A port operation status perception and monitoring system based on a data middle platform

Abstract

This invention relates to the field of port operation status perception and monitoring technology, specifically disclosing a port operation status perception and monitoring system based on a data platform. It uses a micro-weather station array to monitor wind speed and visibility values ​​at various current times, simultaneously acquiring tidal phase data from an astronomical observatory, and comprehensively generating multi-dimensional meteorological data for a set time period. Combined with the target vessel's tonnage, it dynamically calculates the target vessel's berthing safety factor through multi-dimensional constraints. Based on the target vessel's berthing safety factor, it generates a dynamic berthing strategy for the target vessel. Through the integrated application of multi-dimensional meteorological data acquisition, berthing safety factor calculation, dynamic berthing strategy generation, and feedback terminals, port managers can achieve real-time monitoring and optimization of the vessel berthing process. This not only improves the safety and efficiency of port operations but also provides vessels with more scientific and flexible berthing solutions, ensuring the sustainability and economic benefits of port operations.

Description

Technical Field

[0001] This invention belongs to the field of port operation status perception and monitoring technology, and relates to a port operation status perception and monitoring system based on a data platform. Background Technology

[0002] With the continuous development of global trade, ports, as vital logistics hubs, directly impact the operational efficiency and safety of ships through the scientific management of their berthing. Effective ship berthing analysis helps port managers assess the impact of weather conditions, tidal changes, and other environmental factors on ship berthing in real time, thereby developing reasonable berthing plans, reducing ship dwell time in port, and lowering fuel consumption and operating costs. Furthermore, accurate berthing analysis can effectively reduce the risk of accidents caused by weather changes or tidal fluctuations, ensuring the safety of ships, port facilities, and personnel. Therefore, ship berthing analysis is not only key to improving port management efficiency but also an important measure to ensure shipping safety.

[0003] However, current technologies for ship berthing analysis based on meteorological conditions and tidal data still have some significant shortcomings and drawbacks. First, existing berthing analysis systems often rely on static or historical meteorological and tidal data, making it difficult for the analysis results to accurately reflect real-time environmental changes. Meteorological conditions and tidal states are dynamic, especially under severe weather conditions or large tidal fluctuations. Static data can lead to errors in ship berthing decisions, increasing berthing risks. For example, if a ship fails to obtain the latest wind speed, wave height, and tide level information in a timely manner when approaching a port, it may deviate from its berthing position, potentially leading to accidents.

[0004] Furthermore, current berthing analysis technologies typically lack intelligent decision support capabilities and cannot respond to emergencies in real time. For example, when weather conditions change suddenly or tidal fluctuations exceed expectations, existing systems often cannot quickly adjust berthing strategies, leading to prolonged vessel dwell times in port and consequently impacting the overall port's operational efficiency. An intelligent berthing management system should possess real-time monitoring, data analysis, and automated decision-making capabilities to respond rapidly to emergencies. Summary of the Invention

[0005] In view of the problems existing in the prior art, the present invention provides a port operation status perception and monitoring system based on a data middle platform to solve the above-mentioned technical problems.

[0006] To achieve the above and other objectives, the technical solution adopted by the present invention is as follows:

[0007] This invention provides a port operation status perception and monitoring system based on a data middle platform, the system comprising:

[0008] Multi-dimensional meteorological data acquisition module: Real-time monitoring of wind speed and visibility values ​​at each current time point through a micro weather station array, synchronous acquisition of tidal phase data from the observatory, and comprehensive generation of multi-dimensional meteorological data for a set time period;

[0009] Berthing safety factor calculation module: Combines the target vessel's deadweight tonnage with multi-dimensional constraints to dynamically calculate the target vessel's berthing safety factor;

[0010] Vessel berthing strategy generation module: Generates a dynamic vessel berthing strategy for the target vessel based on the target vessel's berthing safety factor;

[0011] Vessel berthing strategy feedback terminal: Feeds back the dynamic berthing strategy of the target vessel to the port data platform, triggering the coordinated execution of the port machinery equipment scheduling system and the waterway traffic control system.

[0012] For example, the logic for generating multidimensional meteorological data is as follows:

[0013] A ship arrival time prediction model is established by inputting the target ship's speed and route coordinates into the model, and the estimated arrival time of the target ship is derived and recorded as the target's starting time. Extract the estimated berthing time of the target vessel from the berthing instructions issued by the target vessel to the port; add the estimated berthing time to the target start time to obtain the target end time. This constitutes a set time period. τ is the set time margin value;

[0014] The system acquires the wind speed and visibility values ​​of the lower atmosphere at each current time point monitored by the port's micro weather station in real time, and generates a raw meteorological dataset with timestamps. The system then performs trend fitting on the raw meteorological dataset to obtain the wind speed gradient change curve and visibility attenuation rate distribution curve of the lower atmosphere within a set time period, thereby extracting the visibility and corresponding wind speed of the lower atmosphere at each expected time point within the set time period.

[0015] Synchronously access the tidal phase data of the observatory and extract the tide height and swell cycle parameters at each expected time point within a set time period;

[0016] The visibility, tide height, swell cycle parameters, and corresponding wind speed in the lower atmosphere at each predicted time point within a set time period are spatiotemporally aligned to generate multidimensional meteorological data for the set time period.

[0017] For example, the visibility and corresponding low-level wind speed at each predicted time point within a set time period are extracted, including:

[0018] Real-time wind speed data in the lower atmosphere of the port's micro weather station is collected, and visibility data at the corresponding timestamp is obtained simultaneously to form a raw meteorological dataset. The raw meteorological dataset is then aligned to the time axis and abrupt noise points are removed.

[0019] Based on the sliding time window method, a 10-minute time window is set, and the calculation is performed in 5-minute time window units. Within each window, the low-altitude wind speed data is divided into N data units per second, and the wind speed change amplitude per minute is calculated. Specifically, the change is calculated by subtracting the wind speed value at the 0th second from the wind speed value at the 60th second of each minute. The absolute value is then used to calculate the average of the changes over the 10-minute segments within the window, which is used as the initial gradient slope for that window. For the complete window, the absolute value of the gradient slope is calculated, and the direction of change is determined by comparing the wind speed at the start and end points of the window. An increase in wind speed is considered a positive value, and a decrease in wind speed is considered a negative value. When identifying continuous trend segments, the gradient direction of three consecutive windows must be consistent, either positive or negative, and the difference in the absolute value of the slope between adjacent windows must not exceed a set threshold. For trend segments that meet the conditions, a cubic spline interpolation algorithm is used for curve smoothing, i.e., smooth transition nodes are inserted between the slope values ​​of adjacent windows to generate the wind speed gradient change curve of the low-altitude layer within the set time period.

