A data processing-based combined fleet safety risk assessment method and system

Abstract

The application provides a kind of combination ship fleet safety risk assessment method and system based on data processing, it is related to data processing technical field, the method includes: step 1, four kinds of data are collected by sensor on main propulsion ship, barge and auxiliary function ship, including ship state data, connecting device working condition data, navigation environment data and cargo safety parameter;Step 2, four kinds of data are transmitted through the data interaction channel of connecting device between ships, and are discretized into spatial distribution data of key area of ship after space-time alignment, to generate six groups of position data sets with three-dimensional space coordinate labels.The application realizes accurate evaluation and targeted early warning of dynamic risk of combination ship fleet in whole voyage by establishing space mapping, quantifying risk coefficient and fusing navigation data, and improves transportation safety and emergency response efficiency.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for assessing the safety risks of a combined fleet based on data processing. Background Technology

[0002] In near-shore bulk cargo transportation (such as coal and iron ore), when using a combined fleet formation model with a main propulsion vessel providing core power, multiple barges carrying cargo, and auxiliary vessels responsible for monitoring dangerous goods and providing emergency support, existing technologies have room for improvement in the comprehensive assessment of dynamically coupled risks. Specifically:

[0003] When fleets navigate to complex nearshore waters (such as bays with frequent swells or densely trafficked nearshore channels), they need to frequently deal with dynamic conditions such as changes in wave height, course adjustments, and avoidance of surrounding vessels. Real-time monitoring of the inter-ship connection devices is still insufficient. Existing monitoring focuses only on collecting basic stress data of mechanical latches and lacks real-time continuous monitoring of hydraulic circuit pressure fluctuations (such as the difference between the instantaneous peak and valley values ​​of hydraulic oil pressure) and power transmission stability indicators (such as voltage deviation rate and current fluctuation frequency). This may lead to the omission of key risks such as instantaneous overload damage to the connection devices caused by swell impacts and fatigue hazards caused by long-term high-frequency stress due to insufficient data support. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for assessing the safety risks of combined fleets based on data processing, which can effectively reduce safety hazards and ensure transportation safety.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0006] Firstly, a data processing-based method for assessing the safety risks of a combined fleet, the method comprising:

[0007] Step 1: Collect four types of data through sensors on the main propulsion vessel, barge, and auxiliary function vessel, including vessel status data, connection device operating status data, navigation environment data, and cargo safety parameters.

[0008] Step 2: The four types of data are transmitted through the data interaction channel of the ship-to-ship connection device. After spatiotemporal alignment, they are discretized into spatial distribution data of key ship areas, generating six sets of location datasets with three-dimensional spatial coordinate labels.

[0009] Step 3: Based on six sets of location datasets with three-dimensional spatial coordinate labels, perform regional feature analysis through preset calculation logic to generate structural connection failure risk coefficient, collaborative operation runaway risk coefficient, and special transportation safety risk coefficient.

[0010] Step 4: Integrate the three types of risk coefficients with the voyage planning data and sea state prediction data to generate a dynamic risk assessment result for the entire voyage and output a risk warning instruction set that includes regional compensation parameters.

[0011] Secondly, a data processing-based combined fleet safety risk assessment system includes:

[0012] The data acquisition module is used to collect four types of data through sensors on the main propulsion vessel, barge, and auxiliary function vessel: vessel status data, connection device operating status data, navigation environment data, and cargo safety parameters.

[0013] The conversion module is used to transmit four types of data through the data interaction channel of the inter-ship connection device, and after spatiotemporal alignment, discretize them into spatial distribution data of key areas of the ship, generating six sets of location datasets with three-dimensional spatial coordinate labels.

[0014] The calculation module is used to perform regional feature analysis based on six sets of location datasets with three-dimensional spatial coordinate labels, and generate structural connection failure risk coefficients, collaborative operation runaway risk coefficients, and special transportation safety risk coefficients through preset calculation logic.

[0015] The instruction generation module is used to integrate the three types of risk coefficients with the voyage planning data and sea state prediction data to generate dynamic risk assessment results for the entire voyage and output a risk warning instruction set that includes regional compensation parameters.

[0016] Thirdly, a computing device includes:

[0017] One or more processors;

[0018] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0019] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0020] The above-described solution of the present invention has at least the following beneficial effects:

[0021] By collecting four core data categories from sensors on various types of vessels, covering the vessel's own status, the operational status of connecting devices, the external environment, and cargo safety, comprehensive and crucial data support is provided for risk assessment, reducing information blind spots. Through spatiotemporal alignment and key area discretization, the data is correlated with the vessel's three-dimensional spatial coordinates, establishing a precise mapping between data and physical areas. This resolves the problem of ambiguity in matching data with risk locations, enabling risk analysis to focus on specific key areas. Based on spatialized data, three types of specialized risk coefficients are generated to accurately quantify core safety risks such as structural connections, collaborative operations, and special transportation, achieving detailed risk identification and quantitative assessment. By integrating voyage planning and sea state prediction data, dynamic assessment results for the entire voyage are generated, and early warning instructions with regional compensation parameters are output. This makes risk response more targeted and forward-looking, facilitating timely measures such as reinforcement, power optimization, and emergency dispatch for the fleet, effectively reducing safety hazards and ensuring transportation safety. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating a data processing-based method for assessing the safety risks of a combined fleet, as provided in an embodiment of the present invention.

[0023] Figure 2 This is a schematic diagram of a combined fleet safety risk assessment system based on data processing, provided by an embodiment of the present invention. Detailed Implementation

[0024] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0025] like Figure 1 As shown, an embodiment of the present invention proposes a data processing-based method for assessing the safety risks of a combined fleet, the method comprising the following steps:

[0026] Step 1: Collect four types of data through sensors on the main propulsion vessel, barge, and auxiliary function vessel, including vessel status data, connection device operating status data, navigation environment data, and cargo safety parameters.

[0027] Step 2: The four types of data are transmitted through the data interaction channel of the ship-to-ship connection device. After spatiotemporal alignment, they are discretized into spatial distribution data of key ship areas, generating six sets of location datasets with three-dimensional spatial coordinate labels.

[0028] Step 3: Based on six sets of location datasets with three-dimensional spatial coordinate labels, perform regional feature analysis through preset calculation logic to generate structural connection failure risk coefficient, collaborative operation runaway risk coefficient, and special transportation safety risk coefficient.

