Motion mechanism time statistical analysis method and device based on unidirectional digital twinning

Abstract

The embodiment of the invention provides a motion mechanism time statistical analysis method and device based on unidirectional digital twinning, and the method comprises the steps: carrying out the receiving and recognition operation of motion mechanism operation data according to a preset time interval, and determining a corresponding time statistical result; the method comprises the following steps: collecting historical motion mechanism data, performing feature extraction operation on the historical motion mechanism data according to a preset robot kinematics model and a kinetic model, determining corresponding motion efficiency physical features, performing interaction feature construction operation on the motion efficiency physical features, and determining a corresponding physical feature data set; performing model training on a preset initial model according to the physical feature data set, and determining a corresponding robot time adjustment model; the time statistics result is input into the robot time adjustment model, the corresponding optimal time parameter is determined, robot control is conducted according to the optimal time parameter, and the motion mechanism control efficiency and accuracy can be improved based on time statistics and adjustment.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to a method and device for time statistical analysis of a motion mechanism based on unidirectional digital twins. Background Art

[0002] In the development process of industrial robots, the controller is the "brain" of the robot, and its performance directly determines the overall performance of the robot. However, there are many challenges in the traditional way of developing controllers. First, the development and testing process based on the real controller is cumbersome and time-consuming, especially when the controller prototype is limited and can only be used by a limited number of developers, which greatly limits the efficiency of research and development. Secondly, before the development of the controller is completed, directly matching the motor and the robot arm for testing will increase the cost of research and development, and may cause equipment damage or safety accidents due to unstable controller performance.

[0003] In order to overcome these challenges, the industry has begun to explore digital twin technology and develop motion mechanism controllers. That is, make full use of data such as physical models, sensor updates, and operation history, integrate multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, and complete mapping in virtual space, thereby reflecting the full life cycle of the corresponding physical equipment. Simulation technology can simulate the robot's movement, control, interaction and other processes in a virtual environment, helping developers to verify algorithms, evaluate performance, and optimize without relying on real machines. However, existing simulation technologies still have some shortcomings. For example, many simulation software only support robots of specific brands, which limits their versatility and flexibility; at the same time, these software also have deficiencies in data processing, trajectory analysis, time statistics, etc., and it is difficult to meet the needs of complex application scenarios.

[0004] In this context, a time statistics analysis method for motion mechanisms based on one-way digital twins is proposed. This method aims to analyze the corresponding trajectory point information by parsing the controller entity data to test the controller, realize robot posture backtracking, time statistics and other functions, and provide an efficient, flexible and accurate solution for the development of motion mechanism controllers. This method can not only significantly improve R&D efficiency and reduce R&D costs, but also improve the performance stability and safety of robots, providing strong support for the widespread application of motion mechanisms. Summary of the invention

[0005] In response to the problems in the prior art, the present application provides a method and device for time statistical analysis of a motion mechanism based on unidirectional digital twins, which can improve the control efficiency and accuracy of the motion mechanism based on time statistics and adjustments.

[0006] In order to solve at least one of the above problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a time statistical analysis method for a motion mechanism based on a one-way digital twin, comprising:

[0008] Receiving and identifying the motion mechanism operation data according to a preset time interval to determine the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters;

[0009] Determine the corresponding motion mechanism posture according to the joint angle data and the preset robot forward kinematics algorithm, determine the corresponding motion mechanism running trajectory according to the expandable additional parameters, perform time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determine the corresponding time statistics result;

[0010] Collect historical motion mechanism data, perform feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and a dynamic model, determine corresponding physical features of motion efficiency, perform interactive feature construction operations on the physical features of motion efficiency, determine corresponding physical feature data sets, perform model training on a preset initial model according to the physical feature data sets, perform performance evaluation on the model after the model training according to a preset determination coefficient, determine corresponding performance evaluation results, update parameters of the initial model according to the performance evaluation results, and determine a corresponding robot time adjustment model;

[0011] The time statistics result is input into the robot time adjustment model to determine the corresponding optimal time parameters, the trajectory point data is updated according to the optimal time parameters, and the robot is controlled according to the updated trajectory point data.

[0012] Further, the determining of the corresponding motion mechanism running trajectory according to the expandable additional parameters includes:

[0013] Performing an identification operation on the expandable additional parameters to determine a corresponding trajectory starting point, a trajectory ending point, and a trajectory distance between each trajectory point;

[0014] The trajectory distances between the trajectory points are accumulated to determine the corresponding total trajectory distance, and the corresponding motion mechanism running trajectory is determined according to the trajectory starting point, the trajectory ending point and the total trajectory distance.

[0015] Further, performing a time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory to determine a corresponding time statistics result includes:

[0016] Determine the trajectory running time according to the number of trajectory points included in the running trajectory of the motion mechanism and the preset time interval;

[0017] A posture mapping operation is performed on the trajectory running time and the total trajectory distance according to the posture of the motion mechanism, and a time statistics operation is performed on the trajectory running time and the total trajectory distance after the mapping operation to determine a corresponding time statistics result.

[0018] Furthermore, before performing a feature extraction operation on the historical motion mechanism data according to the preset robot kinematic model and dynamic model to determine the corresponding physical characteristics of motion efficiency, the method includes:

[0019] Determine a corresponding robot kinematics model according to preset robot joint angles, velocities, and accelerations, wherein the robot kinematics model is used to represent the robot joint motion relationship;

[0020] The corresponding robot dynamics model is determined according to the preset robot torque, load and energy consumption, and the robot dynamics model is used to represent the physical characteristics of the robot movement process.

[0021] Furthermore, the interactive feature construction operation is performed on the physical feature of the motion efficiency to determine the corresponding physical feature data set, including:

[0022] Interactively combining different physical characteristics of the motion efficiency to determine corresponding composite characteristics;

[0023] A corresponding physical feature data set is determined according to the composite feature.

[0024] Further, the updating of the parameters of the initial model according to the performance evaluation result to determine the corresponding robot time adjustment model includes:

[0025] Performing sensitivity analysis on the parameters of the initial model according to a preset sensitivity analysis algorithm to determine corresponding high-sensitivity parameters;

[0026] The highly sensitive parameters are iteratively updated according to the performance evaluation results to determine a corresponding robot time adjustment model.

