A scene reproduction and augmented reality simulation training method for float-over installation

Abstract

The present invention proposes a scene reproduction and augmented reality simulation training method for floating installation, which includes: real-time collection of external environment and equipment status; collection of trainees' operational behavior data during training, matching the operational behavior data with dynamic simulation scenarios by time stamp, building a synchronization model, and calculating key performance indicators based on the synchronized data to quantify the trainees' operational effects, thereby obtaining operational performance records; when a trainee's failed operation is detected, the trainee's failure scenario is reconstructed based on the currently collected operational behavior data and dynamic simulation scenarios, and the failure path is analyzed using a reinforcement learning model; an optimized floating trajectory and attitude adjustment path are generated based on the reconstructed trainee's failure scenario and optimization suggestions; the trainee completes the floating installation operation according to the optimized path displayed by the augmented reality device. The present invention can significantly improve the efficiency and effectiveness of floating installation training, providing a more efficient and intelligent solution for the field of marine engineering.

Description

Technical Field

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

[0002] Floatover installation is a key technology for deploying large-scale structures in marine engineering, widely used in the installation of offshore platforms, wind farm infrastructure, and other applications. Due to the complexity of the marine environment, floatover installation must be carried out in a highly dynamic environment, including fluctuating waves, tides, and wind speeds, as well as complex lifting and docking operations. These environmental factors, combined with the high precision requirements of the installation task, make floatover installation a particularly challenging task.

[0003] Traditional floatover installation training relies primarily on two approaches: theoretical instruction and offline simulation-based training. Theoretical instruction typically focuses on installation principles, equipment operating specifications, and emergency response procedures. However, this approach fails to provide a dynamic experience in a real-world environment, making it difficult to effectively enhance trainees' practical skills. Offline simulation training, on the other hand, provides trainees with operational practice through pre-set scenarios and tasks. However, existing simulation systems often suffer from the following technical limitations:

[0004] Lack of high-fidelity reproduction of dynamic scenarios: Traditional simulation systems are typically based on fixed or simple physical models, which cannot fully represent the dynamic behavior of floaters in real marine environments. For example, key factors such as the nonlinear effects of waves, the impact of wind-wave coupling on floater posture, and the complex motion of lifting equipment are often simplified or ignored in existing simulations.

[0005] Lack of a detailed review mechanism for failed operations: During the actual installation process, trainees may fail due to incorrect operations. However, existing training systems often have difficulty recording and restoring the entire process of failure scenarios, making it difficult for trainees to understand the reasons for failure and obtain optimization strategies.

[0006] Insufficient guidance and poor interactive experience: Current simulation training only provides feedback in the form of text or simple images, lacking real-time intuitive guidance and multi-sensory interactive experience. As a result, students’ learning effect is poor under high-pressure situations. Summary of the Invention

[0007] Floatover installation is a key technology for deploying large-scale structures in marine engineering, widely used in the installation of offshore platforms, wind farm infrastructure, and other applications. Due to the complexity of the marine environment, floatover installation must be carried out in a highly dynamic environment, including fluctuating waves, tides, and wind speeds, as well as complex lifting and docking operations. These environmental factors, combined with the high precision requirements of the installation task, make floatover installation a particularly challenging task.

[0008] Traditional floatover installation training relies primarily on two approaches: theoretical instruction and offline simulation-based training. Theoretical instruction typically focuses on installation principles, equipment operating specifications, and emergency response procedures. However, this approach fails to provide a dynamic experience in a real-world environment, making it difficult to effectively enhance trainees' practical skills. Offline simulation training, on the other hand, provides trainees with operational practice through pre-set scenarios and tasks. However, existing simulation systems often suffer from the following technical limitations:

[0009] Lack of high-fidelity reproduction of dynamic scenarios: Traditional simulation systems are typically based on fixed or simple physical models, which cannot fully represent the dynamic behavior of floaters in real marine environments. For example, key factors such as the nonlinear effects of waves, the impact of wind-wave coupling on floater posture, and the complex motion of lifting equipment are often simplified or ignored in existing simulations.

