A safety boundary early warning method and system for floating vessel operations

Abstract

This invention relates to the field of safety boundary early warning technology, and in particular to a safety boundary early warning method and system for floating vessel operations. The method includes the following steps: collecting floating vessel operation log data; analyzing environmental data to assess the increasing trend of environmental disturbances during floating vessel operations; determining the dynamic imbalance state of the operating platform under pressure based on the log data, identifying the dynamic fatigue trend of the platform support structure and the damage status of the coupled stress of the floating vessel hull; detecting the loss of control over the positioning capability of the floating vessel hull based on structural damage and fatigue trends, and extracting dynamic displacement trajectory data of the floating vessel in conjunction with environmental disturbance trends; determining the spatial constraint parameters of the floating vessel operation based on the log data, and determining the risk of exceeding the boundary based on the trajectory data, generating floating vessel operation boundary risk assessment data; finally, generating multi-level boundary early warning response signal data based on the assessment results. This invention achieves safer and more stable floating vessel operations through safety boundary early warning.

Description

Technical Field

[0001] This invention relates to the field of safety boundary early warning technology, and in particular to a safety boundary early warning method and system for floating vessel operations. Background Technology

[0002] Floating vessels often operate in complex and variable marine environments during tasks such as anchoring, hoisting, resupply, and maintenance. They are susceptible to the combined effects of factors such as sudden changes in wind speed, water current impact, and wave disturbances, leading to decreased positioning capabilities, platform stress imbalance, and accelerated structural fatigue. This can result in serious safety accidents such as displacement, anchor chain breakage, or platform capsizing. Traditional operational safety control methods rely heavily on manual experience or single sensor alarm mechanisms, making it difficult to dynamically grasp the evolution characteristics of environmental disturbances and the coordinated response process of multiple platform components in real time. They also lack the comprehensive ability to assess the risks of floating vessel operations crossing boundaries and the failure trends of supporting structures, and cannot effectively achieve feedforward identification and graded response to safety boundaries. Therefore, there is an urgent need for a comprehensive early warning method that integrates operational log data, structural status information, and environmental disturbance factors. This method should analyze key risk sources throughout the entire floating vessel operation process from multiple dimensions and construct a dynamic evolution model to achieve early identification and graded response control of risks crossing boundaries, thereby improving the risk prevention and control capabilities and intelligent operation level of offshore floating vessel operations. However, traditional floating vessel safety boundary early warning systems have problems with inaccurate detection of coupled stress damage to the floating vessel's hull and inaccurate detection of the floating vessel's dynamic displacement trajectory. Summary of the Invention

[0003] Therefore, it is necessary to provide a safety boundary early warning method and system for floating vessel operations to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a safety boundary early warning method for floating vessel operations includes the following steps:

[0005] Step S1: Collect floating vessel operation log data; collect floating vessel operation environment data based on floating vessel operation log data to obtain floating vessel operation environment data; assess the increasing trend of floating vessel operation environment disturbance based on floating vessel operation environment data;

[0006] Step S2: Determine the dynamic imbalance state of the operating platform based on the floating vessel operation log data; determine the dynamic fatigue trend of the platform support structure based on the dynamic imbalance state of the operating platform; detect the damage status of the floating vessel hull due to coupled stress based on the dynamic fatigue trend of the platform support structure.

[0007] Step S3: Detect the uncontrolled positioning capability of the floating vessel based on the damage status of the coupled stress of the floating vessel hull and the dynamic fatigue trend of the platform support structure; detect the dynamic displacement trajectory data of the floating vessel based on the uncontrolled positioning capability of the floating vessel hull and the increasing trend of disturbance in the floating vessel's operating environment.

[0008] Step S4: Determine the floating vessel operation space constraint parameters based on the floating vessel operation log data; perform floating vessel boundary crossing risk assessment processing on the floating vessel operation space constraint parameters based on the floating vessel displacement dynamic offset trajectory data to obtain floating vessel operation boundary crossing risk assessment data; perform multi-level boundary early warning response signal generation processing based on the floating vessel operation boundary crossing risk assessment data to obtain multi-level boundary early warning response signal data, and upload it to the cloud platform for early warning.

[0009] This invention constructs a full-chain, multi-source fusion method for floating vessel operation status perception and boundary early warning, enabling the systematic identification of key factors such as operational environment disturbance trends, platform structural fatigue evolution, hull positioning loss of control, displacement trajectory, and spatial boundary crossing risks. By coupling and analyzing floating vessel operation log data with operational environment characteristic data, it effectively captures early signs of enhanced environmental disturbances, improving the accuracy of risk trend assessment. A coupled stress damage detection mechanism is constructed based on pressure dynamics and structural fatigue data, enhancing the sensitivity of structural damage identification. A positioning capability loss of control detection path is constructed by perceiving the relationship between failure and attitude change in multiple dimensions, improving the accuracy of hull status diagnosis. Displacement trajectory is extracted by fusing loss of control positioning behavior and environmental disturbance trends, enhancing the real-time performance of dynamic boundary crossing risk identification. By combining boundary crossing judgment results with operational space parameters, differentiated multi-level boundary early warning signals are formed, improving the hierarchy and timeliness of early warning response. All process data and results are uploaded to a cloud platform, enabling remote collaborative monitoring and boundary early warning management, effectively supporting the safety of floating vessel operations in complex sea conditions. Therefore, this invention is an optimization of the traditional safety boundary warning system for floating vessel operations. It solves the problems of inaccurate detection of the coupled stress damage condition of the floating vessel hull and inaccurate detection of the dynamic displacement trajectory of the floating vessel, thus improving the accuracy of detection of the coupled stress damage condition of the floating vessel hull and the accuracy of detection of the dynamic displacement trajectory of the floating vessel.

[0010] The present invention also provides a safety boundary early warning system for floating vessel operations, for executing the safety boundary early warning method for floating vessel operations as described above, the safety boundary early warning system for floating vessel operations comprising:

[0011] The environmental disturbance enhancement assessment module is used to collect floating vessel operation log data; collect floating vessel operation environment data based on the floating vessel operation log data to obtain floating vessel operation environment data; and assess the enhancement trend of floating vessel operation environment disturbance based on the floating vessel operation environment data.

[0012] The hull coupling stress damage detection module is used to determine the dynamic imbalance state of the working platform under pressure based on the floating vessel operation log data; determine the dynamic fatigue trend of the platform support structure based on the dynamic imbalance state of the working platform under pressure; and detect the coupling stress damage status of the floating vessel hull based on the dynamic fatigue trend of the platform support structure.

[0013] The displacement dynamic offset trajectory detection module is used to detect the loss of control of the floating vessel's positioning capability based on the damage status of the coupled stress of the floating vessel's hull and the dynamic fatigue trend of the platform support structure; and to detect the dynamic offset trajectory data of the floating vessel's displacement based on the loss of control of the floating vessel's positioning capability and the increasing trend of disturbance in the floating vessel's operating environment.

[0014] The early warning response module is used to determine the floating vessel operation space constraint parameters based on the floating vessel operation log data; to perform floating vessel boundary crossing risk assessment processing on the floating vessel operation space constraint parameters based on the floating vessel displacement dynamic offset trajectory data, thereby obtaining floating vessel operation boundary crossing risk assessment data; and to perform multi-level boundary early warning response signal generation processing based on the floating vessel operation boundary crossing risk assessment data, thereby obtaining multi-level boundary early warning response signal data, and uploading it to the cloud platform for early warning.

[0015] The present invention relates to a safety boundary early warning system for floating vessel operations. This system can implement any safety boundary early warning method for floating vessel operations as described in the present invention. It serves as a medium for coordinating the operation and signal transmission between various modules to complete the safety boundary early warning method for floating vessel operations. The modules within the system cooperate with each other to construct an early warning path for the entire floating vessel operation process based on the collaborative analysis of operation data, structural status, and environmental disturbances. This enables accurate determination of the risk of floating vessel crossing boundaries and efficient generation of multi-level early warning response signals. Attached Figure Description

[0016] Figure 1 A flowchart illustrating the steps of a safety boundary early warning method for floating vessel operations;

[0017] Figure 2 for Figure 1 A detailed flowchart illustrating the implementation steps of step S3.

[0018] Figure 3 for Figure 1 A detailed flowchart illustrating the implementation steps of step S4.

[0019] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0021] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0022] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0023] To achieve the above objectives, please refer to Figures 1 to 3 A safety boundary early warning method for floating vessel operations includes the following steps:

[0024] Step S1: Collect floating vessel operation log data; collect floating vessel operation environment data based on floating vessel operation log data to obtain floating vessel operation environment data; assess the increasing trend of floating vessel operation environment disturbance based on floating vessel operation environment data;

[0025] In this embodiment of the invention, an industrial-grade embedded control unit (such as a shipborne industrial gateway equipped with an ARM Cortex-A72 processor) on the operating platform accesses a multi-channel data acquisition port to acquire floating vessel operation log data. This log data includes at least the past 72 hours' worth of vessel operation command sequences, anchor chain tension records, platform motion attitude data (pitch angle, roll angle), robotic arm operation records, lifting load change data, and timestamps. After being indexed and organized by a time-series database (such as InfluxDB), the log data is used as baseline data and accessed by the environmental information acquisition module. Based on the operation time period and operation area coordinates (using WGS-84 standard geocoding) recorded in the acquired floating vessel operation log data, the environmental data acquisition unit is activated, calling upon the matching radar wind speed and direction sensor (model Lufft Ventus-X) and Doppler current profiler (such as Nortek Signature1000) to simultaneously measure the wind speed, wind direction, and current velocity and direction information corresponding to the current operation location. The sampling period is set to 10 seconds, and the acquisition duration is continuously maintained for 30 minutes. The resulting data forms a multi-dimensional operation environment dataset. The wind and flow field data are aligned according to timestamps, and indices such as the average wind pressure change rate, flow velocity fluctuation amplitude, and wind direction oscillation angle change rate are calculated with a 5-minute window period. Based on this, a disturbance energy spectrum calculation process is performed, which involves using Fast Fourier Transform (FFT) to extract the spectrum of the wind pressure and flow velocity curves and comparing the frequency energy center change trend over time. If the energy concentration frequency band shifts to higher frequencies over time, and the overall disturbance amplitude continues to increase (e.g., the average wind speed standard deviation increases from 1.5 m / s to 2.3 m / s within 30 minutes), then it is determined that there is an increasing disturbance trend in the floating vessel operation environment. An environmental disturbance increasing trend marker is output for subsequent steps.

[0026] Step S2: Determine the dynamic imbalance state of the operating platform based on the floating vessel operation log data; determine the dynamic fatigue trend of the platform support structure based on the dynamic imbalance state of the operating platform; detect the damage status of the floating vessel hull due to coupled stress based on the dynamic fatigue trend of the platform support structure.