[0027] Furthermore, after controlling the robot according to the updated trajectory point data, the method further includes:

[0028] Performing a saving operation on the updated trajectory point data to determine the corresponding saved trajectory points;

[0029] Perform a backtracking operation on the saved trajectory point to determine the corresponding robot backtracking data, wherein the backtracking operation includes simulating dragging or double-clicking the trajectory point, and the backtracking data includes at least one of the robot posture and the robot running state

[0030] In a second aspect, the present application provides a motion mechanism time statistics analysis device based on a one-way digital twin, comprising:

[0031] a communication and driving module, for receiving and identifying the motion mechanism operation data according to a preset time interval, and determining the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters, wherein the historical form usage data includes at least one of historical form performance data and historical form structure change data;

[0032] A time statistics module, used to determine the corresponding motion mechanism posture according to the joint angle data and a preset robot forward kinematics algorithm, determine the corresponding motion mechanism running trajectory according to the expandable additional parameters, perform a time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determine the corresponding time statistics result;

[0033] The time adjustment model training module is used to collect historical motion mechanism data, perform feature extraction operations on the historical motion mechanism data according to the preset robot kinematic model and dynamic model, determine the corresponding physical characteristics of motion efficiency, perform interactive feature construction operations on the physical characteristics of motion efficiency, determine the corresponding physical characteristic data set, perform model training on the preset initial model according to the physical characteristic data set, perform performance evaluation on the model after the model training according to the preset determination coefficient, determine the corresponding performance evaluation results, update the parameters of the initial model according to the performance evaluation results, and determine the corresponding robot time adjustment model.

[0034] The time adjustment and data storage module is used to input the time statistical results into the robot time adjustment model, determine the corresponding optimal time parameters, update the trajectory point data according to the optimal time parameters, and control the robot according to the updated trajectory point data.

[0035] In a third aspect, the present application provides 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 time statistical analysis of a motion mechanism based on unidirectional digital twins are implemented.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for time statistical analysis of a motion mechanism based on a unidirectional digital twin.

[0037] In a fifth aspect, the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the motion mechanism time statistical analysis method based on unidirectional digital twin.

[0038] It can be seen from the above technical scheme that the present application provides a motion mechanism time statistics analysis method and device based on unidirectional digital twins, which determines the corresponding time statistics results by receiving and identifying the motion mechanism operation data according to preset time intervals; collects historical motion mechanism data, performs feature extraction operations on the historical motion mechanism data according to preset robot kinematic models and dynamic models, determines the corresponding physical characteristics of motion efficiency, performs interactive feature construction operations on the physical characteristics of motion efficiency, determines the corresponding physical feature data set, performs model training on the preset initial model according to the physical feature data set, and determines the corresponding robot time adjustment model; inputs the time statistics results into the robot time adjustment model, determines the corresponding optimal time parameters, and controls the robot according to the optimal time parameters, thereby improving the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 This is one of the flow charts of the time statistical analysis method of a motion mechanism based on a one-way digital twin in an embodiment of the present application;

[0041] Figure 2 This is the second flow chart of the time statistical analysis method of a motion mechanism based on a one-way digital twin in an embodiment of the present application;

[0042] Figure 3 This is the third flow chart of the time statistical analysis method of a motion mechanism based on a one-way digital twin in an embodiment of the present application;

[0043] Figure 4 This is a fourth flow chart of a method for time statistics analysis of a motion mechanism based on a one-way digital twin in an embodiment of the present application;

[0044] Figure 5 This is a fifth flow chart of the time statistical analysis method of a motion mechanism based on a unidirectional digital twin in an embodiment of the present application;

[0045] Figure 6 This is the sixth flow chart of the time statistical analysis method of a motion mechanism based on a one-way digital twin in an embodiment of the present application;

[0046] Figure 7This is the seventh flow chart of the time statistical analysis method of a motion mechanism based on a one-way digital twin in the embodiment of the present application;

[0047] Figure 8 It is a structural diagram of a motion mechanism time statistics analysis device based on unidirectional digital twin in an embodiment of the present application;

[0048] Fig. 9 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application.

[0049] Reference numerals:

[0050] Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver program storage unit 9144, antenna 9111, speaker 9131, microphone 9132. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0053] Considering that the existing motion mechanism simulation technology can only approximate the average value of motion time in time statistics, it is impossible to show the acceleration and deceleration process of the motion mechanism movement, resulting in the problem of low simulation control efficiency. The present application provides a motion mechanism time statistics analysis method and device based on one-way digital twins, which receives and identifies the motion mechanism operation data according to a preset time interval to determine the corresponding time statistics results; collects historical motion mechanism data, performs feature extraction operations on the historical motion mechanism data according to the preset robot kinematic model and dynamic model, determines the corresponding physical characteristics of motion efficiency, performs interactive feature construction operations on the physical characteristics of motion efficiency, determines the corresponding physical characteristic data set, performs model training on the preset initial model according to the physical characteristic data set, and determines the corresponding robot time adjustment model; inputs the time statistics results into the robot time adjustment model, determines the corresponding optimal time parameters, and controls the robot according to the optimal time parameters, thereby improving the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment.

[0054] In order to improve the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment, the present application provides an embodiment of a motion mechanism time statistics analysis method based on a one-way digital twin, see Figure 1 The time statistical analysis method of the motion mechanism based on the one-way digital twin specifically includes the following contents:

[0055] Step S101: receiving and identifying the motion mechanism operation data according to a preset time interval, and determining the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters;

[0056] Optionally, in this embodiment, the motion mechanism operation data is sent by the controller entity, received and identified by the simulation software, and is used to simulate the operation of the physical robot in the virtual space.

[0057] Optionally, in this embodiment, the software defines the communication data format between the software and the controller entity through built-in support for multiple communication protocols such as Socket, MQTT, and serial communication; the json string contains the robot name, joint angle data, and expandable additional parameters (pathstart, pathend, distance), and the software supports the simulation of multiple controller entities. The controller entity serves as the communication server.

[0058] Optionally, in this embodiment, the preset time interval indicates that the time interval for communicating with the controller entity is fixed and known, preferably in milliseconds, 20ms or less. Data is received at the preset time interval, and each received data is recorded as a track point data, and the track point data includes the joint angle data of the robot and expandable additional parameters.

[0059] For example, the following is a sample of track point data:

[0060] "Robots":[

[0061] {

[0062] "Name":"STEP-SA1800",

[0063] "JointCount":6,

[0064] "A0":"0.0",

[0065] "A1":"0.0",

[0066] "A2":"0.0",

[0067] "A3":"0.0",

[0068] "A4":"1.622",

[0069] "A5":"0.0",

[0070] "PathStart":true,

[0071] "PathEnd":false,

[0072] "Distance":"200"

[0073] },

[0074] Among the above trajectory points, there are six joint angle data, which represent the angles of each joint of the motion mechanism; the extendable additional parameters are "PathStart", "PathEnd" and "Distance". When the parameter "PathStart" is detected as true, this point is considered to be the starting point of a trajectory; when the parameter "PathEnd" is detected as true, this point is considered to be the end point of a trajectory; "Distance" represents the movement distance of the robot from the previous data point to this data point, in mm.