[0029] Step 4: Integrate the three types of risk coefficients with the voyage planning data and sea state prediction data to generate a dynamic risk assessment result for the entire voyage and output a risk warning instruction set that includes regional compensation parameters.

[0030] In this embodiment of the invention, four types of core data are collected through sensors on various types of vessels, covering the vessel's own status, the operating condition of connecting devices, the external environment, and cargo safety. This provides comprehensive and crucial data support for risk assessment, reducing information blind spots. Through spatiotemporal alignment and key area discretization, the data is associated with the vessel's three-dimensional spatial coordinates, establishing a precise mapping between data and physical areas. This solves the problem of ambiguity in matching data with risk locations, enabling risk analysis to focus on specific key areas. Based on spatialized data, three types of specialized risk coefficients are generated to accurately quantify core safety risks such as structural connections, collaborative operations, and special transportation, achieving detailed risk identification and quantitative assessment. By integrating voyage planning and sea state prediction data, dynamic assessment results for the entire voyage are generated, and early warning instructions with regional compensation parameters are output. This makes risk response more targeted and forward-looking, facilitating timely measures such as reinforcement, power optimization, and emergency dispatch for the fleet, effectively reducing safety hazards and ensuring transportation safety.

[0031] In a preferred embodiment of the present invention, in step 1 above, four types of data are collected by sensors on the main propulsion vessel, barge, and auxiliary function vessel, including vessel status data, connection device operating condition data, navigation environment data, and cargo safety parameters; the connection device operating condition data includes mechanical locking stress value, hydraulic circuit pressure fluctuation value, and power transmission stability index.

[0032] In this embodiment of the invention, the main propulsion vessel is equipped with an engine sensor that records the engine speed at 5-second intervals, in revolutions per minute (rpm). The engine's operational stability is determined by continuously tracking speed changes. Specifically, if the speed fluctuation exceeds ±50 rpm within one minute, the engine status is marked as abnormal. Simultaneously, the sensor records the fuel consumption rate. The barge is equipped with a hull tilt sensor that monitors the hull's lateral and longitudinal tilt angles in real time, recording data at 1-second intervals. If the tilt angle exceeds 5 degrees for 30 consecutive seconds, it is determined that the hull is under uneven stress. At this point, the barge's cargo distribution data needs to be retrieved to further analyze the cause of the uneven stress and investigate whether cargo displacement has caused the hull to become unbalanced. The auxiliary function vessel is equipped with a navigation sensor that obtains its real-time speed and heading angle using satellite positioning technology. The speed and heading angle data of the auxiliary function vessel are compared with the corresponding data of the main propulsion vessel to calculate the deviation value. For example, when the auxiliary function vessel's speed is 0.5 knots slower than the main propulsion vessel and its heading deviation is 3 degrees, this deviation value can intuitively reflect the overall coordination of the combined fleet's navigation.

[0033] For the mechanical-hydraulic connection device, dedicated sensors are deployed to accurately monitor three core indicators. The specific data acquisition method is as follows: strain gauge sensors are installed at the metal connection of the mechanical latch. These sensors can detect the degree of deformation of the latch in real time when subjected to the traction force of the fleet and the impact force of waves, and convert the deformation data into corresponding stress values, including tensile stress and compressive stress. Instantaneous stress is recorded every 0.1 seconds, and the average stress value and maximum stress value within 10 seconds are dynamically calculated. When the maximum stress value reaches 90% of the latch's design load-bearing limit, the mechanical latch is marked as high-risk, indicating the need for timely inspection or maintenance. Pressure sensors are installed at the hydraulic pump outlet and hydraulic cylinder inlet. The sensor continuously collects the real-time pressure of the hydraulic oil, measured in megapascals (MPa). It calculates the pressure fluctuation amplitude every second, which is the difference between the maximum and minimum pressure values ​​monitored within that second. For example, if the normal pressure range of a hydraulic system is 10-12 MPa, and the pressure fluctuates to 9-13 MPa within a second, the pressure fluctuation value for that second is 4 MPa. A larger pressure fluctuation value indicates poorer sealing of the hydraulic system or less stable pump operation. Voltage and current sensors are installed at the power interface of the connection device, recording voltage and current values ​​at 0.5-second intervals. By comparing the rated voltage with the actual voltage, the voltage deviation rate is calculated. This involves first determining the difference between the actual measured voltage and the rated voltage, and then using the... Divide the difference by the rated voltage, and then multiply the result by 100%. The resulting percentage is the voltage deviation rate. For example, when the rated voltage of the power interface of the connecting device is 380 volts, and the actual measured voltage is 360 volts, first calculate the difference between the actual voltage and the rated voltage, i.e., 360 volts minus 380 volts, which gives a difference of -20 volts. Then divide the absolute value of this difference (20 volts) by the rated voltage of 380 volts, which gives a result of approximately 0.0526. Finally, multiply this result by 100% to calculate the voltage deviation rate as 5.3%. Next, count the number of current fluctuations, using a 1-minute period as a statistical cycle. Record any significant changes in the current value within that period, i.e., exceeding the normal stable range. The number of times the current value changes significantly is recorded. For example, if the current sensor detects more than 5 significant changes in the current value within a certain 1 minute, the number of current fluctuations within that period is recorded as more than 5. Finally, the power transmission status is classified by combining the voltage deviation rate and the current fluctuation frequency. The specific classification criteria are as follows: when the voltage deviation rate is <3% and the current fluctuation frequency within 1 minute is <2 times / minute, the power transmission status is determined to be stable; when the voltage deviation rate is between 3% and 5% and the current fluctuation frequency within 1 minute is between 2 and 5 times / minute, the power transmission status is determined to be slightly fluctuating; when the voltage deviation rate is >5% and the current fluctuation frequency within 1 minute is >5 times / minute, the power transmission status is determined to be severely fluctuating.

