An AI-based DCS ship control system

Abstract

This invention discloses an artificial intelligence-based DCS (Distributed Control System) for ships, relating to the field of artificial intelligence technology. It includes a target record extraction module for acquiring collision records and extracting target records from them based on an automatic identification system; a warning area division module for determining warning areas based on target records and target areas on bridges; a scatter plot creation module for acquiring the planned trajectory of the vessel to be detected passing through the warning area, as well as historical actual route trajectories, extracting characteristic routes, and creating a scatter plot; and a warning notification module for obtaining warning values ​​based on the location of the vessel to be detected and the created scatter plot, and providing timely notifications to the vessel. This invention analyzes historical collision records to obtain warning values ​​corresponding to deviations from the route by the vessel to be detected, and provides timely notifications to relevant personnel, thus improving the reliability of collision detection and reducing the probability of collisions between ships and bridges.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to a DCS ship control system based on artificial intelligence. Background Technology

[0002] DCS is an abbreviation for Distributed Control System. It is a comprehensive system for control, monitoring, and management. Applying DCS to ship control helps improve ship performance in multiple dimensions, including safety, economy, operational efficiency, and convenience. With the booming development of the shipping industry, the size and carrying capacity of ships are constantly increasing. Due to the poor maneuverability and high inertia of large ships, the risk of collisions with bridges increases when ships navigate in bridge-adjacent waters. Although passive collision avoidance methods such as installing floating barriers and protective piles around bridge piers exist to warn ships, these methods not only occupy waterways but also have low levels of intelligence, require real-time monitoring by ship control personnel, and have limited protective capabilities, making it difficult to cope with the collision risks of modern large ships. Summary of the Invention

[0003] The purpose of this invention is to provide an artificial intelligence-based DCS ship control system to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] An artificial intelligence-based DCS ship control system includes a target record extraction module, a warning area division module, a scatter plot establishment module, and a warning prompt module;

[0006] Target record extraction module: used to obtain collision records of collision accidents between ships and bridges in the past; deploy an automatic identification system on the ship to obtain the actual trajectory of the ship during transportation corresponding to the collision record, as well as the planned trajectory preset according to the ship's origin and destination, and analyze the actual trajectory and the planned trajectory to extract the target record from the collision record;

[0007] Warning area division module: It is used to obtain the warning area in the planned trajectory of the ship to be detected based on the collision position corresponding to the target record and the target area on the bridge that restricts the entry and exit of ships.

[0008] Scatter plot creation module: used to obtain the planned trajectory of the vessel to be detected passing through the warning area, as well as several actual route trajectories of historical vessels passing through the warning area, and extract feature routes from the actual route trajectories; based on the heading of the vessel corresponding to the feature route and the weight of the cargo loaded, a scatter plot of the relationship between yaw angle and vessel weight is created.

[0009] Early warning module: It is used to monitor the warning value of the vessel under inspection in real time when it is sailing along the planned trajectory based on the location of the vessel under inspection and the established scatter plot, and to prompt the relevant control personnel of the vessel to take relevant actions in a timely manner based on the warning value.

[0010] Furthermore, the target record extraction module includes a collision record acquisition unit and a target record extraction unit;

[0011] Collision record acquisition unit: This unit acquires collision records of several vessels of the same type as the vessel to be detected that have historically collided with the bridge; it captures panoramic images of the bridge, extracts the collision time, collision location, and collision vessel number corresponding to each collision record, and, based on the automatic identification system deployed on the vessels, identifies the collision vessel S corresponding to a given collision record R. R The actual trajectory T during transportation R A and the actual trajectory T R A The collision position C corresponding to R is recorded in the middle. R Starting from the ship S R The opposite course, along the actual trajectory T R A The distance L1 forward is used as the detection distance, and the corresponding time period D and the ship S are obtained. R The actual trajectory T within time period D D A ;

[0012] The Automatic Identification System (AIS) is capable of obtaining information such as a ship's heading, position, and speed during navigation.

[0013] Obtain according to ship S R The starting point and destination are determined in advance by relevant personnel using navigation tools along a planned trajectory. The maximum width B of the vessel is obtained, and the range with length k on both sides of the planned trajectory is taken as the vessel's S. R The safe trajectory range, where 2k>B.

