Port fog navigation intelligent decision-making system verification method and device

Abstract

The invention provides a port fog navigation intelligent decision system verification method and device. The method comprises the following steps: acquiring port topography and wharf point cloud data by using a laser radar, and constructing a port model in combination with an electronic chart; and constructing a ship model according to the target ship form drawing and the AIS historical data. And simulating different foggy weather conditions, calculating collision and stranding safety coefficients of the target ship, and comparing the collision and stranding safety coefficients with a preset threshold to generate a risk decision text. And counting downshift success rates of different risks, and calculating a decision reasonability evaluation index. And generating a comprehensive fog aviation evaluation index by combining the collision and stranding safety coefficient and the decision rationality index, comparing the comprehensive fog aviation evaluation index with a preset standard value to generate an optimization decision instruction, and sending the optimization decision instruction to a management personnel terminal. According to the method, the real environment is highly simulated, risk assessment and decision rationality assessment are combined, the navigation decision is optimized, and the port fog navigation safety and efficiency are improved.

Description

Technical Field

[0001] The present application belongs to the field of fog navigation decision-making, and in particular, relates to a verification method and device for a port fog navigation intelligent decision-making system. Background Art

[0002] As the core hub for ship transportation, ports face significantly increased navigation risks in low-visibility weather, especially foggy days.

[0003] The traditional verification method of the intelligent decision-making system for port fog navigation mainly relies on sensors to collect information and perform data processing and analysis to generate decision suggestions. However, this method has problems such as over-simplification of scenarios, misjudgment of decisions, and reduced timeliness of historical data, which leads to larger errors in decision results and cannot fully adapt to the complex and changeable port fog navigation environment. Summary of the invention

[0004] The purpose of this application is to overcome the defects in the above-mentioned prior art and provide a verification method and device for a port fog navigation intelligent decision-making system.

[0005] The present application provides a method for verifying a port fog navigation intelligent decision-making system, comprising:

[0006] Obtaining point cloud data of the target port terrain and docks through laser radar; obtaining the channel water depth and obstacle coordinates according to the electronic nautical chart; and constructing a port model based on the point cloud data, channel water depth and obstacle coordinates;

[0007] Obtain ship size parameters based on target ship drawings and build a ship model based on AIS historical data;

[0008] Generate foggy conditions by simulating light fog, moderate fog and dense fog in different levels;

[0009] Calculating the collision safety factor and the grounding safety factor of the target ship based on the port model, the ship model and the foggy weather conditions;

[0010] Comparing the collision safety factor and the grounding safety factor with preset thresholds respectively, and generating decision texts corresponding to no risk, medium risk or high risk respectively according to the comparison results;

[0011] Based on the decision text, a high-risk downshift success rate, a medium-risk downshift success rate, and a low-risk downshift success rate are counted, and a decision rationality evaluation index is calculated by weighting;

[0012] Based on the collision safety factor, grounding safety factor and decision rationality evaluation index, a comprehensive fog navigation evaluation index is generated;

[0013] According to the comparison result between the comprehensive fog navigation evaluation index and the preset standard value, an optimization decision instruction is generated and sent to the management terminal.

[0014] Optionally, obtain the ship size parameters based on the target ship type drawing, and construct a ship model in combination with the AIS historical data, including:

[0015] Obtain the ship size parameters based on the target ship type drawing, and establish a ship motion characteristic model by combining the turning radius and acceleration of the ship extracted from the AIS historical data.

[0016] Optionally, calculate the collision safety factor and the grounding safety factor of the target ship based on the port model, the ship model, and the foggy weather conditions. The calculation of the collision safety factor includes:

[0017] Obtain the velocity vectors and relative position vectors of the target ship and other ships, and calculate the distance and time of the closest point between the two ships;

[0018] Compare the distance of the closest point with a preset distance safety threshold to obtain a first comparison value, and compare the time of the closest point with a preset time safety threshold to obtain a second comparison value;

[0019] Calculate the collision safety factor through a non-linear logarithmic function according to the first comparison value and the second comparison value.

[0020] Optionally, calculate the collision safety factor and the grounding safety factor of the target ship based on the port model, the ship model, and the foggy weather conditions. The calculation of the grounding safety factor includes:

[0021] Monitor the real-time water depth and draft data of the target ship, and obtain the under-keel clearance;

[0022] Obtain the coordinate deviation between the current position and the planned route position of the target ship, and calculate the course deviation;

[0023] Compare the under-keel clearance with a preset water depth safety threshold to obtain a third comparison value, and compare the course deviation with a preset deviation safety threshold to obtain a fourth comparison value;

[0024] Calculate the grounding safety factor through an exponential function according to the third comparison value and the fourth comparison value.