[0075] It can be understood that the joint angle data can be used to represent the robot's posture by parsing it, and additional parameters can be received and parsed at fixed time intervals. When the time interval is in milliseconds, the acceleration and deceleration process on the robot's running trajectory and the real simulation trajectory approximation process can be truly simulated. On the one hand, it increases the accuracy of the simulation, and on the other hand, it lays a solid foundation for subsequent time statistical analysis.

[0076] Step S102: determining the corresponding motion mechanism posture according to the joint angle data and a preset robot forward kinematics algorithm, determining the corresponding motion mechanism running trajectory according to the expandable additional parameters, performing a time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determining a corresponding time statistics result;

[0077] Optionally, in step S101, track point data is obtained by receiving and identifying a controller entity signal. In this step, time statistics are performed by parsing the track point data.

[0078] Optionally, in this embodiment, forward kinematics (FK) is used to calculate the position and posture of the end effector (such as the wrist or tool of the manipulator) in space based on the joint angles of the robot. In the simulation software, the forward kinematics algorithm is used to convert the joint angles into the specific position of the robot in three-dimensional space, thereby simulating the movement of the robot in a virtual environment.

[0079] Optionally, in this embodiment, the corresponding motion mechanism running trajectory is determined according to the expandable additional parameters.

[0080] Specifically, the expandable additional parameters are identified. When the parameter "PathStart" is detected to be true, this point is considered to be the starting point of a trajectory; when the parameter "PathEnd" is detected to be true, this point is considered to be the end point of a trajectory; after parsing and storing the data sent by the controller, the number of trajectory points under each trajectory is known, recorded as PtCount; "Distance" represents the movement distance of the robot from the previous trajectory point to this trajectory point.

[0081] It is understandable that the simulation software may identify multiple trajectory points, but only the two trajectory points where the extensible additional parameter "PathStart" is true and the extensible additional parameter "PathEnd" is true and the trajectory points included between these two trajectory points are used as the time statistics of the trajectory.

[0082] More specifically, since the distance "Distance" between each track point in the known trajectory, the distance between each track point is accumulated, and the sum of the accumulation is the total running distance (length) of this track. The robot running track can be known through the track starting point, track end point and track total distance.

[0083] Optionally, in this embodiment, a time statistics operation is performed according to the motion mechanism posture and the motion mechanism running trajectory to determine a corresponding time statistics result.

[0084] Optionally, in this embodiment, time statistics refers to counting which trajectories the robot has run, how far these trajectories are, and how long they take to run.

[0085] Specifically, the robot's running trajectory and the corresponding trajectory distance are already known, and the actual running time of the trajectory can be calculated using the number of trajectory points PtCount and the fixed time interval, that is, the actual running time of the trajectory = (PtCount-1)*T.

[0086] More specifically, after obtaining the motion mechanism running trajectory data, the motion mechanism's posture running on the trajectory is mapped, and the time statistics of the mapped motion mechanism are performed to obtain the time statistics result, that is, the specific running acceleration and deceleration process of the robot, and the posture state of the robot during the acceleration and deceleration process. By combining the robot posture state for time statistics, the accuracy of time statistics can be improved. Combined with the posture state, the acceleration and deceleration process of the robot can be simulated more accurately, so that the time statistics not only considers the linear motion, but also the dynamic changes during the motion process.

[0087] In terms of effect, the time statistics of the running trajectory can be realized through the definition of fixed time intervals and expandable additional parameters to truly simulate the acceleration and deceleration process of the robot and the real simulation trajectory approximation process. By combining the robot joint angle data on the basis of the running trajectory and analyzing the running time and distance of the robot in different posture states, the bottleneck links in the production process can be identified, and then measures can be taken to optimize and improve the overall production efficiency. Ultimately, combining the time statistics of the motion mechanism posture state can help achieve time balance on the production line, ensure coordinated operation between various processes, and reduce waiting time and resource waste. This combination enables the simulation system to not only perform simple motion simulation, but also lay the foundation for subsequent complex time analysis and optimization, and expand the functions and application scope of the simulation system.

[0088] Step S103: collecting historical motion mechanism data, performing feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and a dynamic model, determining corresponding physical features of motion efficiency, performing interactive feature construction operations on the physical features of motion efficiency, determining corresponding physical feature data sets, performing model training on a preset initial model according to the physical feature data sets, performing performance evaluation on the model after the model training according to a preset determination coefficient, determining corresponding performance evaluation results, updating parameters of the initial model according to the performance evaluation results, and determining a corresponding robot time adjustment model;

[0089] Optionally, in this embodiment, the purpose of this embodiment is to use a machine learning model to predict the impact of different motion parameters on efficiency and dynamically adjust the robot motion time to optimize the workflow.

[0090] Optionally, in this embodiment, the robot kinematic model mainly describes the motion relationship of each joint of the robot, and does not involve factors such as force and mass. The following physical characteristics can be obtained through the kinematic model:

[0091] Joint angle: describes the rotation angle of each joint, which directly affects the position and posture of the robot's end effector.

[0092] Speed: The angular velocity and linear velocity of each joint reflect the dynamic performance of the robot during movement.

[0093] Acceleration: Joint angular acceleration can be used to analyze the rate of change during motion and help optimize the motion trajectory.

[0094] Specifically, during the construction of the kinematic model, a basic coordinate system and a local coordinate system are established. The basic coordinate system is used to establish a global coordinate system (usually a ground coordinate system) for the robot; the local coordinate system is used to establish a local coordinate system for each joint and end effector, which is defined according to the DH (Denavit-Hartenberg) parameter method.

[0095] More specifically, DH parameters: define the DH parameters of each joint (including joint angle θ, link length a, link offset d, torsion angle α), which are used to describe the relative position relationship between the joints.

[0096] It can be understood that the kinematic model constructed by forward kinematics and DH parameters focuses on the relationship between position and posture.

[0097] Optionally, in this embodiment, the robot dynamics model takes into account the forces and moments to which the robot is subjected during movement, and can provide more in-depth physical features, such as:

[0098] Torque: The torque required at each joint is critical for evaluating the energy consumption and stability of robot motion.

[0099] Load: The load condition of each joint of the robot reflects the force state of the robot when performing tasks, and helps determine whether it is within the safety range.

[0100] Energy expenditure: By calculating the power required during exercise, the energy efficiency of different exercise modes can be evaluated.

