Scene reproduction and augmented reality simulation training method for floating installation

Abstract

The invention provides a scene reproduction and augmented reality simulation training method for floating installation. The method comprises the following steps: acquiring an external environment and an equipment state in real time; acquiring operation behavior data of the trainee in the training process, performing timestamp matching on the operation behavior data and the dynamic simulation scene, constructing a synchronous model, calculating a key performance index based on the synchronized data to quantify the operation effect of the trainee, and obtaining an operation performance record; when it is detected that the student fails to operate, a failure scene of the student is reconstructed based on currently collected operation behavior data and a dynamic simulation scene, and a failure path is analyzed by using a reinforcement learning model; generating an optimized floating track and an optimized posture adjustment path according to the failure scene of the reconstructed student and the optimization suggestion; and the trainee completes the floating support installation operation according to the optimized path displayed by the augmented reality equipment. According to the invention, the efficiency and effect of floating support installation training can be greatly improved, and a more efficient and intelligent solution is provided for the ocean engineering field.

Description

Technical Field

[0001] The present invention belongs to the field of floating installation, and particularly relates to a method for scenario reproduction and augmented reality simulation training for floating installation. Background Art

[0002] Floating installation is a key technology for large-scale structure deployment in ocean engineering, and is widely used in the installation processes of offshore platforms, wind farm infrastructures, etc. Due to the complexity of the marine environment, floating installation needs to be completed in a highly dynamic environment, including changes in sea waves, tides, and wind speeds, as well as complex hoisting and docking operations. The combination of these environmental factors and the high-precision requirements of the installation task makes floating installation an extremely challenging task.

[0003] Traditional floating installation training methods mainly rely on two methods: theoretical teaching and training based on offline simulation. Theoretical teaching usually focuses on installation principles, equipment operation specifications, and emergency handling procedures. However, this method cannot provide the experience of dynamic changes in the real environment and is difficult to effectively improve the practical operation ability of trainees. Offline simulation training provides operation practice for trainees through preset scenarios and tasks. However, existing simulation systems usually have the following technical limitations: Lack of high-fidelity reproduction ability of dynamic scenarios: Traditional simulation systems usually rely on fixed or simple physical models and cannot fully represent the dynamic behavior of floating bodies in the real marine environment. For example, the non-linear effects of waves, the influence of wind-wave coupling on the attitude of floating bodies, and the complex movements of hoisting equipment are often simplified or ignored in existing simulations.

[0004] Lack of a refined review mechanism for failed operations: During the actual installation process, trainees may fail due to incorrect operations. However, existing training systems usually have difficulty recording and restoring the entire process of failed scenarios, resulting in trainees being unable to understand the reasons for failure and unable to obtain optimization strategies.

[0005] Insufficient guidance and poor interaction experience: Current simulation training only provides feedback in the form of text or simple images, lacking real-time intuitive guidance and multi-sensory interaction experience, and the learning effect of trainees under high-pressure situations is poor. Summary of the Invention

[0006] The purpose of the present invention is to propose a method for scenario reproduction and augmented reality simulation training for floating installation, which provides a more realistic, refined, and targeted floating installation training method by introducing real-time physical simulation, fine-grained scene reconstruction, and augmented reality interactive guidance; To achieve the above purpose, the present invention provides a method for scenario reproduction and augmented reality simulation training for floating installation, the method comprising: The real-time collection of external environment and equipment status is used to build a dynamic coupling physical model, and the impact of the environment and equipment on the float is comprehensively calculated to initialize the physical simulation scene. Then, the motion trajectory and attitude change of the float are calculated from the acceleration through the numerical integration method, and the motion trajectory and attitude change are added to the initialized physical simulation scene to obtain the dynamic simulation scene. Collect the trainees' operational behavior data during the training process, match the operational behavior data with the dynamic simulation scene by time stamp, build a synchronization model, output the synchronized data, calculate the key performance indicators based on the synchronized data to quantify the trainees' operational effects, and obtain the operational performance record; When a student's failed operation is detected, the student's failure scenario is reconstructed based on the currently collected operation behavior data and dynamic simulation scenarios, and the failure path is analyzed using the reinforcement learning model, and optimization suggestions are generated based on the analysis results; Generate an optimized floating trajectory and attitude adjustment path according to the failure scenario and optimization suggestions, design a path optimization function based on the optimized floating trajectory and attitude adjustment path to obtain an optimized path, and generate dynamic visualization guidance through augmented reality equipment to identify dangerous warning information in real time during interaction, and generate step-by-step operation prompts in real time according to the optimized path; Trainees complete the floatation installation operation according to the optimized path displayed by the augmented reality device, and error aggregation analysis is performed on the trainees’ new operation data and floatation response. Based on the results of the error aggregation analysis, a trainee operation evaluation report is generated.