[0034] Environmental monitoring equipment aboard the main propulsion vessel and auxiliary function vessels comprehensively collects external navigation condition data. Specifically, a wave sensor is installed at the bottom of the bow of the main propulsion vessel, measuring the vertical height of waves every 2 seconds in meters. The average of all measurements within one minute is taken as the current wave height; for example, the average is calculated after measuring 10 wave heights consecutively. The maximum wave height detected within one minute is also recorded. Wind speed and direction sensors are installed at the top of the mast of the auxiliary function vessels, recording horizontal wind speed and direction every second. The wind speed data is categorized by rotating clockwise from due north (0 degrees) and then classifying the wind speed data accordingly. Wind speeds of less than 5 m / s are considered light winds, while wind speeds of 10-15 m / s are considered strong winds. The impact of wind direction data on convoy resistance is assessed. For example, when the convoy is sailing against the wind, the higher the wind speed, the greater the resistance, requiring adjustments to power output. The latitude and longitude data of the combined convoy's current position are obtained through a satellite navigation system. This data is then correlated with an electronic nautical chart database to extract key parameters of the current channel, including channel depth (in meters), channel width (in meters), and obstacle distribution information, such as the specific coordinates of reefs and shoals. When the extracted actual channel depth is less than 1 / 3 of the combined convoy's draft...When the speed is doubled, the channel location is marked as a channel risk point, reminding the fleet to adjust its route to avoid risks; depending on the type of cargo carried by the barge, targeted sensors are deployed in the cargo hold and surrounding area to monitor key safety indicators; for open barges carrying bulk cargo, laser rangefinders are installed inside the cargo hold to measure the stacking height of the cargo every 5 minutes and calculate the rate of change of the stacking height. For example, if the stacking height of the cargo decreases by 5% within 1 hour, it is determined that there may be cargo displacement. At the same time, vibration sensors are installed at the bottom of the cargo hold to record the vibration frequency of the cargo hold. When the vibration frequency exceeds 30% of the vibration frequency when the ship is sailing normally, it is determined that the cargo stacking is unstable and fixation measures need to be taken in time; for barges carrying containers, tension sensors are installed at the container fixing locks to monitor the fixing tension of the locks on the containers in real time, in kilonewtons. When the monitored tension value is lower than 80% of the rated tension value of the locks, it is determined that the container is loose. Each container is equipped with a temperature sensor to record the internal temperature and compare it with the ambient temperature. If the temperature difference exceeds 10°C and the internal temperature continues to rise, further investigation is needed to determine if there is any overheating of the cargo, preventing safety accidents caused by cargo overheating. For sealed cargo holds transporting dangerous goods, corresponding gas concentration sensors are installed according to the type of dangerous goods. For example, electrochemical sensors are installed for toxic gases, and catalytic combustion sensors are installed for flammable gases. The concentration of the corresponding gas in the cargo hold is detected every 10 seconds, in ppm. The detected gas concentration is compared with a preset safety threshold. For example, if the safety threshold for a certain toxic gas is 50 ppm, and the measured value reaches 60 ppm, an alarm is immediately triggered. Simultaneously, pressure sensors are installed inside the cargo hold to monitor the air pressure in kilopascals. When the air pressure fluctuation exceeds ±2 kPa / hour, combined with the temperature change data in the cargo hold, a comprehensive judgment is made to determine if there is a dangerous goods leak.

[0035] In a preferred embodiment of the present invention, step 2 includes:

[0036] Step 200: Using the clock of the central control unit as a reference, synchronize the time of sensor data at six locations: the bow connection of the main propulsion vessel, the stern connection of the main propulsion vessel, the power transmission unit of the barge, the steering control unit of the barge, the dangerous goods monitoring unit of the auxiliary function vessel, and the emergency execution unit of the auxiliary function vessel, to obtain synchronized data.

[0037] Step 201: Map the synchronized data to the ship's physical space coordinates. Specifically, the data of the bow connection of the main propulsion vessel is associated with the longitudinal region of the hull (0-15%), the data of the stern connection of the main propulsion vessel is associated with the longitudinal region of the hull (85-100%), the data of the barge power transmission unit is associated with the longitudinal region of the barge (25-35%), the data of the barge steering control unit is associated with the longitudinal region of the barge (75-85%), the data of the auxiliary function vessel dangerous goods monitoring unit is associated with the midship region (40-60%), and the data of the auxiliary function vessel emergency execution unit is associated with the bow region (5-15%).

[0038] Step 202: Output six sets of location datasets with three-dimensional spatial coordinate labels, where the coordinate labels include longitude, latitude, altitude, physical region, and timestamp information.

[0039] In this embodiment of the invention, the central control unit first establishes a unified reference clock accurate to the millisecond level. This reference clock is calibrated with the local clocks of the main propulsion vessel, barge, and auxiliary function vessel through an internal time synchronization protocol within the ship, such as the NTP protocol. After calibration, it ensures that the clock deviation of all vessels is controlled within 0.1 seconds. After clock calibration is completed, the system performs time alignment operations on sensor data from six key locations. Specifically, for sensors at the bow and stern connections of the main propulsion vessel, such as stress sensors and pressure sensors, a reference timestamp from the central control unit is added to each data point when acquiring its collected data. For example, if a stress data point is recorded at 14:30:05.123 when acquired locally on the main propulsion vessel, after calibration with the reference clock, it is uniformly marked as the reference time 14:30. 05.120; For barge power transmission units, such as power sensors, and barge steering control units, such as angle sensors, the local acquisition time is also calibrated according to the reference clock to eliminate the time difference caused by communication delays between ships. For example, if it takes 0.05 seconds for barge data to be transmitted to the central control unit, then 0.05 seconds is added to the local acquisition time of the barge to match the data timestamp with the reference clock. For auxiliary function ships, dangerous goods monitoring units, such as temperature sensors, and auxiliary function ships emergency execution units, such as response time sensors, the reference timestamp is added according to the same time calibration logic. Through the above operations, all sensor data are based on the reference time of the central control unit as a unified standard, forming a time-synchronized dataset, effectively avoiding subsequent analysis errors caused by time misalignment.