[0101] Specifically, in the process of building the dynamic model, the mass, center of gravity position and moment of inertia of each part of the robot (such as connecting rods and joints) are first determined. These parameters are crucial for dynamic analysis. Secondly, the kinematic model established previously is used as the basis of the dynamic model to describe the movement of the robot in a specific state. Then, the Newton-Euler method is applied to establish the dynamic equation by analyzing the force and torque of each joint. This method is suitable for real-time control and fast response scenarios. The dynamic model constructed through the above steps focuses on the relationship between force, acceleration and motion state.

[0102] It is understandable that the construction process of the kinematic model and the dynamic model complement each other. The kinematic model can simplify the analysis of the dynamic model, while the dynamic model provides a deeper understanding of kinematics. Through reasonable modeling and verification, the performance and accuracy of the robot control system can be effectively improved.

[0103] Optionally, in this embodiment, a feature extraction operation is performed on the historical motion mechanism data according to a preset robot kinematic model and a dynamic model to determine corresponding physical characteristics of motion efficiency.

[0104] Specifically, physical features related to motion efficiency are calculated based on the robot's kinematic model and dynamic model. For example, physical quantities such as joint load and torque can be calculated as model input features. This feature is not only directly related to the motion parameters, but also provides more physical background information to help the model better understand the factors affecting motion efficiency.

[0105] It is understandable that in the collected motion mechanism data, it is necessary to ensure that the data set contains multiple different types of tasks and motion parameter combinations to obtain effective training and testing samples. In such a large amount of data, kinematic models and dynamic models are used to extract key features. By extracting features related to improving motion efficiency, the model can better learn the patterns in the data, thereby improving the accuracy of prediction.

[0106] Finally, the key features extracted include joint angle, velocity, acceleration, load, torque, motion path, running time, etc. By selecting parameter features that are highly correlated with motion efficiency, the trained model can predict the impact of different motion parameters on efficiency.

[0107] Optionally, in this embodiment, an interactive feature construction operation is performed on the physical feature of the motion efficiency to determine a corresponding physical feature data set.

[0108] Specifically, interactive feature construction operations include generating new composite features by combining different features. For example, taking the product of joint angle and velocity as a new feature can capture the comprehensive impact of joint movement. This interactive feature not only provides richer information, but also may reveal the potential relationship between features, further improving the performance of the model.

[0109] After obtaining the composite features through feature extraction, feature selection is performed on the composite features. The goal of this process is to identify the features that contribute most to the model's predictive ability while removing those irrelevant or redundant features. The composite feature subset after feature selection is constructed as a physical feature dataset for training the initial model.

[0110] Optionally, in this embodiment, the parameters of the initial model are updated according to the performance evaluation result to determine the corresponding robot time adjustment model.

[0111] Specifically, before the performance evaluation results, the feature data set is used to train the initial model, and the initial model selects the random forest model, which is suitable for processing complex nonlinear relationships and has strong interpretability.

[0112] The dataset was divided into a training set (70%) and a test set (30%) to ensure the generalization ability of the model. The random forest model was trained using the training set and the hyperparameters were adjusted to optimize the model performance.

[0113] Specifically, the performance evaluation is performed on the test set using the coefficient of determination (R 2 )Evaluate the performance of the model. This evaluation helps determine the effectiveness of the model and update the model parameters accordingly.

[0114] Before updating the model parameters, the sensitivity analysis algorithm is used to perform sensitivity analysis on the parameters of the initial model. Based on the sensitivity analysis results, the highly sensitive parameters that have the greatest impact on the model output are identified.

[0115] A parameter adjustment strategy is formulated based on the performance evaluation results of the model. In each iteration, the values ​​of one or more highly sensitive parameters are updated according to the parameter adjustment strategy, or a better parameter value is searched according to the gradient descent algorithm. When the model performance reaches the preset standard or can no longer be significantly improved through parameter adjustment, the iteration process is stopped, and the model at this time is the optimized robot time adjustment model.

[0116] Step S104: input the time statistics result into the robot time adjustment model, determine the corresponding optimal time parameters, update the trajectory point data according to the optimal time parameters, and control the robot according to the updated trajectory point data.

[0117] Optionally, in this embodiment, the time statistics result obtained in step S102 is input into the robot time adjustment model trained in step S103, and the movement time of the robot is optimized according to the model prediction.

[0118] For example, when developing a new motion mechanism for complex assembly tasks, the model predicts the operating efficiency of different motion parameters and finds that a specific combination of joint angles and speeds can shorten the assembly time by 20%. At this time, the original time parameters and their corresponding multiple trajectory point data are updated according to the parameters predicted by the model.

[0119] Optionally, in this embodiment, after obtaining the updated trajectory point data, the simulation software will save the updated optimal trajectory point data.

[0120] In terms of technical effects, the saved data can be used for simulation, fast forward and reverse playback, which can greatly solve the problem of real machine testing of the controller. The received joint angle data is stored as posture trajectory points, which is convenient for backtracking to view the posture of the robot at that point. When the user wants to backtrack or pay special attention to the robot state at a certain stage of movement, he only needs to use the software's double-click to point, trajectory simulation and other functions to move the robot to the specified point, and view the robot's state by rotating and zooming the view. At the same time, since the updated trajectory point data is combined with expandable additional parameters, the acceleration and deceleration of the robot's operation and the trajectory approximation process will be truly reflected when simulating the robot's running trajectory. Compared with the current time statistics technology, which can only obtain the approximate average value of the robot's movement speed for a section of the trajectory, the advantages of this application are:

[0121] 1. Real simulation can show the real state of a trajectory motion, including acceleration, deceleration and trajectory approach process, which improves the accuracy of robot controller testing.

[0122] 2. Posture backtracking: Use the backtracking function of the software to quickly locate the trajectory points of interest during the simulation process, and view the status of the robot by rotating and zooming the view.

[0123] 3. Simulation adjustment: Use the simulation adjustment model to make more accurate statistics on the posture, running time and distance of each trajectory of the robot, predict the impact of different motion parameters on efficiency, and intelligently modify the robot's rhythm within the motion time according to the motion efficiency prediction results, observe its impact on the simulation results, generate the optimal time statistical parameters, optimize the workflow, and improve control efficiency.

[0124] This example demonstrates how this embodiment performs time statistics and intelligently adjusts the time statistics results according to the time adjustment model, so as to simulate the operation process of the motion mechanism realistically and accurately, thereby improving the efficiency of simulation testing.