[0010] Lack of a detailed review mechanism for failed operations: During the actual installation process, trainees may fail due to incorrect operations. However, existing training systems often have difficulty recording and restoring the entire process of failure scenarios, making it difficult for trainees to understand the reasons for failure and obtain optimization strategies.

[0011] Insufficient guidance and poor interactive experience: Current simulation training only provides feedback in the form of text or simple images, lacking real-time intuitive guidance and multi-sensory interactive experience. As a result, students’ learning effect is poor under high-pressure situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0013] Figure 1 This is a flow chart of a scene reproduction and augmented reality simulation training method for floatation installation according to the present invention. DETAILED DESCRIPTION

[0014] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0015] like Figure 1 As shown, an embodiment of the present invention provides a scene reproduction and augmented reality simulation training method for floating installation, the method comprising the following steps S1-S5:

[0016] S1. Real-time collection of external environment and equipment status is used to construct a dynamic coupling physical model. The impact of the environment and equipment on the float is comprehensively calculated to initialize the physical simulation scene. Then, through the numerical integration method, the motion trajectory and attitude changes of the float are calculated from the acceleration. The motion trajectory and attitude changes are added to the initialized physical simulation scene to obtain a dynamic simulation scene. The dynamic simulation scene includes the motion trajectory, the time series of the float's attitude angle, and wave forces.

[0017] Specifically, this step aims to generate a highly realistic dynamic scenario through real-time physics simulation, serving as the foundation for floatover installation training. By collecting external environmental parameters (such as wave height and wind speed) and equipment status (such as crane position and floatover attitude), a dynamic coupled physics model is established. This model comprehensively calculates the impact of the environment and equipment on the forces and motion of the floatover, generating dynamic simulation data streams such as 3D trajectory and attitude changes. This data supports subsequent training and behavior monitoring, ensuring that the scenario closely aligns with actual working conditions.

[0018] Specifically, the input parameters come from the real-time collection of external environment and device status, including:

[0019] : A time series of wave heights in meters, measured from multiple ocean buoys.

[0020] : Time series of wind speed in meters per second, from the wind speed sensor.

[0021] : Time series of tidal direction, in radians, collected by water flow sensors.

[0022] : The initial position of the crane, in three-dimensional coordinates (meters), comes from the crane positioning system.

[0023] : Initial attitude of the float, in attitude angles (pitch, yaw, roll, in degrees), provided by the float attitude sensor.

[0024] Furthermore, the physical simulation scene is initialized:

[0025] A specially designed dynamic coupled physics model is used to comprehensively calculate the impact of the environment and equipment on floatation. The main process of the model is:

[0026] First, the wave forces are calculated using nonlinear wave theory , which acts at the center of mass of the float, and the formula is:

[0027] ;

[0028] in, is the density of seawater (about 1025kg / m³). is the acceleration due to gravity (9.81 m / s²). is the wave amplitude (with related). is the wave number (related to the wave period). is the angular frequency ( , is the wave period).

[0029] Will Solve the problem together with the crane load position and the center of gravity balance of the float to obtain the linear acceleration of the float under instantaneous action. and angular acceleration .

[0030] Furthermore, the trajectory of the float is calculated from the acceleration by numerical integration method. and posture changes :

[0031] ;

[0032] in, is the instantaneous linear velocity of the float (by integrating get). is the instantaneous angular velocity of the float (by integrating get).

[0033] Furthermore, dynamic simulation scenarios Include: It is the time series of attitude angle of floatation, in degrees. is the wave force, in Newtons. This scenario serves as the basic scenario input for subsequent student operations.

[0034] S2. 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 operational performance records; wherein, the operational behavior data includes the crane operating position, crane angle adjustment, and the lifting force applied by the crane; the key performance indicators include floating deviation and posture 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 posture adjustment error is the error between the actual floating posture and the ideal posture.