[0027] In this embodiment of the invention, based on the floating vessel operation log data obtained in step S1, the changes in the operating load of the operating platform at different time periods are identified, and load mutation events (such as a change in lifting load exceeding 15% within 10 seconds) are extracted. Combined with the pressure distribution map obtained from the deck sensor array, the platform's pressure-bearing state is analyzed. The deck pressure sensor array has four piezoelectric sensors per square meter, recording the force data per unit area of ​​each deck section, with a sampling frequency of 50Hz. Combining the load path changes and the pressure distribution map, the offset rate of the force center in each section is calculated. If the maximum offset rate exceeds 15% within 5 consecutive minutes, and the overall center of gravity of the platform exhibits lateral / longitudinal imbalance drift (pitch angle fluctuation exceeding ±3°), the platform is identified as entering a dynamic imbalance state under pressure. Based on this, strain gauges and acceleration sensors (such as HBM's fiber Bragg grating-based strain system) deployed at key nodes of the supporting structure (such as the connection of the lifting outriggers) are invoked to monitor the structural stress-time curve in real time. Taking each support leg as a unit, its stress response sequence over the past 30 minutes is reconstructed. A regional risk threshold is set based on historical fatigue limit thresholds (e.g., 60% of the corresponding metal yield strength). The fatigue trend evolution path is identified using cumulative damage analysis methods (e.g., the Miner linear damage criterion). Furthermore, the spatial symmetry distribution of stress at the support structure nodes under dynamic loads is obtained. If uneven stress distribution is found at the support points (e.g., the stress on the front support leg is consistently more than 30% higher than that on the rear support leg), and the structural tilt angle exceeds 5°, a load path deviation is identified. Based on mechanical stability analysis, the risk of coupled stress damage inducing plastic deformation or structural cracks is determined. The above detection results are output as data on the ship's coupled stress damage status.

[0028] Step S3: Detect the uncontrolled positioning capability of the floating vessel based on the damage status of the coupled stress of the floating vessel hull and the dynamic fatigue trend of the platform support structure; detect the dynamic displacement trajectory data of the floating vessel based on the uncontrolled positioning capability of the floating vessel hull and the increasing trend of disturbance in the floating vessel's operating environment.

[0029] In this embodiment of the invention, the data on the hull coupling stress damage obtained in step S2 and the dynamic fatigue trend data of the supporting structure are jointly input into the positioning loss-of-control judgment module. This module is jointly constructed by an inertial navigation unit (IMU) and a GNSS dual-redundant positioning system, and uses changes in inertial acceleration and structural tilt angle to detect platform stability. Under the condition of coupling damage, if the IMU records abnormal oscillations (such as roll angle fluctuations greater than ±7° within 1 minute) or GNSS signal drift (position jumps exceeding 1 meter within 30 seconds), it is comprehensively judged that the hull positioning capability has lost control. Subsequently, the displacement trajectory calculation module is activated. This module reads the data from the anchor chain tension sensor (accuracy 0.1kN) and the rudder angle feedback signal to identify the response behavior of the floating vessel under hydrodynamic action. Using a 30-second window, the module performs integral calculations on parameters such as lateral drift speed, anchor chain tension change rate, and forward thrust angle to invert and obtain the dynamic offset trajectory of the floating vessel on the two-dimensional working surface. In this process, the disturbance enhancement trend data obtained in S1 is used as a weight input factor to correct the inertial and random wave terms in the hydrodynamic response model, so that the trajectory prediction is closer to the actual disturbance environment. The output floating vessel displacement dynamic offset trajectory data is formed into a structured time-series coordinate sequence, and the current drift trend direction and position change rate are marked for the boundary judgment in the next step.

[0030] Step S4: Determine the floating vessel operation space constraint parameters based on the floating vessel operation log data; perform floating vessel boundary crossing risk assessment processing on the floating vessel operation space constraint parameters based on the floating vessel displacement dynamic offset trajectory data to obtain floating vessel operation boundary crossing risk assessment data; perform multi-level boundary early warning response signal generation processing based on the floating vessel operation boundary crossing risk assessment data to obtain multi-level boundary early warning response signal data, and upload it to the cloud platform for early warning.

[0031] In this embodiment of the invention, based on the displacement dynamic offset trajectory data obtained in S3 and combined with the operation area configuration parameters recorded in the floating vessel operation log, the operation space constraint parsing module is invoked to extract spatial boundary data, including the effective radius of the anchor chain, the platform's allowable movement boundary (e.g., ±5m range), and the equipment movement protection zone (e.g., the robotic arm's operation sector), to construct a three-dimensional operation boundary model. Spatial overlap analysis is performed using the operation area boundary model and the displacement trajectory data to determine whether the trajectory touches the operation boundary. During the determination process, if the distance between the trajectory point and the boundary is consistently less than 0.5m, or the number of times the boundary is touched exceeds 3 times within 30 seconds, a boundary crossing risk is identified. Boundary crossing risk determination data is output, including risk level (high, medium, low), boundary contact direction, drift rate, and prediction time window. Subsequently, based on the risk level and trajectory change trend, a multi-level early warning response module is invoked to generate a boundary early warning response signal of the corresponding level. The warning levels are divided into three levels: Level 1 warning: high risk of boundary crossing, the system issues an audible and visual alarm and activates the anchor chain tensioning mechanism; Level 2 warning: medium risk of boundary crossing, prompting the control terminal to adjust the rudder angle; Level 3 warning: initial deviation, providing interface prompts and logging all generated warning response signal data, which is then uploaded to the shore-based cloud platform via a wireless communication module (such as a 5G industrial module). Within the cloud platform, log archiving, operational anomaly analysis, and remote monitoring are synchronized to build a complete closed-loop control mechanism.

[0032] Preferably, step S1 includes the following steps:

[0033] Step S11: Collect floating vessel operation log data;

[0034] In this embodiment of the invention, by deploying industrial-grade edge data acquisition terminals on the floating platform, and utilizing industrial communication protocol interfaces such as CAN bus and Modbus-TCP, key operational parameters such as power system operating parameters (including main propulsion motor current, voltage, speed, and rudder angle feedback), attitude angles (pitch angle, roll angle, and heading angle) output by the three-axis gyroscope, platform load information (including load weight, load position, and robotic arm angle), and tension values ​​and release lengths measured by the anchor chain tension sensor are collected in real time. The sampling frequency is 1Hz. All data is summarized into floating operation log data after being marked with an industrial timestamp. The data is then cached at the edge and uploaded to the data storage unit in minute segments to ensure data integrity, continuity, and time synchronization, providing basic raw data for subsequent operational environment analysis and risk assessment in each stage.

[0035] Step S12: Collect the geographical coordinate data of the floating vessel operation based on the floating vessel operation log data;

[0036] In this embodiment of the invention, based on the floating vessel operation log data obtained in step S11, the high-precision differential GPS positioning module equipped on the operation platform is used to collect the real-time geographic coordinate information of the floating vessel. The positioning accuracy reaches the centimeter level. The positioning data includes longitude, latitude and altitude information. The sampling frequency is synchronized with the log data. All positioning data are stored synchronously with the operation log data after being accompanied by a precise timestamp. This completes the systematic collection of geographic coordinate data of the floating vessel operation, ensuring that the position status of the floating vessel in the operation area is traceable in real time and supporting the spatiotemporal dynamic analysis of the subsequent operating environment.

[0037] Step S13: Collect floating vessel operation environment data based on floating vessel operation geographic coordinate data and floating vessel operation log data;

[0038] In this embodiment of the invention, the floating vessel operation log data collected in step S11 and the floating vessel operation geographic coordinate data obtained in step S12 are combined. Through industrial data fusion technology, the marine meteorological parameters (wind speed, wind direction, ocean current speed, wave height) and water depth information of the floating vessel's location are collected in real time. A multi-point marine observation sensor network, including sonar wave meters and current meters, is deployed around the operation area. The sensor data is uploaded to the operation platform through an Internet of Things gateway. The floating vessel's own status data and environmental monitoring data are fused to complete the comprehensive collection of floating vessel operation environment data, realize the spatial dynamic mapping of the operation environment, and provide multi-dimensional data support for subsequent environmental disturbance trend assessment.

[0039] Step S14: Assess the increasing trend of environmental disturbances during floating vessel operations based on the floating vessel operation environment data.

[0040] In this embodiment of the invention, based on the floating vessel operation environment data obtained in step S13, a time series analysis method is used to statistically calculate the key disturbance factors in the environmental parameters (such as wind speed change rate, wave height change trend, ocean current speed fluctuation, etc.), calculate their short-term and long-term change gradients, and after filtering out random noise, quantify the environmental disturbance enhancement trend to obtain trend parameters reflecting the change in the intensity of environmental disturbance in the floating vessel operation. All calculation processes are automatically executed in the edge processor, and the result data is transmitted to the control system to input the environmental disturbance enhancement trend parameters into the floating vessel operation risk assessment module, ensuring timely capture and accurate quantification of environmental changes.

[0041] Preferably, step S14 includes the following steps:

[0042] Step S141: Set the wind speed measurement range of the wind sensor to 0-60m / s, set the wind speed resolution to 0.01m / s, set the wind speed measurement accuracy to ±0.1m / s, set the wind direction measurement range to 0°-360°, set the wind direction resolution to 1°, and set the sampling frequency to 10Hz;

[0043] In this embodiment of the invention, an industrial-grade wind sensor module is used. The wind speed measurement range is set to 0 to 60 meters per second to ensure coverage of wind speed changes under extreme weather conditions. The wind speed resolution is adjusted to 0.01 meters per second to ensure the capture of minute wind speed changes. The measurement accuracy is set to ±0.1 meters per second to meet the high-precision requirements of the working environment. The wind direction measurement range is set to 0 to 360 degrees to capture wind direction changes from all directions. The wind direction resolution is adjusted to 1 degree to obtain detailed wind direction information. The sampling frequency is set to 10 times per second (10Hz) to ensure real-time dynamic monitoring of wind speed and wind direction data. After analog-to-digital conversion, the sensor signal is transmitted to the data acquisition unit through an industrial communication bus to complete the high-precision real-time acquisition of wind data, providing basic data for environmental disturbance analysis.

[0044] Step S142: Set the flow velocity measurement range of the water flow sensor to 0-5m / s, set the flow velocity resolution to 0.001m / s, set the flow velocity measurement accuracy to ±0.01m / s, set the flow direction measurement range to 0°-360°, and set the sampling frequency to 5Hz;

[0045] In this embodiment of the invention, a water flow sensor is selected, with the flow velocity measurement range set to 0 to 5 meters per second, covering the common water flow velocity range within the operational sea area. The flow velocity resolution is adjusted to 0.001 meters per second to accurately detect minute changes in water flow, and the measurement accuracy is controlled within ±0.01 meters per second to ensure the reliability of the water flow velocity data. The flow direction measurement range is set to 0 to 360 degrees to completely record changes in water flow direction. The sampling frequency is set to 5 times per second (5Hz) to meet the dynamic water flow environment monitoring requirements of floating vessel operations. The water flow sensor data is transmitted to the operational platform data center via a wired transmission interface, forming a synchronized data stream with the wind force sensor data, providing an accurate timing basis for subsequent coupled analysis.