[0125] From the above description, it can be seen that the motion mechanism time statistics analysis method based on one-way digital twin provided in the embodiment of the present application can determine the corresponding time statistics results by receiving and identifying the motion mechanism operation data according to preset time intervals; collect historical motion mechanism data, perform feature extraction operations on the historical motion mechanism data according to preset robot kinematic models and dynamic models, determine the corresponding physical characteristics of motion efficiency, perform interactive feature construction operations on the physical characteristics of motion efficiency, determine the corresponding physical characteristic data set, perform model training on the preset initial model according to the physical characteristic data set, and determine the corresponding robot time adjustment model; input the time statistics results into the robot time adjustment model, determine the corresponding optimal time parameters, and control the robot according to the optimal time parameters, thereby improving the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment.

[0126] In one embodiment of the motion mechanism time statistical analysis method based on unidirectional digital twin of the present application, see Figure 2 , and can also include the following:

[0127] Step S201: performing an identification operation on the expandable additional parameters to determine the corresponding trajectory starting point, trajectory ending point and trajectory distance between each trajectory point;

[0128] Step S202: Accumulating the trajectory distances between the trajectory points to determine the corresponding total trajectory distance, and determining the corresponding motion mechanism running trajectory according to the trajectory starting point, the trajectory ending point and the total trajectory distance.

[0129] Optionally, in this embodiment, expandable additional parameters are identified. When the parameter "PathStart" is detected to be true, this point is considered to be the starting point of a trajectory; when the parameter "PathEnd" is detected to be true, this point is considered to be the end point of a trajectory; after parsing and storing the data sent by the controller, the number of trajectory points under each trajectory is known, recorded as PtCount; "Distance" represents the movement distance of the robot from the previous trajectory point to this trajectory point.

[0130] It is understandable that the simulation software may identify multiple trajectory points, but only the two trajectory points where the extensible additional parameter "PathStart" is true and the extensible additional parameter "PathEnd" is true and the trajectory points included between these two trajectory points are used as the time statistics of the trajectory.

[0131] More specifically, since the distance "Distance" between each track point in the known trajectory, the distance between each track point is accumulated, and the sum of the accumulation is the total running distance (length) of this track. The robot running track can be known through the track starting point, track end point and track total distance.

[0132] Through step S202, this embodiment calculates the running trajectory by identifying the extensible additional parameters, laying a foundation for subsequent time statistics of the trajectory.

[0133] In one embodiment of the motion mechanism time statistical analysis method based on unidirectional digital twin of the present application, see Figure 3 , and can also include the following:

[0134] Step S301: determining the trajectory running time according to the number of trajectory points included in the running trajectory of the motion mechanism and the preset time interval;

[0135] Step S302: performing a posture mapping operation on the trajectory running time and the total trajectory distance according to the posture of the motion mechanism, performing a time statistics operation on the trajectory running time and the total trajectory distance after the mapping operation, and determining a corresponding time statistics result.

[0136] Optionally, in this embodiment, the robot running trajectory and the corresponding trajectory distance are already known, and the actual running time of the trajectory can be calculated using the number of trajectory points PtCount and a fixed time interval, that is, the actual running time of the trajectory = (PtCount-1)*T.

[0137] Optionally, in this embodiment, the posture of the motion mechanism running on the trajectory is mapped, and the time statistics of the mapped motion mechanism are performed to obtain the time statistics result, that is, the specific acceleration and deceleration process of the robot, and the posture state of the robot during the acceleration and deceleration process. By combining the robot posture state for time statistics, the accuracy of time statistics can be improved, and combined with the posture state, the acceleration and deceleration process of the robot can be simulated more accurately, so that the time statistics not only considers the linear motion, but also the dynamic changes during the motion process.

[0138] Through step S302, this embodiment realizes mapping the robot posture with the trajectory distance and time, and performs time statistics based on the mapped data, laying a foundation for adjusting the time statistical parameters in the subsequent combination of the motion mechanism posture state.

[0139] In one embodiment of the motion mechanism time statistical analysis method based on unidirectional digital twin of the present application, see Figure 4 , and can also include the following:

[0140] Step S401: determining a corresponding robot kinematics model according to preset robot joint angles, velocities, and accelerations, wherein the robot kinematics model is used to represent the robot joint motion relationship;

[0141] Step S402: determining a corresponding robot dynamics model according to preset robot torque, load and energy consumption, wherein the robot dynamics model is used to represent the physical characteristics of the robot motion process.

[0142] Optionally, in this embodiment, two mathematical models are constructed for subsequent feature extraction tasks. By analyzing the impact of motion parameters on efficiency, the most critical features are obtained to improve the model prediction performance.

[0143] Optionally, in this embodiment, the kinematic model mainly describes the motion relationship of each joint of the robot, and does not involve factors such as force and mass. The following physical characteristics can be obtained through the kinematic model:

[0144] Joint angle: describes the rotation angle of each joint, which directly affects the position and posture of the robot's end effector.

[0145] Speed: The angular velocity and linear velocity of each joint reflect the dynamic performance of the robot during movement.

[0146] Acceleration: Joint angular acceleration can be used to analyze the rate of change during motion and help optimize the motion trajectory.

[0147] Specifically, during the construction of the kinematic model, a basic coordinate system and a local coordinate system are established. The basic coordinate system is used to establish a global coordinate system (usually a ground coordinate system) for the robot; the local coordinate system is used to establish a local coordinate system for each joint and end effector, which is defined according to the DH (Denavit-Hartenberg) parameter method.

[0148] More specifically, DH parameters: define the DH parameters of each joint (including joint angle θ, link length a, link offset d, torsion angle α), which are used to describe the relative position relationship between the joints.

[0149] It can be understood that the kinematic model constructed by forward kinematics and DH parameters focuses on the relationship between position and posture.

[0150] Optionally, in this embodiment, the robot dynamics model takes into account the forces and moments to which the robot is subjected during movement, and can provide more in-depth physical features, such as:

[0151] Torque: The torque required at each joint is critical for evaluating the energy consumption and stability of robot motion.

[0152] Load: The load condition of each joint of the robot reflects the force state of the robot when performing tasks, and helps determine whether it is within the safety range.

[0153] Energy expenditure: By calculating the power required during exercise, the energy efficiency of different exercise modes can be evaluated.

[0154] Specifically, in the process of building the dynamic model, the mass, center of gravity position and moment of inertia of each part of the robot (such as connecting rods and joints) are first determined. These parameters are crucial for dynamic analysis. Secondly, the kinematic model established previously is used as the basis of the dynamic model to describe the movement of the robot in a specific state. Then, the Newton-Euler method is applied to establish the dynamic equation by analyzing the force and torque of each joint. This method is suitable for real-time control and fast response scenarios. The dynamic model constructed through the above steps focuses on the relationship between force, acceleration and motion state.

