e is the error gain matrix, τ n is the nominal value; (92) Build an intelligent control architecture based on model predictive control or adaptive control algorithms, tightly coupled with the physical model; (93) With the help of Simulink 3D Animation toolbox, the fine geometric model built by SolidWorks is deeply bound to the physical model to render the virtual robotic arm operation scene.

10. The digital twin system of a robotic arm for deep space exploration according to claim 9, characterized in that: The specific method of building a twin control interface is as follows: (101) In the design of twin control interface, multimodal information fusion display is introduced, including position, posture, speed, force, audio, and tactile feedback information; (102) Develop an intelligent decision-making support system integrated into the control interface; (103) Build adaptive control functions for interfaces to accommodate long-duration missions and high-latency communications for deep space exploration; (104) Implementing distributed collaborative control of the interface, allowing multiple operators to access the control interface simultaneously through the network at different locations; (105) Establish a multi-level security protection mechanism, including authority authentication and real-time risk assessment of operation commands; (106) The system automatically records the operator’s operation history and the robot’s response, analyzes the pros and cons of the operation based on a machine learning algorithm, and provides the operator with suggestions for improving his or her operating skills.

Images