[0046] Step S143: Use wind and water flow sensors to collect environmental fluctuation coupling and superposition data of the floating vessel operation environment to obtain environmental fluctuation coupling and superposition data;

[0047] In this embodiment of the invention, the wind speed and direction data collected in step S141 and the water flow speed and direction data collected in step S142 are fused together. Time synchronization technology is used to align the different frequency data collected by the two types of sensors according to a unified timestamp. The coupled superposition calculation of environmental fluctuations is realized through a weighted superposition algorithm. During the calculation process, based on the principle of vector superposition, the speed and direction data of wind force and water flow are vector synthesized in three-dimensional space to obtain coupled superposition data representing the overall intensity and direction of environmental fluctuations. All data calculations are completed in the edge processing unit. The result data is output after format conversion for subsequent spatiotemporal calibration of environmental disturbances.

[0048] Step S144: Perform spatiotemporal synchronization calibration processing on the environmental fluctuation coupled superimposed data to obtain environmental coupled superimposed spatiotemporal synchronization calibration data;

[0049] In this embodiment of the invention, a spatiotemporal synchronization calibration algorithm is applied to the environmental fluctuation coupled superimposed data obtained in step S143. The calibration process includes time alignment and spatial location matching. Time alignment eliminates time differences caused by different sensor sampling frequencies through interpolation, ensuring data timestamp consistency. Spatial matching is performed by calibrating the floating vessel's geolocation data with the coordinates of the environmental sensors, mapping the environmental disturbance data to the floating vessel's current spatial location, achieving spatiotemporal synchronization calibration of the environmental disturbance data, and obtaining environmental coupled superimposed spatiotemporal synchronization calibration data. The data format supports multidimensional arrays, containing time, spatial coordinates, and coupling disturbance intensity, serving as input data for dynamic environmental analysis.

[0050] Step S145: Construct multidimensional time-series data of environmental disturbance factors based on environmental coupling superposition spatiotemporal synchronization calibration data;

[0051] In this embodiment of the invention, based on the environmental coupling and spatiotemporal synchronization calibration data obtained in step S144, a multidimensional time-series data structure is constructed, including time series, spatial coordinates, and coupling perturbation factor values. Specifically, by dividing the work area into different grid cells, the numerical changes of coupling perturbation factors are statistically analyzed at different time periods, forming a multidimensional time-series dataset of environmental perturbation factors with three dimensions: time, space, and intensity. Data storage adopts high-performance time-series database management, supporting rapid retrieval and analysis, ensuring continuous tracking and quantification of dynamic changes in environmental perturbations, and forming a complete spatiotemporal change trajectory.

[0052] Step S146: Analyze the nonlinear periodic variation characteristics of environmental disturbances based on multidimensional time-series data of environmental disturbance factors and spatiotemporal synchronous calibration data of environmental coupling superposition;

[0053] In this embodiment of the invention, using the multidimensional time-series data of environmental disturbance factors constructed in step S145, a nonlinear periodic analysis method is employed to perform spectral analysis on the disturbance factor data of each spatiotemporal unit, extracting nonlinear periodic variation characteristics, including period amplitude, period frequency, and their modulation characteristics. The analysis process combines autocorrelation function and Fourier transform to reveal the periodic fluctuations and nonlinear variation laws of environmental disturbances. The data processing results form a set of nonlinear periodic variation characteristic parameters of environmental disturbances, supporting a deeper understanding of disturbance variation trends and providing quantitative indicators for intensity assessment.

[0054] Step S147: Evaluate the intensity characteristics of environmental disturbances during floating vessel operations based on the nonlinear periodic variation characteristics of environmental disturbances and multidimensional time-series data of environmental disturbance factors;

[0055] In this embodiment of the invention, based on the nonlinear periodic variation characteristics of environmental disturbances obtained in step S146 and the multidimensional time-series data of environmental disturbance factors obtained in step S145, the intensity characteristics of environmental disturbances within the floating vessel operation area are calculated. A weighted statistical method is used to comprehensively analyze the periodic amplitude, frequency, and multidimensional factor amplitudes to quantitatively assess the disturbance intensity. The assessment results are a set of numerical parameters reflecting the strength changes of environmental disturbances at different time periods and spatial locations. The parameter results are stored in time series form for subsequent trend analysis.

[0056] Step S148: Assess the increasing trend of disturbance in the floating vessel's operating environment based on the disturbance intensity characteristics of the floating vessel's operating environment.

[0057] In this embodiment of the invention, based on the characteristic parameters of the disturbance intensity of the floating vessel's operating environment obtained in step S147, a trend analysis method is used to perform linear regression and sliding window averaging on the data sequence to determine the increasing trend of the environmental disturbance intensity over time. The trend determination is based on a set threshold standard; when the trend parameter shows an upward trend for multiple consecutive time periods, the increasing trend of environmental disturbance is deemed valid. The trend analysis results are presented in numerical and graphical form, serving as the environmental disturbance risk input for the floating vessel safety boundary early warning system, supporting precise triggering of the early warning response.

[0058] Preferably, determining the dynamic imbalance state of the operating platform based on the floating vessel operation log data in step S2 includes:

[0059] Collect data on the temporal changes in floating vessel operational requirements based on floating vessel operation log data;

[0060] In this embodiment of the invention, continuous time-series data is extracted from the floating vessel operation log system. This data includes, but is not limited to, information related to task scheduling time, load changes, personnel dispatching, and material transportation time nodes. High-frequency timestamp annotation technology is used to align the collected data along the timeline, ensuring the data's temporal integrity and accuracy. The collected time-series data is preprocessed to remove outliers and missing values, ensuring data continuity and reliability. Subsequently, a sliding window technique is used to segment and analyze the time-series data, statistically analyzing changes in work requirement parameters within each hour or minute, including workload, transportation frequency, and duration. By plotting time-series changes, the dynamic trends of floating vessel work requirements at different points in time are accurately displayed, providing specific data on the temporal changes in floating vessel work requirements and offering precise basic data support for subsequent analysis.

[0061] Collect data on the fluctuation of floating vessel operational demand based on the temporal changes in floating vessel operational demand.

[0062] In this embodiment of the invention, based on the obtained time-series data of floating vessel work demand, statistical methods are used to calculate the amplitude and frequency of demand fluctuations. Specifically, this includes performing variance analysis on the work load for each time period in the time-series data to quantify the fluctuation intensity, and using peak-valley analysis to identify periods of high and low demand. By constructing demand change curves, the periodicity and sudden fluctuation characteristics of demand changes are determined. Simultaneously, Fourier transform is used to perform spectral analysis on the demand time-series signal to extract the dominant frequency components of the fluctuations, thereby assessing the regularity and stability of demand fluctuations. The resulting data on floating vessel work demand fluctuations includes multiple dimensions such as fluctuation amplitude, fluctuation period, and fluctuation frequency, providing data support for determining periods of sudden demand growth.

[0063] Data on periods of sudden demand growth are determined based on fluctuations in demand for floating vessel operations.

[0064] In this embodiment of the invention, based on demand fluctuation data, a threshold detection method is used to determine the statistical threshold for normal demand fluctuations in floating vessel operations during periods of sudden growth. For example, a fluctuation exceeding twice the historical average is considered a sudden increase. The demand fluctuation curve is traversed to locate all time intervals exceeding this threshold, and their start and end times and durations are recorded. By combining timestamps and work task logs, transient peaks caused by human scheduling factors are excluded, ensuring that the identified growth periods reflect genuine sudden changes in demand. The output is a set of time period data, clearly marking the start and end points of each sudden growth period, providing time reference and data input for subsequent detection of excessive structural component weight.

[0065] Detection of excessive weight of floating vessel transport structural components based on data from periods of sudden demand surge;

[0066] In this embodiment of the invention, based on identified periods of sudden demand surges, load monitoring data of the floating transport structure components during those periods is retrieved, including the component weight, transport frequency, and weight distribution per transport. Data is collected using a distributed load sensor network to monitor the load-bearing capacity of the structure components in real time, ensuring the timeliness and accuracy of data collection. The transport load data is correlated with the periods of sudden demand surges to analyze whether any abnormal phenomena exist where the transport load exceeds the design load capacity. By statistically analyzing the number of times and the magnitude of exceedances, the degree of overweight of the structure components is determined, further forming a quantitative indicator of the overweight status of the structure components. The overweight status data of the structure components is output as a key input for estimating the platform's overload trend.

[0067] Based on data on the overweight status of floating operation transport structural components and periods of sudden demand surges, the trend of floating operation platform exceeding its load limit is estimated;

[0068] In this embodiment of the invention, a load-bearing overload trend assessment model is established by combining structural component overload indicators and periods of sudden demand surges using a time series overlay analysis method. The peak load data of the structural components is aligned with the time window of the sudden growth period to analyze the frequency and duration of load-bearing overload occurrences and infer the trend of load-bearing pressure changes within a certain future time range. Through numerical integration and trend extrapolation, the proximity of the platform's critical point in load-bearing capacity is calculated, yielding a time prediction and risk level for load-bearing overload. The load-bearing overload trend data is output, including the probability of overload, trend intensity, and estimated time window, providing a predictive basis for fatigue state detection of deck structures.

[0069] The fatigue status of the floating deck structure was detected based on the overload trend of the floating platform and the overweight condition of the floating transport structural components.

[0070] In this embodiment of the invention, fatigue damage is analyzed by utilizing platform load-bearing overload trend data and structural component overload status, combined with deck structure stress-strain monitoring data. Strain gauges and accelerometers deployed at key load-bearing nodes of the deck are used to collect real-time data on structural stress changes. The stress-life curve (SN curve) theory is employed to calculate the fatigue life consumption rate corresponding to the current stress level. By combining the load-bearing overload trend with actual load fluctuations, the cumulative effect of structural fatigue is identified, and it is determined whether the fatigue threshold has been reached. The fatigue state data of the deck structure is output, including the cumulative degree of fatigue damage and the remaining life estimate, providing a structural safety basis for determining the dynamic imbalance state.

[0071] The dynamic imbalance state of the operating platform under pressure is determined based on the fatigue state of the floating deck structure and the overload trend of the floating platform.

[0072] In this embodiment of the invention, fatigue state data of the integrated deck structure and the platform's load-bearing over-limit trend are used to determine the dynamic imbalance state through a multi-parameter fusion algorithm. The fatigue state and load-bearing trend data are normalized to eliminate dimensional differences. Then, a weighted average method is used to combine the two types of indicators to form a comprehensive risk score. Based on the score, multi-level imbalance state thresholds are set to distinguish between normal, warning, and dangerous states. When the score exceeds the warning threshold, a dynamic imbalance alarm signal is generated, indicating the specific time period and affected area. The dynamic imbalance state data of the operating platform under pressure is output for subsequent hull coupling stress damage detection and positioning capability loss assessment, forming a data closed loop.