[0155] It is understandable that the construction process of the kinematic model and the dynamic model complement each other. The kinematic model can simplify the analysis of the dynamic model, while the dynamic model provides a deeper understanding of kinematics. Through reasonable modeling and verification, the performance and accuracy of the robot control system can be effectively improved.

[0156] Through step S403, this embodiment successfully constructs two mathematical models, generates the most critical features for improving the robot's motion efficiency, and lays a solid foundation for subsequent feature extraction.

[0157] In one embodiment of the motion mechanism time statistical analysis method based on unidirectional digital twin of the present application, see Figure 5 , and can also include the following:

[0158] Step S501: performing interactive combination operations on different physical characteristics of the motion efficiency to determine corresponding composite characteristics;

[0159] Step S502: Determine a corresponding physical feature data set according to the composite feature.

[0160] Optionally, in this embodiment, the interactive feature construction operation includes generating new composite features by combining different features. For example, the product of joint angle and velocity is used as a new feature to capture the comprehensive impact of joint movement. This interactive feature not only provides richer information, but also may reveal the potential relationship between features, further improving the performance of the model.

[0161] After obtaining the composite features through feature extraction, feature selection is performed on the composite features. The goal of this process is to identify the features that contribute most to the model's predictive ability while removing those irrelevant or redundant features. The composite feature subset after feature selection is constructed as a physical feature dataset for training the initial model.

[0162] Through step S502, this embodiment successfully constructs a physical feature data set, laying a solid foundation for subsequent model training.

[0163] In one embodiment of the motion mechanism time statistical analysis method based on unidirectional digital twin of the present application, see Figure 6 , and can also include the following:

[0164] Step S601: performing sensitivity analysis on the parameters of the initial model according to a preset sensitivity analysis algorithm to determine corresponding high-sensitivity parameters;

[0165] Step S602: iteratively updating the high-sensitivity parameters according to the performance evaluation results to determine a corresponding robot time adjustment model.

[0166] Optionally, in this embodiment, a sensitivity analysis algorithm is used to perform sensitivity analysis on the parameters of the initial model, and based on the sensitivity analysis results, highly sensitive parameters that have the greatest impact on the model output are identified.

[0167] Specifically, before the performance evaluation results, the feature data set is used to train the initial model, and the initial model selects the random forest model, which is suitable for processing complex nonlinear relationships and has strong interpretability.

[0168] Specifically, the performance evaluation is performed on the test set using the coefficient of determination (R 2 )Evaluate the performance of the model. This evaluation helps determine the effectiveness of the model and update the model parameters accordingly.

[0169] A parameter adjustment strategy is formulated based on the performance evaluation results of the model. In each iteration, the values ​​of one or more highly sensitive parameters are updated according to the parameter adjustment strategy, or a better parameter value is searched according to the gradient descent algorithm. When the model performance reaches the preset standard or can no longer be significantly improved through parameter adjustment, the iteration process is stopped, and the model at this time is the optimized robot time adjustment model.

[0170] Through step S602, this embodiment successfully implements the training and tuning of the initial model, obtains the robot time adjustment model, and lays a solid foundation for subsequent time optimization.

[0171] In one embodiment of the motion mechanism time statistical analysis method based on unidirectional digital twin of the present application, see Figure 7 , and can also include the following:

[0172] Step S701: performing a saving operation on the updated trajectory point data to determine the corresponding saved trajectory points;

[0173] Step S702: Perform a backtracking operation on the saved trajectory point to determine the corresponding robot backtracking data, wherein the backtracking operation includes simulating dragging or double-clicking the trajectory point, and the backtracking data includes at least one of the robot posture and the robot running status.

[0174] Optionally, the simulation software will save these updated optimal trajectory point data.

[0175] In terms of technical effects, the saved data can be used for simulation, fast forward and reverse playback, which can greatly solve the problem of real machine testing of the controller. The received joint angle data is stored as a posture trajectory point, which is convenient for backtracking to view the posture of the robot at that point. When the user wants to backtrack or pay special attention to the robot status at a certain stage of movement, he only needs to use the software's double-click to point, trajectory simulation and other functions to move the robot to the specified point, and view the robot's status by rotating and zooming the view. At the same time, since the updated trajectory point data is combined with expandable additional parameters, the acceleration and deceleration of the robot's operation and the trajectory approach process will also be truly reflected when simulating the robot's running trajectory.

[0176] Through step S702, this embodiment successfully realizes direct backtracking of the robot posture at a certain point by double-clicking the point or dragging, without having to wait for the specified program to run to the point for observation, thereby increasing the simulation control efficiency.

[0177] In order to improve the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment, the present application provides an embodiment of a motion mechanism time statistics analysis device based on a one-way digital twin for realizing all or part of the content of the motion mechanism time statistics analysis method based on a one-way digital twin, see Figure 8 The motion mechanism time statistics analysis device based on one-way digital twin specifically includes the following contents:

[0178] The communication and driving module 10 is used to receive and identify the motion mechanism operation data according to a preset time interval, and determine the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters;

[0179] A time statistics module 20 is used to determine the corresponding motion mechanism posture according to the joint angle data and a preset robot forward kinematics algorithm, determine the corresponding motion mechanism running trajectory according to the expandable additional parameters, perform a time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determine the corresponding time statistics result;

[0180] The time adjustment model training module 30 is used to collect historical motion mechanism data, perform feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and a dynamic model, determine corresponding physical characteristics of motion efficiency, perform interactive feature construction operations on the physical characteristics of motion efficiency, determine corresponding physical characteristic data sets, perform model training on a preset initial model according to the physical characteristic data sets, perform performance evaluation on the model after the model training according to a preset determination coefficient, determine corresponding performance evaluation results, update parameters of the initial model according to the performance evaluation results, and determine corresponding robot time adjustment model;

[0181] The time adjustment and data storage module 40 is used to input the time statistical results into the robot time adjustment model, determine the corresponding optimal time parameters, update the trajectory point data according to the optimal time parameters, and control the robot according to the updated trajectory point data.

[0182] From the above description, it can be seen that the motion mechanism time statistics analysis device based on unidirectional digital twin provided in the embodiment of the present application can determine the corresponding time statistics results by receiving and identifying the motion mechanism operation data according to preset time intervals; collect historical motion mechanism data, perform feature extraction operations on the historical motion mechanism data according to preset robot kinematic models and dynamic models, determine the corresponding physical characteristics of motion efficiency, perform interactive feature construction operations on the physical characteristics of motion efficiency, determine the corresponding physical characteristic data set, perform model training on the preset initial model according to the physical characteristic data set, and determine the corresponding robot time adjustment model; input the time statistics results into the robot time adjustment model, determine the corresponding optimal time parameters, and control the robot according to the optimal time parameters, thereby improving the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment.

