Intelligent guiding method and system for berthing and unberthing-stable berthing of ship

Abstract

The invention relates to a ship berthing and unberthing-stable berthing intelligent guiding method and system, and the method comprises the steps: obtaining a berthing allocation scheme based on berthing resource data, ship characteristic data and real-time environment data; based on the berth allocation scheme, an A-satellite path planning algorithm is adopted to generate a berth approaching and leaving guide path; based on the berthing and unberthing guiding path, a real-time monitoring algorithm is adopted to track the berthing and unberthing state of the ship, and the guiding path is updated according to the real-time position of the ship; optimizing the berth allocation scheme according to the updated guide path in combination with the scheduling stability; and obtaining berth distribution, a berth approaching and leaving sequence and a guiding path from the optimized berth distribution scheme, and executing berth distribution and ship berth approaching and leaving guiding. According to the method, dynamic optimal configuration of port berth resources and accurate guidance of ships can be realized, the port operation efficiency, the resource utilization rate and the safety are improved, and the method is of great significance to port intelligent management.

Description

Technical Field

[0001] The present invention relates to the technical field of ship berthing and unberthing, and in particular to a method and system for intelligent guidance of ship berthing, unberthing and stabilizing mooring. Background Art

[0002] With the continued growth of global maritime trade, ports, as key nodes in the international logistics chain, have a direct impact on the stability of the global supply chain and economic development through their operational efficiency. As a core part of port operations, the efficiency and safety of ship berthing and unberthing have a decisive impact on port throughput capacity.

[0003] Traditional ship berthing and unberthing management relies primarily on manual experience and simple scheduling rules, lacking comprehensive consideration of multi-dimensional factors and struggling to cope with the increasingly complex port operating environment. As the number of ships increases and port congestion intensifies, this approach often leads to low berth resource utilization, prolonged berthing and unberthing times, and even safety hazards.

[0004] The core challenge facing ports today lies in the complexity of berth resource allocation and vessel berthing and unberthing scheduling. Berth resources are limited, and vessels vary significantly in size, load capacity, and maneuverability, requiring berth allocation to consider multiple constraints. This complexity further complicates optimizing berthing and unberthing schedules, especially given uncertainties such as changing weather conditions and port congestion. Static berthing plans often fail to adapt to the ever-changing port environment, resulting in longer vessel wait times and reduced overall port operational efficiency.

[0005] Therefore, how to build an intelligent system that can dynamically optimize berth allocation and accurately guide ships to berth and leave berths based on the characteristics of port berth resources, individual differences of ships and the real-time operating environment, so as to maximize the utilization of port resources and ensure safe and efficient berthing and leaving of ships has become a key issue in enhancing the competitiveness of modern ports. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for intelligent guidance of ship berthing, unberthing and stabilizing berthing, so as to solve the problems existing in the above-mentioned prior art.

[0007] To achieve the above object, the present invention provides the following solutions:

[0008] A method for intelligently guiding ships to berth, leave berth, and maintain berth, comprising:

[0009] Obtain berth allocation plans based on berth resource data, ship characteristics data and real-time environmental data;

[0010] Based on the berth allocation plan, an A-star path planning algorithm is used to generate a berthing and unberthing guidance path;

[0011] Based on the berthing and unberthing guidance path, a real-time monitoring algorithm is used to track the berthing and unberthing status of the ship, and the guidance path is updated according to the real-time position of the ship;

[0012] Optimizing the berth allocation plan based on the updated guidance path and in combination with scheduling stability;

[0013] The system obtains berth allocation, berthing and unberthing sequence and guidance path from the optimized berth allocation plan, and performs berth allocation and ship berthing and unberthing guidance.

[0014] Optionally, obtaining the berth allocation plan includes:

[0015] Based on berth resource data, ship characteristic data, and real-time environmental data, the initial berth availability status, ship scheduling requirements, and environmental constraints are determined, and an initial berth availability list, ship berthing time windows, and environmental safety thresholds are generated. The environmental safety thresholds include wind speed thresholds, wave height thresholds, and visibility thresholds.

[0016] Based on the initial berth availability list and ship characteristic data, a genetic algorithm is used to calculate an initial berth allocation plan; wherein the initial berth allocation plan includes: the berth number allocated to the ship, the order of berthing and unberthing, and the expected berth occupancy time;

[0017] When the real-time environmental data exceeds the environmental safety threshold, the particle swarm optimization algorithm is used to adjust the berth allocation plan, with the goal of minimizing the berth occupancy time and meeting the environmental safety constraints, and generating an adjusted berth allocation plan.

[0018] Optionally, based on the berth allocation plan, generating a berthing and unberthing guidance path using an A-star path planning algorithm includes:

[0019] Obtaining the order of ship berthing and unberthing, berth numbers and berth position coordinates based on the berth allocation plan;

[0020] According to the order of ships' berthing and unberthing, the control performance parameters of the corresponding ships are obtained from the ship database;

[0021] Using a preset port map, load the coordinates of obstacles and other ship positions in the map, build a two-dimensional grid environment, and mark the coordinates of the port entrance and berth;

[0022] The A-star algorithm is used to input the ship's maneuverability parameters, port entrance, berth coordinates, and a two-dimensional grid environment, calculate the path from the entrance to the berth, and generate a sequence of path point coordinates.