[0040] Step 201: The system first acquires the real-time physical parameters of each vessel, specifically the total hull length of the main propulsion vessel, barge, and auxiliary function vessel, pre-set according to the vessel design parameters. For example, the main propulsion vessel is 100 meters long, the barge is 80 meters long, and the auxiliary function vessel is 50 meters long. After acquiring the total hull length parameters, the system associates the time-synchronized data with specific physical areas of the vessel. That is, based on the longitudinal total length of the main propulsion vessel (100 meters), the system calculates the physical range corresponding to the 0-15% longitudinal region of the hull, which is from the bow to 15 meters. The calculation method is 100 meters multiplied by 15%. The data collected by the sensors within this region... Data such as the stress and hydraulic pressure of the connecting device are linked to this physical range; the physical range corresponding to the 85-100% longitudinal region of the hull is the stern section of the hull, from 85 meters to 100 meters, calculated as 100 meters multiplied by 85% to get 85 meters. Data such as the latching stress and power transmission stability indicators collected by sensors in this region are associated with this physical range; based on the total length of the barge being 80 meters, the physical range corresponding to the 25-35% region along the barge's length is calculated to be from 20 meters to 28 meters, calculated as 80 meters multiplied by 25% to get 20 meters, and 80 meters multiplied by 35% to get 28 meters. Data such as power distribution values ​​and power output stability collected by sensors within the designated area are mapped to this physical range. The physical range corresponding to 75-85% of the barge's length is 60 to 68 meters, calculated as 80 meters multiplied by 75% to get 60 meters, and 80 meters multiplied by 85% to get 68 meters. Data such as steering angle and rudder operating status collected by sensors within this area are also mapped to this physical range. The physical range corresponding to 40-60% of the auxiliary vessel's midship section is 20 to 30 meters, calculated as 50 meters multiplied by 40% to get 20 meters, and 50 meters multiplied by 60% to get 30 meters. The monitoring data of dangerous goods temperature, pressure, gas concentration, etc. collected by sensors in this area are bound to this physical range. The physical range corresponding to the 5-15% area of ​​the bow of the auxiliary function vessel is 2.5 meters to 7.5 meters. The calculation method is 50 meters multiplied by 5% to get 2.5 meters, and 50 meters multiplied by 15% to get 7.5 meters. The emergency response time, equipment start-up status, etc. collected by sensors in this area are associated with this physical range. Through the above data and physical area mapping operation, each piece of time-synchronized data is given a clear physical area attribute, realizing the accurate correspondence between data and location.

[0041] Step 202: The system combines the real-time positioning information of each vessel with the associated physical area attributes to add a three-dimensional spatial coordinate label to each data point. Specifically, it uses the GPS positioning systems onboard the main propulsion vessel, barge, and auxiliary vessel to acquire the longitude and latitude data of each vessel in real time. The accuracy of the longitude and latitude is controlled to six decimal places, for example, 120.123456°E and 30.654321°N. This serves as the reference coordinate for each vessel's own position. Based on the acquired longitude and latitude of each vessel, and combined with the established relative positional relationships between vessels (e.g., the barge is 100 meters behind the main propulsion vessel, and the auxiliary vessel is 50 meters to the left of the dangerous goods barge), the spatial coordinates are used to determine the vessel's position. The real-time longitude and latitude of the six key areas were calculated. Specifically, each vessel's own longitude and latitude were first set as the reference point coordinates. For example, the longitude and latitude of the main propulsion vessel were used as the reference point for its associated key area, and the longitude and latitude of the barge were used as the reference point for its associated key area. Then, the azimuth was determined based on the direction parameters in the relative positions of the vessels. For example, the barge's azimuth relative to the rear of the main propulsion vessel was 180°, meaning it was centered south in the north-south direction; the auxiliary vessel's azimuth relative to the left of the dangerous goods barge was 270°, meaning it was centered west in the east-west direction. The specified relative distance parameter refers to the relative distance between each vessel and the reference vessel, such as the relative distance between the barge and the main propulsion vessel. The distance is 100 meters, and the relative distance between the auxiliary function vessel and the dangerous goods barge is 50 meters. This relative distance is then decomposed into north-south and east-west distance components according to a defined azimuth. The north-south distance component is used to calculate the latitude difference; the actual distance corresponding to 1 degree of latitude is approximately 111,319 meters. Therefore, the latitude difference equals the north-south distance component divided by 111,319 meters. The east-west distance component needs to be combined with the latitude of the reference point to calculate the longitude difference. That is, the actual distance corresponding to 1 degree of longitude at a certain latitude varies with the latitude, approximately 111,319 meters multiplied by the cosine of that latitude. Therefore, the longitude difference equals the east-west distance component divided by (111,319 meters multiplied by the cosine of the reference point's latitude). (Sine value). If the critical area is located north of the reference point, the north-south distance component is positive, and the latitude difference is positive, which is added to the latitude of the reference point. If it is located south of the reference point, the north-south distance component is negative, and the latitude difference is negative, in which case the absolute value needs to be subtracted from the latitude of the reference point (i.e., subtraction). If the critical area is located east of the reference point, the east-west distance component is positive, and the longitude difference is positive, which is added to the longitude of the reference point. If it is located west of the reference point, the east-west distance component is negative, and the longitude difference is negative, in which case the absolute value needs to be subtracted from the longitude of the reference point (i.e., subtraction). Through this calculation, the real-time longitude and latitude corresponding to each critical area of ​​the ship are obtained, ensuring that the spatial coordinates of the six critical areas can accurately reflect their actual positions.

[0042] Using sea level as the reference height, the initial elevation of six key areas is determined by combining the hull design parameters of each vessel. For example, the bow connection of the main propulsion vessel is 5 meters above sea level, and the power transmission unit of the barge is 3 meters above sea level. At the same time, the hull draft is monitored in real time by pressure sensors. The initial elevation is corrected based on the monitored draft data. For example, if the hull sinks by 0.5 meters due to draft, the initial elevation of that area is subtracted by 0.5 meters to obtain the corrected actual elevation. The system integrates all data from each key region according to a fixed format of longitude, latitude, altitude, physical region, and timestamp, ultimately generating six independent location datasets. Taking the dataset of the bow connection of the main propulsion ship as an example, it contains complete information such as longitude 120.123456°E, latitude 30.654321°N, altitude 5 meters, longitudinal 0-15% region of the hull, 14:30:05.120, and stress value XXX. The datasets of the other five key regions are also integrated in the same format to ensure that each dataset is complete and structurally consistent.

[0043] By using a unified reference clock to eliminate time discrepancies among various ship sensors, analysis errors caused by misaligned data acquisition times are avoided. Data is directly associated with key physical areas of the ship, such as connections and power units, clarifying the specific locations corresponding to the data and resolving the problem of ambiguity between data and risk point locations, enabling risk analysis to focus on specific areas.