[0020] The visibility change is calculated second by second, which is the difference between the current second value and the previous second value; when the difference is negative, it is marked as a decay event; the number of decay events is counted within a 10-minute window, and when the decay event count accounts for more than 70%, it is judged as a high decay window; three consecutive high decay windows are merged to form a decay risk segment, and the weighted average of the correction factors of each window is calculated during merging, with the weight coefficients set to 0.2, 0.3, and 0.5 in chronological order; a quadratic polynomial fitting algorithm is used to generate a baseline curve for the risk segment data, and the first and last parts are extended by 5 minutes to form a visibility decay rate distribution curve;

[0021] The wind speed gradient curve and visibility attenuation rate distribution curve in the lower atmosphere within the set time period are plotted with the time point as the horizontal axis and the corresponding value as the vertical axis. Then, based on the horizontal axis, the visibility and the corresponding wind speed in the lower atmosphere at each expected time point within the set time period are extracted sequentially.

[0022] For example, the operation logic of the berthing safety factor calculation module is as follows:

[0023] S21: The wind speed values ​​at each predicted time point in the multidimensional meteorological data are smoothed by a moving window, and the dynamic influence weighting factor of wind speed at each predicted time point is calculated based on the ratio of wind speed to the safety threshold of ship tonnage.

[0024] S22: Map the tide height data at each expected time point to the port terminal reference elevation coordinate system, classify the tide level hazard level according to the characteristics of the rising and falling tide periods, and output a set of tide height hazard coefficients with time correlation.

[0025] S23: Frequency domain matching analysis is performed using the swell cycle values ​​at each expected time point and the ship's rolling cycle. The swell resonance risk index of the target ship is generated through the cycle overlap discrimination rule. Simultaneously, piecewise linear interpolation is performed on the visibility values ​​to convert them into visibility coefficients at each expected time point.

[0026] S24: Construct a constraint scoring matrix and perform polarity normalization on the wind speed dynamic influence weight factor, tide height hazard coefficient, surge resonance risk index, and visibility coefficient at each expected time point. The polarity normalization process includes taking the original value for positive parameters and taking (1-original value) for negative parameters.

[0027] S25: Set a time dimension decay function, the calculation formula is: weight of each expected time point = exp(-α×|each expected time point-target end time point|), where α is the dock geological stability coefficient, and the constraint scoring matrix is ​​weighted and summed in the time domain through the decay function;

[0028] S26: Perform range compression processing on the time-domain weighted summation result to map the maximum value range of multidimensional meteorological parameters to the [0,1] interval, and generate the target ship berthing safety factor.

[0029] For example, S21 includes:

[0030] S211: Set the time window width parameter, use the moving average algorithm to denoise the wind speed values ​​at each expected time point, and output a smooth wind speed sequence;

[0031] S212: Based on the target vessel's deadweight tonnage, retrieve the baseline safe wind speed value corresponding to the current vessel's deadweight tonnage from the pre-stored safe wind speed threshold table;

[0032] S213: Calculate the deviation between each wind speed value in the smoothed wind speed sequence and the baseline safe wind speed value at each expected time point. The calculation formula is: Deviation = Wind speed value in the smoothed wind speed sequence / Baseline safe wind speed value - 1.

[0033] S214: Construct a piecewise weight transformation function, where the weight factor = 0 when the deviation is ≤ 0, the weight factor = deviation × 1.5 when 0 < deviation ≤ 0.3, and the weight factor = 0.45 + (deviation - 0.3) × 2 when the deviation is > 0.3;

[0034] S215: Input the deviation of each expected time point into the piecewise weight conversion function, and output the dynamic influence weight factor of wind speed at each expected time point.

[0035] For example, S22 includes:

[0036] S221: Obtain the reference elevation zero point defined in the geological survey report of the port terminal, and establish a dataset of the relative elevation difference between the tide level and the terminal operation platform at each expected time point;

[0037] S222: Analyze the time interval markers of high tide and low tide in the observatory's tide table to generate a set of tidal phase feature timestamps;

[0038] S223: When it is high tide and the relative elevation difference is greater than the upper safety threshold H1, the risk factor is 1.2 × (relative elevation difference / H1); when it is high tide and the relative elevation difference is less than or equal to the upper safety threshold H1, the risk factor is 0.8 × (relative elevation difference / H1); when it is low tide and the relative elevation difference is less than the lower safety threshold H2, the risk factor is 0.5 × (1 - relative elevation difference / H2).

[0039] S224: Match the set of tidal phase characteristic timestamps with the current timestamp, and calculate the initial value of the hazard coefficient for each expected time point by looking up the table in conjunction with the real-time tide height;

[0040] S225: Historical extreme tide data for the same period are introduced to correct the initial value of the hazard coefficient. The correction formula is: Hazard coefficient of tide height at each expected time point = Initial value of hazard coefficient at each expected time point × (1 + Exceedance ratio of historical extreme values ​​for the same period) × Wharf breakwater attenuation factor.

[0041] For example, S23 includes:

[0042] S231: Extract the inherent sway period reference value from the target ship's design parameters and construct the ship-swell period ratio calculation formula as follows: Period ratio at each expected time point = Swell period value at each expected time point / Inherent sway period reference value;

[0043] S232: According to the maritime safety regulations, a dangerous threshold range is set. When the cycle ratio at a certain expected time point falls into the dangerous threshold range, it is determined to be a cycle overlap state. The overlap time ratio parameter is calculated as the overlap state duration / total monitoring time.

[0044] S233: Generate the surge resonance risk index of the target ship based on the overlap time ratio parameter. The calculation formula is: Surge resonance risk index = overlap time ratio parameter × (absolute value of (median of the period ratio of each expected time point - 1) × channel depth correction coefficient.

[0045] S234: Establish a three-stage mapping rule between visibility values ​​and visibility coefficients: When the visibility at a certain predicted time point is ≥ 5000 meters, the visibility coefficient at the corresponding predicted time point = 1; when 1000 meters ≤ the visibility at a certain predicted time point < 5000 meters, the visibility coefficient at the corresponding predicted time point = 0.5 + (visibility - 1000) / 8000; when the visibility at a certain predicted time point < 1000 meters, the visibility coefficient at the corresponding predicted time point = visibility / 2000.