[0073] Preferably, step S2, determining the dynamic fatigue trend of the platform support structure based on the dynamic imbalance state of the working platform under pressure, includes:

[0074] Based on the dynamic imbalance state of the pressure bearing of the working platform, the pressure difference distribution area of ​​the working platform is divided to obtain the pressure difference distribution area data of the working platform;

[0075] In this embodiment of the invention, pressure data related to the dynamic imbalance state of the operating platform determined in step S2 is obtained. This pressure data originates from real-time monitoring values ​​of pressure sensors deployed on key nodes of the platform's load-bearing structure. These pressure sensors cover all key load-bearing components and connection nodes of the platform, continuously collecting pressure magnitudes and corresponding timestamp information to ensure the spatiotemporal continuity and accuracy of the pressure data. The collected pressure measurement data undergoes data preprocessing, including noise reduction, calibration, and time synchronization, eliminating sensor errors and environmental interference to ensure the authenticity and reliability of the data. All preprocessed pressure measurement data corresponds to their precise three-dimensional spatial coordinates. Combined with the geometric model of the platform structure, spatial annotation of each measurement point is achieved, forming complete spatial distribution information of the pressure measurement points. Based on this, all annotated coordinates and pressure values ​​are imported into 3D modeling software to construct a 3D pressure distribution model of the platform's load-bearing structure. The model can intuitively display the pressure distribution and dynamic trends at different locations. Subsequently, using numerical calculation methods, specifically differential calculation technology, the pressure difference between adjacent pressure measuring points was calculated point by point, constructing a pressure difference matrix. Each element in the matrix represents the pressure gradient between two adjacent measuring points, reflecting the local characteristics and overall gradient distribution of pressure changes in various regions of the platform surface. To better analyze the spatial characteristics of pressure gradient changes, clustering analysis was used to divide the platform surface into regions based on the pressure difference matrix. The clustering algorithm employed a hierarchical clustering method based on distance and difference, ensuring that the clustering results reflect the actual stress state of the structure. This algorithm, by calculating the similarity of pressure differences and the spatial distance between measuring points, grouped measuring points with similar pressure differences and geographical proximity into the same region, forming several pressure difference distribution areas. The pressure changes within these areas are uniform and independent, facilitating subsequent targeted structural analysis and fatigue prediction for different regions. The output data includes the pressure difference range of each divided region, the three-dimensional geographical coordinates of that region, and its spatial coverage information, providing a foundation and basis for subsequent regionalized dynamic fatigue trend detection and stress damage analysis of the platform structure.

[0076] Based on the pressure difference distribution area data of the working platform, the displacement recovery rate data of the structural unit is calculated for the dynamic imbalance state of the working platform under pressure.

[0077] In this embodiment of the invention, pressure difference distribution area data, combined with the elastic mechanical properties of the platform support structure units, are used to accurately calculate the displacement changes of each structural unit under different pressure loads. High-precision displacement sensors, including laser displacement sensors and capacitive displacement sensors, are deployed in key units of the platform support structure to capture minute displacement changes of the structural units in real time during the stress process. The displacement sensors and pressure sensors achieve synchronous data acquisition, ensuring that the time axis of pressure change and displacement response is consistent, facilitating subsequent data correlation analysis. Combining the known elastic modulus, Poisson's ratio, and other elastic mechanical parameters of each structural unit material, and using the pressure change sequence within the pressure difference distribution area as input, the theoretical elastic displacement response of each unit is calculated. To more accurately reflect the actual working conditions, the actual displacement data collected in real time by the sensors is combined with a numerical differentiation method to process the displacement time series data and calculate the displacement recovery rate of the structural unit. Specifically, numerical differentiation quantifies the speed at which the structural unit recovers from a loaded deformation state to an initial unloaded state by calculating the rate of change of displacement over time. The recovery rate reflects the elastic recovery capability of the structural unit and whether the deformation can be released in a timely manner. By continuously acquiring time-series data, displacement recovery rate curves for each structural element were obtained. These curves detail the dynamic elastic behavior and recovery process of the structural elements under different loading and unloading cycles. The recovery rate curves not only reflect the elastic response characteristics of the structural elements but also reveal any existing plastic deformation or fatigue accumulation. As a core parameter for quantifying the dynamic response of the structure, the recovery rate data provides fundamental data for subsequent time-series analysis of the displacement recovery time of the structural elements, supporting the reconstruction of the platform's regionalized deformation stress-time curves and the determination of dynamic fatigue trends.

[0078] Analyze the displacement recovery time series data of structural units based on the displacement recovery rate data of structural units;

[0079] In this embodiment of the invention, based on the displacement recovery rate curve of structural units, the displacement recovery rate values ​​of each structural unit at continuous time points are integrated and accumulated to construct a corresponding structural unit displacement recovery time series data sequence. This sequence records in detail the entire process of the structural unit displacement recovering from the loaded state to the unloaded state at each moment, fully reflecting the temporal evolution characteristics of the recovery process. To ensure the accuracy and stability of the time series data, time series processing techniques are used to filter the original recovery rate data. Digital filters such as low-pass filters or Kalman filters are mainly used to effectively suppress sensor noise, environmental interference, and abnormal fluctuations during data acquisition, ensuring the smoothness and continuity of the data sequence. After filtering, the time series data is further cleaned up with outliers and abrupt changes through a denoising algorithm, improving the reliability and resolution of the data. Based on the processed time series data, trend analysis methods and time series statistical analysis are used to reveal the dynamic recovery behavior characteristics of structural units at different time periods. The focus is on detecting and identifying the hysteresis effect in the recovery process, namely the nonlinear hysteresis phenomenon of displacement recovery after unloading of structural units, and the stress retention phenomenon, reflecting that the internal stress of the structure has not been completely released during the recovery process, leading to the accumulation of residual stress. By analyzing the temporal trends of displacement recovery of each structural unit, the dynamic elastic and plastic response behavior of the structural units is quantitatively described, and potential fatigue accumulation regions are identified. The displacement recovery time-series data of all structural units are systematically summarized and integrated to form a complete dynamic response time-series database covering the entire platform support structure. This database includes recovery time-series curves, timestamps, and displacement amplitudes of the structural units, providing a comprehensive data foundation and technical support for subsequent stress-time curve reconstruction and fatigue trend analysis based on regionalization.

[0080] The displacement recovery time series data of structural units is processed by platform-regional deformation stress-time curve reconstruction to obtain regionalized stress-time characteristic data.

[0081] In this embodiment of the invention, based on the displacement recovery time-series data of structural units, the displacement data at each time node is accurately mapped to the corresponding structural unit node, ensuring the accuracy of the spatial correspondence of the data. Utilizing the geometric information and displacement changes of the structural units, the strain distribution within the unit is calculated. Specifically, a differential geometry method is used to obtain the strain tensor through the difference in nodal displacements, obtaining the strain state at each time and location. Combining the constitutive relations in mechanics of materials, and adopting the linear elastic assumption, the calculated strain values ​​are converted into corresponding stress values ​​using pre-determined material parameters such as the elastic modulus and Poisson's ratio. This conversion process strictly follows Hooke's law, ensuring the accuracy and physical rationality of the stress calculation. The stress data of each structural unit are arranged according to the time series, forming a detailed stress time-series dataset. Based on the pressure difference distribution region obtained through clustering or partitioning techniques in the previous steps, the stress time-series data of the corresponding structural units are regionally summarized and integrated to comprehensively reflect the stress changes of the structural units within that region at different time points. To ensure the high accuracy and physical continuity of the reconstructed stress-time curves, a numerical calculation method combining numerical interpolation and the finite element method is employed. Weighted averaging and spatial smoothing are used to eliminate local data fluctuations and noise, avoiding the occurrence of non-physical peaks. This reconstruction method accurately depicts the dynamic stress variation curves within each region, revealing the temporal distribution and evolution trend of stress peaks. The resulting stress-time characteristic data includes the time-series stress variation curve, peak stress magnitude, peak occurrence time, and geographical location for each region. This provides a solid numerical foundation and technical support for subsequent analysis of stress peak distribution within the region and the assessment of platform structural stability.

[0082] The local stress peak distribution of the platform was analyzed based on the regionalized stress-time characteristic data.

[0083] In this embodiment of the invention, local stress peaks are extracted for each region using the reconstructed regionalized stress-time curves. A peak detection algorithm is employed to locate local maximum points on the curves, recording characteristic parameters such as peak magnitude, peak occurrence time, and duration. Peak values ​​within different time periods are statistically analyzed to determine their frequency and distribution patterns. Combined with historical structural stress data, regions of concentrated stress peaks and high-frequency peak regions are identified, and a local stress peak distribution map of the platform is generated. The output data includes the set of stress peaks for each region and their temporal distribution, providing a quantitative basis for stability weight allocation.

[0084] Based on the distribution of local stress peaks on the platform, the platform stability support weight allocation process is performed to obtain platform stability support weight allocation data.

[0085] In this embodiment of the invention, the local stress peak distribution is used as input. Based on the importance and load-bearing capacity of each support structure on the platform, stability support weights are assigned to classify each support structure node. Combined with the stress peak intensity, a weighted algorithm is used to assign weight values, which reflect the contribution of each node to maintaining the overall platform stability. The weight allocation process includes normalization to ensure that the sum of the weights is 1, facilitating subsequent calculations. The output is a weight allocation table for each region of the platform and key support nodes, quantitatively reflecting the supporting role of each region in overall stability. The support weight data is used for comprehensive evaluation of dynamic fatigue trends.

[0086] The dynamic fatigue trend of the platform support structure is determined based on the platform stability support weight allocation data and the distribution of local stress peaks on the platform.

[0087] In this embodiment of the invention, stability support weights and local stress peak distribution data are fused to construct a dynamic fatigue trend evaluation model. The fatigue load of each structural unit under actual stress conditions is reflected by calculating the weighted product of the weights and stress peaks. Time-series analysis is performed on this load data to capture the fatigue accumulation trend. Applying fatigue life theory and combining it with historical monitoring data, the fatigue life consumption rate of each structural unit is estimated to generate dynamic fatigue trend data for the platform support structure. This data includes fatigue accumulation strength, trend curves, and warning thresholds, providing a basis for safety boundary warnings regarding the dynamic fatigue state of the structure.

[0088] Preferably, step S2, which involves detecting the coupled stress damage of the floating vessel hull based on the dynamic fatigue trend of the platform support structure, includes:

[0089] Determine the load path imbalance of the work platform based on the dynamic fatigue trend of the platform support structure.

[0090] In this embodiment of the invention, dynamic fatigue trend data of the work platform support structure obtained in the aforementioned steps is acquired. This data includes information on the cumulative fatigue strength and fatigue rate of each support unit. Combined with the load path model of the platform design, the path distribution of load transferred from the work platform to each support structure unit under the current fatigue state is calculated using mechanical analysis software or finite element analysis tools. The numerical results of the load transfer path are compared with the ideal design path to identify abnormal offsets and stress concentration areas on the load path, thereby determining the imbalance status of the load path. Load path imbalance parameter data, including the imbalance amplitude, location, and range of influence, are output as input for subsequent plastic deformation trend detection.