[0035] Specifically, this step records the trainee's behavioral data during the float-over installation operation in real time and integrates it with the dynamic simulation scenario data to generate a complete operational performance record. Considering the complexity and dynamic nature of float-over installation, this step has designed a high-precision recording scheme tailored to the interaction between trainee behavior and the scenario. Specifically, it incorporates performance indicator calculations based on error feedback and a weighting formula for dynamic environmental interference. This design ensures comprehensive and targeted operational records, laying the foundation for subsequent failure scenario analysis and optimization.

[0036] Input dynamic simulation scene data:

[0037] Receive the dynamic simulation scene data stream from step S1 ,include:

[0038] : The three-dimensional motion trajectory of the float, in meters.

[0039] : Time series of floating attitude changes, in degrees.

[0040] : Wave force time series, in Newtons.

[0041] Furthermore, the student operation behavior data is collected:

[0042] Utilize high-precision motion capture systems and equipment sensors to collect real-time data on trainees’ operational behaviors during training. ,Include:

[0043] : Crane operating position, in three-dimensional coordinates (meters).

[0044] : Crane angle adjustment, unit is degree.

[0045] : The lifting force applied by the crane, in Newtons.

[0046] Furthermore, the students’ operational behavior data Dynamic scene data Perform timestamp matching and establish a synchronization model:

[0047] ;

[0048] in, It is a complete record of operational performance, including trainees’ operational behaviors and scenario responses.

[0049] A weighted time interpolation model is used synchronously to address alignment issues caused by differences in sensor sampling frequencies:

[0050] ;

[0051] in, is the interpolation weight based on time difference, defined as ,in and are adjacent timestamps. The crane position after synchronization, in meters.

[0052] Furthermore, in order to reflect the impact of environmental dynamics (such as waves and wind speed) during floatover operations, an environmental interference weight correction term is introduced into the collected operation data:

[0053] ;

[0054] in, is the environmental dynamic weight, and the larger the value, the stronger the environmental disturbance. It is an adjustment coefficient used to adjust the intensity of the influence of wave force on the weight (the value range is 0.1-0.5). is the reference wave force and is the mean value of the wave force.

[0055] Key behavioral parameters (such as crane force ) multiplied by a weight correction to reflect the dynamic interference of the environment on the operation:

[0056] ;

[0057] Furthermore, based on the synchronized data , calculate key performance indicators to quantify the students' operational effectiveness:

[0058] floatation deviation : The deviation between the actual floatation position and the target position, used to evaluate the operation accuracy.

[0059] ;

[0060] in, is the actual position of the float, which comes from the simulation scenario data. The target position for floating, which is preset by the scene.

[0061] Attitude adjustment error : The error between the actual and ideal floating postures.

[0062] ;

[0063] in, is the actual posture of the float, which comes from the simulation scene data. It is the ideal floating posture, preset by the scene.

[0064] By introducing time-synchronized interpolation and environmental dynamic weighting correction, this step effectively reflects the dynamic complexity of floatover installation operations, ensuring a precise correlation between operational data and environmental factors. These highly accurate operational records provide reliable foundational data for subsequent failure scenario reconstruction and optimization.

[0065] S3. 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 scenario, and the failure path is analyzed using a reinforcement learning model. The optimization goal of the reinforcement learning model is centered on the deviation of the floating trajectory and posture, and optimization suggestions are generated based on the analysis results.

[0066] Specifically, this step reconstructs float-over installation failure scenarios based on operational performance records and analyzes key operational issues encountered by trainees to generate optimization recommendations. To address the dynamic complexity and high-precision requirements of float-over installation, this step combines 3D point cloud reconstruction with enhanced path analysis to construct a multimodal fusion model.