[0044] In a preferred embodiment of the present invention, step 3 includes:

[0045] Step 300: Based on six sets of location datasets with three-dimensional spatial coordinate labels, perform regional feature analysis to generate three types of risk coefficients. The generation process of the three types of risk coefficients is as follows:

[0046] Step 301: Extract the location datasets of the 0-15% and 85-100% longitudinal regions of the hull. Combine the wave height and wind speed parameters in the navigation environment data, and calculate the structural connection failure risk coefficient by weighted superposition of the real-time stress value of the mechanical latch and the wave height and wind speed parameters.

[0047] Step 302: Extract the location datasets of the 25-35% and 75-85% areas of the barge. Calculate the deviation between the actual power distribution values ​​recorded by the power transmission unit and the planned power values. Overlay the maximum error value between the real-time steering angle and the commanded angle recorded by the steering control unit. Generate a coordinated operation runaway risk coefficient according to a preset ratio, specifically including:

[0048] Based on the location dataset of the 25-35% area of ​​the barge, the dynamic deviation between the actual power value allocated by the power transmission unit and the planned power value issued by the central control unit is calculated; based on the location dataset of the 75-85% area of ​​the barge, the maximum error value between the real-time steering angle of the steering control unit and the command angle of the central control unit during the coordinated operation is extracted.

[0049] Using dynamic deviation as the first input factor and maximum error as the second input factor, a weighted calculation is performed using a preset first weighting coefficient and a second weighting coefficient to generate a collaborative operation loss of control risk coefficient representing the risk of loss of control of fleet power and steering coordination.

[0050] Step 303: Extract temperature and pressure monitoring data of dangerous goods from 40-60% of the midship area and emergency response time records from 5-15% of the bow area. When the temperature and pressure data exceed a preset safety threshold, generate a special transportation safety risk coefficient based on the correlation between the threshold exceedance and the emergency response time. Specifically, this includes:

[0051] Threshold judgment is performed on the temperature and pressure monitoring data of the midship section 40-60% area. When any parameter continuously exceeds the preset safety threshold, the exceedance value and duration are recorded. Emergency response time records are extracted from the location data of the bow section 5-15% area. The emergency response time is the measured time delay from the triggering of the warning to the initiation of emergency operation by the auxiliary function ship.

[0052] Based on the product relationship between the exceedance magnitude, exceedance duration, and emergency response time, a special transport safety risk coefficient representing the risk of uncontrolled transport of dangerous goods is generated.

[0053] In this embodiment of the invention, the system filters out regional data directly related to three types of risks from six sets of location datasets labeled with three-dimensional spatial coordinates. Specifically, data from the 0-15% longitudinal region of the main propulsion vessel hull (bow connection) and the 85-100% region (stern connection) are used to calculate the risk of structural connection failure. Data from the 25-35% region of the barge (power transmission unit) and the 75-85% region (steering control unit) are used to calculate the risk of loss of control during coordinated operation. Data from the 40-60% region of the auxiliary function vessel (dangerous goods monitoring unit) and the 5-15% region (emergency execution unit) are used to calculate the safety risks of special transportation. After filtering, feature analysis is performed on each set of regional data according to a preset logic, ultimately generating three types of risk coefficients. The specific calculation process unfolds in three steps:

[0054] Step 301: First, extract real-time stress values ​​of the mechanical latches from the dataset of the 0-15% longitudinal region of the main propulsion vessel hull, i.e., the location of the bow connection. This data is recorded every 0.5 seconds and includes parameters such as the tension and pressure borne by the latches. Simultaneously, extract real-time stress values ​​of the same type of mechanical latches from the dataset of the 85-100% region, i.e., the location of the stern connection. In addition, extract the current real-time wave height (e.g., average wave height 1.5 meters) and wind speed (e.g., average wind speed 10 meters per second) from the navigation environment data. Based on historical navigation data and ship design standards, assign different weights to wave height and wind speed. Wave height has a greater direct impact on the hull connection, so its weight is set to 60%. Wind speed indirectly increases the load on the connection by affecting hull rolling, so its weight is set to 40%. First, calculate the environmental impact value by multiplying the wave height by its corresponding weight and then adding the wind speed multiplied by its corresponding weight. The higher the environmental impact value, the higher the weight. The greater the load on the connection from the environment, the higher the structural stress base value is calculated. The mechanical locking stress values ​​of the bow and stern connections are averaged. Taking a bow stress of 200 MPa and a stern stress of 180 MPa as an example, the two stress values ​​are first added together to obtain 380 MPa, then divided by 2 to obtain an average of 190 MPa. This average is the structural stress base value. Finally, the comprehensive value is calculated. Since the structural stress itself is the core risk source, the environmental impact value and the structural stress base value are superimposed at a ratio of 1:9. That is, the environmental impact value is multiplied by 1, and then the structural stress base value is multiplied by 9. The result is the comprehensive value. The higher the comprehensive value, the greater the possibility of structural connection failure. Based on this, a structural connection failure risk coefficient is generated. If the comprehensive value is in the range of 0 to 500, it corresponds to low risk; if it is in the range of 501 to 1000, it corresponds to medium risk; and if it is above 1000, it corresponds to high risk.