[0007] Furthermore, the dynamic simulation scenario includes motion trajectory, floating attitude angle time series and wave force; The external environment and equipment status include a time series of wave height, a time series of wind speed, a time series of tidal direction, an initial position of the crane and an initial attitude of the floatation; The steps for constructing the dynamic coupling physical model are: The wave force vector is calculated using nonlinear wave theory, and its action is at the center of mass of the float. The wave force vector is solved together with the crane load position and the center of mass balance of the float to obtain the linear acceleration and angular acceleration of the float under instantaneous action. The magnitude of the wave force vector is the wave force. The motion trajectory and attitude change of the float are calculated from the acceleration by numerical integration method, specifically including: By integrating the linear acceleration and the angular acceleration, the instantaneous linear velocity and the instantaneous angular velocity of the floatation are obtained, and the motion trajectory and attitude change of the floatation are calculated according to the instantaneous linear velocity and the instantaneous angular velocity.

[0008] Furthermore, the operation behavior data includes the crane operation position, crane angle adjustment, and the lifting force applied by the crane; the key performance indicators include the floating deviation and the attitude adjustment error. The floating deviation is the deviation between the actual position and the target position of the floating, which is used to evaluate the operation accuracy. The attitude adjustment error is the error between the actual attitude and the ideal attitude of the floating. The synchronization model is constructed as follows: Match the time stamps of the trainee's operation behavior data and the dynamic simulation scenario data. Weighted time interpolation model is used for synchronization to address the alignment issues caused by differences in sensor sampling frequencies.

[0009] Furthermore, the failure operation criteria for the trainee are based on real-time data monitoring during the installation process: If the floating fails to complete the docking within the specified time during the installation process, or its position error exceeds the preset tolerance range, the attitude error exceeds the allowable angle, and the floating fails to be firmly fixed at the target position, showing deviation or imbalance, or abnormal force fluctuations are sensed during the installation process, it is determined that the installation has failed.

[0010] Furthermore, the reinforcement learning model is constructed as follows: Define a comprehensive error function that combines the floating trajectory deviation and the attitude adjustment error, and introduce a regularization term to control the influence of waves. Optimize the comprehensive error function through the reinforcement learning strategy to generate an improved solution for the failure path.

[0011] Furthermore, during the process of generating the optimized path, to reflect the influence of wave forces on the floating trajectory, an environmental dynamic term based on the environmental dynamic adjustment coefficient is added to the path optimization. Among them, the environmental dynamic adjustment coefficient is used to adjust the influence intensity of waves on the floating path and is determined according to the floating mass and the environmental perturbation amplitude. And for the common error patterns of trainees, a correction term based on the crane angle adjustment is introduced in the optimized attitude adjustment path. The correction term based on the crane angle adjustment is used to dynamically adjust the correction amplitude of the crane angle for the attitude error, and the value range .

[0012] Furthermore, the generation of dynamic visualization guidance through the augmented reality device includes the following parts: Dynamically project the optimized floating trajectory in the trainee's field of vision and display the direction in which the floating needs to move in the form of a continuous path line. Display the difference between the current floating attitude and the optimized attitude adjustment path in a graphical overlay manner, and prompt the trainee how to adjust the attitude angle through an arrow. Mark the areas where the floating may tip over or collide with other structures, and use a color warning mechanism to update the danger information in real time.