[0025] Optionally, compare the collision safety factor and the grounding safety factor with preset thresholds respectively, and generate decision texts corresponding to risk-free, medium-risk, or high-risk according to the comparison results, including:

[0026] If both the collision safety factor and the grounding safety factor are greater than or equal to the preset threshold, generate a risk-free decision and maintain navigation;

[0027] If the collision safety factor is less than the preset threshold and the grounding safety factor is greater than or equal to the preset threshold, generate a medium-risk decision and generate a detour route;

[0028] If the collision safety factor is greater than or equal to a preset threshold and the grounding safety factor is less than the preset threshold, generate a medium-risk decision and correct the waterway;

[0029] If both the collision safety factor and the grounding safety factor are less than the preset threshold, generate a high-risk decision and execute an emergency stop and anchoring.

[0030] This application also provides a verification device for a port fog navigation intelligent decision-making system, including:

[0031] A port module that obtains point cloud data of the target port terrain and the wharf through a lidar; obtains the water depth of the waterway and the coordinates of obstacles according to an electronic nautical chart; constructs a port model based on the point cloud data, the water depth of the waterway, and the coordinates of obstacles;

[0032] A ship module that obtains ship size parameters based on the target ship type drawing and constructs a ship model in combination with AIS historical data;

[0033] A weather module that generates foggy conditions by classifying and simulating light fog, medium fog, and thick fog;

[0034] A coefficient module that calculates the collision safety factor and the grounding safety factor of the target ship based on the port model, the ship model, and the foggy conditions;

[0035] A decision module that compares the collision safety factor and the grounding safety factor with the preset thresholds respectively, and generates decision texts corresponding to no risk, medium risk, or high risk according to the comparison results;

[0036] An index module that statistically calculates the high-risk downshift success rate, the medium-risk downshift success rate, and the low-risk downshift success rate based on the decision text, and calculates a decision rationality evaluation index through weighted calculation;

[0037] A comprehensive module that generates a comprehensive fog navigation evaluation index based on the collision safety factor, the grounding safety factor, and the decision rationality evaluation index;

[0038] A management module that generates an optimization decision instruction according to the comparison result between the comprehensive fog navigation evaluation index and a preset standard value and sends it to the manager's terminal.

[0039] Optionally, the ship module obtains ship size parameters based on the target ship type drawing and constructs a ship model in combination with AIS historical data, including:

[0040] Obtain ship size parameters based on the target ship type drawing, and establish a ship motion characteristic model in combination with the turning radius and acceleration of the ship extracted from AIS historical data.

[0041] Optionally, the coefficient module calculates the collision safety coefficient and the grounding safety coefficient of the target ship based on the port model, the ship model, and the foggy weather conditions. The calculation of the collision safety coefficient includes:

[0042] Obtain the velocity vectors and relative position vectors of the target ship and other ships, and calculate the distance and time of the closest point between the two ships;

[0043] Compare the distance of the closest point with a preset distance safety threshold to obtain a first comparison value, and compare the time of the closest point with a preset time safety threshold to obtain a second comparison value;

[0044] Calculate the collision safety coefficient through a non-linear logarithmic function according to the first comparison value and the second comparison value.

[0045] Optionally, the coefficient module calculates the collision safety coefficient and the grounding safety coefficient of the target ship based on the port model, the ship model, and the foggy weather conditions. The calculation of the grounding safety coefficient includes:

[0046] Monitor the real-time water depth and draft data of the target ship, and obtain the under-keel clearance;

[0047] Obtain the coordinate deviation between the current position and the planned route position of the target ship, and calculate the course deviation;

[0048] Compare the under-keel clearance with a preset water depth safety threshold to obtain a third comparison value, and compare the course deviation with a preset deviation safety threshold to obtain a fourth comparison value;

[0049] Calculate the grounding safety coefficient through an exponential function according to the third comparison value and the fourth comparison value.

[0050] Optionally, the decision-making module compares the collision safety coefficient and the grounding safety coefficient with preset thresholds respectively, and generates decision texts corresponding to risk-free, medium-risk, or high-risk according to the comparison results, including:

[0051] If both the collision safety coefficient and the grounding safety coefficient are greater than or equal to the preset threshold, generate a risk-free decision and maintain navigation;

[0052] If the collision safety coefficient is less than the preset threshold and the grounding safety coefficient is greater than or equal to the preset threshold, generate a medium-risk decision and generate a detour route;

[0053] If the collision safety coefficient is greater than or equal to the preset threshold and the grounding safety coefficient is less than the preset threshold, generate a medium-risk decision and correct the course;

[0054] If both the collision safety coefficient and the grounding safety coefficient are less than the preset threshold, generate a high-risk decision and execute an emergency stop and anchoring.