[0014] Furthermore, the target record extraction unit is used to obtain the ship's S based on the automatic identification system. R The actual position C at time t within time period D. t And the actual heading H1; obtain the distance C from the actual position in the planned trajectory. t The nearest trajectory position P t And will be based on trajectory position P t Starting from point S, respectively according to ship S RThe forward and reverse headings, the corresponding positions along the planned trajectory L2 distance forward, are taken as the first position P1 and the second position P2. The direction from the second position P2 to the first position P1 is taken as the predicted heading H2. The angle between the actual heading H1 and the predicted heading H2 is taken as the characteristic angle at time t.

[0015] If the actual location C t Within the safe trajectory range, the deviation characteristic value at time t is taken as 0, if the actual position C t Location C is outside the safe trajectory range. t The length closest to the safe trajectory range is used as the deviation characteristic value at time t: Divide the time period D evenly into several sub-time periods, and sum the deviation characteristic values ​​at each time point within a sub-time period to obtain the average characteristic value of that sub-time period. Then, calculate the variance S based on the average characteristic values ​​of all sub-time periods. D If the variance S D If the variance is greater than the preset variance threshold and the feature angle at each moment in time period D is less than the preset angle threshold, then the collision record R is taken as the target record, and then all target records in the collision record are extracted.

[0016] When a collision occurs even though a vessel gradually deviates from its course before the collision but its direction of travel is similar to the planned direction, this phenomenon reveals a systemic risk in vessel safety management. The area recorded in this case is an area prone to accidents. Since the judgment in this scheme is based on variance, the average characteristic value of the sub-period corresponding to the collision is relatively large (the vessel deviates from its course at the time of the collision), and the average characteristic value of the sub-period corresponding to the non-collision period is relatively small. This indicates that the situation is consistent with the above, so variance can be used for judgment.

[0017] Furthermore, the early warning area division module includes early warning area division units;

[0018] Warning area division unit: used to obtain the collision position in the target record, and take the area with the collision position as the center and the radius of r as the first warning area; obtain the target area on each bridge based on the historical division of the floating gate and the protective pile, which restricts the entry and exit of ships, and take the first warning area and the target area as the warning area in the planning trajectory of the ship to be detected.

[0019] Furthermore, the scatter plot creation module includes a feature route extraction unit and a scatter plot creation unit;

[0020] Feature route extraction unit: used to obtain a certain warning area A in the planned trajectory of the vessel to be detected, and take the warning area A as the starting point, and follow the opposite direction of the vessel to be detected along the planned trajectory for a distance L3, as the trajectory to be detected;

[0021] Obtain the navigation records of several vessels of the same type as the vessel to be detected that passed through warning area A without collision; extract the vessel S corresponding to a certain navigation record M. M And the actual flight path T M Several target points are randomly obtained from the trajectory to be detected, and then the actual flight path T is obtained. M The point closest to a target point is identified, and its distance is used as the feature distance of that target point. For each feature distance, the variance and mean feature distance are calculated. If the variance is less than a preset variance threshold and the mean feature distance is less than a preset distance value, then the actual flight path T is... M As characteristic routes, several characteristic routes are obtained.

[0022] Furthermore, the scatter plot building unit is used to obtain the position point P of the ship to be detected at a certain time n. n In a certain characteristic route T0, the distance from position point P is obtained. n The nearest position point is P0, and the ship corresponding to a certain characteristic route T0 is taken as S0. The time of ship S0 at position point P0 is taken as t0. The prediction duration is set as DP. The position point P1 of ship S0 after time t0 for a duration of DP is obtained. The angle between the heading V0 of ship S0 at position point P0 and the heading V1 of ship S0 at position point P1 is taken as the yaw angle. The heading V0 is rotated 180 degrees clockwise and counterclockwise respectively to obtain the first range and the second range. If the heading V1 is in the first range, the yaw angle is set to be greater than 0. If the heading V1 is in the second range, the yaw angle is set to be less than 0. According to the actual ship weight of ship S0 at time t0, the coordinate point corresponding to ship S0 is marked in a scatter plot of the yaw angle changing with the ship weight at a certain time n, and then several coordinate points in the scatter plot are marked.