[0046] For example, the operation process of the ship berthing strategy generation module is as follows:

[0047] Extract the target vessel's berthing safety coefficient and obtain the port's preset berthing safety threshold coefficient. Compare the two coefficients to obtain a berthing permission determination indicator. If the target vessel's berthing safety coefficient is greater than or equal to the preset berthing safety threshold coefficient, a dynamic berthing scheme is generated; otherwise, a buffer waiting strategy is generated.

[0048] The port operation status perception and monitoring system based on a data middle platform provided by this invention has at least the following beneficial effects:

[0049] The multi-dimensional meteorological data acquisition module of this invention monitors key meteorological parameters such as wind speed and visibility in real time through a micro-weather station array, and simultaneously acquires tidal phase data from an observatory. This process not only provides a comprehensive view of current environmental conditions but also provides reliable data support for subsequent berthing decisions. The safety and efficiency of port operations are directly affected by meteorological conditions, especially in cases of strong winds or low visibility, which significantly increases the berthing risk for ships. By collecting and analyzing this multi-dimensional meteorological data in real time, port managers can understand weather changes in a timely manner, make more scientific decisions, and thus effectively reduce the probability of accidents, ensuring the safety of ships and port facilities.

[0050] Secondly, the berthing safety factor calculation module dynamically calculates the berthing safety factor of a vessel by combining the target vessel's deadweight tonnage and multi-dimensional constraints. The introduction of this module ensures that berthing decisions are not based solely on static historical data, but rather on real-time dynamic information. By comprehensively considering factors such as the vessel's load, weather conditions, and tidal changes, the safety of the vessel during berthing can be assessed more accurately. This dynamic evaluation mechanism ensures that the berthing strategy for each vessel is the optimal choice based on the current actual situation, further improving the safety of port operations.

[0051] In the module that generates ship berthing strategies, a dynamic ship berthing strategy is generated based on the target ship's berthing safety factor. This strategy can not only be adjusted in real time according to changes in weather conditions and ship status, but also optimize resource allocation during the berthing process. For example, a berthing strategy generated based on real-time data can effectively reduce the time and resources required for ships to berth, improving port operational efficiency. This flexible strategy generation mechanism not only improves ship berthing efficiency but also provides a guarantee for the overall operation of the port.

[0052] In summary, by integrating multi-dimensional meteorological data collection, berthing safety factor calculation, dynamic vessel berthing strategy generation, and feedback terminals, port managers can achieve real-time monitoring and optimization of the vessel berthing process. This not only improves the safety and efficiency of port operations but also provides vessels with more scientific and flexible berthing solutions, ensuring the sustainability and economic benefits of port operations. Attached Figure Description

[0053] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a schematic diagram showing the connections of the various modules in the system of the present invention. Detailed Implementation

[0055] The following description, in conjunction with the implementation of this invention, is merely an example and illustration of the concept of this invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the inventive concept or exceed the scope defined in these claims, all of which should fall within the protection scope of this invention.

[0056] Please see Figure 1 As shown, a port operation status perception and monitoring system based on a data middle platform is disclosed. The system includes a multi-dimensional meteorological data acquisition module, a berthing safety factor calculation module, a ship berthing strategy generation module, and a ship berthing strategy feedback terminal. The modules are connected by wired and / or wireless connections to realize data transmission between the modules.

[0057] Multi-dimensional meteorological data acquisition module: Real-time monitoring of wind speed and visibility values ​​at each current time point through a micro weather station array, synchronous acquisition of tidal phase data from the observatory, and comprehensive generation of multi-dimensional meteorological data for a set time period;

[0058] The generation logic of multidimensional meteorological data is as follows:

[0059] A ship arrival time prediction model is established by inputting the target ship's speed and route coordinates into the model, and the estimated arrival time of the target ship is derived and recorded as the target's starting time. Extract the estimated berthing time of the target vessel from the berthing instructions issued by the target vessel to the port; add the estimated berthing time to the target start time to obtain the target end time. This constitutes a set time period. τ is the set time margin value;

[0060] The system acquires the wind speed and visibility values ​​of the lower atmosphere at each current time point monitored by the port's micro weather station in real time, and generates a raw meteorological dataset with timestamps. The system then performs trend fitting on the raw meteorological dataset to obtain the wind speed gradient change curve and visibility attenuation rate distribution curve of the lower atmosphere within a set time period, thereby extracting the visibility and corresponding wind speed of the lower atmosphere at each expected time point within the set time period.

[0061] Synchronously access the tidal phase data of the observatory and extract the tide height and swell cycle parameters at each expected time point within a set time period;

[0062] The visibility, tide height, swell cycle parameters, and corresponding wind speed in the lower atmosphere at each predicted time point within a set time period are spatiotemporally aligned to generate multidimensional meteorological data for the set time period.

[0063] The visibility and corresponding lower-level wind speeds at each predicted time point within a set time period are extracted, including:

[0064] Real-time wind speed data in the lower atmosphere of the port's micro weather station is collected, and visibility data at the corresponding timestamp is obtained simultaneously to form a raw meteorological dataset. The raw meteorological dataset is then aligned to the time axis and abrupt noise points are removed.

[0065] Based on the sliding time window method, a 10-minute time window is set, and the calculation is performed in 5-minute time window units. Within each window, the low-altitude wind speed data is divided into N data units per second, and the wind speed change amplitude per minute is calculated. Specifically, the change is calculated by subtracting the wind speed value at the 0th second from the wind speed value at the 60th second of each minute. The absolute value is then used to calculate the average of the changes over the 10-minute segments within the window, which is used as the initial gradient slope for that window. For the complete window, the absolute value of the gradient slope is calculated, and the direction of change is determined by comparing the wind speed at the start and end points of the window. An increase in wind speed is considered a positive value, and a decrease in wind speed is considered a negative value. When identifying continuous trend segments, the gradient direction of three consecutive windows must be consistent, either positive or negative, and the difference in the absolute value of the slope between adjacent windows must not exceed a set threshold. For trend segments that meet the conditions, a cubic spline interpolation algorithm is used for curve smoothing, i.e., smooth transition nodes are inserted between the slope values ​​of adjacent windows to generate the wind speed gradient change curve of the low-altitude layer within the set time period.