[0067] Further, failure scenario reconstruction:

[0068] Based on operational data and simulation data , reconstructing the students’ failure scenarios The criteria for determining failure is based on real-time data monitoring during the installation process. Specifically, if the floatover fails to dock within the specified time during installation, if its position error exceeds the preset tolerance range (e.g., ±2 cm), if its attitude error exceeds the allowable angle (e.g., ±1 degree), if the floatover fails to securely hold its target position and exhibits significant offset or imbalance, or if abnormal force fluctuations (e.g., overload pressure exceeding 100N) are detected during installation, the installation is considered a failure.

[0069] Introducing environmental dynamic correction terms to reflect wave forces Impact on floating trajectory and attitude:

[0070] ;

[0071] in, The reconstructed floating trajectory. It is a dynamic correction coefficient, which is set according to the quality of the floatation and environmental parameters.

[0072] For posture data Introduce an operational interference term to adjust the impact of the crane angle:

[0073] ;

[0074] in, is the operational interference coefficient, which is used to quantify the effect of the crane angle on the floatation attitude.

[0075] Finally, the failure scenario Combining trajectory and pose reconstruction results provides a complete dynamic description for analysis.

[0076] Furthermore, reinforcement learning models are used to analyze failure paths. , the optimization objective is centered on the deviation of the floating trajectory and attitude:

[0077] Define a comprehensive error function , the float trajectory deviation and attitude adjustment error Combined with the introduction of regularization terms To control wave effects:

[0078] ;

[0079] in, is the weight factor of the attitude error. is the regulating factor of wave impact.

[0080] Through reinforcement learning strategy Perform optimization and generate improved solutions for failed paths.

[0081] S4. Generate an optimized floating trajectory and attitude adjustment path based on the reconstructed student's failure scenario and optimization suggestions, design a path optimization function based on the optimized floating trajectory and attitude adjustment path to obtain the optimized path, and simultaneously generate dynamic visualization guidance through augmented reality equipment to identify dangerous warning information in the interaction in real time, and generate step-by-step operation prompts in real time according to the optimized path.

[0082] Specifically, this step integrates the failure scenario data and optimization suggestions from the previous step to generate optimized dynamic guidance, visually presenting the required operational path and recommended adjustments. Taking into account the dynamic complexity of floating installation scenarios, this step incorporates environmental dynamics and student operational corrections into the path optimization. Furthermore, the optimization results are dynamically projected using augmented reality (AR) technology to ensure accurate and interactive guidance. The entire design addresses the specific requirements of floating installation, focusing on dynamic adaptability to the environment and student operations in both path optimization and interaction.

[0083] Furthermore, the optimization path is generated:

[0084] Generate optimized floating trajectory based on input data and posture adjustment path . Introducing the following key innovations:

[0085] Environmental dynamics: To reflect wave forces Impact on floating trajectory, adding environmental dynamics items to path optimization :

[0086] ;

[0087] in, It is the environmental dynamic adjustment coefficient, which adjusts the intensity of the impact of waves on the floating path and is determined according to the floating quality and the amplitude of environmental disturbance.

[0088] Furthermore, in view of the common error patterns of students, the posture adjustment path Introducing correction items :

[0089] ;

[0090] is the correction coefficient, which dynamically adjusts the crane angle to the correction amplitude of the posture error. The value range is .

[0091] Furthermore, to avoid environmental correction To prevent excessive trajectory drift, a regularization constraint is added to balance the amplitude of path adjustment:

[0092] ;

[0093] in, It is the objective function of path smoothing, which is used to limit the excessive deviation between the optimized path and the original path. is the regularization strength, used to control the environmental term The weight changes.

[0094] Furthermore, based on the optimized path, dynamic visual guidance is generated through augmented reality (AR) devices, which is divided into the following parts:

[0095] Trajectory projection:

[0096] Dynamically project the trajectory of the floating target in the students' field of view , showing the direction in which the float needs to move in the form of a continuous path line.

[0097] Posture adjustment highlight:

[0098] Display the current floating posture in graphic overlay mode Target posture The arrows indicate the differences and prompt the trainees on how to adjust the posture angles.

[0099] Dangerous area marking:

[0100] Mark areas where floatovers may capsize or collide with other structures, and use a color warning mechanism to update hazard information in real time.