[0091] Based on the load path imbalance of the work platform and the dynamic fatigue trend of the platform support structure, the plastic deformation trend of the platform support structure is detected.

[0092] In this embodiment of the invention, load path imbalance data, combined with dynamic fatigue trend analysis results, are used to evaluate the plastic deformation development of structural units using an elastoplastic mechanical analysis method. Real-time collected displacement and strain sensor data are used to calculate the cumulative strain values ​​of each key support node. The cumulative strain is compared with the material's yield criterion to determine whether the plastic stage has been entered and the rate of plastic deformation. Using strain time-series data, the plastic deformation trend is analyzed, focusing on identifying areas of continuous intensification to obtain the plastic deformation trend curve and corresponding parameters of the platform support structure, providing a basis for subsequent symmetry loss estimation.

[0093] Estimate the platform's force transmission symmetry deficiency based on the plastic deformation trend of the platform's supporting structure;

[0094] In this embodiment of the invention, based on plastic deformation trend data, a force transmission symmetry index is calculated by comparing the stress and deformation states of the left and right sides or multiple symmetrical parts of the platform. This index reflects the degree of symmetry loss in force transmission through statistical and weighted summation of stress and deformation differences among structural units at symmetrical positions. Statistical analysis methods are used to determine the spatial distribution characteristics of the symmetry loss and locate key areas with significant asymmetrical stress. Force transmission symmetry loss data is output, including the missing index value and spatial distribution map, providing a basis for structural damage detection.

[0095] Based on the absence of symmetry in platform force transmission and the plastic deformation trend of platform support structure, the failure status of platform force transmission structure is detected;

[0096] In this embodiment of the invention, by combining symmetry-deficient data with plastic deformation trends, fracture mechanics and damage mechanics theories are used to analyze the risk of structural failure. Crack initiation and propagation locations are identified by monitoring data from fracture and strain sensors. Detailed mechanical modeling of the plastic deformation region is performed to calculate local stress concentration and damage evolution processes. The structural failure level is determined based on crack size and propagation rate. The results include data on the structural failure distribution area, failure severity, and failure evolution trend, providing a basis for estimating the tilt degree of the lifting structure.

[0097] Estimate the degree of abnormal tilt of the platform's lifting structure based on the damage status of the platform's force transmission structure and the lack of symmetry in the platform's force transmission.

[0098] In this embodiment of the invention, based on structural damage distribution and symmetry missing data, a three-dimensional attitude measurement system monitors the tilt angle and direction of the platform's lifting structure in real time. High-precision gyroscopes and tilt sensors, combined with laser scanning technology, are used to acquire the spatial displacement and attitude changes of the platform's lifting device. The amplitude and development trend of abnormal tilt are calculated based on the structural damage distribution. Time-series data analysis determines whether the tilt exceeds a safety threshold. Abnormal tilt parameter data of the lifting structure are output, including tilt angle, tilt rate, and location of the abnormal area.

[0099] The damage status of the floating vessel's hull due to coupled stress was detected based on the abnormal tilt of the platform's lifting structure.

[0100] In this embodiment of the invention, abnormal tilt data is used in conjunction with a ship structural mechanical model, and a multiphysics coupling analysis method is employed to assess the coupled stress state of the ship. Stress sensor grids are used to acquire stress distribution and stress concentration areas at different parts of the ship. The coupled stress response of the ship structure is calculated by incorporating the mechanical off-center loading effect caused by tilting. Damage risk areas and stress over-limit points are identified, and coupled stress damage data of the floating vessel hull is output, including damage distribution maps and anomaly stress parameters, providing critical structural status information for the safety boundary early warning system.

[0101] Preferably, step S3 includes the following steps:

[0102] Step S31: Detect the damage trend of the floating vessel operation structure based on the damage status of the coupled stress of the floating vessel hull and the dynamic fatigue trend of the platform support structure;

[0103] In this embodiment of the invention, the coupled stress damage data of the floating vessel hull and the dynamic fatigue trend data of the platform support structure obtained in step S2 are acquired. These two sets of data reflect the damage distribution and fatigue accumulation of the hull structure under complex stress. Time series analysis is used to perform correlation analysis on these two sets of data to identify the evolution law of structural damage. A mathematical model of the structural damage state changing over time is constructed to calculate the damage propagation rate and the growth trend of the damage area. A nonlinear damage accumulation method is used, combined with historical monitoring data, to estimate the structural damage trend parameters for a future period, outputting structural damage trend data, specifically including the predicted range of future damage areas, damage rate, and severity distribution, providing a basis for subsequent operational assessment of failure status.

[0104] Step S32: Determine the floating vessel operation sensing failure status based on the damage trend of the floating vessel operation structure;

[0105] In this embodiment of the invention, based on the structural damage trend data obtained in step S31, multiple damage thresholds are set, and the degree of structural damage is compared with the limits of each threshold to determine whether the structural damage has reached or exceeded the preset judgment criteria for a perceived failure state. These judgment criteria are formulated based on engineering experience and design specifications, covering the damage ratio of key parts and overall structural integrity indicators. Combined with real-time operational status data monitored by sensors, the correspondence between damage trends and actual operational performance is confirmed. Perceived failure states are classified, such as minor failure, moderate failure, and severe failure levels, and perceived failure level data is output. This data serves as a key input for detecting loss of control in the ship's positioning capability, ensuring that the identified failure states have high timeliness and accuracy.

[0106] Step S33: Detect the loss of control over the hull positioning capability of the floating vessel based on the floating vessel operation failure status and the floating vessel operation structure damage trend;

[0107] In this embodiment of the invention, the functional status of the key support structure and positioning sensors of the positioning system is analyzed by combining the perceived failure status data obtained in step S32 and the structural damage trend data in step S31. Multi-sensor fusion technology is employed to comprehensively assess the impact of structural damage on the positioning sensor mounting points and support components, thereby evaluating the stability and accuracy of the positioning signal. A correlation model between positioning capability and structural damage is established by combining historical positioning error data and real-time monitoring data, and the positioning capability attenuation rate is calculated. The critical point of positioning system signal loss of control is detected to determine whether the current positioning capability is out of control. The out-of-control parameters of the ship's positioning capability are output, including the time point of loss of control, the area of ​​loss of control, and the level of loss of control, providing a basis for subsequent dynamic displacement trajectory detection.

[0108] Step S34: Detect the dynamic displacement trajectory data of the floating vessel based on the loss of control of the floating vessel's positioning capability and the disturbance trend of the floating vessel's operating environment.

[0109] In this embodiment of the invention, based on the data on the loss of control of the hull positioning capability obtained in step S33, and combined with the environmental disturbance trend data obtained in step S14, the three-dimensional displacement data of the floating vessel is collected in real time using a high-precision satellite positioning system, an inertial navigation system, and a marine environmental monitoring system. Through a data fusion algorithm, the noise impact of environmental disturbances on the displacement data is eliminated, and the dynamic offset trajectory during the floating vessel's operation is accurately extracted. Using time series analysis technology, a dynamic model of the floating vessel's displacement trajectory is constructed to identify abnormal offset characteristics. The dynamic offset trajectory data of the floating vessel is output, including the offset amplitude, direction, and rate of change, providing dynamic monitoring parameters for safety boundary early warning. This step achieves comprehensive monitoring of the operating platform status and environmental disturbances, ensuring the accuracy and real-time nature of the offset trajectory data.

[0110] Of particular importance, step S32 includes the following steps:

[0111] Step S321: Predict the abnormal extension of structural damage based on the damage trend of the floating vessel operation structure;

[0112] In this embodiment of the invention, after detecting a damage trend in the floating structure, a three-dimensional geometric boundary model of the local damage area is constructed by calling data on local structural fatigue degree, stress concentration location, and structural stiffness reduction curve obtained from previous steps. Based on this model, a perturbation load is applied to the critical region of structural damage using the finite difference time-domain method (FDTD), and a secondary distribution map of the internal stress field of the structure is obtained by simulating the perturbation response. By comparing the rate of change of the stress field before and after the perturbation, the abnormal stress amplification region is extracted, and the elongation rate per unit length is calculated by combining material performance parameters and structural geometric characteristics. By analyzing the region where the elongation rate exceeds a set threshold, the abnormal damage propagation path is further delineated. In the above calculation process, time-series structural deformation data obtained by the laser strain sensor and high-frequency vibration acquisition device in the platform's existing online structural health monitoring system are used to ensure that the predicted input data has real-time and continuous output data on the abnormal extension status of structural damage, including indicators such as extension direction, extension speed, and boundary of the affected area, providing basic data for subsequent stability analysis of the sensing device.

[0113] Step S322: Estimate the drift status of the reference point of the floating vessel sensing device based on the abnormal extension of structural damage;

[0114] In this embodiment of the invention, after acquiring data on the abnormal extension of structural damage, the structural unit numbers directly connected to the base of the sensing device are extracted, and the coordinate change information of the nodes covered by the damage extension path is read accordingly. A three-axis laser displacement sensor is used to acquire the spatial displacement of the structural nodes, and the node movement vector trajectory is calculated using multi-time interval differences. Based on this, the spatial geometric offset is calculated by combining the original calibration position of the sensing device's reference point in the structural mesh. To ensure calculation accuracy, at least five nodes on the extension path are selected to form a multi-point fitting region. The least squares method is used to establish a structural deformation surface, and the original reference point of the sensing device is projected onto this deformation surface to obtain the coordinates of the new reference point after drift. By comparing the two coordinate positions, the drift vector and its magnitude of the reference point are obtained as a measure of the device's drift. Finally, reference point drift status data containing drift direction, drift amplitude, and dynamic drift change curves are generated, providing input for collaborative system calibration and attitude stability analysis.

[0115] Step S323: Determine the degree of change in the attitude stability of the work platform based on the damage trend of the floating vessel operation structure;

[0116] In this embodiment of the invention, based on the structural damage area and center of gravity change data extracted from the floating vessel's structural damage trend, and combined with the real-time tilt angle data and pitch, roll, and bow-stern difference curves of each node in the platform's attitude control system, the three-dimensional attitude changes before and after the damage are compared. A center of gravity-buoyancy moment calculation method is used to predict the new center of gravity position through changes in the overall platform mass distribution, and then the platform's attitude change trend is calculated using the moment balance formula based on the buoyancy center position. Attitude stability evaluation indicators are introduced, including the maximum tilt angle increase of each key node of the platform, the attitude recovery period, and the attitude oscillation frequency, to construct a comprehensive evaluation factor for the degree of attitude stability change. By analyzing the trend of this factor over time, it is determined whether structural damage leads to platform attitude instability. All analytical data originates from the floating vessel's built-in six-degree-of-freedom inertial measurement unit (IMU) and distributed attitude monitoring array system. High-frequency sampling ensures the timeliness and continuity of the change trend. The output attitude stability change data is a quantitative matrix, including stability attenuation coefficient, attitude disturbance amplification factor, and nonlinear response index.