[0066] The visibility change is calculated second by second, which is the difference between the current second value and the previous second value; when the difference is negative, it is marked as a decay event; the number of decay events is counted within a 10-minute window, and when the decay event count accounts for more than 70%, it is judged as a high decay window; three consecutive high decay windows are merged to form a decay risk segment, and the weighted average of the correction factors of each window is calculated during merging, with the weight coefficients set to 0.2, 0.3, and 0.5 in chronological order; a quadratic polynomial fitting algorithm is used to generate a baseline curve for the risk segment data, and the first and last parts are extended by 5 minutes to form a visibility decay rate distribution curve;

[0067] It should be added that the quadratic polynomial fitting formula is expressed as:

[0068] Visibility value V(t) = a×t² + b×t + c;

[0069] Where: t represents the normalized time variable, which converts the time coordinates of each risk segment into a normalized scale of 0 to 1; a is the quadratic coefficient, which determines the direction of curve opening and curvature intensity; b is the linear coefficient, which reflects the linear component of the changing trend; c is the constant term, which represents the correction amount of the baseline starting point; the coefficient combination [a,b,c] constitutes the fitting parameter set.

[0070] Parameter estimation is performed using the least squares method:

[0071] For n data points (t_i, v_i) within the risk segment, calculate the sum of squared residuals between the predicted and measured values; take the partial derivatives of the three unknown parameters and set them equal to zero to form a 3×3 linear equation system; by constructing the design matrix X and the observation vector Y, obtain the optimal parameter solution according to the formula (X^TX)^{-1} X^TY.

[0072] Map the start time t_start of the risk segment to t=0 and the end time t_end to t=1. Substitute the parameters [a,b,c] to calculate V(t) corresponding to the normalized time t. Map the normalized time back to the actual time coordinate system. Generate a continuous function curve V(t)=a(t)^2 + b(t) + c. Finally, the visibility attenuation rate distribution curve is generated with the UNIX timestamp as the abscissa. Discretize the value of the above function V(t) according to the time series and draw it as a continuous broken line graph.

[0073] The wind speed gradient curve and visibility attenuation rate distribution curve in the lower atmosphere within the set time period are plotted with the time point as the horizontal axis and the corresponding value as the vertical axis. Then, based on the horizontal axis, the visibility and the corresponding wind speed in the lower atmosphere at each expected time point within the set time period are extracted sequentially.

[0074] In this embodiment of the invention, the extraction process is as follows: First, wind speed values ​​are collected in real time by meteorological sensors deployed in the lower atmosphere of the port, and visibility values ​​at corresponding timestamps are obtained simultaneously by the port visibility monitoring device, forming a raw meteorological dataset containing a time series; the wind speed and visibility signals in the raw data are aligned on the time axis, and missing values ​​caused by sensor transmission delays or malfunctions are filled using linear interpolation, and abrupt noise points exceeding a reasonable range are identified and removed using the interquartile range method; for wind speed data processing, a sliding time window method is used with a window length of 10 minutes and a 5-minute interval. The clock is used as a sliding unit to segment time-series data. Within a single window, the low-altitude wind speed values ​​collected every second are divided into continuous data units. The wind speed change within each minute is calculated by subtracting the absolute value of the initial wind speed value from the wind speed value in the last second of each minute. The absolute values ​​of wind speed changes over 10 minute segments within the window are accumulated and their average is calculated to obtain the initial gradient slope. The gradient slope is then assigned a sign based on the direction of wind speed increase or decrease at the start and end points of the window: positive for increasing wind speed and negative for decreasing wind speed. After completing the gradient calculation within the window, continuous trend segments are identified by scanning the entire window, and selected... For sections where the gradient direction is consistent across three consecutive windows and the absolute difference in slope between adjacent windows is below a set threshold, a cubic spline interpolation algorithm is used to smooth the gradient slope of adjacent windows, inserting continuous slope values ​​from intermediate nodes to generate a low-altitude wind speed gradient change curve. For visibility data processing, the difference between the visibility value and the previous second is compared second by second. When the difference is less than zero, it is marked as an attenuation event. The number of attenuation events is counted within a 10-minute window. When the number of attenuation events accounts for more than 70% of the total events in the window, it is determined to be a high attenuation window. For sections with three consecutive high attenuation windows... The combined attenuation risk parameters were calculated by weighting the correction factors of the window with weights of 0.2, 0.3, and 0.5 according to the time sequence. Then, the visibility data points in the risk segment were fitted with a quadratic polynomial to generate the attenuation rate baseline curve, and the data range at both ends of the baseline curve was extended by 5 minutes to cover the potential attenuation impact area. Finally, the wind speed gradient change curve and the visibility attenuation rate distribution curve in the lower atmosphere were combined, and the wind speed and visibility values ​​at each expected time point within the set time period were extracted point by point using the time point as the index to form a meteorological parameter sequence for dynamic ship berthing strategy analysis.

[0075] Berthing safety factor calculation module: Combines the target vessel's deadweight tonnage with multi-dimensional constraints to dynamically calculate the target vessel's berthing safety factor;

[0076] The operation logic of the berthing safety factor calculation module is as follows:

[0077] S21: The wind speed values ​​at each predicted time point in the multidimensional meteorological data are smoothed by a moving window, and the dynamic influence weighting factor of wind speed at each predicted time point is calculated based on the ratio of wind speed to the safety threshold of ship tonnage.

[0078] S22: Map the tide height data at each expected time point to the port terminal reference elevation coordinate system, classify the tide level hazard level according to the characteristics of the rising and falling tide periods, and output a set of tide height hazard coefficients with time correlation.

[0079] S23: Frequency domain matching analysis is performed using the swell cycle values ​​at each expected time point and the ship's rolling cycle. The swell resonance risk index of the target ship is generated through the cycle overlap discrimination rule. Simultaneously, piecewise linear interpolation is performed on the visibility values ​​to convert them into visibility coefficients at each expected time point.

[0080] S24: Construct a constraint scoring matrix and perform polarity normalization on the wind speed dynamic influence weight factor, tide height hazard coefficient, surge resonance risk index, and visibility coefficient at each expected time point. The polarity normalization process includes taking the original value for positive parameters and taking (1-original value) for negative parameters.

[0081] S25: Set a time dimension decay function, the calculation formula is: weight of each expected time point = exp(-α×|each expected time point-target end time point|), where α is the dock geological stability coefficient, and the constraint scoring matrix is ​​weighted and summed in the time domain through the decay function;

[0082] S26: Perform range compression processing on the time-domain weighted summation result to map the maximum value range of multidimensional meteorological parameters to the [0,1] interval, and generate the target ship berthing safety factor.