[0023] Furthermore, the early warning module includes a location analysis early warning unit and an early warning notification unit;

[0024] Position analysis and early warning unit: used to obtain the actual ship weight wgt and position point P of the ship to be detected at a certain time q. q Actual heading H q and speed Y q If the location point P q If the location point P is outside the safe trajectory range, a warning will be issued; q Within the safe trajectory range, the predicted heading H of the vessel to be detected at a certain time q is obtained based on the target record extraction module. f and the characteristic included angle V q If the characteristic angle V q If the angle exceeds the preset threshold, an early warning will be issued.

[0025] Furthermore, the early warning unit is used to determine if location point P... q Within the safe trajectory range and the characteristic angle V q If the yaw angle is not greater than a preset threshold, obtain a scatter plot at time q, and find the coordinates of the X ship weights that have the smallest difference from the weight wgt in the scatter plot. Then, average the yaw angles corresponding to the X coordinates to obtain the average yaw angle G. If G > 0, proceed along the actual heading H. q Rotate clockwise in a direction of magnitude G, with position P q Starting from the point, proceed forward DP×Y q The endpoint is taken as the target location; if G < 0, the target location is determined along the actual heading H. q Rotate counterclockwise in a direction of magnitude G, with position P. q Starting from the point, proceed forward DP×Y q The endpoint is taken as the target location point; then the location point in the planned trajectory that is closest to the target location point is obtained, and the corresponding distance value is denoted as L.

[0026] Therefore, the warning value Z for the ship to be detected at time q is obtained. q =W1×(1-e -L )+W2×(1-e -|G| ), where W1 and W2 are the first and second weights, respectively, and are based on the warning value Z. q The system issues warnings to vessels under inspection and alerts relevant personnel to take timely action.

[0027] In this scheme, the warning value represents the degree of deviation of the ship's position over a future period. As is common sense, when a ship does not travel along a pre-set suitable trajectory, it is extremely easy for the planned trajectory in the target area to deviate, which may lead to bridge collisions. Therefore, this scheme analyzes the ship's travel situation to obtain the warning value between the ship and the preset planned trajectory, and issues early warnings to help relevant personnel make judgments and make corrections in advance, thus reducing the risk of collision when passing through the warning area.

[0028] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides an artificial intelligence-based DCS ship control system, including a target record extraction module for acquiring collision records and extracting target records from the collision records based on an automatic identification system; a warning area division module for obtaining warning areas based on target records and target areas on bridges; a scatter plot establishment module for acquiring the planned trajectory of the vessel to be detected passing through the warning area, as well as historical actual route trajectories, extracting characteristic routes, and establishing a scatter plot; and a warning prompt module for obtaining warning values ​​based on the location of the vessel to be detected and the established scatter plot, and promptly prompting the vessel to be detected. This invention, by analyzing historical collision records, obtains warning values ​​corresponding to the deviation of the vessel to be detected from its route and promptly prompts relevant personnel, which helps improve the reliability of collision detection and reduce the probability of collisions between ships and bridges. Attached Figure Description

[0029] Figure 1 This is a structural diagram of a DCS ship control system based on artificial intelligence according to the present invention. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] Example: Figure 1 As shown, the present invention provides a DCS ship control system technical solution based on artificial intelligence, including a target record extraction module, a warning area division module, a scatter plot establishment module, and a warning prompt module.

[0032] Target record extraction module: used to obtain collision records of collision accidents between ships and bridges in the past; deploy an automatic identification system on the ship to obtain the actual trajectory of the ship during transportation corresponding to the collision record, as well as the planned trajectory preset according to the ship's origin and destination, and analyze the actual trajectory and the planned trajectory to extract the target record from the collision record;

[0033] The target record extraction module includes a collision record acquisition unit and a target record extraction unit;

[0034] Collision record acquisition unit: This unit acquires collision records of several vessels of the same type as the vessel to be detected that have historically collided with the bridge; it captures panoramic images of the bridge, extracts the collision time, collision location, and collision vessel number corresponding to each collision record, and, based on the automatic identification system deployed on the vessels, identifies the collision vessel S corresponding to a given collision record R. R The actual trajectory T during transportation R A and the actual trajectory T R A The collision position C corresponding to R is recorded in the middle. R Starting from the ship S R The opposite course, along the actual trajectory T R A The distance L1 forward is used as the detection distance, and the corresponding time period D and the ship S are obtained. R The actual trajectory T within time period D D A ;

[0035] Obtain according to ship S R The starting point and destination are determined in advance by relevant personnel using navigation tools along a planned trajectory. The maximum width B of the vessel is obtained, and the range with length k on both sides of the planned trajectory is taken as the vessel's S. R The safe trajectory range, where 2k>B.