[0013] Furthermore, the real-time generation of step-by-step operation prompts includes: The prompt includes the optimized crane position and the optimized angle adjustment; The prompt mechanism introduces a priority rule.

[0014] Furthermore, when the trainee executes the installation according to the optimized path, the actual operation data of the trainee is recorded in real time, including the new crane position, angle adjustment, and lifting force. At the same time, the real-time response data of the floating dock is recorded, including the floating dock trajectory and the floating dock adjustment attitude. The new operation data of the trainee and the floating dock response are analyzed, and the key performance indicators of the trainee's operation are calculated. The key performance indicators include the floating dock trajectory error and the attitude adjustment error, and an environmental sensitivity analysis item is introduced. The weights of the floating dock trajectory error and the attitude adjustment error are corrected in combination with the wave action to obtain an error aggregation evaluation value, which represents the quantitative result of the trainee's overall operation effect.

[0015] Furthermore, based on the error aggregation evaluation value, a trainee operation evaluation report is generated, including: The overall operation score, based on the error aggregation evaluation value is scored; The independent evaluation results of each subtask; Improvement suggestions for the trainee are put forward, including: Targeted practice tasks; Environmental adaptability strategy adjustment.

[0016] The beneficial technical effects of the present invention are at least as follows: By introducing computational fluid dynamics (CFD) and multi-rigid body dynamics (MBD) models, the present invention dynamically simulates the force and motion behavior of the floating dock in a complex marine environment. By combining real-time environmental parameters (such as waves, wind speed, and tides) and equipment operation parameters (such as crane position and floating dock attitude), the present invention can generate a highly realistic dynamic scene. This technology breaks through the static and simplified problems of traditional simulation systems and provides a more practical training experience for trainees.

[0017] The present invention designs a failure scenario reconstruction module based on high-precision 3D point clouds and physical parameter records. When the operation fails, the system can restore the entire failure process, including key steps, equipment status, and environmental factors. By superimposing a reinforcement learning algorithm, the failure path is analyzed and an optimized strategy is generated, so as to provide clear improvement suggestions for trainees. This invention effectively solves the pain point of the lack of failure analysis and guidance in the prior art, enabling trainees to quickly master coping skills in complex scenarios.

[0018] Through augmented reality (AR) technology, the present invention overlays simulation and optimization content onto the actual operation scenario in real time, providing trainees with dynamic step-by-step guidance and real-time feedback. For example, the system can highlight the ideal installation trajectory of the floating support during the hoisting process, mark dangerous areas, or provide operation adjustment tips. This multi-sensory interaction experience greatly improves trainees' understanding and execution abilities of complex tasks, while making up for the lack of guidance in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the following drawings.

[0020] Figure 1 It is a flowchart of a method for scenario reproduction and augmented reality simulation training for floating support installation according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention.

[0022] As Figure 1 shown, a method for scenario reproduction and augmented reality simulation training for floating support installation provided by an embodiment of the present invention includes the following steps S1 - S5: S1. Collect the external environment and equipment status in real time, construct a dynamic coupled physical model, comprehensively calculate the influence of the environment and equipment on the floating support to initialize the physical simulation scenario, and then use the numerical integration method to calculate the movement trajectory and attitude change of the floating support from the acceleration, and add the movement trajectory and attitude change to the initialized physical simulation scenario to obtain a dynamic simulation scenario. The dynamic simulation scenario includes the movement trajectory, the time series of the attitude angle of the floating support, and the wave force.

[0023] Specifically, this step aims to generate a highly realistic dynamic scenario through real-time physical simulation as the basic environment for floating support installation training. By collecting external environment parameters (such as wave height, wind speed) and equipment status (such as crane position, floating support attitude), a dynamic coupled physical model is established to comprehensively calculate the force and movement influence of the environment and equipment on the floating support, and generate dynamic simulation data streams such as three-dimensional trajectories and attitude changes. These data support the trainees' operations and behavior monitoring in the subsequent steps, ensuring that the scenario is highly consistent with the actual working conditions.