[0055] The beneficial effects of this application are as follows:

[0056] This application provides a verification method for an intelligent decision-making system for port navigation in fog, including: obtaining point cloud data of the terrain and wharves of the target port through a lidar; obtaining the water depth of the waterway and the coordinates of obstacles according to the electronic nautical chart; constructing a port model based on the point cloud data, water depth of the waterway and coordinates of obstacles; obtaining the ship size parameters based on the target ship type drawing and constructing a ship model in combination with the AIS historical data; generating foggy weather conditions by grading and simulating light fog, medium fog and heavy fog; calculating the collision safety factor and grounding safety factor of the target ship based on the port model, ship model and foggy weather conditions; comparing the collision safety factor and grounding safety factor with preset thresholds respectively, and generating decision texts corresponding to no risk, medium risk or high risk according to the comparison results; counting the success rates of high-risk gear reduction, medium-risk gear reduction and low-risk gear reduction based on the decision texts, and calculating the decision rationality evaluation index through weighted calculation; generating a comprehensive fog navigation evaluation index based on the collision safety factor, grounding safety factor and decision rationality evaluation index; and generating an optimized decision instruction according to the comparison result between the comprehensive fog navigation evaluation index and the preset standard value and sending it to the manager's terminal. By constructing a highly realistic port environment, ship model and foggy weather conditions, combining collision and grounding risk assessment, and decision rationality assessment, this application generates a comprehensive fog navigation evaluation index, thereby optimizing navigation decisions and improving the safety and efficiency of port navigation in fog. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a schematic diagram of the verification process of the intelligent decision-making system for port navigation in fog in this application;

[0058] Figure 2 is a schematic diagram of the verification device of the intelligent decision-making system for port navigation in fog in this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it can be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, the embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0060] Please refer to Figure 1 as shown, this application provides a verification method for an intelligent decision-making system for port navigation in fog, including:

[0061] S101, obtaining point cloud data of the target port terrain and dock through laser radar; obtaining the channel water depth and obstacle coordinates according to the electronic nautical chart; and constructing a port model according to the point cloud data, channel water depth and obstacle coordinates;

[0062] Obtain point cloud data of the target port terrain and docks through LiDAR;

[0063] Obtain channel depth and obstacle coordinates based on electronic nautical charts;

[0064] A port model is constructed based on the point cloud data, channel water depth and obstacle coordinates, thereby establishing a real-scene three-dimensional grid model.

[0065] S102, obtaining ship size parameters based on the target ship type drawing, and building a ship model in combination with AIS historical data;

[0066] Through comprehensive analysis of target ship drawings and AIS historical data, a ship model is constructed and typical ship motion characteristics including turning radius and acceleration are extracted.

[0067] S103, generating foggy weather conditions by simulating light fog, moderate fog and dense fog in different levels;

[0068] Different levels of fog conditions include light fog, moderate fog and dense fog. The diffusion speed of the fog is dynamically adjusted, and AIS noise interference is generated at this time to simulate foggy days.

[0069] For example: the visibility range of light fog is 500 to 1000 meters, which is manifested by blurred outlines of distant buildings; the visibility range of moderate fog is 200 to 500 meters, which is manifested by reduced visibility of channel markers and diffused lights; the visibility range of heavy fog is less than 200 meters, which is manifested by blurred outlines of nearby ships and enhanced radar clutter. The diffusion speed of fog is based on the Navier-Stokes equation to simulate the flow of fog with wind speed.

[0070] Different levels of fog conditions are simulated during meteorological simulation instead of a single fog condition. This is because a single level of fog condition cannot fully test the performance of the system under different visibilities and fog conditions. At the same time, the fog navigation conditions in ports are complex and changeable, and the concentration, range and duration of fog are also different. By simulating different levels of fog conditions, the reliability and accuracy of system decision-making in different environments can be improved, effectively avoiding safety incidents such as collisions and groundings.

[0071] Generate AIS noise interference to interfere with navigation in fog. This is because AIS is the Automatic Identification System for Ships, which can automatically exchange information between ships, including key data such as the position, course, and speed of the ship. The concentration of fog will interfere with AIS. The greater the concentration of fog, the higher the degree of interference on AIS. Simulating noise interference can improve the accuracy of system verification.

[0072] S104. Calculate the collision safety factor and grounding safety factor of the target ship based on the port model, ship model, and foggy conditions.

[0073] The specific process of collision risk assessment is as follows:

[0074] The port uses the AIS system to collect the dynamic information of ships at different time nodes, covering the position, course, and speed, and then determines the velocity vectors and relative position vectors of the target ship and other ships.

[0075] Cross-multiply the relative position vector by taking the difference between the velocity vectors of the ship and other ships, and then perform a ratio calculation to obtain the distance to the closest point. The specific calculation formula is:

[0076]

[0077] Among them, DC represents the distance to the closest point. represents the relative position vector. represents the velocity vector of the target ship. represents the velocity vector of other ships.

[0078] As can be seen from the above formula, represents the relative velocity vector of the two ships. The smaller sinθ is, the closer the headings of the two ships are to parallel, and the higher the collision risk. The larger sinθ is, the closer the headings of the two ships are to perpendicular, and the lower the collision risk.