[0083] In this embodiment of the invention, the implementation process of the berthing safety factor calculation module is as follows: First, the wind speed values ​​at each expected time point in the multidimensional meteorological data are smoothed using a moving window to eliminate the interference of instantaneous wind speed fluctuations. By setting a dynamic threshold range associated with the ship's tonnage, the ratio difference between the actual wind speed value and the upper limit of the safety threshold is calculated as the basic weight. This is then combined with the wind speed change trend of adjacent time windows to correct and generate the dynamic influence weight factor for wind speed at each time point. Simultaneously, the real-time tide level data is mapped to a reference coordinate system based on the wharf's design elevation, and based on historical data... The historical tide table divides the tide into periods such as the high tide acceleration period, the low tide period, and the low tide buffer period. A gradient-based hazard level assessment standard is set for different periods. During the high tide acceleration period, the closer the tide level is to the wharf's flood control limit elevation, the higher the hazard coefficient increases linearly, generating a set of tide level hazard coefficients precisely correlated with the time axis. Furthermore, a frequency domain superposition analysis is performed using the natural period of ship swaying and the measured period of swells. The cumulative duration of the ratio of these two periods falling within a preset hazard range is calculated as the swell resonance risk index. Simultaneously, a piecewise linear interpolation method is used for visibility monitoring values ​​to... The values ​​are mapped and transformed in three segments: low visibility range, safe range, and high visibility range, generating a visibility coefficient in the range of 0 to 1. Subsequently, a constraint scoring matrix is ​​constructed, and a polarity normalization method is used to unify the wind speed influence factor, tide level hazard coefficient, swell risk index, and visibility coefficient to the same dimension, while retaining the original values ​​for positive parameters and reversing the negative parameters to 1 minus the original values. Specifically, to address the attenuation effect of time on the safety coefficient, an exponential attenuation function based on the geological stability of the wharf is adopted, where the geological stability coefficient α is determined by the geotechnical engineering investigation report. The bearing capacity parameters of the foundation and the vibration modal test data of the wharf structure are comprehensively calibrated. Specifically, the ratio of the foundation shear wave velocity to the pile foundation resonance frequency is determined. This coefficient is used to apply an exponential decay weight to time points far from the target berthing time, so that the weighted constraint scoring matrix forms a differentiated contribution in the time dimension. Finally, the range compression algorithm is used to linearly map the numerical range of the weighted result to the standardized range of 0 to 1. The final value is normalized according to the expansion ratio between the maximum and minimum values ​​to generate the target ship berthing safety coefficient that intuitively represents the safety level.

[0084] S21 includes:

[0085] S211: Set the time window width parameter, use the moving average algorithm to denoise the wind speed values ​​at each expected time point, and output a smooth wind speed sequence;

[0086] S212: Based on the target vessel's deadweight tonnage, retrieve the baseline safe wind speed value corresponding to the current vessel's deadweight tonnage from the pre-stored safe wind speed threshold table;

[0087] S213: Calculate the deviation between each wind speed value in the smoothed wind speed sequence and the baseline safe wind speed value at each expected time point. The calculation formula is: Deviation = Wind speed value in the smoothed wind speed sequence / Baseline safe wind speed value - 1.

[0088] S214: Construct a piecewise weight transformation function, where the weight factor = 0 when the deviation is ≤ 0, the weight factor = deviation × 1.5 when 0 < deviation ≤ 0.3, and the weight factor = 0.45 + (deviation - 0.3) × 2 when the deviation is > 0.3;

[0089] S215: Input the deviation of each expected time point into the piecewise weight conversion function, and output the dynamic influence weight factor of wind speed at each expected time point.

[0090] In this embodiment of the invention, firstly, a time window width parameter is set, and a moving average algorithm is used to denoise the original wind speed values ​​at each expected time point. Specifically, the arithmetic mean of the wind speed data at consecutive time points within the window is taken to generate a smooth wind speed sequence, eliminating the influence of short-term random fluctuations on the calculation results. Then, based on the target ship's tonnage, a matching search is performed in a pre-established ship tonnage-safe wind speed mapping table. This mapping table stores the benchmark safe wind speed values ​​corresponding to different tonnage classes, indexed by ship tonnage. These benchmark values ​​are derived from a fluid dynamics model relating the ship's waterline area and fluid resistance coefficient. The deviation between the measured wind speed and the benchmark safe wind speed value in the smooth wind speed sequence is compared point by point. The calculation formula is expressed as dividing the measured wind speed at each time point by the benchmark value. Subtracting 1 from the value represents the proportional offset relative to the benchmark value, where a negative offset indicates that the measured wind speed is below the safety threshold. To convert linear deviation into nonlinear risk weights, a piecewise weight conversion function is constructed: when the wind speed deviation is less than or equal to zero, the weight factor is set to zero, indicating no safety risk; when the deviation is between zero and three times the benchmark value, the weight factor increases linearly by 1.5 times the offset, reflecting the cumulative effect of low risk; when the deviation exceeds three times the benchmark value, to prevent the risk coefficient from rising rapidly, the weight factor is superimposed with double the excess on the base value of 0.45, strengthening the gradient penalty mechanism in the high-risk range; finally, the wind speed deviation at each time point is input into the above piecewise function, and the dynamic influence weight factor of wind speed at each expected time point is output.

[0091] S22 includes:

[0092] S221: Obtain the reference elevation zero point defined in the geological survey report of the port terminal, and establish a dataset of the relative elevation difference between the tide level and the terminal operation platform at each expected time point;

[0093] S222: Analyze the time interval markers of high tide and low tide in the observatory's tide table to generate a set of tidal phase feature timestamps;

[0094] S223: When it is high tide and the relative elevation difference is greater than the upper safety threshold H1, the risk factor is 1.2 × (relative elevation difference / H1); when it is high tide and the relative elevation difference is less than or equal to the upper safety threshold H1, the risk factor is 0.8 × (relative elevation difference / H1); when it is low tide and the relative elevation difference is less than the lower safety threshold H2, the risk factor is 0.5 × (1 - relative elevation difference / H2).

[0095] S224: Match the set of tidal phase characteristic timestamps with the current timestamp, and calculate the initial value of the hazard coefficient for each expected time point by looking up the table in conjunction with the real-time tide height;

[0096] S225: Historical extreme tide data for the same period are introduced to correct the initial value of the hazard coefficient. The correction formula is: Hazard coefficient of tide height at each expected time point = Initial value of hazard coefficient at each expected time point × (1 + Exceedance ratio of historical extreme values ​​for the same period) × Wharf breakwater attenuation factor.