[0024] Specifically, the input parameters come from the external environment and equipment status collected in real time and include: : Time series of wave height, in meters, measured from a multi-point ocean buoy.

[0025] : Time series of wind speed, in meters per second, from a wind speed sensor.

[0026] : Time series of current direction, in radians, collected by a current sensor.

[0027] : Initial position of the crane, in three-dimensional coordinates (meters), from the crane positioning system.

[0028] : Initial attitude of the floating support, in attitude angles (pitch angle, yaw angle, roll angle, in degrees), provided by the floating support attitude sensor.

[0029] Furthermore, initialize the physical simulation scenario: Adopt a specially designed dynamic coupling physical model to comprehensively calculate the influence of the environment and equipment on the floating support. The main process of the model is as follows: First, calculate the wave force using the nonlinear wave theory , which acts on the centroid position of the floating support, and the formula is: ; Where, is the seawater density (about 1025 kg / m³). is the acceleration due to gravity (9.81 m / s²). is the wave amplitude (related to ). is the wave number (related to the wave period). is the angular frequency ( , is the wave period).

[0030] Combine with the crane load position and the balance of the floating support center of gravity to solve simultaneously, and obtain the linear acceleration and angular acceleration of the floating support under instantaneous action.

[0031] Furthermore, through the numerical integration method, calculate the movement trajectory and attitude change of the floating support from the acceleration: ; Where, is the instantaneous linear velocity of the floating support (obtained by integrating ). is the instantaneous angular velocity of the floating barge (obtained by integration ).

[0032] Furthermore, the dynamic simulation scenario includes: is the time series of the attitude angle of the floating barge, in degrees. is the wave acting force, in Newtons. This scenario is input as the basic scenario for subsequent trainee operations.

[0033] S2. Collect the operation behavior data of the trainee during the training process, match the operation behavior data with the dynamic simulation scenario by timestamp, construct a synchronization model, output the synchronized data, calculate the key performance indicators based on the synchronized data to quantify the operation effect of the trainee, and obtain the operation performance record; wherein, the operation behavior data includes the crane operation position, the crane angle adjustment, and the lifting force applied by the crane; the key performance indicators include the floating barge deviation and the attitude adjustment error, the floating barge deviation is the deviation between the actual position and the target position of the floating barge, used to evaluate the operation accuracy, and the attitude adjustment error is the error between the actual attitude and the ideal attitude of the floating barge.

[0034] Specifically, this step generates a complete operation performance record by real-time recording the behavior data of the trainee during the floating barge installation operation and integrating it with the dynamic simulation scenario data. Considering the complexity and dynamics of the floating barge installation, this step designs a high-precision recording scheme for the interaction between the trainee's behavior and the scenario, and particularly introduces a performance indicator calculation based on error feedback and a weight regulation formula for environmental dynamic interference. This design ensures the comprehensiveness and pertinence of the operation record, laying a foundation for subsequent failure scenario analysis and optimization.

[0035] Input the dynamic simulation scenario data: Receive the dynamic simulation scenario data stream from step S1 , including: : The three-dimensional motion trajectory of the floating barge, in meters.

[0036] : The time series of the attitude change of the floating barge, in degrees.

[0037] : The time series of the wave acting force, in Newtons.

[0038] Furthermore, collect the operation behavior data of the trainee: Use a high-precision motion capture system and device sensors to real-time collect the operation behavior data of the trainee during the training process , including: : The crane operation position, in three-dimensional coordinates (meters).

[0039] : Crane angle adjustment, in degrees.

[0040] : Lifting force applied by the crane, in Newtons.

[0041] Furthermore, match the trainee operation behavior data with the dynamic scenario data and establish a synchronization model: ; where is a complete operation performance record, including trainee operation behavior and scenario response.

[0042] The synchronization adopts a weighted time interpolation model to address the alignment issue caused by differences in sensor sampling frequencies: ; where is the interpolation weight based on the time difference, defined as where and are adjacent timestamps. is the crane position after synchronization, in meters.