[0079] Perform a ratio calculation by taking the difference between the relative position vector and the velocity vectors of the ship and other ships to obtain the time to the closest point. The specific calculation formula is:

[0080]

[0081] Among them, TC represents the time to the closest point, and θ represents the course angle between the two ships. As can be seen from the above formula, the smaller cosθ is, the opposite the relative velocity direction and the relative position direction, and the lower the collision risk. The larger cosθ is, the closer the two ships are, and the higher the collision risk.

[0082] Calculate the collision safety coefficients for different levels of foggy weather conditions respectively based on the closest point distance and the closest point time combined with the collision safety thresholds. The collision safety thresholds include the distance safety threshold and the time safety threshold. The specific operation is to take the logarithm after adding 1 to the ratio of the closest point distance and the closest point time compared with the collision safety thresholds respectively, and obtain the collision safety coefficient, which is specifically expressed as:

[0083]

[0084] Among them, Cr represents the collision safety coefficient, represents the distance safety threshold, represents the time safety threshold.

[0085] It can be seen from the above formula that the closer the closest point distance and time are to their respective safety thresholds, the larger the result obtained by taking the logarithm after adding 1 to their ratio, that is, the larger the collision safety coefficient, which means the smaller the collision risk of the target ship.

[0086] The closest point distance and the closest point time are obtained separately because the closest point distance represents the minimum distance when two ships meet without changing their current headings and speeds, and the closest point time represents the time required to reach the closest point distance. A smaller closest point distance means a higher potential collision risk between two objects, while a smaller closest point time indicates that a collision event is about to occur and immediate action needs to be taken to avoid the collision.

[0087] The specific process of stranding risk assessment is as follows:

[0088] Apply the heaving amplitude to the target ship model, monitor the real-time water depth and ship draft at different timestamps, and then calculate using the formula for the under-keel clearance depth. The formula for the under-keel clearance depth is:

[0089] UD = Real-time water depth - Ship draft - Dynamic settlement

[0090] The dynamic settlement is the heaving correction caused by waves;

[0091] Obtain the current position and planned route position of the target ship through the electronic nautical chart, calculate the sum of squares of the coordinates respectively and then take the square root to get the course deviation. The specific calculation formula is:

[0092]

[0093] Among them, DD represents the course deviation, ( , ) represents the current position of the target ship, ( , ) represents the planned route position.

[0094] Based on the under-keel clearance and the deviation from the fairway, the grounding safety factors under different levels of foggy weather conditions are calculated respectively in combination with the grounding safety threshold, which includes the water depth safety threshold and the deviation safety threshold.

[0095] The grounding safety factor is obtained, and the specific calculation formula is:

[0096]

[0097] Where Ar represents the grounding safety factor, represents the water depth safety threshold, represents the deviation safety threshold.

[0098] It can be seen from the above formula that when the under-keel clearance is closer to the water depth safety threshold, the water depth deviation value is smaller; when the deviation from the fairway is closer to the deviation safety threshold, the deviation degree of the fairway is smaller. At this time, the grounding safety factor is larger and the grounding risk is lower.

[0099] The calculation of the under-keel clearance and the deviation from the fairway is crucial because the under-keel clearance provides a safety margin for the ship. In foggy navigation, the visibility is low and it is difficult for the crew to detect the shallow water area in advance. Therefore, sufficient under-keel clearance can greatly reduce the grounding risk. At the same time, the limited visibility makes the crew rely on navigation equipment to locate the course, and the increase in the deviation from the fairway increases the navigation difficulty.

[0100] S105. Compare the collision safety factor and the grounding safety factor with the preset thresholds respectively, and generate decision texts corresponding to no risk, medium risk or high risk according to the comparison results;

[0101] The method for obtaining the decision text is as follows:

[0102] Set a preset collision safety factor, compare the collision safety factor with the preset collision safety factor. If the collision safety factor is greater than or equal to the preset collision safety factor, it is displayed as no risk; otherwise, it is displayed as having a risk; Set a preset grounding safety factor, compare the grounding safety factor with the preset grounding safety factor. If the grounding safety factor is greater than or equal to the preset grounding safety factor, it is displayed as no risk; otherwise, it is displayed as having a risk;

[0103] Under different levels of foggy weather conditions, if neither collision nor grounding risk exists, the decision is determined as no risk and continue to sail; if only collision risk exists and no grounding risk, the decision is medium risk and it is necessary to avoid collision and plan a detour route; if only grounding risk exists and no collision risk, the decision is also medium risk and it is necessary to adjust the fairway; if both risks exist, the decision is high risk and it is necessary to immediately stop the ship and anchor in a safe water area.

[0104] Furthermore, integrate the decision-making text, which includes risk-free, medium-risk, and high-risk.