[0097] In this embodiment of the invention, based on the reference elevation zero point coordinates determined in the port terminal geological survey report, the real-time collected tidal height data is converted into a vertical difference dataset relative to the elevation surface of the terminal operation platform; by analyzing the tidal phase timetable published by the observatory, the precise time stamps of the high and low tide periods are extracted to form a characteristic timestamp sequence, and combined with high-precision satellite time synchronization data to achieve synchronization between the tidal phase and the actual time axis; according to the tidal phase characteristics, the state of each expected time point is judged: if it is during the high tide period and the tidal elevation difference exceeds the safety upper limit threshold H1, the ratio of the relative difference of the excess part to the threshold is multiplied by a 1.2-fold enhancement coefficient for calculation; if the elevation difference during the high tide period does not reach H1... When the difference is less than or equal to the threshold, the safety buffer coefficient is calculated by multiplying the ratio of the difference to the threshold by 0.8. When the tide is low and the elevation difference is below the safety lower limit threshold H2, the warning coefficient is calculated by multiplying the inverse difference between the actual difference and the threshold by 0.5. For the initial value calculation results at each time point, the historical extreme tide level data of the same period are used for dynamic adjustment. The percentage of the current tide level exceeding the highest value of the same period in history is quantified. The percentage increase is multiplied by the attenuation factor parameter reflecting the performance of the breakwater structure. The attenuation factor is determined by a comprehensive evaluation of the concrete carbonation depth detection data of the wharf structure and the degree of marine organism attachment. Finally, a set of tide level height danger coefficients for each expected time point is generated.

[0098] S23 includes:

[0099] S231: Extract the inherent sway period reference value from the target ship's design parameters and construct the ship-swell period ratio calculation formula as follows: Period ratio at each expected time point = Swell period value at each expected time point / Inherent sway period reference value;

[0100] S232: According to the maritime safety regulations, a dangerous threshold range is set. When the cycle ratio at a certain expected time point falls into the dangerous threshold range, it is determined to be a cycle overlap state. The overlap time ratio parameter is calculated as the overlap state duration / total monitoring time.

[0101] S233: Generate the surge resonance risk index of the target ship based on the overlap time ratio parameter. The calculation formula is: Surge resonance risk index = overlap time ratio parameter × (absolute value of (median of the period ratio of each expected time point - 1) × channel depth correction coefficient.

[0102] S234: Establish a three-stage mapping rule between visibility values ​​and visibility coefficients: When the visibility at a certain predicted time point is ≥ 5000 meters, the visibility coefficient at the corresponding predicted time point = 1; when 1000 meters ≤ the visibility at a certain predicted time point < 5000 meters, the visibility coefficient at the corresponding predicted time point = 0.5 + (visibility - 1000) / 8000; when the visibility at a certain predicted time point < 1000 meters, the visibility coefficient at the corresponding predicted time point = visibility / 2000.

[0103] In this embodiment of the invention, the inherent sway period reference parameter of the ship is first extracted from the ship design technical document. The ratio of the measured swell period value at each expected time point to the reference value is calculated to generate a period ratio sequence reflecting the coupling state between the ship and the wave motion. Based on the resonance risk interval threshold defined by the maritime safety regulations, the period ratio is judged at each time point to determine whether it is within the danger interval. The cumulative duration of the time period that continuously meets the risk conditions is counted as the proportion of the total monitoring time as a risk exposure indicator. The resonance intensity coefficient is calculated based on the exposure indicator and superimposed on it. The intensity coefficient is obtained by taking the absolute deviation of the median of all period ratios in the danger interval from the reference value and multiplying it by a correction factor parameter that is dynamically adjusted according to the measured water depth data of the waterway.

[0104] S24 includes:

[0105] S241: Define the parameter polarity mapping rule: where the positive parameter set is the visibility coefficient; the negative parameter set is the wind speed dynamic influence weighting factor, the tide height hazard coefficient, and the swell resonance risk index;

[0106] S242: Perform time dimension alignment operation to sort the four types of parameters at each expected time point by timestamp and generate a synchronization data array;

[0107] S243: Perform negative normalization transformation on the negative parameter matrix. The transformation formula is: normalized value = 1 - original value × 0.98, where 0.98 is the tolerance calibration coefficient.

[0108] S244: Perform preservation processing on the positive parameter matrix and directly use the original values ​​to construct the visible coefficient data matrix;

[0109] S245: The four types of parameter arrays are horizontally spliced ​​in the order of timestamps to generate a multidimensional constraint scoring matrix, where the matrix structure is: row vector = time point sequence, column vector = [normalized wind speed weight | normalized tide level hazard | normalized swell risk | original visibility coefficient].

[0110] Vessel berthing strategy generation module: Generates a dynamic vessel berthing strategy for the target vessel based on the target vessel's berthing safety factor;

[0111] The operation process of the ship berthing strategy generation module is as follows:

[0112] Extract the target vessel's berthing safety coefficient and obtain the port's preset berthing safety threshold coefficient. Compare the two coefficients to obtain a berthing permission determination indicator. If the target vessel's berthing safety coefficient is greater than or equal to the preset berthing safety threshold coefficient, a dynamic berthing scheme is generated; otherwise, a buffer waiting strategy is generated.

[0113] When a dynamic mooring scheme is generated, port hydrological data, ship navigation attitude parameters, and berth occupancy status are collected in real time. Through multi-source data fusion processing, a lateral anchoring force compensation function and a longitudinal cable tension balance equation are constructed to calculate and generate a mooring scheme that includes mooring point coordinate deviation compensation values. The number of cables in the mooring scheme is determined based on the cosine of the angle between the ship's berthing velocity vector and the surge direction vector. The mooring scheme includes at least: optimized mooring point locations, safe tension ranges for each cable, and a time window allowing mooring operations. When a buffer waiting strategy is generated, historical data is retrieved. Based on historical tidal cycle fluctuation data and combined with current port vessel scheduling priorities and target berth operation plans, a time window dynamic equilibrium algorithm is used to calculate the estimated waiting time for target vessels. The estimated waiting time is calculated based on the product of the remaining operation time of the target berth and the number of vessels waiting to berth in the same area, and a correction coefficient determined by the ratio of the historical average berth operation efficiency to the current tidal level change rate is introduced for recursive correction. Simultaneously, based on minimum fuel consumption constraints and radar collision avoidance safety distance thresholds, the dynamic stationary coordinate trajectory and corresponding velocity gradient of the target vessel during the temporary berthing period are dynamically planned and generated.