[0036] Target record extraction unit: used to obtain the ship's S based on the automatic identification system. R The actual position C at time t within time period D. t And the actual heading H1; obtain the distance C from the actual position in the planned trajectory. t The nearest trajectory position P t And will be based on trajectory position P t Starting from point S, respectively according to ship S R The forward and reverse headings, the corresponding positions along the planned trajectory L2 distance forward, are taken as the first position P1 and the second position P2. The direction from the second position P2 to the first position P1 is taken as the predicted heading H2. The angle between the actual heading H1 and the predicted heading H2 is taken as the characteristic angle at time t.

[0037] If the actual location C t Within the safe trajectory range, the deviation characteristic value at time t is taken as 0, if the actual position C t Location C is outside the safe trajectory range. tThe length closest to the safe trajectory range is used as the deviation characteristic value at time t: Divide the time period D evenly into several sub-time periods, and sum the deviation characteristic values ​​at each time point within a sub-time period to obtain the average characteristic value of that sub-time period. Then, calculate the variance S based on the average characteristic values ​​of all sub-time periods. D If the variance S D If the variance is greater than the preset variance threshold and the feature angle at each moment in time period D is less than the preset angle threshold, then the collision record R is taken as the target record, and then all target records in the collision record are extracted.

[0038] When a collision occurs even though a vessel gradually deviates from its course before the collision but its direction of travel is similar to the planned direction, this phenomenon reveals a systemic risk in vessel safety management. The area recorded in this case is an area prone to accidents. Since the judgment in this scheme is based on variance, the average characteristic value of the sub-period corresponding to the collision is relatively large (the vessel deviates from its course at the time of the collision), and the average characteristic value of the sub-period corresponding to the non-collision period is relatively small. This indicates that the situation is consistent with the above, so variance can be used for judgment.

[0039] Warning area division module: It is used to obtain the warning area in the planned trajectory of the ship to be detected based on the collision position corresponding to the target record and the target area on the bridge that restricts the entry and exit of ships.

[0040] The early warning area division module includes early warning area division units;

[0041] Warning area division unit: used to obtain the collision position in the target record, and take the area with the collision position as the center and the radius of r as the first warning area; obtain the target area on each bridge based on the historical division of the floating gate and the protective pile, which restricts the entry and exit of ships, and take the first warning area and the target area as the warning area in the planning trajectory of the ship to be detected.

[0042] Scatter plot creation module: used to obtain the planned trajectory of the vessel to be detected passing through the warning area, as well as several actual route trajectories of historical vessels passing through the warning area, and extract feature routes from the actual route trajectories; based on the heading of the vessel corresponding to the feature route and the weight of the cargo loaded, a scatter plot of the relationship between yaw angle and vessel weight is created.

[0043] The scatter plot creation module includes a feature route extraction unit and a scatter plot creation unit;

[0044] Feature route extraction unit: used to obtain a certain warning area A in the planned trajectory of the vessel to be detected, and take the warning area A as the starting point, and follow the opposite direction of the vessel to be detected along the planned trajectory for a distance L3, as the trajectory to be detected;

[0045] Obtain the navigation records of several vessels of the same type as the vessel to be detected that passed through warning area A without collision; extract the vessel S corresponding to a certain navigation record M. M And the actual flight path T M Several target points are randomly obtained from the trajectory to be detected, and then the actual flight path T is obtained. M The point closest to a target point is identified, and its distance is used as the feature distance of that target point. For each feature distance, the variance and mean feature distance are calculated. If the variance is less than a preset variance threshold and the mean feature distance is less than a preset distance value, then the actual flight path T is... M As characteristic routes, several characteristic routes are obtained.