[0105] S106. Based on the decision-making text, statistically calculate the high-risk downshift success rate, medium-risk downshift success rate, and low-risk downshift success rate, and calculate the decision-making rationality evaluation index through weighted calculation;

[0106] Adjust the target ship model according to the decision-making text;

[0107] Statistically calculate the total number of scenarios with high risk in the decision-making text. At the same time, statistically calculate the scenarios where the risk level is reduced from high risk to medium risk, and calculate the high-risk downshift success rate. The specific calculation formula is:

[0108] P1 = Nd1 / Nt1 × 100%

[0109] Where P1 represents the high-risk downshift success rate, Nd1 represents the number of scenarios where the risk level is reduced from high risk to medium risk, and Nt1 represents the total number of scenarios with high risk in the decision-making text.

[0110] Statistically calculate the total number of scenarios with medium risk in the decision-making text. At the same time, statistically calculate the scenarios where the risk level is reduced from medium risk to low risk. Similarly, calculate the medium-risk downshift success rate. The specific calculation formula is:

[0111] P2 = Nd2 / Nt2 × 100%

[0112] Where P2 represents the medium-risk downshift success rate, Nd2 represents the number of scenarios where the risk level is reduced from medium risk to low risk, and Nt2 represents the total number of scenarios with medium risk in the decision-making text.

[0113] Statistically calculate the total number of scenarios with low risk in the decision-making text. At the same time, statistically calculate the scenarios where the risk level is reduced from low risk to risk-free. Similarly, calculate the low-risk downshift success rate. The specific calculation formula is:

[0114] P3 = Nd3 / Nt3 × 100%

[0115] Where P3 represents the low-risk downshift success rate, Nd3 represents the number of scenarios where the risk level is reduced from low risk to risk-free, and Nt3 represents the total number of scenarios with low risk in the decision-making text.

[0116] Perform weighted summation on the high-risk downshift success rate, medium-risk downshift success rate, and low-risk downshift success rate to obtain the decision-making rationality evaluation index, which is specifically expressed as:

[0117] P = λ1 × P1 + λ2 × P2 + λ3 × P3

[0118] Where P represents the decision-making rationality evaluation index, and λ1, λ2, and λ3 respectively represent the weight coefficients of the high-risk downshift success rate, medium-risk downshift success rate, and low-risk downshift success rate.

[0119] For example, the weight coefficients of the high-risk downshift success rate, medium-risk downshift success rate, and low-risk downshift success rate are 0.5, 0.3, and 0.2 respectively.

[0120] Calculating the high-risk, medium-risk, and low-risk downshift success rates can accurately evaluate the risk level of the navigation state and predict the trend of risk changes. This can not only help the system make more reasonable decisions and reduce the risk of misjudgment, but also, under foggy navigation conditions, when the ship faces challenges such as low visibility and high collision risk, the downshift success rate reflects the effectiveness of different navigation strategies in reducing risks. The foggy navigation decision-making system selects the best navigation strategy accordingly, such as adjusting the speed, changing the course, or emergency braking, to minimize the navigation risk. At the same time, it can evaluate the practicality and applicability of the foggy navigation decision-making system under different navigation conditions and ship types, and improve the safety of foggy navigation.

[0121] S107. Generate a comprehensive foggy navigation evaluation index based on the collision safety factor, grounding safety factor, and decision rationality evaluation index;

[0122] The process of the comprehensive foggy navigation evaluation is as follows:

[0123] Perform weighted summation based on the risk assessment results to obtain the driving safety evaluation index, which is specifically expressed as:

[0124]

[0125] Among them, R represents the driving safety evaluation index, Cr represents the collision safety factor, Ar represents the grounding safety factor, and η1 and η2 respectively represent the weights of the grounding safety factor and the collision safety factor.

[0126] For example, the weight coefficients of the collision safety factor and the grounding safety factor are 0.7 and 0.3 respectively.

[0127] Establish a comprehensive foggy navigation evaluation model, and import the driving safety evaluation index and the decision rationality evaluation index into the comprehensive foggy navigation evaluation model, which is specifically expressed as:

[0128]

[0129] Among them, Z represents the comprehensive foggy navigation evaluation index, P represents the decision rationality evaluation index, R represents the driving safety evaluation index, represents the communication attenuation evaluation index, 、 、 are the proportionality coefficients corresponding to the evaluation indexes, >0, >0, >0, is the fog concentration corresponding to different levels of foggy weather conditions.

[0130] For example, when the foggy weather condition is light fog, = , at this time = , when the foggy weather condition is moderate fog, = , at this time = , when the foggy weather condition is thick fog, = , at this time = , and > > . represents the light fog concentration, represents the moderate fog concentration, represents the thick fog concentration, is the communication attenuation evaluation index, represents the communication attenuation evaluation index under light fog conditions, represents the communication attenuation evaluation index under moderate fog conditions, represents the communication attenuation evaluation index under thick fog conditions.