[0117] Step S324: Predict the disorder of the cooperative relationship of the floating vessel operation sensing system based on the drift status of the floating vessel sensing device reference point and the degree of change in the attitude stability of the operating platform;

[0118] In this embodiment of the invention, the spatial positioning topology map of each sensing node in the floating sensing system is constructed by combining the reference point drift status and attitude stability change data obtained in the aforementioned two steps. This topology map is based on the actual deployment location of the device and is calibrated in real time using the platform's dynamic coordinate system. Subsequently, the original coordinates of each sensing device are corrected by superimposing the attitude disturbance vector induced by attitude change using the reference point drift vector as a disturbance factor, simulating the changes in the spatial layout of the sensing network over different time periods. Based on this, the relative distance change and signal synchronization error value between each node in the sensing system are calculated. By setting distance tolerance and time window synchronization error thresholds, the cooperative error region is determined. The weighted network consistency analysis method is used to extract the disordered subgraph within the system and output evaluation indicators of the degree of disorder in cooperative relationships, including average synchronization error, number of cooperative mismatched nodes, and the decrease in system redundancy coverage. All of the above analyses rely on the real-time data transmission guarantee of the high-precision clock synchronization system and the fiber optic communication bus to ensure the accuracy of the sensing system state restoration.

[0119] Step S325: Determine the failure status of the floating vessel operation sensing system based on the disorder of the cooperative relationship of the floating vessel operation sensing system.

[0120] In this embodiment of the invention, after obtaining the disordered collaborative relationship of the sensing system, a deep analysis is performed on the identified disordered subgraph of the system. Combined with the specific sensing task type, such as platform attitude monitoring, ship motion estimation, and environmental disturbance perception, the loss ratio of key functional nodes, the number of interrupted information redundancy paths, and the level of sensing data fusion error are calculated. Based on the task function chain, a system functional integrity matrix is ​​constructed. By comparing with preset task completion standards, functional modules that cannot be completed or whose data errors exceed safety limits are identified. A functional mismatch marking mechanism is used to mark modules that do not meet operational requirements as "failure states," and the corresponding impact range and list of affected tasks are recorded. Sensing failure states manifest as: key sensing modules failing to sense normally, information fusion errors exceeding limits, and system data output interruptions. The system output results are a sensing system failure structure diagram and a task risk index table. During the above processing, the redundancy verification mechanism and task mapping relationship table of each sensing module are invoked to ensure that the failure judgment is targeted and accurate, and consistent with the preceding structural damage trend data.

[0121] Of particular importance, step S33 includes the following steps:

[0122] Step S331: Detect the disorder of the floating vessel operation feedback loop based on the floating vessel operation failure status and the floating vessel operation structure damage trend;

[0123] In this embodiment of the invention, the floating vessel operation sensing failure status data obtained in the aforementioned steps is acquired. This data includes the reference point drift of multiple sensing devices, the frequency of sensor signal loss, the signal response delay time, and their coupling change parameters with the structural attitude offset angle. Simultaneously, the identified floating vessel operation structural damage trend data is retrieved, including the crack propagation rate of platform structural units, the fatigue factor change rate of local connection nodes, and the corresponding time series. A time synchronization mechanism is used to perform unified time reference correction on the two data sources to ensure the consistency of the information transmission sequence in the feedback path. Based on the closed-loop characteristics of the feedback path and relying on the topological information structure, a node information integrity discrimination mechanism is constructed in the floating vessel sensing-processing-execution link to calculate the offset and packet loss rate between signal input and output in each link; then, the response matching curves between each node in the feedback chain under normal operating conditions are compared. If a continuous response delay, increased signal interference, or a control node unresponsive window exceeding a threshold of 10 seconds is detected in the logic link between the sensor and the actuator, it is determined to be a feedback loop disorder. The feedback loop disorder parameter set includes: node synchronization error distribution map, signal flow stability index, closed-loop error integral curve, and imbalance level labels for each path, which are used as input data support for subsequent positioning distortion analysis.

[0124] Step S332: Determine the floating vessel positioning distortion based on the disorder in the floating vessel operation feedback loop;

[0125] In this embodiment of the invention, a pre-generated set of feedback loop disorder parameters is invoked and compared with the existing positioning output data of the operating platform. The positioning output data used comes from the floating inertial navigation system, GNSS module, and photoelectric / radar-based auxiliary ranging system. This data is recorded at a frequency of 1Hz, including the ship's X / Y / Z position, yaw angle, pitch angle, roll angle, and relative distance to the anchor point. The control output of the feedback disorder marked area is paired and analyzed with the positioning data of the corresponding time period, and a multipath offset detection algorithm is introduced to calculate the difference value of the positioning results from different sensor sources within the same time window. When the difference value exceeds the allowable deviation threshold (e.g., 0.5m spatial deviation or 2° angular deviation), it is recorded as a positioning distortion event, and its duration and frequency are tracked. Statistical analysis reveals the drift trajectory, fluctuation characteristics, and dynamic error trends of each sensor combination. Combined with platform structural stress and deformation data, it is determined whether the positioning distortion is caused by abnormal feedback control due to structural damage. This includes positioning drift vector field diagrams, signal drift duration distribution, and mapping relationship matrix between drift nodes and feedback paths, which are used to support the identification of subsequent positioning error conditions.

[0126] Step S333: Predict the floating vessel positioning error situation based on the floating vessel positioning distortion;

[0127] In this embodiment of the invention, based on the acquired positioning distortion data, a set of positioning judgment logic rules is constructed for the floating vessel operation process. This set includes: control logic for maintaining the stability of the vessel's operational posture, anchoring adjustment response relationships, and distance judgment rules with surrounding obstacles. Actual positioning data is matched and analyzed against preset judgment rules, and a dynamic threshold comparison strategy is used to identify judgment logic deviation events caused by positioning signal drift. For example, when the floating vessel detection system misjudges the platform as deviating from the set safety boundary due to signal drift and mistakenly triggers an attitude correction command, this is recorded as a positioning judgment error event. By comparing the response deviation between the execution of the judgment logic and the actual changes in the platform state through time-window comparisons, the frequency, spatial distribution, time interval, and signal source of the judgment system for positioning judgment errors are extracted. Combined with structural fatigue trend information, the mechanical structural correlation of the judgment errors is further evaluated, and the corresponding judgment chain trigger points are marked to form a positioning judgment error status dataset, including a judgment error trigger map, an error frequency distribution map, and a mis-trigger path link table, providing quantitative basis for subsequent adjustment behavior analysis.

[0128] Step S334: Estimate the extent of over-adjustment of the floating vessel's positioning based on the error and distortion of its positioning.

[0129] In this embodiment of the invention, the number of times the positioning correction command was triggered and the corresponding adjustment amplitude data within each time period are extracted from the positioning error data. This data is then compared and analyzed with positioning distortion records to determine if there is an over-adjustment phenomenon in the correction behavior that is inconsistent with the actual hull displacement. A correction response analysis mechanism is introduced to calculate the adjustment speed, displacement, and coupling response curve of the thrusters or lifting structures in each direction of the execution system with the actual attitude change. If multiple corrections are executed but the hull attitude does not change accordingly, or if the adjustment action significantly exceeds the set displacement threshold (e.g., exceeding the standard correction amplitude by 1.5 times), it is marked as a positioning over-adjustment event. Furthermore, the sensing sources corresponding to each event are correlated and tracked to determine whether the over-adjustment originates from repeated misjudgments by specific sensors or control loops, forming a positioning over-adjustment data table. The recorded content includes: the number of over-corrections, the level of exceeding the adjustment path amplitude limit, the duration of superposition with the judgment error, and the trend curve of thruster / structural load changes, providing dynamic behavioral basis for subsequent loss-of-control situation identification.

[0130] Step S335: Detect the out-of-control status of the floating vessel's positioning capability based on the floating vessel's over-adjustment status and floating vessel positioning error judgment status.

[0131] In this embodiment of the invention, data on over-adjustment and positioning error are fused to construct a loss-of-control behavior identification map, analyzing whether the vessel enters a closed-loop cycle of continuous positioning errors and over-adjustment during long-term operations. State transition analysis technology is used to construct a closed-loop state diagram of "judgment error—over-adjustment—pose deviation—re-misjudgment" to identify whether there is a periodically increasing trend of positioning loss of control. The degree of response matching between the density of positioning control execution commands and the actual rate of change of platform pose is detected, and attitude stability parameters, operational boundary offset, and correction path cross-data are introduced to systematically evaluate the positioning closed-loop stability of the entire control system. If the system experiences judgment deviation, execution deviation, and callback failure of the same structural path within multiple consecutive cycles, the floating vessel is determined to have entered a positioning capability loss-of-control state. The generated positioning capability loss-of-control status output includes: control execution-attitude response deviation matrix, continuous judgment / adjustment mismatch path diagram, loss-of-control closed-loop cycle frequency table, vessel attitude deviation integral value and its changing trend, providing reliable signal support for triggering the safety boundary early warning model.

[0132] Preferably, step S34 includes the following steps:

[0133] Step S341: Estimate the trend of excessive water flow velocity on the surface of the floating vessel based on the disturbance trend of the floating vessel's operating environment;

[0134] In this embodiment of the invention, water flow velocity sensor data around the floating vessel is collected from a marine environmental monitoring system, including water flow velocity information at different depths and time points. Combined with meteorological monitoring data, such as wind speed, wind direction, and air pressure trends, hydrodynamic analysis methods are used to calculate the water flow velocity variation trend. By constructing a time-series variation curve of ocean current velocity, abnormal growth intervals of water flow velocity are identified. Based on numerical integration methods, trend parameters of future short-term water flow velocity changes are estimated, and data on excessive ocean surface water flow velocity trends are output. This data provides a basic input for subsequent analysis of the impact of water flow on the floating vessel, enabling dynamic monitoring and prediction of environmental disturbance changes.

[0135] Step S342: Determine the degree of increase in lateral thrust of the water flow based on the trend of excessive water velocity on the surface of the floating vessel;

[0136] In this embodiment of the invention, based on the excessive water flow velocity trend data obtained in step S341, the water flow pressure acting on the hull of the floating vessel is calculated. Using the resistance formula in fluid mechanics, combined with the force-bearing cross-sectional area and shape factor of the hull, the change in lateral thrust caused by the change in water flow velocity is calculated. Employing a dynamic force balance method, with the thrust as the input force, the force distribution of the floating vessel in the water flow is solved using a hull mechanics model, obtaining a quantitative index of the increase in lateral thrust. This index is output to characterize the changing trend of the lateral force exerted by the water flow on the hull, providing a quantitative basis for subsequent hull drift analysis.