[0043] Furthermore, to reflect the impact of environmental dynamics (such as waves, wind speed) during the floating operation, introduce an environmental disturbance weight correction term to the collected operation data: ; where is the environmental dynamics weight, and the larger the value, the stronger the environmental disturbance. is the adjustment coefficient, used to adjust the influence intensity of wave force on the weight (value range 0.1 - 0.5). is the reference wave force, which is the mean value of wave acting forces.

[0044] Multiply the key behavior parameters (such as crane force ) by the weight correction to reflect the dynamic interference of the environment on the operation: ; Furthermore, based on the synchronized data , calculate the key performance indicators to quantify the operation effect of the trainee: Floating deviation : The deviation between the actual floating position and the target position, used to evaluate the operation accuracy.

[0045] ; where The actual position of the floating support, from the simulation scenario data. The target position of the floating support, preset by the scenario.

[0046] Attitude adjustment error : The error between the actual attitude of the floating support and the ideal attitude.

[0047] ; Among them, The actual attitude of the floating support, from the simulation scenario data. The ideal attitude of the floating support, preset by the scenario.

[0048] By introducing time synchronization interpolation and environmental dynamic weight correction, the design of this step effectively reflects the dynamic complexity in the floating support installation operation, ensuring the precise association between operation data and environmental factors. These high-precision operation records provide reliable basic data for subsequent failure scenario reconstruction and optimization.

[0049] S3. When it is detected that the trainee has a failed operation, based on the currently collected operation behavior data and the dynamic simulation scenario, reconstruct the trainee's failure scenario, and use the reinforcement learning model to analyze the failure path. The optimization goal of the reinforcement learning model takes the deviation of the floating support trajectory and attitude as the core, and generates optimization suggestions based on the analysis results.

[0050] Specifically, this step reconstructs the failure scenario of the floating support installation based on the operation performance record, and analyzes the key problem points in the trainee's operation process to generate optimization suggestions. In view of the dynamic complexity and high-precision requirements of the floating support installation, this step combines 3D point cloud reconstruction and enhanced path analysis to construct a multi-modal fusion model.

[0051] Furthermore, failure scenario reconstruction: Based on the operation data and the simulation data , reconstruct the trainee's failure scenario , and the judgment criterion for whether it is a failure is based on the real-time data monitoring during the installation process. Specifically, if the floating support fails to complete the docking within the specified time during the installation process, or its position error exceeds the preset tolerance range (such as ±2 cm), the attitude error exceeds the allowable angle (such as ±1 degree), and the floating support fails to be firmly fixed at the target position, showing obvious deviation or imbalance, or abnormal force fluctuations (such as overloading pressure exceeding 100 N) are sensed during the installation process, it is determined that the installation fails.

[0052] Introduce an environmental dynamic correction term to reflect the influence of wave force on the floating support trajectory and attitude: ; Among them, Is the reconstructed floating trajectory. Is the dynamic correction coefficient, which is set according to the mass of the floating support and environmental parameters.

[0053] For the attitude data Introduce an operation interference term to adjust the influence of the crane angle: ; Among them, Is the operation interference coefficient, which is used to quantify the influence of the crane angle on the floating support attitude.

[0054] Finally, the failure scenario Combines the trajectory and attitude reconstruction results to provide a complete dynamic description for analysis.

[0055] Furthermore, use the reinforcement learning model to analyze the failure path , and the optimization objective takes the deviation of the floating support trajectory and attitude as the core: Define a comprehensive error function , combine the floating support trajectory deviation and the attitude adjustment error , and introduce a regularization term to control the influence of waves: ; Among them, Is the weight factor of the attitude error. Is the regulation factor of the wave influence.

[0056] Through the reinforcement learning strategy for Optimize to generate an improved plan for the failure path.

[0057] S4. Generate an optimized floating support trajectory and attitude adjustment path according to the failure scenario and optimization suggestions of the reconstructed trainee. Based on the optimized floating support trajectory and attitude adjustment path, design a path optimization function to obtain the optimized path. At the same time, generate dynamic visual guidance through an augmented reality device to real-time identify warning information in the interaction, and generate step-by-step operation prompts in real-time according to the optimized path.