[0046] Scatter plot building unit: used to obtain the position point P of the ship to be detected at a certain time n. n In a certain characteristic route T0, the distance from position point P is obtained. n The nearest position point is P0, and the ship corresponding to a certain characteristic route T0 is taken as S0. The time of ship S0 at position point P0 is taken as t0. The prediction duration is set as DP. The position point P1 of ship S0 after time t0 for a duration of DP is obtained. The angle between the heading V0 of ship S0 at position point P0 and the heading V1 of ship S0 at position point P1 is taken as the yaw angle. The heading V0 is rotated 180 degrees clockwise and counterclockwise respectively to obtain the first range and the second range. If the heading V1 is in the first range, the yaw angle is set to be greater than 0. If the heading V1 is in the second range, the yaw angle is set to be less than 0. According to the actual ship weight of ship S0 at time t0, the coordinate point corresponding to ship S0 is marked in a scatter plot of the yaw angle changing with the ship weight at a certain time n, and then several coordinate points in the scatter plot are marked.

[0047] Early warning module: It is used to monitor the warning value of the vessel under inspection in real time when it is sailing along the planned trajectory based on the location of the vessel under inspection and the established scatter plot, and to prompt the relevant control personnel of the vessel to take relevant actions in a timely manner based on the warning value.

[0048] The early warning module includes a location analysis early warning unit and an early warning notification unit;

[0049] Position analysis and early warning unit: used to obtain the actual ship weight wgt and position point P of the ship to be detected at a certain time q. q Actual heading H q and speed Y q If the location point P q If the location point P is outside the safe trajectory range, a warning will be issued; qWithin the safe trajectory range, the predicted heading H of the vessel to be detected at a certain time q is obtained based on the target record extraction module. f and the characteristic included angle V q If the characteristic angle V q If the angle exceeds the preset threshold, an early warning will be issued.

[0050] According to the target record extraction unit in the target record extraction module, the predicted heading H corresponding to time q is obtained. f and the characteristic angle V q The process is as follows: Obtain the distance point P in the planned trajectory of the vessel to be detected. q The nearest trajectory position P a And will be based on trajectory position P a Starting from the planned trajectory, the points corresponding to distances L2 forward along the planned trajectory, corresponding to the forward and reverse course of the vessel under test, are designated as the third position P3 and the fourth position P4. The direction from the fourth position P4 to the third position P3 is then used as the predicted course H. f and the actual heading H q With predicted heading H f The included angle between them is used as the characteristic included angle V. q .

[0051] Early warning unit: used to determine if location point P q Within the safe trajectory range and the characteristic angle V q If the yaw angle is not greater than a preset threshold, obtain a scatter plot at time q, and find the coordinates of the X ship weights that have the smallest difference from the weight wgt in the scatter plot. Then, average the yaw angles corresponding to the X coordinates to obtain the average yaw angle G. If G > 0, proceed along the actual heading H. q Rotate clockwise in a direction of magnitude G, with position P q Starting from the point, proceed forward DP×Y q The endpoint is taken as the target location; if G < 0, the target location is determined along the actual heading H. q Rotate counterclockwise in a direction of magnitude G, with position P. q Starting from the point, proceed forward DP×Y q The endpoint is taken as the target location point; then the location point in the planned trajectory that is closest to the target location point is obtained, and the corresponding distance value is denoted as L.

[0052] Therefore, the warning value Z for the ship to be detected at time q is obtained. q =W1×(1-e -L )+W2×(1-e -|G| ), where W1 and W2 are the first and second weights, respectively, and are based on the warning value Z. qThe system issues warnings to vessels under inspection and alerts relevant personnel to take timely action.

[0053] In this scheme, the warning value represents the degree of deviation of the ship's position over a future period. As is common sense, when a ship does not travel along a pre-set suitable trajectory, it is extremely easy for the planned trajectory in the target area to deviate, which may lead to bridge collisions. Therefore, this scheme analyzes the ship's travel situation to obtain the warning value between the ship and the preset planned trajectory, and issues early warnings to help relevant personnel make judgments and make corrections in advance, thus reducing the risk of collision when passing through the warning area.