[0055] Step 302, the calculation of the risk coefficient for loss of control in collaborative operation is divided into three parts: dynamic deviation calculation, maximum steering angle error calculation, and weighted calculation of the risk coefficient. From the 25-35% region of the barge, i.e., the location data of the power transmission unit, the actual power distribution value is extracted. For example, the actual power transmitted to the barge at a certain moment is 800kW. Simultaneously, the planned power value at the same moment is retrieved from the central control unit. For example, the preset planned power value is 1000kW. The dynamic deviation is calculated by first calculating the difference between the planned power value and the actual power value, then dividing this difference by the planned power value, and finally multiplying the result by 100%. From the 75-85% region of the barge, i.e., the location data of the steering control unit, the real-time steering angles within 5 consecutive minutes are extracted. For example, when the command requires a 30-degree turn, the actual steering angles are 28 degrees, 29 degrees, and 27 degrees respectively. These real-time steering angles are then compared with the commanded steering angle issued by the central control unit, such as 30 degrees. The difference between each real-time angle and the commanded angle is calculated, and the largest value among these differences is the maximum steering angle error. Taking the comparison of real-time angles of 27 degrees, 28 degrees, and 29 degrees with the commanded angle of 30 degrees as an example, the differences are 3 degrees, 2 degrees, and 1 degree respectively, with the maximum difference being 3 degrees, meaning the maximum steering angle error is 3 degrees. A first weighting coefficient is preset, corresponding to a power deviation of 60%, because power distribution is the core of coordinated operation. A second weighting coefficient is preset, corresponding to a steering angle error of 40%, because steering accuracy affects the overall course of the fleet. In the calculation, the dynamic deviation is first multiplied by the first weighting coefficient; for example, with a dynamic deviation of 20%, 20% is multiplied by 60. The percentage is 12%. Next, the maximum steering angle error is processed. Assuming that each degree of angle error corresponds to a 1% risk percentage, the maximum steering angle error is first multiplied by 1% to get the risk percentage corresponding to the angle error. Then, this percentage is multiplied by the second weighting coefficient. Taking a maximum steering angle error of 3 degrees as an example, 3 degrees multiplied by 1% gives a risk percentage of 3%, which is then multiplied by 40% to get 1.2%. Finally, the two calculated results are added together. 12% plus 1.2% gives 13.2%. This value is the risk coefficient of loss of control in coordinated operation. The higher the value, the higher the risk.

[0056] Step 303, the calculation of the special transport safety risk coefficient is divided into four parts: threshold judgment and parameter recording, recording the duration of exceedance, extracting the emergency response time, and calculating the coefficient based on the product relationship. From the 40-60% area amidships of the auxiliary function vessel, i.e., the location data of the dangerous goods monitoring unit, the real-time temperature and pressure of the dangerous goods are extracted. For example, the preset safe temperature threshold for a certain chemical is 30℃, the measured temperature is 35℃, the preset safe pressure threshold is 0.5MPa, and the measured pressure is 0.6MPa. When either the temperature or pressure parameter continuously exceeds the preset safe threshold... When the temperature remains at 35℃ for 5 consecutive minutes, calculate and record the exceedance value. The exceedance value is calculated by subtracting the preset safety threshold from the measured value. The temperature exceedance is 35℃ minus 30℃, resulting in 5℃. The pressure exceedance is 0.6MPa minus 0.5MPa, resulting in 0.1MPa. The larger of the two values ​​is taken as the primary parameter. The cumulative duration of this period is recorded from the moment the temperature (or pressure) exceeds the preset safety threshold for the first time until the current moment. For example, from the moment the temperature is first detected to 35℃ until... Currently, the cumulative duration is 5 minutes. Emergency response time is extracted from the location data of the emergency execution unit in the 5-15% area of ​​the bow of the auxiliary function vessel. This time is the measured delay from the moment the temperature (or pressure) exceeds the threshold triggering the warning signal (e.g., when the temperature reaches 35℃, the system automatically alarms) to the moment the emergency execution unit of the auxiliary function vessel initiates the corresponding emergency operation, such as activating the cooling device. For example, the measured delay from the alarm to the activation of the cooling device is 10 seconds. The exceedance amplitude value, exceedance duration, and emergency response time are standardized in units, i.e., the exceedance amplitude value, such as... The 5℃ value remains unchanged; the duration exceeding the limit needs to be converted to seconds. For example, 5 minutes equals 60 seconds, so 5 minutes multiplied by 60 seconds equals 300 seconds; the emergency response time, such as 10 seconds, remains unchanged. The standardized values ​​of the three are multiplied together, i.e., 5℃ multiplied by 300 seconds, then multiplied by 10 seconds, to obtain the product. The higher the product value, the higher the risk. For example, a product value in the range of 10,000-20,000 corresponds to medium risk; a product value above 20,000 corresponds to high risk. Based on this, a special transportation safety risk coefficient is generated.

[0057] By selectively extracting data from key areas and combining it with details such as environmental parameters and operational deviations, risks are quantified into specific coefficients, avoiding ambiguity in assessments and enabling intuitive judgment of risk points such as structural connections, collaborative operations, and special transportation. The three types of risk coefficients correspond to the most critical safety hazards of the combined fleet, namely connection failure, operational loss of control, and dangerous goods accidents, covering high-risk scenarios in the transportation process. The calculation logic of the risk coefficients is strongly correlated with actual navigation conditions, such as wave height and turning errors, and cargo status, such as temperature exceeding thresholds, improving the timeliness and effectiveness of fleet safety management.

[0058] In a preferred embodiment of the present invention, step 4 includes:

[0059] Based on the range of structural connection failure risk coefficient values, generate bow connection reinforcement instructions and stern connection reinforcement instructions; decompose the risk coefficient of uncontrolled collaborative operation into power compensation parameters and steering compensation parameters, and generate power distribution optimization instructions and rudder angle correction instructions; based on the special transportation safety risk coefficient level, match the preset emergency resource scheduling plan to generate resource allocation instructions;

[0060] By combining connection reinforcement commands, power distribution optimization commands, rudder angle correction commands, and resource allocation commands, a dynamic risk warning command set for the entire flight segment is output.