[0137] Step S343: Detect the lateral drift of the floating vessel by using the increase in the lateral thrust of the water flow to assess the loss of control over the hull positioning capability, and obtain the lateral drift data of the floating vessel.

[0138] In this embodiment of the invention, the influence of the water flow force on the hull positioning device is analyzed based on the degree of increase in the lateral thrust of the water flow determined in step S342. Multi-point displacement sensors and high-precision GPS positioning equipment are used to monitor the displacement changes of the floating vessel in the horizontal direction in real time. The lateral drift velocity and drift distance under the action of the water flow thrust are calculated using mechanical equilibrium equations. During data processing, positioning system errors and environmental noise are eliminated to ensure the accuracy of the lateral drift data. The lateral drift data of the working vessel, including drift amplitude, velocity, and direction, is output to provide real-time dynamic information for hull stability control.

[0139] Step S344: Estimate the degree of increase in vertical impact on the sea surface based on the trend of excessive water flow velocity on the floating vessel.

[0140] In this embodiment of the invention, based on the water flow velocity trend analyzed in step S341, and combined with wave height and frequency data obtained from the wave monitoring system, the change in vertical impact force on the sea surface is calculated using a marine dynamics model. Specifically, wave mechanics calculation formulas are used to consider the superposition effect of water flow velocity and waves, calculating the increase in vertical impact force on the floating deck and structural components. Through dynamic load analysis methods, the short-term trend of vertical impact growth on the sea surface is predicted, and data on the degree of vertical impact growth are output, providing a basis for subsequent anchor chain stress analysis.

[0141] Step S345: Estimate the trend of stress growth on the floating vessel's anchor chain based on the lateral drift data of the working vessel and the degree of vertical impact growth on the sea surface;

[0142] In this embodiment of the invention, the lateral drift data of the working vessel obtained in step S343 is combined with the vertical impact growth data in step S344 to analyze the comprehensive load borne by the anchor chain. The stress state of the anchor chain under the combined action of lateral tension and vertical impact is calculated using structural mechanics analysis methods. Specifically, finite element analysis tools are used to mechanically model the anchor chain structure, calculating the tension changes and stress distribution at each node of the anchor chain. Based on the calculation results, the growth trend parameters of the anchor chain stress are determined, and the anchor chain stress growth trend data is output, providing data support for subsequent anchor chain tensile stability analysis.

[0143] Step S346: Predict the degree of decrease in the stability of the anchor chain tension based on the trend of the increase in anchor chain stress during floating operations and the degree of increase in vertical impact on the sea surface;

[0144] In this embodiment of the invention, the anchor chain tensile stability attenuation is calculated by utilizing the anchor chain stress growth trend obtained in step S345 and the vertical impact growth data from step S344, combined with the anchor chain material performance parameters and fatigue life curve. The fatigue damage accumulation theory is employed, along with the actual load history of the anchor chain, to calculate the fatigue damage index of key parts of the anchor chain. By comparing the fatigue damage index with a safety threshold, the degree of anchor chain tensile stability attenuation over time is predicted. The anchor chain tensile stability attenuation data is output, providing key parameters for evaluating vertical tension adjustment capability.

[0145] Step S347: Based on the degree of decrease in the stability of the anchor chain tension and the loss of control over the hull positioning ability of the floating vessel, conduct an assessment of the imbalance of the hull's vertical tension adjustment capability to obtain the imbalance status of the hull's vertical tension adjustment capability.

[0146] In this embodiment of the invention, the working state of the vertical tension adjustment system is analyzed by combining the anchor chain tension stability attenuation data obtained in step S346 and the ship's positioning capability loss of control status in step S33. Through tension sensor data and a dynamic model, the response capability of the tension adjustment device under conditions of anchor chain force changes and positioning loss of control is evaluated. Using control system theory, the stability index of the vertical tension adjustment capability is calculated and compared with a set standard to determine whether the tension adjustment capability is unbalanced. Data on the imbalance status of the ship's vertical tension adjustment capability is output, reflecting the current performance status of the adjustment system.

[0147] Step S348: Detect the dynamic offset trajectory data of the floating vessel's displacement based on the imbalance of the hull's vertical tension adjustment capability and the lateral drift data of the working vessel.

[0148] In this embodiment of the invention, the data on the imbalance of the hull's vertical tension adjustment capability in step S347 and the data on the lateral drift of the working vessel in step S343 are integrated. Using a high-precision inertial navigation system and differential GPS data, the three-dimensional displacement data of the floating vessel is collected in real time. A multi-dimensional dynamic analysis algorithm is employed, combining the information on vertical tension imbalance and lateral drift, to calculate the comprehensive displacement trajectory of the floating vessel under the operating environment. Through trajectory reconstruction technology, dynamic offset trajectory data of the floating vessel's displacement is generated, including the displacement path, velocity vector, and offset trend. This data is used for dynamic monitoring of the safety boundary early warning system, enabling a comprehensive understanding of the floating vessel's displacement status.

[0149] Preferably, step S4 includes the following steps:

[0150] Step S41: Determine the floating vessel operation space constraint parameters based on the floating vessel operation log data;

[0151] In this embodiment of the invention, this step collects automatically recorded operation log data during the floating vessel operation, including operation time, geographical coordinates, operation radius, operation platform size, operation task type, and environmental constraint information. Using Geographic Information System (GIS) technology, the geographical boundary of the floating vessel operation area is compared and integrated with the operation space information recorded in the operation log. Through spatial data analysis, the actual operation range of the floating vessel in each operation period is extracted, and the limiting parameters of the operable space around the operation platform are calculated, such as the maximum allowable operation radius, operation boundary limit line, and distance to nearby obstacles. Using 3D spatial modeling technology, a 3D geometric model of the floating vessel operation space constraints is constructed to accurately represent the spatial boundary shape of the operation space. Spatial constraint parameter data is output, including the operation area boundary coordinate set, constraint radius range, spatial obstacle coordinates, and related spatial constraint conditions, for subsequent risk assessment and processing.

[0152] Step S42: Based on the dynamic offset trajectory data of the floating vessel displacement, the floating vessel operation space constraint parameters are processed to determine the floating vessel boundary risk, and floating vessel operation boundary risk determination data is obtained.

[0153] In this embodiment of the invention, this step is based on the dynamic offset trajectory data of the floating vessel obtained in step S34, and compares and analyzes the trajectory data with the spatial constraint parameter model in step S41 in real time. A spatial collision detection algorithm is used to determine whether each trajectory point has exceeded the boundary of the work space. A distance measurement algorithm is used to calculate the shortest distance between each trajectory point and the work boundary; when this distance is less than a set safety threshold, it is marked as a boundary violation risk point. Time series analysis is used to identify the continuity and frequency of boundary violation risk points and assess the severity of the boundary violation risk. Combining the spatial distribution and temporal characteristics of the boundary violation points, boundary violation risk judgment data for floating vessel operations is generated, including boundary violation location coordinates, boundary violation timestamps, number of boundary violations, and risk level. This data provides a direct basis for determining abnormal increases in the difficulty of floating vessel operations.

[0154] Step S43: Determine the abnormal increase in the difficulty of floating vessel operations based on the risk assessment data of floating vessel operations crossing boundaries;

[0155] In this embodiment of the invention, the boundary crossing risk assessment data generated in step S42 is subjected to in-depth analysis to statistically analyze the number of boundary crossing risk events and their changing trends of the floating vessel within a certain time window. A trend detection algorithm is used to identify abnormal increases in the frequency of boundary crossing risks, and combined with changes in the operational environment such as wind and wave intensity and current velocity, a comprehensive assessment of the changes in the difficulty of floating vessel operations is conducted. By establishing an operational difficulty evaluation index system, boundary crossing risks and environmental disturbance indicators are weighted and calculated to quantify the level of abnormal increase in difficulty. Data on the abnormal increase in floating vessel operational difficulty is output, specifically including the distribution of difficulty levels, the rate of change in difficulty, and the relevant time periods. This data serves as a core parameter for generating multi-level boundary early warning responses, supporting safety boundary early warning decisions.

[0156] Step S44: Based on the risk assessment data of floating vessel operations crossing boundaries and the abnormal increase in the difficulty of floating vessel operations, multi-level boundary early warning response signals are generated and processed to obtain multi-level boundary early warning response signal data, which is then uploaded to the cloud platform for early warning.

[0157] In this embodiment of the invention, a multi-level early warning response rule is designed by combining the boundary risk assessment data from step S42 and the abnormal increase in operational difficulty data from step S43. By setting different risk thresholds and difficulty levels corresponding to different early warning levels (such as warning level, alert level, and alarm level), a tiered output of early warning signals is achieved. Using a real-time data processing system, the current risk status is mapped to the corresponding early warning level, and early warning response signal data is generated, including the early warning level, trigger time, risk source description, and corresponding floating vessel location information. This early warning response signal is uploaded to a cloud platform via a communication module. The cloud platform utilizes big data analysis and remote monitoring technology to achieve centralized management and real-time early warning dissemination of the floating vessel's operational status. This step ensures rapid transmission and response of early warning information, contributing to effective control of the safety boundaries of floating vessel operations.

[0158] The present invention also provides a safety boundary early warning system for floating vessel operations, for executing the safety boundary early warning method for floating vessel operations as described above, the safety boundary early warning system for floating vessel operations comprising:

[0159] The environmental disturbance enhancement assessment module is used to collect floating vessel operation log data; collect floating vessel operation environment data based on the floating vessel operation log data to obtain floating vessel operation environment data; and assess the enhancement trend of floating vessel operation environment disturbance based on the floating vessel operation environment data.

[0160] The hull coupling stress damage detection module is used to determine the dynamic imbalance state of the working platform under pressure based on the floating vessel operation log data; determine the dynamic fatigue trend of the platform support structure based on the dynamic imbalance state of the working platform under pressure; and detect the coupling stress damage status of the floating vessel hull based on the dynamic fatigue trend of the platform support structure.

[0161] The displacement dynamic offset trajectory detection module is used to detect the loss of control of the floating vessel's positioning capability based on the damage status of the coupled stress of the floating vessel's hull and the dynamic fatigue trend of the platform support structure; and to detect the dynamic offset trajectory data of the floating vessel's displacement based on the loss of control of the floating vessel's positioning capability and the increasing trend of disturbance in the floating vessel's operating environment.

[0162] The early warning response module is used to determine the floating vessel operation space constraint parameters based on the floating vessel operation log data; to perform floating vessel boundary crossing risk assessment processing on the floating vessel operation space constraint parameters based on the floating vessel displacement dynamic offset trajectory data, thereby obtaining floating vessel operation boundary crossing risk assessment data; and to perform multi-level boundary early warning response signal generation processing based on the floating vessel operation boundary crossing risk assessment data, thereby obtaining multi-level boundary early warning response signal data, and uploading it to the cloud platform for early warning.