[0114] In this embodiment of the invention, by comparing the target vessel's berthing safety factor with the port's preset safety threshold in real time, a dynamic berthing scheme generation mechanism is triggered when the safety factor meets the standard. At this time, multi-source parameters such as the port's real-time tidal current velocity, the vessel's draft and pitch angle, and berth occupancy status are integrated. A hydrodynamic compensation model is used to calculate the dynamic adjustment of the vessel's lateral anchoring force. Combined with the longitudinal cable tension balance equation, the torsional moment caused by wave loads is eliminated, generating an optimized scheme that includes compensation for mooring point position offset. The number of cables is dynamically adjusted based on the real-time angle between the vessel's velocity vector and the surge direction when it enters berth. When the cosine value of the angle is less than a preset critical value, two base cables are added for every unit decrease in the cosine value to ensure the vessel's mooring stability under complex hydrological conditions. When the safety factor does not reach the threshold, a dynamic berthing scheme generation mechanism is triggered. The tidal phase prediction model retrieves historical tidal level fluctuation data for the same period, overlays it with the current berth operation progress and priority scheduling sequence, and uses a dynamic estimation algorithm for berth occupancy time to calculate the waiting time. Its core logic is to multiply the remaining berth operation time by the number of ships waiting to berth in the same area, and then make a weighted correction based on the ratio coefficient of the port's historical average loading and unloading efficiency and the current tidal level rise and fall rate. At the same time, it integrates the ship's power system fuel consumption model and the movement trajectory of surrounding ships monitored by radar to construct a trajectory planning model with the goal of optimizing fuel consumption. Combined with the spatial constraints of the collision avoidance safety corridor, it dynamically generates a closed-loop stationary trajectory consisting of speed segment control commands and coordinate point sequences to ensure that the ship always maintains a safe distance above the radar ranging threshold from neighboring ships during the waiting period and performs standby cruise on the fuel-efficient path.

[0115] Vessel berthing strategy feedback terminal: Feeds back the dynamic berthing strategy of the target vessel to the port data platform, triggering the coordinated execution of the port machinery equipment scheduling system and the waterway traffic control system.

[0116] It should be noted that the interval and threshold sizes are set for ease of comparison. The size of the threshold depends on the amount of sample data and the base number set by those skilled in the art for each set of sample data, as long as it does not affect the proportional relationship between the parameter and the quantized value. Furthermore, the above formulas are all dimensionless calculations, and the formulas are derived from software simulations using a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0117] It should be understood that, in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0118] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0119] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A port operation status perception and monitoring system based on a data middle platform, characterized in that, include: Multi-dimensional meteorological data acquisition module: Real-time monitoring of wind speed and visibility values ​​at each current time point through a micro weather station array, synchronous acquisition of tidal phase data from the observatory, and comprehensive generation of multi-dimensional meteorological data for a set time period; Berthing safety factor calculation module: Based on the target vessel's deadweight tonnage, dynamically calculates the target vessel's berthing safety factor using multi-dimensional constraints; including: The wind speed values ​​at each predicted time point in the multidimensional meteorological data are smoothed by a moving window, and the dynamic influence weighting factor of wind speed at each predicted time point is calculated based on the ratio of wind speed to the safety threshold of ship tonnage. Map the tide level at each expected time point to the port terminal reference elevation coordinate system, classify the tide level hazard level according to the characteristics of the rising and falling tide periods, and output the tide level hazard coefficient at each expected time point. Frequency domain matching analysis was performed using the swell cycle values ​​at each expected time point and the ship's rolling cycle. The swell resonance risk index of the target ship was generated through the cycle overlap discrimination rule. Simultaneously, piecewise linear interpolation was performed on the visibility values ​​to convert them into visibility coefficients at each expected time point. A constraint scoring matrix is ​​constructed, and the dynamic influence weight factor of wind speed, the hazard coefficient of tide height, the swell resonance risk index, and the visibility coefficient at each expected time point are normalized by polarity. The polarity normalization process includes positive parameter processing and negative parameter processing. The positive parameter takes the original value, and the negative parameter = 1 - the original value. A time-dimensional attenuation function is set, and the calculation formula is: weight of each expected time point = exp(-α×|each expected time point-target end time point|), where α is the geological stability coefficient of the wharf. The constraint scoring matrix is ​​then summed in the time domain using the attenuation function. The time-domain weighted summation result is subjected to range compression processing to map the maximum value range of multidimensional meteorological parameters to the [0,1] interval, thereby generating the target ship berthing safety factor; Vessel berthing strategy generation module: Generates a dynamic vessel berthing strategy for the target vessel based on the target vessel's berthing safety factor; Vessel berthing strategy feedback terminal: Feeds back the dynamic berthing strategy of the target vessel to the port data platform, triggering the coordinated execution of the port machinery equipment scheduling system and the waterway traffic control system.

2. The port operation status perception and monitoring system based on a data middle platform according to claim 1, characterized in that, The generation logic of multidimensional meteorological data is as follows: A ship arrival time prediction model is established by inputting the target ship's speed and route coordinates into the model, and the estimated arrival time of the target ship is derived and recorded as the target's starting time. Extract the estimated berthing time of the target vessel from the berthing instructions issued by the target vessel to the port; add the estimated berthing time to the target start time to obtain the target end time. This constitutes a set time period. τ is the set time margin value; The system acquires the wind speed and visibility values ​​of the lower atmosphere at each current time point monitored by the port's micro weather station in real time, and generates a raw meteorological dataset with timestamps. The system then performs trend fitting on the raw meteorological dataset to obtain the wind speed gradient change curve and visibility attenuation rate distribution curve of the lower atmosphere within a set time period, thereby extracting the visibility and corresponding wind speed of the lower atmosphere at each expected time point within the set time period. Synchronously access the tidal phase data of the observatory and extract the tide height and swell cycle parameters at each expected time point within a set time period; The visibility, tide height, swell cycle parameters, and corresponding wind speed in the lower atmosphere at each predicted time point within a set time period are spatiotemporally aligned to generate multidimensional meteorological data for the set time period.