[0061] In this embodiment of the invention, the system presets three value ranges for the structural connection failure risk coefficient: low risk (0-30), medium risk (31-60), and high risk (61-100). Each range is matched with a corresponding reinforcement strategy. If the coefficient is in the low risk range, such as 25, a mild reinforcement command is generated, instructing the hydraulic system of the main propulsion ship's bow and stern connection device to slightly increase the pressure by 10% of the original pressure (i.e., multiplying the original pressure by 1.1). This enhances connection stability through slight tightening of the mechanical latches. Simultaneously, the crew is prompted to check the connection status every 30 minutes. If the coefficient is in the medium risk range, such as 45, a moderate reinforcement command is generated, increasing the hydraulic system pressure by 30% of the original pressure (i.e., multiplying the original pressure by 1.3). The mechanical latches switch to a high-strength engagement mode, and the vibration monitoring sensor at the connection point is activated to provide real-time feedback on the reinforcement effect. The crew must immediately report to their posts and prepare emergency reinforcement tools. If the coefficient is in the high risk range, such as 70, an emergency reinforcement command is generated, increasing the hydraulic system pressure to the maximum safe value, i.e., 90% of the design pressure. The design pressure is multiplied by 0.9, and the mechanical lock is fully locked. Simultaneously, auxiliary vessels are moved closer to the connection point, and additional temporary support devices are used to strengthen the structure. The crew activates the emergency plan for connection failure, suspending non-essential navigation operations. The system decomposes the risk coefficient of uncontrolled collaborative operation into power compensation parameters and steering compensation parameters according to a preset ratio, with power-related parameters accounting for 60% and steering-related parameters accounting for 40%. That is, the power compensation parameter equals the risk coefficient of uncontrolled collaborative operation multiplied by 60%, and the steering compensation parameter equals the risk coefficient of uncontrolled collaborative operation multiplied by 40%. Based on the positive or negative value of the power compensation parameter, where a positive value indicates insufficient power and a negative value indicates excess power, the power output of the main propulsion vessel to each barge is adjusted. For example, if the parameter is +15%, it means an additional 15% power compensation is needed, and the main propulsion vessel is instructed to increase the power output to the power transmission unit by 15%, that is, multiply the original power output by 1.15, prioritizing barges in the upwind or downcurrent direction. If the parameter is -10%, it means a 10% power excess, and the power output is reduced by 10%, that is, multiply the original power output by 0.9. To avoid wasted power or overloading of the hull; based on the value of the steering compensation parameter, in degrees, the rudder angle of the barge steering control unit is corrected. For example, if the parameter is +3°, it means the actual steering angle is 3° smaller than the command, and the steering control unit will increase the rudder angle by 3°, i.e., add 3° to the original rudder angle, to ensure the convoy turns along the preset route; if the parameter is -2°, it means the actual steering angle is 2° larger than the command, then the rudder angle will be decreased by 2°, i.e., subtract 2° from the original rudder angle, to avoid convoy deviation caused by over-steering. The system classifies the special transport safety risk coefficient into three levels: Level 1 is low risk, Level 2 is medium risk, and Level 3 is medium risk. Risk is categorized into three levels, with each level corresponding to a pre-set emergency resource allocation plan. For example, if the risk level is 1 (Level 1), the basic resource allocation plan is used, instructing the emergency execution unit of the auxiliary vessel to prepare standard fire-fighting equipment such as fire extinguishers, fire hoses, and protective gear such as gas masks, and ensuring unobstructed emergency access routes, without requiring additional external resource mobilization. If the risk level is 2 (Level 2), the enhanced resource allocation plan is used, instructing the emergency execution unit to activate specialized dangerous goods handling equipment, such as explosion-proof pumps and neutralizing agent storage tanks, in addition to basic equipment; simultaneously, the emergency response of nearby ports is notified. The rescue team is on standby, ready to arrive within one hour to provide support; the ventilation system of the dangerous goods barge is switched to strong exhaust mode to reduce the risk of gas concentration; if the coefficient is level three, such as risk level 3, an emergency resource allocation plan is matched, and all available emergency resources are immediately mobilized, including all emergency equipment of the auxiliary function vessel, such as high-pressure water cannons, gas detection drones, fireboats and medical ships in nearby ports; the emergency execution unit is instructed to activate the isolation rescue mode, such as closing the direct passage between the dangerous goods barge and other vessels; at the same time, a distress signal is sent to the nearby maritime administration department, requesting temporary route control to make room for emergency handling. The system sorts the above-generated connection reinforcement instructions, power distribution optimization instructions, rudder angle correction instructions, and resource allocation instructions according to their urgency, such as emergency reinforcement instructions taking priority over power optimization instructions, and resource allocation instructions directly related to safety taking priority. A timestamp is added to each instruction, such as execution in the second hour of the voyage, completion before entering the XX sea area, and the executing entity, such as the crew of the main propulsion vessel and the emergency team of the auxiliary function vessel. Finally, a structured dynamic risk warning instruction set for the entire voyage is formed, which is distributed to the operating terminals of each vessel through the central control system to ensure that the instructions can be directly executed. .

[0062] Command generation is directly linked to the specific values ​​and levels of risk coefficients. Different levels of risk correspond to different intensities of response measures, such as mild / emergency reinforcement, avoiding over-operation or inadequate response and improving risk handling efficiency. Abstract risk coefficients are transformed into specific operational parameters, such as hydraulic pressure increase ratios, rudder angle correction degrees, and clear execution steps, such as mobilizing emergency equipment and notifying crew members to report for duty. Crew members can operate directly without secondary interpretation, shortening emergency response time. By matching risk levels with preset plans, the blind mobilization of emergency resources is avoided. For example, high-priced equipment is not wasted in low-risk situations, while resources are concentrated for rapid response in high-risk situations, optimizing resource utilization efficiency and reducing emergency costs.

[0063] like Figure 2 As shown, embodiments of the present invention also provide a combined fleet safety risk assessment system based on data processing, comprising:

[0064] The data acquisition module is used to collect four types of data through sensors on the main propulsion vessel, barge, and auxiliary function vessel: vessel status data, connection device operating status data, navigation environment data, and cargo safety parameters.

[0065] The conversion module is used to transmit four types of data through the data interaction channel of the inter-ship connection device, and after spatiotemporal alignment, discretize them into spatial distribution data of key areas of the ship, generating six sets of location datasets with three-dimensional spatial coordinate labels.

[0066] The calculation module is used to perform regional feature analysis based on six sets of location datasets with three-dimensional spatial coordinate labels, and generate structural connection failure risk coefficients, collaborative operation runaway risk coefficients, and special transportation safety risk coefficients through preset calculation logic.

[0067] The instruction generation module is used to integrate the three types of risk coefficients with the voyage planning data and sea state prediction data to generate dynamic risk assessment results for the entire voyage and output a risk warning instruction set that includes regional compensation parameters.