[0131] The communication attenuation evaluation index is fitted by simulating the AIS noise interference under different levels of foggy weather conditions and combining the visibility adjustment parameters corresponding to the foggy weather conditions, which can more realistically reproduce the actual navigation environment. This makes the testing and evaluation of the port fog navigation intelligent decision-making system closer to reality and ensures that the system can operate effectively under various foggy conditions. When evaluating the safety of ship navigation, the port fog navigation intelligent decision-making system improves the reliability of the decision-making judgment for safe navigation by identifying the collision risk and grounding risk in the navigation environment. When the decision-making rationality evaluation index is relatively high, the decision-making success rate of the system is higher under different levels of foggy weather conditions, effectively reducing the navigation risk and improving the fog navigation efficiency. And improving the reliability of the decision-making judgment for safe fog navigation, and at the same time when the decision-making rationality evaluation index is relatively high, it means that the port fog navigation intelligent decision-making system has a higher decision-making success rate under different levels of foggy weather conditions, and by making corresponding decisions for different situations, the navigation risk is minimized to the greatest extent and the fog navigation efficiency is improved.

[0132] S108. Generate an optimized decision-making instruction according to the comparison result between the comprehensive fog navigation evaluation index and the preset standard value, and send it to the management personnel terminal;

[0133] The process of optimizing the navigation decision-making is as follows:

[0134] Based on the comprehensive fog navigation evaluation index, set the comprehensive fog navigation standard value Zc. Compare the comprehensive fog navigation evaluation index with the comprehensive fog navigation standard value. If Zc is greater than Z, it indicates that the comprehensive fog navigation evaluation index is lower than the standard value. At this time, the fog navigation decision is unreasonable and needs to be optimized and adjusted. If Zc is equal to Z, the comprehensive fog navigation evaluation index is equal to the standard value. At this time, the fog navigation decision is relatively balanced, but still needs further verification. If Zc is less than Z, the comprehensive fog navigation evaluation index is higher than the standard value. At this time, the fog navigation decision is reasonable and the generated navigation decision can be continued to be executed.

[0135] The decision feedback automatically conducts feedback on the optimized navigation decision through the manager's terminal, including the foggy conditions, decision text, and optimized navigation decision at this time, thereby generating a fog navigation decision inspection report. The manager views the navigation decision through the fog navigation decision inspection report. The preset summary methods include any one of report summary, picture summary, and chart summary.

[0136] As Figure 2 shown, the present application also provides a verification device for a port fog navigation intelligent decision-making system, including:

[0137] A port module 201, which obtains the point cloud data of the target port terrain and the wharf through a lidar; obtains the channel water depth and the coordinates of obstacles according to the electronic nautical chart; constructs a port model based on the point cloud data, channel water depth, and obstacle coordinates;

[0138] A ship module 202, which obtains the ship size parameters based on the target ship type drawing and constructs a ship model in combination with the AIS historical data;

[0139] A weather module 203, which generates foggy conditions by grading and simulating light fog, medium fog, and thick fog;

[0140] A coefficient module 204, which calculates the collision safety coefficient and the grounding safety coefficient of the target ship based on the port model, ship model, and foggy conditions;

[0141] A decision module 205, which compares the collision safety coefficient and the grounding safety coefficient with the preset thresholds respectively, and generates decision texts corresponding to no risk, medium risk, or high risk according to the comparison results;

[0142] An index module 206, which statistically calculates the high-risk downshift success rate, medium-risk downshift success rate, and low-risk downshift success rate based on the decision text, and calculates the decision rationality evaluation index through weighted calculation;

[0143] A comprehensive module 207, which generates a comprehensive fog navigation evaluation index based on the collision safety coefficient, grounding safety coefficient, and decision rationality evaluation index;

[0144] The management module 208 generates an optimization decision instruction according to the comparison result between the comprehensive fog navigation assessment index and the preset standard value, and sends it to the manager's terminal.

[0145] Optionally, the ship module obtains the ship size parameters based on the target ship type drawing, and constructs a ship model in combination with the AIS historical data, including:

[0146] Obtain the ship size parameters based on the target ship type drawing, and establish a ship motion characteristic model by combining the turning radius and acceleration of the ship extracted from the AIS historical data.

[0147] Furthermore, the coefficient module calculates the collision safety coefficient and the grounding safety coefficient of the target ship based on the port model, the ship model and the foggy weather conditions. The calculation of the collision safety coefficient includes:

[0148] Obtain the velocity vectors and relative position vectors of the target ship and other ships, and calculate the distance and time of the closest point between the two ships;

[0149] Compare the distance of the closest point with a preset distance safety threshold to obtain a first comparison value, and compare the time of the closest point with a preset time safety threshold to obtain a second comparison value;

[0150] Calculate the collision safety coefficient through a non-linear logarithmic function according to the first comparison value and the second comparison value.