[0054] Due to (1-e) -L ) and (1-e -|G| The values ​​of Z are all between 0 and 1, and represent the position deviation and heading deviation of the ship to be detected, respectively. In this embodiment, the sum of W1 and W2 is set to 1, W1 is 0.6, and W2 is 0.4. Therefore, in this embodiment, Z q When the value is between 0 and 0.5, the ship is in a relatively safe state, but vigilance is still required, and relevant personnel should continue to monitor the ship's various operating parameters; Z q When the value is between 0.5 and 0.8, the vessel is in a generally dangerous state and requires vigilance; relevant personnel should be advised to take preventative measures in advance. q When the value is between 0 and 0.5, the ship faces a high risk and must take immediate emergency measures to adjust its course as soon as possible to get it back to a safe route. The specific value should be determined based on the actual situation.

[0055] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. An artificial intelligence based DCS ship control system, characterized by, The system comprises a target record extraction module, a pre-warning area division module, a scatter plot establishment module and a pre-warning prompting module. The target record extraction module is used to obtain collision records of collision accidents between ships and bridges, to obtain actual trajectories of the ships in transportation corresponding to the collision records by deploying an automatic identification system on the ships, to obtain planned trajectories of the ships according to starting points and destinations of the ships, and to analyze the actual trajectories and the planned trajectories to extract target records in the collision records. The pre-warning area division module is used to obtain pre-warning areas in planned trajectories corresponding to the target record according to collision positions corresponding to the target records and target areas on the bridges for limiting the ships to enter or exit. The scatter plot establishment module is used to obtain planned trajectories of a to-be-detected ship passing through the pre-warning areas and a plurality of actual route trajectories of historical ships passing through the pre-warning areas, and to extract feature routes from the actual route trajectories. A scatter plot of a relationship between yaw angles and weights of the ships is established according to headings of the ships corresponding to the feature routes and weights of cargos loaded by the ships. The pre-warning prompting module is used to monitor pre-warning values of the to-be-detected ship in sailing according to the planned trajectories in real time according to positions of the to-be-detected ship and the established scatter plot, and to prompt relevant control personnel of the to-be-detected ship to handle relevant matters in time according to the pre-warning values. The pre-warning prompting module comprises a position analysis pre-warning unit and a pre-warning prompting unit. The position analysis early warning unit is used for acquiring the actual ship weight wgt, position point P q , actual heading H q and speed Y q of the ship to be detected at a certain time q, and giving a warning prompt if the position point P q is not within the safe track range. If the position point P q Within the safety trajectory range, according to the target record extraction module, the predicted heading H f corresponding to the ship to be detected at a certain time q is obtained q , and the characteristic angle V q is greater than the preset angle threshold, a warning prompt is performed. The early warning prompt unit is used for judging whether the position point P q is within the safety trajectory range and the feature included angle V q is not greater than a preset included angle threshold value, acquiring a scatter diagram corresponding to the time q, obtaining X coordinate points corresponding to the ship weights with the smallest weight difference wgt in the scatter diagram, and averaging the yaw angles corresponding to the X coordinate points to obtain an average yaw angle G; if G>0, the actual heading H q is rotated clockwise by the direction with the size G, and the position point P q is taken as a starting point, and a terminal point with a distance of DP×Y q is taken as a target position point. If G < 0, along H q clockwise rotation of size G, with the position point P q as the starting point, and the end point of DP x Y q as the target position point; and then the position point closest to the target position point in the planned trajectory is obtained, and the corresponding distance value is recorded as L; Further, the early warning value of the to-be-detected ship at time q is Z q = W1 x (1 - e -L ) + W2 x (1 - e -|G| ), wherein W1 and W2 are respectively a first weight value and a second weight value, and Z q The to-be-detected ship is given an early warning, and a ship-related control personnel is prompted to timely handle relevant matters.

2. An AI-based DCS ship control system according to claim 1, characterized in that, The target record extraction module comprises a collision record obtaining unit and a target record extraction unit. The collision record acquisition unit is used to acquire collision records of several ships of the same type as the to-be-detected ship and bridge accidents; take panoramic images of the bridge, extract the collision time, collision position and collision ship number corresponding to each collision record, and acquire the collision ship S corresponding to a certain collision record R according to an automatic identification system deployed on the ship R Actual trajectory T of the ship during transportation R A , and the actual trajectory T of the ship during transportation R A The actual trajectory T of the ship during transportation R The actual trajectory T of the ship during transportation R The actual trajectory T of the ship during transportation R A The actual trajectory T of the ship during transportation R The actual trajectory T of the ship during transportation D A The actual trajectory T of the ship during transportation Obtaining the starting point and destination of the ship S R , the planned trajectory determined in advance by the relevant personnel through navigation tools before transportation, obtaining the maximum width B of the ship, taking the range with the length of k on both sides of the planned trajectory as the safe trajectory range of the ship S R , where 2k>B.