[0183] From the hardware level, in order to improve the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment, the present application provides an embodiment of an electronic device for implementing all or part of the content of the motion mechanism time statistics analysis method based on unidirectional digital twin, and the electronic device specifically includes the following content:

[0184] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between the time statistical analysis method of the motion mechanism based on the one-way digital twin and the core business system, user terminal and related databases and other related equipment; the logic controller can be a desktop computer, a tablet computer and a mobile terminal, etc., and the present embodiment is not limited to this. In this embodiment, the logic controller can be implemented with reference to the embodiment of the time statistical analysis method of the motion mechanism based on the one-way digital twin and the embodiment of the time statistical analysis method of the motion mechanism based on the one-way digital twin, and the content thereof is incorporated herein, and the repeated parts are not repeated.

[0185] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0186] In practical applications, part of the time statistical analysis method of the motion mechanism based on the one-way digital twin can be executed on the electronic device side as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0187] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0188] Fig. 9 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig. 9 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig. 9 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0189] In one embodiment, the function of the time statistical analysis method of the motion mechanism based on the one-way digital twin can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0190] Step S101: receiving and identifying the motion mechanism operation data according to a preset time interval, and determining the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters;

[0191] Step S102: determining the corresponding motion mechanism posture according to the joint angle data and a preset robot forward kinematics algorithm, determining the corresponding motion mechanism running trajectory according to the expandable additional parameters, performing a time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determining a corresponding time statistics result;

[0192] Step S103: collecting historical motion mechanism data, performing feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and a dynamic model, determining corresponding physical features of motion efficiency, performing interactive feature construction operations on the physical features of motion efficiency, determining corresponding physical feature data sets, performing model training on a preset initial model according to the physical feature data sets, performing performance evaluation on the model after the model training according to a preset determination coefficient, determining corresponding performance evaluation results, updating parameters of the initial model according to the performance evaluation results, and determining a corresponding robot time adjustment model;

[0193] Step S104: input the time statistics result into the robot time adjustment model, determine the corresponding optimal time parameters, update the trajectory point data according to the optimal time parameters, and control the robot according to the updated trajectory point data.

[0194] From the above description, it can be seen that the electronic device provided in the embodiment of the present application determines the corresponding time statistical results by receiving and identifying the motion mechanism operation data according to a preset time interval; collects historical motion mechanism data, performs feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and dynamic model, determines the corresponding physical characteristics of motion efficiency, performs interactive feature construction operations on the physical characteristics of motion efficiency, determines the corresponding physical characteristic data set, performs model training on the preset initial model according to the physical characteristic data set, and determines the corresponding robot time adjustment model; inputs the time statistical results into the robot time adjustment model, determines the corresponding optimal time parameters, and controls the robot according to the optimal time parameters, thereby being able to improve the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment.

[0195] In another embodiment, the time statistical analysis method of the motion mechanism based on the one-way digital twin can be configured separately from the central processing unit 9100. For example, the time statistical analysis method of the motion mechanism based on the one-way digital twin can be configured as a chip connected to the central processing unit 9100, and the function of the time statistical analysis method of the motion mechanism based on the one-way digital twin can be realized through the control of the central processing unit.

[0196] like Fig. 9 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig. 9 In addition, the electronic device 9600 may also include Fig. 9 For components not shown, reference may be made to the prior art.

[0197] like Fig. 9 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0198] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0199] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0200] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0201] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0202] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0203] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless local area network module, etc. The communication module 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the machine through the microphone 9132, and the sound stored on the machine can be played through the speaker 9131.

[0204] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the method for time statistics analysis of a motion mechanism based on a one-way digital twin in the above-mentioned embodiment, where the execution subject is a server or a client. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, all the steps of the method for time statistics analysis of a motion mechanism based on a one-way digital twin in the above-mentioned embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0205] Step S101: receiving and identifying the motion mechanism operation data according to a preset time interval, and determining the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters;

[0206] Step S102: determining the corresponding motion mechanism posture according to the joint angle data and a preset robot forward kinematics algorithm, determining the corresponding motion mechanism running trajectory according to the expandable additional parameters, performing a time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determining a corresponding time statistics result;

[0207] Step S103: collecting historical motion mechanism data, performing feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and a dynamic model, determining corresponding physical features of motion efficiency, performing interactive feature construction operations on the physical features of motion efficiency, determining corresponding physical feature data sets, performing model training on a preset initial model according to the physical feature data sets, performing performance evaluation on the model after the model training according to a preset determination coefficient, determining corresponding performance evaluation results, updating parameters of the initial model according to the performance evaluation results, and determining a corresponding robot time adjustment model;

[0208] Step S104: input the time statistics result into the robot time adjustment model, determine the corresponding optimal time parameters, update the trajectory point data according to the optimal time parameters, and control the robot according to the updated trajectory point data.

[0209] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present application determines the corresponding time statistical results by receiving and identifying the motion mechanism operation data according to a preset time interval; collects historical motion mechanism data, performs feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and dynamic model, determines the corresponding physical characteristics of motion efficiency, performs interactive feature construction operations on the physical characteristics of motion efficiency, determines the corresponding physical characteristic data set, performs model training on the preset initial model according to the physical characteristic data set, and determines the corresponding robot time adjustment model; inputs the time statistical results into the robot time adjustment model, determines the corresponding optimal time parameters, and controls the robot according to the optimal time parameters, thereby being able to improve the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment.

[0210] The embodiments of the present application also provide a computer program product capable of implementing all the steps of the time statistical analysis method of a motion mechanism based on a one-way digital twin in the above embodiment, where the execution subject is a server or a client. When the computer program / instruction is executed by a processor, the steps of the time statistical analysis method of a motion mechanism based on a one-way digital twin are implemented. For example, the computer program / instruction implements the following steps:

[0211] Step S101: receiving and identifying the motion mechanism operation data according to a preset time interval, and determining the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters;

[0212] Step S102: determining the corresponding motion mechanism posture according to the joint angle data and a preset robot forward kinematics algorithm, determining the corresponding motion mechanism running trajectory according to the expandable additional parameters, performing a time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determining a corresponding time statistics result;

[0213] Step S103: collecting historical motion mechanism data, performing feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and a dynamic model, determining corresponding physical features of motion efficiency, performing interactive feature construction operations on the physical features of motion efficiency, determining corresponding physical feature data sets, performing model training on a preset initial model according to the physical feature data sets, performing performance evaluation on the model after the model training according to a preset determination coefficient, determining corresponding performance evaluation results, updating parameters of the initial model according to the performance evaluation results, and determining a corresponding robot time adjustment model;

[0214] Step S104: input the time statistics result into the robot time adjustment model, determine the corresponding optimal time parameters, update the trajectory point data according to the optimal time parameters, and control the robot according to the updated trajectory point data.