[0151] Furthermore, the coefficient module calculates the collision safety coefficient and the grounding safety coefficient of the target ship based on the port model, the ship model and the foggy weather conditions. The calculation of the grounding safety coefficient includes:

[0152] Monitor the real-time water depth and draft data of the target ship, and obtain the under-keel clearance;

[0153] Obtain the coordinate deviation between the current position and the planned route position of the target ship, and calculate the course deviation;

[0154] Compare the under-keel clearance with a preset water depth safety threshold to obtain a third comparison value, and compare the course deviation with a preset deviation safety threshold to obtain a fourth comparison value;

[0155] Calculate the grounding safety coefficient through an exponential function according to the third comparison value and the fourth comparison value.

[0156] Furthermore, the decision module compares the collision safety coefficient and the grounding safety coefficient with the preset thresholds respectively, and generates decision texts corresponding to no risk, medium risk or high risk according to the comparison results, including:

[0157] If both the collision safety factor and the grounding safety factor are greater than or equal to a preset threshold, generate a risk-free decision and maintain navigation;

[0158] If the collision safety factor is less than the preset threshold and the grounding safety factor is greater than or equal to the preset threshold, generate a medium-risk decision and generate a detour route;

[0159] If the collision safety factor is greater than or equal to the preset threshold and the grounding safety factor is less than the preset threshold, generate a medium-risk decision and correct the waterway;

[0160] If both the collision safety factor and the grounding safety factor are less than the preset threshold, generate a high-risk decision and execute an emergency stop and anchoring.

[0161] The above description of the embodiments is to enable those of ordinary skill in the art to understand and apply the present invention. It is obvious that those skilled in the art can easily make various modifications to the above embodiments and apply the general principles described herein to other embodiments without creative efforts. Therefore, the present invention is not limited to the above embodiments, and all improvements and modifications made by those skilled in the art based on the disclosure of the present invention should be within the protection scope of the present invention.

Claims

1. A verification method for an intelligent decision-making system for fog navigation in ports, characterized in that Including: Obtaining the point cloud data of the target port terrain and the wharf through lidar; obtaining the channel water depth and obstacle coordinates according to the electronic nautical chart; Constructing a port model based on the point cloud data, channel water depth and obstacle coordinates; Obtaining ship size parameters based on the target ship type drawing and constructing a ship model in combination with AIS historical data; Generating foggy weather conditions by classifying and simulating light fog, moderate fog and thick fog; Calculating the collision safety factor and grounding safety factor of the target ship based on the port model, ship model and foggy weather conditions; Comparing the collision safety factor and grounding safety factor with preset thresholds respectively, and generating decision texts corresponding to no risk, medium risk or high risk according to the comparison results; Statistically calculating the high-risk downshift success rate, medium-risk downshift success rate and low-risk downshift success rate based on the decision text, and calculating the decision rationality evaluation index through weighted calculation; Generating a comprehensive fog navigation evaluation index based on the collision safety factor, grounding safety factor and decision rationality evaluation index; Generating an optimized decision instruction according to the comparison result between the comprehensive fog navigation evaluation index and the preset standard value and sending it to the manager's terminal.

2. The verification method of an intelligent decision-making system for port navigation in fog according to claim 1, wherein, Obtaining ship size parameters based on the target ship type drawing and constructing a ship model in combination with AIS historical data, including: Obtaining ship size parameters based on the target ship type drawing, and establishing a ship motion characteristic model by combining the turning radius and acceleration of the ship extracted from AIS historical data.

3. A verification method for an intelligent decision-making system for port navigation in fog according to claim 1, characterized in that, In calculating the collision safety factor and grounding safety factor of the target ship based on the port model, ship model and foggy weather conditions, the calculation of the collision safety factor includes: Obtaining the velocity vectors and relative position vectors of the target ship and other ships, and calculating the closest point distance and closest point time between the two ships; Comparing the closest point distance with a preset distance safety threshold to obtain a first comparison value, and comparing the closest point time with a preset time safety threshold to obtain a second comparison value; Calculating the collision safety factor through a non-linear logarithmic function according to the first comparison value and the second comparison value.

4. A verification method for an intelligent decision-making system for port navigation in fog according to claim 1, characterized in that In calculating the collision safety factor and grounding safety factor of the target ship based on the port model, ship model and foggy weather conditions, the calculation of the grounding safety factor includes: Monitoring the real-time water depth and draft data of the target ship to obtain the under-keel clearance depth; Obtaining the coordinate deviation between the current position and the planned route position of the target ship, and calculating the channel deviation degree; Comparing the under-keel clearance depth with a preset water depth safety threshold to obtain a third comparison value, and comparing the channel deviation degree with a preset deviation safety threshold to obtain a fourth comparison value; Calculating the grounding safety factor through an exponential function according to the third comparison value and the fourth comparison value.