[0101] Real-time interactive prompt generation:

[0102] According to the optimized path , generate step-by-step operation prompts in real time:

[0103] Tips include target crane position and angle adjustment .

[0104] The prompt mechanism introduces priority rules, such as when the wave force When the value is large, stability adjustment prompts are given priority.

[0105] Specifically, this step, based on dynamic guidance data, helps trainees execute optimized floatover installation operations and evaluates the effectiveness of these improvements through precise data comparison and quantitative analysis. By incorporating an error aggregation-based evaluation model and environmental dynamic sensitivity analysis, this step fully considers the dynamic characteristics of the floatover installation scenario and trainees' operational performance in the operational assessment, providing specific recommendations for subsequent training optimization.

[0106] Further, perform improvement operations:

[0107] Students follow the optimized path Complete the floatover installation operation:

[0108] The system records students’ actual operation data in real time , including new crane positions , Angle adjustment and lifting force .

[0109] Simultaneously record real-time response data of floatover , including floating trajectory and posture .

[0110] Furthermore, the trainee's new operation data and floatation response are analyzed to calculate the key performance indicators of the trainee's operation, including floatation trajectory error. and attitude adjustment error :

[0111] ;

[0112] in, It is the deviation between the actual floatation trajectory and the target trajectory, used to evaluate the accuracy of the operation. It is the deviation between the actual value and the target value of the floating attitude, which is used to evaluate the effect of attitude adjustment.

[0113] Introducing environmental sensitivity analysis items , and make weight correction on the error in combination with the wave action:

[0114] ;

[0115] in, It is the error aggregation evaluation value, which represents the quantitative result of the trainee's overall operation effect. Adjust the weight of the error for the posture, adjusting the importance ratio of trajectory and posture. is the environmental sensitivity adjustment coefficient, which reflects the degree of influence of wave force on operation.

[0116] Furthermore, an evaluation report and improvement suggestions are generated:

[0117] Generate a trainee operation evaluation report based on the results of error aggregation analysis :

[0118] Overall operational score, based on The value is scored.

[0119] Independent evaluation results of each subtask (such as crane position adjustment and floating attitude adjustment).

[0120] Furthermore, suggestions for improvement are made for the students, including:

[0121] Targeted practice tasks (such as focusing on strengthening the ability to adjust floating posture).

[0122] Adjustment of environmental adaptability strategies (e.g., optimizing operational flexibility in scenarios with strong wave forces).

[0123] Furthermore, output evaluation and recommendation data:

[0124] Output trainee operation evaluation report ,include:

[0125] Operation error analysis results (trajectory error and attitude error ).

[0126] Assessment of the impact of environmental sensitivity on errors.

[0127] Targeted improvement suggestions.

[0128] As input for subsequent training optimization, a closed-loop improvement mechanism is formed.

[0129] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0130] In addition, for technical details not fully described in this embodiment, please refer to the parameter operation method provided in any embodiment of the present invention, and will not be repeated here.

[0131] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0132] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0133] Through the above description of the embodiments, those skilled in the art will clearly understand that the methods of the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred implementation method. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, a magnetic disk, or an optical disk) and includes a number of instructions for enabling a terminal device (such as a mobile phone, computer, server, air conditioner, or network device) to execute the methods described in the various embodiments of the present invention.