3. The port operation status perception and monitoring system based on a data middle platform according to claim 2, characterized in that, The visibility and corresponding lower-level wind speeds at each predicted time point within a set time period are extracted, including: Real-time wind speed data in the lower atmosphere of the port's micro weather station is collected, and visibility data at the corresponding timestamp is obtained simultaneously to form a raw meteorological dataset. The raw meteorological dataset is then aligned to the time axis and abrupt noise points are removed. Based on the sliding time window method, a 10-minute time window is set, and the calculation is performed in 5-minute time window units. Within each window, the low-level wind speed data is divided into N data units per second, and the wind speed change amplitude per minute is calculated. Specifically, the wind speed value at the 60th second of each minute is subtracted from the wind speed value at the 0th second to obtain the change amount. The absolute value is then used to calculate the average of the changes over 10 minutes within the window, which is used as the initial gradient slope of the window. The direction of change is determined by comparing the wind speed at the start and end points of the window; an increase in wind speed is considered positive, and a decrease is considered negative. When identifying continuous trend segments, the gradient direction of three consecutive windows must be consistent, either positive or negative, and the absolute difference in the slope values ​​of adjacent windows must not exceed a set threshold. For trend segments that meet the conditions, a cubic spline interpolation algorithm is used for curve smoothing, i.e., smooth transition nodes are inserted between the slope values ​​of adjacent windows to generate the wind speed gradient change curve of the low-level layer within the set time period. The visibility change is calculated second by second, which is the difference between the current second value and the previous second value; when the difference is negative, it is marked as a decay event; the number of decay events is counted within a 10-minute window, and when the decay event count accounts for more than 70%, it is judged as a high decay window; three consecutive high decay windows are merged to form a decay risk segment, and the weighted average of the correction factors of each window is calculated during merging, with the weight coefficients set to 0.2, 0.3, and 0.5 in chronological order; a quadratic polynomial fitting algorithm is used to generate a baseline curve for the risk segment data, and the first and last parts are extended by 5 minutes to form a visibility decay rate distribution curve; The wind speed gradient curve and visibility attenuation rate distribution curve in the lower atmosphere within the set time period are plotted with the time point as the horizontal axis and the corresponding value as the vertical axis. Then, based on the horizontal axis, the visibility and the corresponding wind speed in the lower atmosphere at each expected time point within the set time period are extracted sequentially.

4. The port operation status perception and monitoring system based on a data middle platform according to claim 1, characterized in that, S21 includes: S211: Set the time window width parameter, use the moving average algorithm to denoise the wind speed values ​​at each expected time point, and output a smooth wind speed sequence; S212: Based on the target vessel's deadweight tonnage, retrieve the baseline safe wind speed value corresponding to the current vessel's deadweight tonnage from the pre-stored safe wind speed threshold table; S213: Calculate the deviation between each wind speed value in the smoothed wind speed sequence and the baseline safe wind speed value at each expected time point. The calculation formula is: Deviation = Wind speed value in the smoothed wind speed sequence / Baseline safe wind speed value - 1. S214: Construct a piecewise weight transformation function, where the weight factor = 0 when the deviation is ≤ 0, the weight factor = deviation × 1.5 when 0 < deviation ≤ 0.3, and the weight factor = 0.45 + (deviation - 0.3) × 2 when the deviation is > 0.3; S215: Input the deviation of each expected time point into the piecewise weight conversion function, and output the dynamic influence weight factor of wind speed at each expected time point.

5. A port operation status perception and monitoring system based on a data middle platform according to claim 1, characterized in that, S22 includes: S221: Obtain the reference elevation zero point defined in the geological survey report of the port terminal, and establish a dataset of the relative elevation difference between the tide level and the terminal operation platform at each expected time point; S222: Analyze the time interval markers of high tide and low tide in the observatory's tide table to generate a set of tidal phase feature timestamps; S223: When it is high tide and the relative elevation difference is greater than the upper safety threshold H1, the risk factor is 1.2 × (relative elevation difference / H1); when it is high tide and the relative elevation difference is less than or equal to the upper safety threshold H1, the risk factor is 0.8 × (relative elevation difference / H1); when it is low tide and the relative elevation difference is less than the lower safety threshold H2, the risk factor is 0.5 × (1 - relative elevation difference / H2). S224: Match the set of tidal phase characteristic timestamps with the current timestamp, and calculate the initial value of the hazard coefficient for each expected time point by looking up the table in conjunction with the real-time tide height; S225: Historical extreme tide data for the same period are introduced to correct the initial value of the hazard coefficient. The correction formula is: Hazard coefficient of tide height at each expected time point = Initial value of hazard coefficient at each expected time point × (1 + Exceedance ratio of historical extreme values ​​for the same period) × Wharf breakwater attenuation factor.

6. The port operation status perception and monitoring system based on a data middle platform according to claim 1, characterized in that, S23 includes: S231: Extract the inherent sway period reference value from the target ship's design parameters and construct the ship-swell period ratio calculation formula as follows: Period ratio at each expected time point = Swell period value at each expected time point / Inherent sway period reference value; S232: According to the maritime safety regulations, a dangerous threshold range is set. When the cycle ratio at a certain expected time point falls into the dangerous threshold range, it is determined to be a cycle overlap state. The overlap time ratio parameter is calculated as follows: overlap time ratio parameter = overlap state duration / total monitoring duration. S233: Generate the surge resonance risk index of the target ship based on the overlap time ratio parameter. The calculation formula is: Surge resonance risk index = overlap time ratio parameter × (absolute value of (median of the period ratio of each expected time point - 1) × channel depth correction coefficient. S234: Establish a three-stage mapping rule between visibility values ​​and visibility coefficients: When the visibility at a certain predicted time point is ≥ 5000 meters, the visibility coefficient at the corresponding predicted time point = 1; when 1000 meters ≤ the visibility at a certain predicted time point < 5000 meters, the visibility coefficient at the corresponding predicted time point = 0.5 + (visibility - 1000) / 8000; when the visibility at a certain predicted time point < 1000 meters, the visibility coefficient at the corresponding predicted time point = visibility / 2000.

7. A port operation status perception and monitoring system based on a data middle platform according to claim 1, characterized in that, The operation process of the ship berthing strategy generation module is as follows: Extract the target vessel's berthing safety coefficient and obtain the port's preset berthing safety threshold coefficient. Compare the two coefficients to obtain a berthing permission determination indicator. If the target vessel's berthing safety coefficient is greater than or equal to the preset berthing safety threshold coefficient, a dynamic berthing scheme is generated; otherwise, a buffer waiting strategy is generated.

Images