5. The verification method of an intelligent decision-making system for port navigation in fog according to claim 1, wherein, Comparing the collision safety factor and grounding safety factor with preset thresholds respectively, and generating decision texts corresponding to no risk, medium risk or high risk according to the comparison results, including: If both the collision safety factor and the grounding safety factor are greater than or equal to the preset threshold, generating a no-risk decision and maintaining navigation; If the collision safety factor is less than the preset threshold and the grounding safety factor is greater than or equal to the preset threshold, generating a medium-risk decision and generating a detour route; If the collision safety factor is greater than or equal to the preset threshold and the grounding safety factor is less than the preset threshold, generate a medium-risk decision and correct the waterway; If both the collision safety factor and the grounding safety factor are less than the preset threshold, generate a high-risk decision and execute an emergency stop and anchoring.

6. An intelligent decision-making system verification device for port navigation in fog, characterized in that, It includes: A port module that obtains the point cloud data of the target port terrain and the wharf through lidar; Obtain the water depth of the waterway and the coordinates of obstacles according to the electronic nautical chart; construct a port model based on the point cloud data, water depth of the waterway and coordinates of obstacles; A ship module that obtains the ship size parameters based on the target ship type drawing and constructs a ship model in combination with the AIS historical data; A weather module that generates foggy weather conditions by grading and simulating light fog, moderate fog, and heavy fog; A coefficient module that calculates the collision safety factor and the grounding safety factor of the target ship based on the port model, ship model, and foggy weather conditions; A decision-making module that compares the collision safety factor and the grounding safety factor with the preset thresholds respectively, and generates decision texts corresponding to no risk, medium risk, or high risk according to the comparison results; An index module that statistically calculates the high-risk downshift success rate, medium-risk downshift success rate, and low-risk downshift success rate based on the decision text, and calculates the decision rationality evaluation index through weighted calculation; A comprehensive module that generates a comprehensive fog navigation evaluation index based on the collision safety factor, grounding safety factor, and decision rationality evaluation index; A management module that generates an optimization decision instruction according to the comparison result between the comprehensive fog navigation evaluation index and the preset standard value and sends it to the manager's terminal.

7. The verification device for an intelligent decision-making system for port navigation in fog according to claim 6, characterized in that, The ship module obtains the ship size parameters based on the target ship type drawing and constructs a ship model in combination with the AIS historical data, including: Obtain the ship size parameters based on the target ship type drawing, and establish a ship motion characteristic model by combining the turning radius and acceleration of the ship extracted from the AIS historical data.

8. An apparatus for verifying an intelligent decision-making system for port navigation in fog according to claim 6, characterized in that, In the calculation of the collision safety factor and the grounding safety factor of the target ship by the coefficient module based on the port model, ship model, and foggy weather conditions, the calculation of the collision safety factor includes: Obtain the velocity vectors and relative position vectors of the target ship and other ships, and calculate the closest point distance and closest point time between the two ships; Compare the closest point distance with the preset distance safety threshold to obtain a first comparison value, and compare the closest point time with the preset time safety threshold to obtain a second comparison value; Calculate the collision safety factor through a non-linear logarithmic function according to the first comparison value and the second comparison value.

9. The verification device for an intelligent decision-making system for port navigation in fog according to claim 6, characterized in that, In the calculation of the collision safety factor and the grounding safety factor of the target ship by the coefficient module based on the port model, ship model, and foggy weather conditions, the calculation of the grounding safety factor includes: Monitor the real-time water depth and draft data of the target ship, and obtain the under-keel clearance; Obtain the coordinate deviation between the current position and the planned route position of the target ship, and calculate the waterway deviation degree; Compare the under-keel clearance with the preset water depth safety threshold to obtain a third comparison value, and compare the waterway deviation degree with the preset deviation safety threshold to obtain a fourth comparison value; Calculate the grounding safety factor through an exponential function according to the third comparison value and the fourth comparison value.

10. The verification device for a port fog navigation intelligent decision-making system according to claim 6, characterized in that, The decision-making module compares the collision safety factor and the grounding safety factor with preset thresholds respectively, and generates decision texts corresponding to no risk, medium risk or high risk according to the comparison results, including: If both the collision safety factor and the grounding safety factor are greater than or equal to the preset threshold, generate a no-risk decision and maintain navigation; If the collision safety factor is less than the preset threshold and the grounding safety factor is greater than or equal to the preset threshold, generate a medium-risk decision and generate a detour route; If the collision safety factor is greater than or equal to the preset threshold and the grounding safety factor is less than the preset threshold, generate a medium-risk decision and correct the waterway; If both the collision safety factor and the grounding safety factor are less than the preset threshold, generate a high-risk decision and execute an emergency stop and anchoring.

Images