[0134] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

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. The impact of the environment and equipment on the float is comprehensively calculated to initialize the physical simulation scene. Then, through the numerical integration method, the motion trajectory and attitude changes of the float are calculated from the acceleration. The motion trajectory and attitude changes are added to the initialized physical simulation scene to obtain the dynamic simulation scene. Collect the trainee's 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, and calculate key performance indicators based on the synchronized data to quantify the trainee's operational effect, thereby obtaining an operational performance record. The operational behavior data includes the crane operating position, crane angle adjustment, and the lifting force applied by the crane; the key performance indicators include floatation deviation and attitude adjustment error. The floatation deviation is the deviation between the actual floatation position and the target position, and the attitude adjustment error is the error between the actual floatation attitude and the ideal attitude. When a student's failed operation is detected, the system reconstructs the student's failure scenario based on the currently collected operation behavior data and dynamic simulation scenarios, analyzes the failure path using the reinforcement learning model, and generates optimization suggestions based on the analysis results; Generate an optimized floating trajectory and attitude adjustment path based on 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 simultaneously 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 based on the optimized path; The trainee completes the float installation operation according to the optimized path displayed by the augmented reality device. The trainee's new operation data and float installation response are re-analyzed with error aggregation. Based on the results of the error aggregation analysis, a trainee operation evaluation report is generated. The reinforcement learning model is constructed as follows: A comprehensive error function is defined, combining the float trajectory deviation and attitude adjustment error, and a regularization term is introduced to control the influence of waves. The comprehensive error function is optimized through a reinforcement learning strategy to generate an improved solution for the failure path. During the optimization path generation process, an optimized floatation trajectory is generated by the reconstructed floatation trajectory and the environmental dynamic term based on the environmental dynamic adjustment coefficient. The environmental dynamic adjustment coefficient is used to adjust the intensity of the influence of wave forces on the floatation path and is determined according to the floatation quality and the environmental disturbance amplitude. In response to the common error patterns of trainees, a correction item based on crane angle adjustment is introduced into the optimized posture adjustment path; the correction item based on crane angle adjustment is used to dynamically adjust the correction amplitude of the crane angle on the posture data, with a value range of 0.1-0.

5.

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, floatation 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 floatation posture; The steps for constructing the dynamic coupling physical model are: The wave force vector acting on the float's center of mass is calculated using nonlinear wave theory. The wave force vector is solved in conjunction with the crane load position and the float's center of mass equilibrium to obtain the float's linear acceleration and angular acceleration under instantaneous action. The magnitude of the wave force vector is the wave force. The numerical integration method is then used to calculate the motion trajectory and attitude change of the float from the acceleration, 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. The scene reproduction and augmented reality simulation training method for floating installation according to claim 1 is characterized in that: The operational behavior data includes the crane operating position, crane angle adjustment, and the lifting force applied by the crane. The key performance indicators include float deviation and attitude adjustment error. The float deviation is the deviation between the actual float position and the target position, which is used to evaluate the operational accuracy. The attitude adjustment error is the error between the actual float attitude and the ideal attitude. The synchronization model is constructed as follows: Match the trainee's 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 frequency.

4. The scene reproduction and augmented reality simulation training method for floating installation according to claim 1 is characterized in that: The student's failure criteria are based on real-time data monitoring during the installation process: If the float fails to dock 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, or an offset or imbalance state occurs, or abnormal force fluctuations are sensed during the installation process, the installation is judged to have failed.

5. The scene reproduction and augmented reality simulation training method for floating installation according to claim 4 is 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 on 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.

6. The scene reproduction and augmented reality simulation training method for floating installation according to claim 4 is 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.

7. The scene reproduction and augmented reality simulation training method for float installation according to claim 6, characterized in that: When the trainee performs the installation according to the optimized path, the trainee's actual operation data 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 floatation is recorded, including the floatation trajectory and floatation adjustment posture. The trainee's new operation data and floatation response are analyzed, and the key performance indicators of the trainee's operation are calculated. The environmental sensitivity analysis item is introduced, and the environmental sensitivity adjustment coefficient of the environmental sensitivity analysis item is combined to perform weight correction on the floatation trajectory error and posture adjustment error to obtain an error aggregation evaluation value, which represents the quantitative result of the trainee's overall operation effect. Among them, the environmental sensitivity adjustment coefficient reflects the degree of influence of wave force on the operation.

8. The scene reproduction and augmented reality simulation training method for floating installation according to claim 7, characterized in that: Based on the error aggregate evaluation value, a trainee operation evaluation report is generated, including: Overall operation score, which 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