[0163] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A safety boundary early warning method for floating vessel operations, characterized in that, Includes the following steps: Step S1: Collect floating vessel operation log data; collect floating vessel operation environment data based on floating vessel operation log data to obtain floating vessel operation environment data; assess the increasing trend of floating vessel operation environment disturbance based on floating vessel operation environment data; Step S2: Determine the dynamic imbalance state of the operating platform based on the floating vessel operation log data; determine the dynamic fatigue trend of the platform support structure based on the dynamic imbalance state of the operating platform; detect the damage status of the floating vessel hull due to coupled stress based on the dynamic fatigue trend of the platform support structure. Step S3: Detect the loss of control over the positioning capability of the floating vessel based on the damage status of the coupled stress of the floating vessel hull and the dynamic fatigue trend of the platform support structure; Based on the loss of control over the hull positioning capability of the floating vessel and the increasing trend of disturbance in the floating vessel's operating environment, the dynamic displacement trajectory data of the floating vessel is detected. Step S4: Determine the floating vessel operation space constraint parameters based on the floating vessel operation log data; perform floating vessel boundary crossing risk assessment processing on the floating vessel operation space constraint parameters based on the floating vessel displacement dynamic offset trajectory data to obtain floating vessel operation boundary crossing risk assessment data; perform multi-level boundary early warning response signal generation processing based on the floating vessel operation boundary crossing risk assessment data to obtain multi-level boundary early warning response signal data, and upload it to the cloud platform for early warning.

2. The safety boundary early warning method for floating vessel operations according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Collect floating vessel operation log data; Step S12: Collect the geographical coordinate data of the floating vessel operation based on the floating vessel operation log data; Step S13: Collect floating vessel operation environment data based on floating vessel operation geographic coordinate data and floating vessel operation log data; Step S14: Assess the increasing trend of environmental disturbances during floating vessel operations based on the floating vessel operation environment data.

3. The safety boundary early warning method for floating vessel operations according to claim 2, characterized in that, Step S14 includes the following steps: Step S141: Set the wind speed measurement range of the wind sensor to 0-60m / s, set the wind speed resolution to 0.01m / s, set the wind speed measurement accuracy to ±0.1m / s, set the wind direction measurement range to 0°-360°, set the wind direction resolution to 1°, and set the sampling frequency to 10Hz; Step S142: Set the flow velocity measurement range of the water flow sensor to 0-5m / s, set the flow velocity resolution to 0.001m / s, set the flow velocity measurement accuracy to ±0.01m / s, set the flow direction measurement range to 0°-360°, and set the sampling frequency to 5Hz; Step S143: Use wind and water flow sensors to collect environmental fluctuation coupling and superposition data of the floating vessel operation environment to obtain environmental fluctuation coupling and superposition data; Step S144: Perform spatiotemporal synchronization calibration processing on the environmental fluctuation coupled superimposed data to obtain environmental coupled superimposed spatiotemporal synchronization calibration data; Step S145: Construct multidimensional time-series data of environmental disturbance factors based on environmental coupling superposition spatiotemporal synchronization calibration data; Step S146: Analyze the nonlinear periodic variation characteristics of environmental disturbances based on multidimensional time-series data of environmental disturbance factors and spatiotemporal synchronous calibration data of environmental coupling superposition; Step S147: Evaluate the intensity characteristics of environmental disturbances during floating vessel operations based on the nonlinear periodic variation characteristics of environmental disturbances and multidimensional time-series data of environmental disturbance factors; Step S148: Assess the increasing trend of disturbance in the floating vessel's operating environment based on the disturbance intensity characteristics of the floating vessel's operating environment.

4. The safety boundary early warning method for floating vessel operations according to claim 1, characterized in that, Step S2, determining the dynamic imbalance state of the operating platform based on the floating vessel operation log data, includes: Collect data on the temporal changes in floating vessel operational requirements based on floating vessel operation log data; Collect data on the fluctuation of floating vessel operational demand based on the temporal changes in floating vessel operational demand. Data on periods of sudden demand growth are determined based on fluctuations in demand for floating vessel operations. Detection of excessive weight of floating vessel transport structural components based on data from periods of sudden demand surge; Based on data on the overweight status of floating operation transport structural components and periods of sudden demand surges, the trend of floating operation platform exceeding its load limit is estimated; The fatigue status of the floating deck structure was detected based on the overload trend of the floating platform and the overweight condition of the floating transport structural components. The dynamic imbalance state of the operating platform under pressure is determined based on the fatigue state of the floating deck structure and the overload trend of the floating platform.

5. The safety boundary early warning method for floating vessel operations according to claim 1, characterized in that, Step S2, determining the dynamic fatigue trend of the platform support structure based on the dynamic imbalance state of the working platform under pressure, includes: Based on the dynamic imbalance state of the pressure bearing of the working platform, the pressure difference distribution area of ​​the working platform is divided to obtain the pressure difference distribution area data of the working platform; Based on the pressure difference distribution area data of the working platform, the displacement recovery rate data of the structural unit is calculated for the dynamic imbalance state of the working platform under pressure. Analyze the displacement recovery time series data of structural units based on the displacement recovery rate data of structural units; The displacement recovery time series data of structural units is processed by platform-regional deformation stress-time curve reconstruction to obtain regionalized stress-time characteristic data. The local stress peak distribution of the platform was analyzed based on the regionalized stress-time characteristic data. Based on the distribution of local stress peaks on the platform, the platform stability support weight allocation process is performed to obtain platform stability support weight allocation data. The dynamic fatigue trend of the platform support structure is determined based on the platform stability support weight allocation data and the distribution of local stress peaks on the platform.

6. The safety boundary early warning method for floating vessel operations according to claim 1, characterized in that, Step S2, which involves detecting the coupled stress damage of the floating vessel hull based on the dynamic fatigue trend of the platform support structure, includes: Determine the load path imbalance of the work platform based on the dynamic fatigue trend of the platform support structure. Based on the load path imbalance of the work platform and the dynamic fatigue trend of the platform support structure, the plastic deformation trend of the platform support structure is detected. Estimate the platform's force transmission symmetry deficiency based on the plastic deformation trend of the platform's supporting structure; Based on the absence of symmetry in platform force transmission and the plastic deformation trend of platform support structure, the failure status of platform force transmission structure is detected; Estimate the degree of abnormal tilt of the platform's lifting structure based on the damage status of the platform's force transmission structure and the lack of symmetry in the platform's force transmission. The damage status of the floating vessel's hull due to coupled stress was detected based on the abnormal tilt of the platform's lifting structure.

7. The safety boundary early warning method for floating vessel operations according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Detect the damage trend of the floating vessel operation structure based on the damage status of the coupled stress of the floating vessel hull and the dynamic fatigue trend of the platform support structure; Step S32: Determine the floating vessel operation sensing failure status based on the damage trend of the floating vessel operation structure; Step S33: Detect the loss of control over the hull positioning capability of the floating vessel based on the floating vessel operation failure status and the floating vessel operation structure damage trend; Step S34: Detect the dynamic displacement trajectory data of the floating vessel based on the loss of control of the floating vessel's positioning capability and the disturbance trend of the floating vessel's operating environment.

8. The safety boundary early warning method for floating vessel operations according to claim 7, characterized in that, Step S34 includes the following steps: Step S341: Estimate the trend of excessive water flow velocity on the surface of the floating vessel based on the disturbance trend of the floating vessel's operating environment; Step S342: Determine the degree of increase in lateral thrust of the water flow based on the trend of excessive water velocity on the surface of the floating vessel; Step S343: Detect the lateral drift of the floating vessel by using the increase in the lateral thrust of the water flow to assess the loss of control over the hull positioning capability, and obtain the lateral drift data of the floating vessel. Step S344: Estimate the degree of increase in vertical impact on the sea surface based on the trend of excessive water flow velocity on the floating vessel. Step S345: Estimate the trend of stress growth on the floating vessel's anchor chain based on the lateral drift data of the working vessel and the degree of vertical impact growth on the sea surface; Step S346: Predict the degree of decrease in the stability of the anchor chain tension based on the trend of the increase in anchor chain stress during floating operations and the degree of increase in vertical impact on the sea surface; Step S347: Based on the degree of decrease in the stability of the anchor chain tension and the loss of control over the hull positioning ability of the floating vessel, conduct an assessment of the imbalance of the hull's vertical tension adjustment capability to obtain the imbalance status of the hull's vertical tension adjustment capability. Step S348: Detect the dynamic offset trajectory data of the floating vessel's displacement based on the imbalance of the hull's vertical tension adjustment capability and the lateral drift data of the working vessel.

9. The safety boundary early warning method for floating vessel operations according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Determine the floating vessel operation space constraint parameters based on the floating vessel operation log data; Step S42: Based on the dynamic offset trajectory data of the floating vessel displacement, the floating vessel operation space constraint parameters are processed to determine the floating vessel boundary risk, and floating vessel operation boundary risk determination data is obtained. Step S43: Determine the abnormal increase in the difficulty of floating vessel operations based on the risk assessment data of floating vessel operations crossing boundaries; Step S44: Based on the risk assessment data of floating vessel operations crossing boundaries and the abnormal increase in the difficulty of floating vessel operations, multi-level boundary early warning response signals are generated and processed to obtain multi-level boundary early warning response signal data, which is then uploaded to the cloud platform for early warning.

10. A safety boundary early warning system for floating vessel operations, characterized in that, For executing the safety boundary early warning method for floating vessel operations as described in claim 1, the safety boundary early warning system for floating vessel operations comprises: The environmental disturbance enhancement assessment module is used to collect floating vessel operation log data; collect floating vessel operation environment data based on the floating vessel operation log data to obtain floating vessel operation environment data; and assess the enhancement trend of floating vessel operation environment disturbance based on the floating vessel operation environment data. The hull coupling stress damage detection module is used to determine the dynamic imbalance state of the working platform under pressure based on the floating vessel operation log data; determine the dynamic fatigue trend of the platform support structure based on the dynamic imbalance state of the working platform under pressure; and detect the coupling stress damage status of the floating vessel hull based on the dynamic fatigue trend of the platform support structure. The displacement dynamic offset trajectory detection module is used to detect the loss of control of the floating vessel's positioning capability based on the damage status of the coupled stress of the floating vessel's hull and the dynamic fatigue trend of the platform support structure; and to detect the dynamic offset trajectory data of the floating vessel's displacement based on the loss of control of the floating vessel's positioning capability and the increasing trend of disturbance in the floating vessel's operating environment. The early warning response module is used to determine the floating vessel operation space constraint parameters based on the floating vessel operation log data; to perform floating vessel boundary crossing risk assessment processing on the floating vessel operation space constraint parameters based on the floating vessel displacement dynamic offset trajectory data, thereby obtaining floating vessel operation boundary crossing risk assessment data; and to perform multi-level boundary early warning response signal generation processing based on the floating vessel operation boundary crossing risk assessment data, thereby obtaining multi-level boundary early warning response signal data, and uploading it to the cloud platform for early warning.

Images