3. An AI-based DCS ship control system according to claim 2, characterized in that, The target record extraction unit is used to obtain the ship S based on the automatic identification system. R The actual position C at time t within time period D. t And the actual heading H1; obtain the distance C from the actual position in the planned trajectory. t The nearest trajectory position P t And will be based on trajectory position P t Starting from the ship S, respectively R The forward and reverse headings, the corresponding positions along the planned trajectory at a distance L2, are designated as the first position P1 and the second position P2. The direction from the second position P2 to the first position P1 is designated as the predicted heading H2, and the angle between the actual heading H1 and the predicted heading H2 is designated as the characteristic angle at time t. If the actual position C t Within the safety trajectory range, the deviation characteristic value at time t is 0, if the actual position C t Not within the safety trajectory range, the distance between the position C t The closest length to the safety trajectory range is the deviation characteristic value at time t: evenly divide the time period D into several sub-periods, according to the deviation characteristic value at each time in a certain sub-period, add and average to obtain the average characteristic value of the certain sub-period, and then according to the average characteristic values of all sub-periods, calculate the variance S D If the variance S D is greater than the preset variance threshold and the characteristic angle at each time in the time period D is less than the preset angle threshold, the collision record R is taken as the target record, and then all target records in the collision record are extracted.

4. The DCS ship control system based on artificial intelligence according to claim 1, characterized in that, The pre-warning area division module comprises a pre-warning area division unit. The pre-warning area division unit is used to obtain collision positions in the target records, to take an area with the collision positions as centers and a radius r as a first pre-warning area.

5. The DCS ship control system based on artificial intelligence according to claim 1, characterized in that, Target areas on the bridges for limiting the ships to enter or exit are obtained based on floating fenders and guard piles, and the first pre-warning areas and the target areas are taken as pre-warning areas in planned trajectories corresponding to the to-be-detected ship. The scatter plot establishment module comprises a feature route extraction unit and a scatter plot establishment unit. The feature route extraction unit is used to obtain a certain pre-warning area A in a planned trajectory of the to-be-detected ship, to take the pre-warning area A as a starting point, to take a to-be-detected trajectory corresponding to a distance L3 forward along the planned trajectory in the opposite direction of the to-be-detected ship as a to-be-detected trajectory. Obtain the sailing records of several ships of the same type as the to-be-detected ship and which have not collided when passing through the early warning area A; extract the ship S corresponding to a sailing record M M and the actual route track T M , randomly obtain several target points from the to-be-detected track, and then obtain the actual route track T M The position point with the closest distance to a target point in the actual route track T M is taken as the characteristic distance of the target point, and according to each characteristic distance, the variance and the average characteristic distance are calculated. If the variance is less than the preset variance threshold and the average characteristic distance is less than the preset distance value, the actual route track T M is taken as the characteristic route, and then several characteristic routes are obtained.

6. An artificial intelligence based DCS ship control system according to claim 5, characterized in that, The scatter plot building unit is used to obtain the position point P of the ship to be detected at a certain time n. n In a certain characteristic route T0, the distance from the location point P is obtained. n The nearest position point is P0, and the ship corresponding to the certain characteristic route T0 is taken as S0. The time of ship S0 at position point P0 is taken as t0. The prediction duration is set as DP. The position point P1 of ship S0 after time t0 for a duration of DP is obtained. The angle between the heading V0 of ship S0 at position point P0 and the heading V1 of ship S0 at position point P1 is taken as the yaw angle. The heading V0 is rotated 180 degrees clockwise and counterclockwise respectively to obtain the first range and the second range. If the heading V1 is in the first range, the yaw angle is set to be greater than 0. If the heading V1 is in the second range, the yaw angle is set to be less than 0. According to the actual ship weight of ship S0 at time t0, the coordinate point corresponding to ship S0 is marked in a scatter plot of the yaw angle changing with the ship weight at a certain time n, and then several coordinate points in the scatter plot are marked.

Images