[0068] It should be noted that this system is a system corresponding to the above method. All implementation methods in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0069] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0070] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0071] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for assessing the safety risks of a combined fleet based on data processing, characterized in that, The method includes: Step 1: Collect four types of data through sensors on the main propulsion vessel, barge, and auxiliary function vessel, including vessel status data, connection device operating status data, navigation environment data, and cargo safety parameters. Step 2: The four types of data are transmitted through the data exchange channel of the inter-ship connection device. After spatiotemporal alignment, the data is discretized into spatial distribution data of key ship areas, generating six sets of location datasets with three-dimensional spatial coordinate labels. These datasets include: time synchronization of sensor data at six locations—the bow connection of the main propulsion vessel, the stern connection of the main propulsion vessel, the barge power transmission unit, the barge steering control unit, the dangerous goods monitoring unit of the auxiliary function vessel, and the emergency execution unit of the auxiliary function vessel—based on the clock of the central control unit, resulting in synchronized data. The synchronized data is then mapped to the ship's physical space coordinates. The main propulsion vessel bow connection... The data is associated with the following regions: 0-15% longitudinal region for the main propulsion vessel; 85-100% longitudinal region for the stern connection of the main propulsion vessel; 25-35% longitudinal region for the barge's power transmission unit; 75-85% longitudinal region for the barge's steering control unit; 40-60% midship region for the auxiliary function vessel's dangerous goods monitoring unit; and 5-15% bow region for the auxiliary function vessel's emergency execution unit. Six sets of location datasets with three-dimensional spatial coordinate labels are output, including longitude, latitude, altitude, physical region, and timestamp information. Step 3: Based on six sets of location datasets with three-dimensional spatial coordinate labels, perform regional feature analysis to generate three types of risk coefficients. The generation process of the three types of risk coefficients is as follows: Extract location datasets from the 0-15% and 85-100% longitudinal regions of the hull. Combine the wave height and wind speed parameters in the navigation environment data. Calculate the structural connection failure risk coefficient by weighted superposition of the real-time stress value of the mechanical latch and the wave height and wind speed parameters. Extract location datasets from the 25-35% and 75-85% regions of the barge. Calculate the deviation between the actual power distribution value recorded by the power transmission unit and the planned power value. Superimpose the maximum error value between the real-time steering angle and the command angle recorded by the steering control unit. Generate a coordinated operation loss of control risk coefficient according to a preset ratio. Extract dangerous goods temperature and pressure monitoring data from the 40-60% midship region and emergency response time records from the 5-15% bow region. When the temperature and pressure data exceed a preset safety threshold, generate a special transportation safety risk coefficient based on the correspondence between the threshold exceedance and the emergency response time. Step 4: Integrate the three types of risk coefficients with the voyage planning data and sea state prediction data to generate a dynamic risk assessment result for the entire voyage and output a risk warning instruction set that includes regional compensation parameters.

2. The data processing-based combined fleet safety risk assessment method according to claim 1, characterized in that, The operating data of the connection device includes mechanical locking stress value, hydraulic circuit pressure fluctuation value, and power transmission stability index.

3. The data processing-based combined fleet safety risk assessment method according to claim 2, characterized in that, The location datasets of the 25-35% and 75-85% areas of the barge are extracted. The deviation between the actual power distribution values ​​recorded by the power transmission unit and the planned power values ​​is calculated. The maximum error value between the real-time steering angle and the commanded angle recorded by the steering control unit is then overlaid. A coordinated operation loss-of-control risk coefficient is generated according to a preset ratio, including: Based on the location dataset of the 25-35% area of ​​the barge, the dynamic deviation between the actual power value allocated by the power transmission unit and the planned power value issued by the central control unit is calculated; based on the location dataset of the 75-85% area of ​​the barge, the maximum error value between the real-time steering angle of the steering control unit and the command angle of the central control unit during the coordinated operation is extracted. Using dynamic deviation as the first input factor and maximum error as the second input factor, a weighted calculation is performed using a preset first weighting coefficient and a second weighting coefficient to generate a collaborative operation loss of control risk coefficient representing the risk of loss of control of fleet power and steering coordination.

4. The data processing-based combined fleet safety risk assessment method according to claim 3, characterized in that, Extract temperature and pressure monitoring data of dangerous goods from 40-60% of the midship area and emergency response time records from 5-15% of the bow area. When the temperature and pressure data exceed a preset safety threshold, generate a special transportation safety risk coefficient based on the correlation between the magnitude of the threshold exceedance and the emergency response time, including: Threshold judgment is performed on the temperature and pressure monitoring data of the midship section 40-60% area. When any parameter continuously exceeds the preset safety threshold, the exceedance value and duration are recorded. Emergency response time records are extracted from the location data of the bow section 5-15% area. The emergency response time is the measured time delay from the triggering of the warning to the initiation of emergency operation by the auxiliary function ship. Based on the product relationship between the exceedance magnitude, exceedance duration, and emergency response time, a special transport safety risk coefficient representing the risk of uncontrolled transport of dangerous goods is generated.

5. The data processing-based combined fleet safety risk assessment method according to claim 4, characterized in that, Step 4 includes: Based on the range of structural connection failure risk coefficient values, generate bow connection reinforcement instructions and stern connection reinforcement instructions; decompose the risk coefficient of uncontrolled collaborative operation into power compensation parameters and steering compensation parameters, and generate power distribution optimization instructions and rudder angle correction instructions; generate resource allocation instructions based on the special transportation safety risk coefficient level and match the preset emergency resource scheduling plan. By combining connection reinforcement commands, power distribution optimization commands, rudder angle correction commands, and resource allocation commands, a dynamic risk warning command set for the entire flight segment is output.

6. A data processing-based combined fleet safety risk assessment system, wherein the system implements the method as described in any one of claims 1 to 5, characterized in that, include: The data acquisition module is used to collect four types of data through sensors on the main propulsion vessel, barge, and auxiliary function vessel: vessel status data, connection device operating status data, navigation environment data, and cargo safety parameters. The conversion module is used to transmit four types of data through the data interaction channel of the inter-ship connection device, and after spatiotemporal alignment, discretize them into spatial distribution data of key areas of the ship, generating six sets of location datasets with three-dimensional spatial coordinate labels. The calculation module is used to perform regional feature analysis based on six sets of location datasets with three-dimensional spatial coordinate labels, and generate structural connection failure risk coefficients, collaborative operation runaway risk coefficients, and special transportation safety risk coefficients through preset calculation logic. The instruction generation module is used to integrate the three types of risk coefficients with the voyage planning data and sea state prediction data to generate dynamic risk assessment results for the entire voyage and output a risk warning instruction set that includes regional compensation parameters.

7. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 5.

Images