[0058] Specifically, this step integrates the failure scenario data and optimization suggestions of the previous step to generate optimized dynamic guidance, intuitively showing the operation path and adjustment suggestions that the trainee needs to complete. Combining the dynamic complexity of the floating support installation scenario, this step introduces an environmental dynamic term and trainee operation correction in path optimization, and at the same time dynamically projects the optimization results through augmented reality (AR) technology to ensure the accuracy and interactivity of the guidance. The entire design focuses on the special requirements of floating support installation, and pays attention to the dynamic adaptability of the environment and trainee operation in path optimization and interaction.

[0059] Furthermore, generate an optimized path: Generate an optimized floating trajectory based on the input data and an attitude adjustment path . Introduce the following key innovations: Environmental dynamic term: To reflect the influence of wave forces on the floating trajectory, add an environmental dynamic term to the path optimization : ; where is the environmental dynamic adjustment coefficient, which adjusts the influence intensity of waves on the floating path and is determined according to the floating mass and environmental disturbance amplitude.

[0060] Furthermore, for the common error patterns of trainees, introduce a correction term in the attitude adjustment path : ; is the correction coefficient, which dynamically adjusts the correction amplitude of the crane angle for attitude errors, and the value range is .

[0061] Furthermore, to avoid excessive drift of the trajectory caused by the environmental correction term , add a regularization constraint term to balance the amplitude of path adjustment: ; where is the objective function for path smoothing, which is used to limit the excessive deviation of the optimized path from the original path. is the regularization strength, which is used to control the weight change of the environmental term .

[0062] Furthermore, based on the optimized path, generate dynamic visual guidance through an augmented reality (AR) device, which is divided into the following parts: Trajectory projection: Dynamically project the floating target trajectory in the trainee's field of vision , and display the direction in which the floating body needs to move in the form of a continuous path line.

[0063] Attitude adjustment highlighting: Display the difference between the current floating attitude and the target attitude in the form of a graphical overlay, and prompt the trainee how to adjust the attitude angle through an arrow.

[0064] Hazard area marking: Mark the areas where the floating body may overturn or collide with other structures, and use a color warning mechanism to update the hazard information in real time.

[0065] Real-time interactive prompt generation: According to the optimized path , real-time generate step-by-step operation prompts: The prompt includes the target crane position and angle adjustment .

[0066] The prompt mechanism introduces a priority rule. For example, when the wave force is large, priority is given to providing stability adjustment prompts.

[0067] S5. The trainee completes the floating installation operation according to the optimized path shown by the augmented reality device, and re-performs error aggregation analysis on the trainee's new operation data and the floating response. Based on the results of the error aggregation analysis, a trainee operation evaluation report is generated.

[0068] Specifically, this step is based on dynamic guidance data to help the trainee perform the optimized floating installation operation, and evaluates its improvement effect through precise data comparison and quantitative analysis. By introducing an evaluation model based on error aggregation and environmental dynamic sensitivity analysis, this step fully considers the dynamic characteristics of the floating installation scenario and the trainee's operation performance in the operation evaluation, and provides specific suggestions for subsequent training optimization.

[0069] Furthermore, perform improvement operations: The trainee completes the floating installation operation according to the optimized path : The system records the trainee's actual operation data in real time , including the new crane position , angle adjustment and lifting force .

[0070] At the same time, record the real-time response data of the floating , including the floating trajectory and attitude .

[0071] Furthermore, analyze the trainee's new operation data and the floating response, and calculate the key performance indicators of the trainee's operation, including the floating trajectory error and attitude adjustment error : ; Among them, is the deviation between the actual floating trajectory and the target trajectory, used to evaluate the accuracy of the operation. is the deviation between the actual value and the target value of the floating attitude, used to evaluate the attitude adjustment effect.

[0072] Introduce an environmental sensitivity analysis item , combined with wave action, weight correction is performed on the error: ; Among them, is the error aggregation evaluation value, representing the quantitative result of the overall operation effect of the trainee. is the weight of the attitude adjustment error, adjusting the importance ratio of the trajectory and the attitude. is the environmental sensitivity adjustment coefficient, reflecting the degree of influence of wave force on the operation.