[0215] From the above description, it can be seen that the computer program product provided in the embodiment of the present application determines the corresponding time statistical results by receiving and identifying the motion mechanism operation data according to a preset time interval; collects historical motion mechanism data, performs feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and dynamic model, determines the corresponding physical characteristics of motion efficiency, performs interactive feature construction operations on the physical characteristics of motion efficiency, determines the corresponding physical characteristic data set, performs model training on the preset initial model according to the physical characteristic data set, and determines the corresponding robot time adjustment model; inputs the time statistical results into the robot time adjustment model, determines the corresponding optimal time parameters, and controls the robot according to the optimal time parameters, thereby being able to improve the control efficiency and accuracy of the motion mechanism based on time statistics and adjustment.

[0216] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0217] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0218] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0219] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0220] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A time statistical analysis method for a motion mechanism based on a one-way digital twin, characterized in that: The method comprises: Receiving and identifying the motion mechanism operation data according to a preset time interval to determine the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters; Determine the corresponding motion mechanism posture according to the joint angle data and the preset robot forward kinematics algorithm, determine the corresponding motion mechanism running trajectory according to the expandable additional parameters, perform time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determine the corresponding time statistics result; Collect historical motion mechanism data, perform feature extraction operations on the historical motion mechanism data according to a preset robot kinematic model and a dynamic model, determine corresponding physical features of motion efficiency, perform interactive feature construction operations on the physical features of motion efficiency, determine corresponding physical feature data sets, perform model training on a preset initial model according to the physical feature data sets, perform performance evaluation on the model after the model training according to a preset determination coefficient, determine corresponding performance evaluation results, update parameters of the initial model according to the performance evaluation results, and determine a corresponding robot time adjustment model; The time statistics result is input into the robot time adjustment model to determine the corresponding optimal time parameters, the trajectory point data is updated according to the optimal time parameters, and the robot is controlled according to the updated trajectory point data.

2. The time statistical analysis method of a motion mechanism based on a one-way digital twin according to claim 1 is characterized in that: The step of determining the corresponding motion mechanism running trajectory according to the expandable additional parameters includes: Performing an identification operation on the expandable additional parameters to determine a corresponding trajectory starting point, a trajectory ending point, and a trajectory distance between each trajectory point; The trajectory distances between the trajectory points are accumulated to determine the corresponding total trajectory distance, and the corresponding motion mechanism running trajectory is determined according to the trajectory starting point, the trajectory ending point and the total trajectory distance.

3. The time statistical analysis method of a motion mechanism based on a one-way digital twin according to claim 1 is characterized in that: The performing of time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory to determine the corresponding time statistics result includes: Determine the trajectory running time according to the number of trajectory points included in the running trajectory of the motion mechanism and the preset time interval; A posture mapping operation is performed on the trajectory running time and the total trajectory distance according to the posture of the motion mechanism, and a time statistics operation is performed on the trajectory running time and the total trajectory distance after the mapping operation to determine a corresponding time statistics result.

4. The time statistical analysis method of a motion mechanism based on a one-way digital twin according to claim 1 is characterized in that: Before performing a feature extraction operation on the historical motion mechanism data according to the preset robot kinematic model and dynamic model to determine the corresponding physical features of motion efficiency, the method includes: Determine a corresponding robot kinematics model according to preset robot joint angles, velocities, and accelerations, wherein the robot kinematics model is used to represent the robot joint motion relationship; The corresponding robot dynamics model is determined according to the preset robot torque, load and energy consumption, and the robot dynamics model is used to represent the physical characteristics of the robot movement process.

5. The time statistical analysis method of a motion mechanism based on a one-way digital twin according to claim 1 is characterized in that: The performing interactive feature construction operation on the physical feature of the motion efficiency to determine a corresponding physical feature data set includes: Interactively combining different physical characteristics of the motion efficiency to determine corresponding composite characteristics; A corresponding physical feature data set is determined according to the composite feature.

6. The time statistical analysis method of a motion mechanism based on one-way digital twin according to claim 1 is characterized in that: The updating of the parameters of the initial model according to the performance evaluation result to determine the corresponding robot time adjustment model includes: Performing sensitivity analysis on the parameters of the initial model according to a preset sensitivity analysis algorithm to determine corresponding high-sensitivity parameters; The highly sensitive parameters are iteratively updated according to the performance evaluation results to determine a corresponding robot time adjustment model.

7. The time statistical analysis method of a motion mechanism based on one-way digital twin according to claim 1 is characterized in that: After the robot is controlled according to the updated trajectory point data, the method further comprises: Performing a saving operation on the updated trajectory point data to determine the corresponding saved trajectory points; A backtracking operation is performed on the saved trajectory point to determine corresponding robot backtracking data, wherein the backtracking operation includes simulating dragging or double-clicking the trajectory point, and the backtracking data includes at least one of a robot posture and a robot operating state.

8. A motion mechanism time statistics analysis device based on one-way digital twin, characterized in that: The device comprises: A communication and driving module, used to receive and identify the motion mechanism operation data according to a preset time interval, and determine the corresponding trajectory point data, wherein the trajectory point data includes joint angle data and expandable additional parameters; A time statistics module, used to determine the corresponding motion mechanism posture according to the joint angle data and a preset robot forward kinematics algorithm, determine the corresponding motion mechanism running trajectory according to the expandable additional parameters, perform a time statistics operation according to the motion mechanism posture and the motion mechanism running trajectory, and determine the corresponding time statistics result; The time adjustment model training module is used to collect historical motion mechanism data, perform feature extraction operations on the historical motion mechanism data according to the preset robot kinematic model and dynamic model, determine the corresponding physical characteristics of motion efficiency, perform interactive feature construction operations on the physical characteristics of motion efficiency, determine the corresponding physical characteristic data set, perform model training on the preset initial model according to the physical characteristic data set, perform performance evaluation on the model after the model training according to the preset determination coefficient, determine the corresponding performance evaluation results, update the parameters of the initial model according to the performance evaluation results, and determine the corresponding robot time adjustment model. The time adjustment and data storage module is used to input the time statistical results into the robot time adjustment model, determine the corresponding optimal time parameters, update the trajectory point data according to the optimal time parameters, and control the robot according to the updated trajectory point data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the motion mechanism time statistical analysis method based on unidirectional digital twin according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the time statistical analysis method of a motion mechanism based on a unidirectional digital twin as described in any one of claims 1 to 7 are implemented.

Images