[0073] Furthermore, an evaluation report and improvement suggestions are generated: According to the results of the error aggregation analysis, an operation evaluation report for the trainee is generated : The overall operation score is based on value for scoring.

[0074] Independent evaluation results of each subtask (such as crane position adjustment, floating support attitude adjustment).

[0075] Furthermore, improvement suggestions for the trainee are put forward, including: Targeted practice tasks (such as focusing on strengthening the floating support attitude adjustment ability).

[0076] Environmental adaptability strategy adjustment (such as optimizing the operation flexibility in scenarios with strong wave force).

[0077] Furthermore, the evaluation and suggestion data are output: Output the operation evaluation report of the trainee , including: Analysis results of operation errors (trajectory error and attitude error ).

[0078] Evaluation of the influence of environmental sensitivity on errors.

[0079] Targeted improvement suggestions.

[0080] As the input for subsequent training optimization, a closed-loop improvement mechanism is formed.

[0081] It should be noted that the above-described work process is only illustrative and does not limit the protection scope of the present invention. In actual applications, those skilled in the art can select some or all of them according to actual needs to achieve the purpose of the solution of this embodiment, and no limitation is made here.

[0082] In addition, for the technical details not described in detail in this embodiment, reference can be made to the parameter operation method provided in any embodiment of the present invention, and details are not repeated here.

[0083] It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or system that includes a series of elements not only includes those elements, but also includes other elements that are not explicitly listed, or also includes such a process.

Claims

1. A scene reproduction and augmented reality simulation training method for floating installation, characterized in that: The method comprises: The real-time collection of external environment and equipment status is used to build a dynamic coupling physical model, and the impact of the environment and equipment on the float is comprehensively calculated to initialize the physical simulation scene. Then, the motion trajectory and attitude change of the float are calculated from the acceleration through the numerical integration method, and the motion trajectory and attitude change are added to the initialized physical simulation scene to obtain the dynamic simulation scene. Collect the trainees' operational behavior data during the training process, match the operational behavior data with the dynamic simulation scene by time stamp, build a synchronization model, output the synchronized data, calculate the key performance indicators based on the synchronized data to quantify the trainees' operational effects, and obtain the operational performance record; When a student's failed operation is detected, the student's failure scenario is reconstructed based on the currently collected operation behavior data and dynamic simulation scenarios, and the failure path is analyzed using the reinforcement learning model, and optimization suggestions are generated based on the analysis results; Generate an optimized floating trajectory and attitude adjustment path according to the failure scenario and optimization suggestions, design a path optimization function based on the optimized floating trajectory and attitude adjustment path to obtain an optimized path, and generate dynamic visualization guidance through augmented reality equipment to identify dangerous warning information in real time during interaction, and generate step-by-step operation prompts in real time according to the optimized path; Trainees complete the floatation installation operation according to the optimized path displayed by the augmented reality device, and error aggregation analysis is performed on the trainees’ new operation data and floatation response. Based on the results of the error aggregation analysis, a trainee operation evaluation report is generated.

2. A scene reproduction and augmented reality simulation training method for floating installation according to claim 1, characterized in that: The dynamic simulation scenario includes motion trajectory, floating attitude angle time series and wave force; The external environment and equipment status include a time series of wave height, a time series of wind speed, a time series of tidal direction, an initial position of the crane and an initial attitude of the floatation; The steps for constructing the dynamic coupling physical model are: The wave force vector is calculated using nonlinear wave theory, and its action is at the center of mass of the float. The wave force vector is solved together with the crane load position and the center of mass balance of the float to obtain the linear acceleration and angular acceleration of the float under instantaneous action. The magnitude of the wave force vector is the wave force. The motion trajectory and attitude change of the float are calculated from the acceleration by numerical integration method, specifically including: By integrating the linear acceleration and the angular acceleration, the instantaneous linear velocity and the instantaneous angular velocity of the floatation are obtained, and the motion trajectory and attitude change of the floatation are calculated according to the instantaneous linear velocity and the instantaneous angular velocity.

3. A scene reproduction and augmented reality simulation training method for floating installation according to claim 1, characterized in that: The operation behavior data includes the crane operation position, crane angle adjustment and the lifting force applied by the crane; the key performance indicators include floating deviation and attitude adjustment error, the floating deviation is the deviation between the actual floating position and the target position, which is used to evaluate the operation accuracy, and the attitude adjustment error is the error between the actual floating attitude and the ideal attitude; The synchronization model is constructed as follows: Match the trainee operation behavior data with the dynamic simulation scene data by time stamp; A weighted time interpolation model is used synchronously to deal with the alignment problem caused by the difference in sensor sampling frequencies.

4. A scene reproduction and augmented reality simulation training method for floating installation according to claim 1, characterized in that: The student's failure operation criteria are based on real-time data monitoring during the installation process: If the float fails to complete docking within the specified time during the installation process, or its position error exceeds the preset tolerance range, the attitude error exceeds the allowable angle, and the float fails to be firmly fixed at the target position, an offset or unbalanced state occurs, or abnormal force fluctuations are sensed during the installation process, it is judged as an installation failure.

5. A scene reproduction and augmented reality simulation training method for floating installation according to claim 4, characterized in that: The reinforcement learning model is constructed as follows: Define a comprehensive error function that combines the floating trajectory deviation and attitude adjustment error, and introduce a regularization term to control the wave impact; The comprehensive error function is optimized through reinforcement learning strategy to generate improvement plans for the failure path.

6. A scene reproduction and augmented reality simulation training method for floating installation according to claim 5, characterized in that: In the process of optimizing the path generation, in order to reflect the influence of wave force on the floating trajectory, an environmental dynamic term based on the environmental dynamic adjustment coefficient is added to the path optimization; wherein the environmental dynamic adjustment coefficient is used to adjust the intensity of the influence of waves on the floating path, which is determined according to the floating quality and the amplitude of environmental disturbance; In view of the common error patterns of students, a correction item based on crane angle adjustment is introduced into the optimization posture adjustment path; the correction item based on crane angle adjustment is used to dynamically adjust the correction amplitude of the crane angle to the posture error, and the value range is .

7. A scene reproduction and augmented reality simulation training method for floating installation according to claim 6, characterized in that: The method of generating dynamic visual guidance by using an augmented reality device includes the following parts: Dynamically project the optimized float trajectory in the trainee's field of view, showing the direction the float needs to move in the form of a continuous path line; The difference between the current floating posture and the optimized posture adjustment path is displayed in a graphical overlay, and arrows are used to prompt students how to adjust the posture angle; Mark areas where floatovers may capsize or collide with other structures, and use a color warning mechanism to update hazard information in real time.

8. The scene reproduction and augmented reality simulation training method for floating installation according to claim 6, characterized in that: The real-time generation of step-by-step operation prompts includes: Tips include optimized crane position and optimized angle adjustment; The prompt mechanism introduces priority rules.

9. A scene reproduction and augmented reality simulation training method for floating installation according to claim 8, characterized in that: When the trainees perform the installation according to the optimized path, the trainees' actual operation data are recorded in real time, including the new crane position, angle adjustment and lifting force. At the same time, the real-time response data of the floatation is recorded, including the floatation trajectory and the floatation adjustment posture. The trainees' new operation data and floatation response are analyzed, and the key performance indicators of the trainees' operation are calculated. The key performance indicators include the floatation trajectory error and the attitude adjustment error. The environmental sensitivity analysis item is introduced, and the floatation trajectory error and the attitude adjustment error are weighted and corrected in combination with the wave action to obtain the error aggregation evaluation value, which represents the quantitative result of the trainees' overall operation effect.

10. A scene reproduction and augmented reality simulation training method for floating installation according to claim 9, characterized in that: Based on the error aggregate evaluation value, a trainee operation evaluation report is generated, including: The overall operation score is scored based on the error aggregation evaluation value; Independent evaluation results of each subtask; Provide suggestions for improvement to students, including: Targeted practice tasks; Environmental adaptability strategy adjustment.

Images