[0023] If there is overlap between the path point coordinate sequence and the position of an obstacle or other ship, the cost function of the A-star algorithm is readjusted, the obstacle avoidance weight is increased, and the path point coordinate sequence is regenerated;

[0024] According to the coordinate sequence of the waypoints and the ship's speed, the distance and sailing time between adjacent waypoints are calculated and the total sailing time is accumulated;

[0025] Key nodes are extracted from the path point coordinate sequence and combined with the total sailing time to generate a berthing and unberthing guidance path; wherein the berthing and unberthing guidance path includes: a coordinate sequence and an estimated sailing time.

[0026] Optionally, updating the guidance path according to the real-time position of the vessel includes:

[0027] Get the real-time position and speed of the ship;

[0028] A real-time monitoring algorithm is used to process the real-time position and speed of the ship, and the berthing and unberthing status is determined based on time series analysis to obtain the ship's motion trajectory.

[0029] Calculating the Euclidean distance between the actual path point and the guided path point based on the ship's motion trajectory and the berthing and unberthing guidance path to obtain the path deviation;

[0030] If the path deviation exceeds the preset threshold, the A-star path planning algorithm is called to generate an updated guidance path based on the current real-time position of the ship and the target berth position, and obtain the path point coordinate sequence;

[0031] By comparing the Euclidean distance between the updated guidance path and the actual path, it is determined whether the path deviation is lower than a preset threshold and the deviation correction state is obtained. According to the deviation correction state, the interpolation algorithm is used to adjust the path point coordinate sequence of the updated guidance path to generate a smooth guidance path.

[0032] Optionally, optimizing the berth allocation scheme according to the updated guidance path and in combination with scheduling stability includes:

[0033] Calculate the berth occupancy time in the berth allocation plan based on the updated guidance path;

[0034] Calculate port resource utilization efficiency and throughput based on berth occupancy time and scheduling cycle time;

[0035] If the port resource utilization efficiency is lower than the preset threshold or the throughput does not meet the standard, the berth allocation will be clustered and optimized using the K-means algorithm to generate an optimized berth allocation plan based on ship type and docking time.

[0036] A ship berthing, unberthing and stabilizing intelligent guidance system is used to implement the ship berthing, unberthing and stabilizing intelligent guidance method, the system comprising:

[0037] The berth allocation module is used to obtain berth allocation plans based on berth resource data, ship characteristic data and real-time environmental data;

[0038] A path generation module is used to generate a berthing and unberthing guidance path based on the berth allocation plan using an A-star path planning algorithm;

[0039] a path updating module for tracking the berthing and unberthing status of a ship using a real-time monitoring algorithm based on the berthing and unberthing guidance path, and updating the guidance path according to the real-time position of the ship;

[0040] an allocation optimization module, which optimizes the berth allocation plan according to the updated guidance path and in combination with scheduling stability;

[0041] The guidance module is used to obtain berth allocation, berthing and unberthing sequence and guidance path from the optimized berth allocation plan, and perform berth allocation and ship berthing and unberthing guidance.

[0042] Optionally, the berth allocation module includes: a generating unit, a calculating unit and an adjusting unit;

[0043] The generating unit is configured to determine the initial berth availability status, ship scheduling requirements, and environmental constraints based on berth resource data, ship characteristic data, and real-time environmental data, and generate an initial berth availability list, a ship berthing time window, and an environmental safety threshold; wherein the environmental safety threshold includes: a wind speed threshold, a wave height threshold, and a visibility threshold;

[0044] The calculation unit is used to calculate an initial berth allocation plan using a genetic algorithm based on the initial berth availability list and the ship characteristic data; wherein the initial berth allocation plan includes: the berth number allocated to the ship, the order of berthing and unberthing, and the expected berth occupancy time;

[0045] The adjustment unit is used to adjust the berth allocation plan using a particle swarm optimization algorithm when the real-time environmental data exceeds the environmental safety threshold, with the goal of minimizing the berth occupancy time and satisfying the environmental safety constraints, and generate an adjusted berth allocation plan.

[0046] Optionally, the path generation module generates a berthing and unberthing guidance path based on the berth allocation plan using an A-star path planning algorithm, including:

[0047] Obtaining the order of ship berthing and unberthing, berth numbers and berth position coordinates based on the berth allocation plan;

[0048] According to the order of ships' berthing and unberthing, the control performance parameters of the corresponding ships are obtained from the ship database;

[0049] Using a preset port map, load the coordinates of obstacles and other ship positions in the map, build a two-dimensional grid environment, and mark the coordinates of the port entrance and berth;

[0050] The A-star algorithm is used to input the ship's maneuverability parameters, port entrance, berth coordinates, and a two-dimensional grid environment, calculate the path from the entrance to the berth, and generate a sequence of path point coordinates.

[0051] If there is overlap between the path point coordinate sequence and the position of an obstacle or other ship, the cost function of the A-star algorithm is readjusted, the obstacle avoidance weight is increased, and the path point coordinate sequence is regenerated;

[0052] According to the coordinate sequence of the waypoints and the ship's speed, the distance and sailing time between adjacent waypoints are calculated and the total sailing time is accumulated;

[0053] Key nodes are extracted from the path point coordinate sequence and combined with the total sailing time to generate a berthing and unberthing guidance path; wherein the berthing and unberthing guidance path includes: a coordinate sequence and an estimated sailing time.

[0054] The beneficial effects of the present invention are:

[0055] The present invention uses genetic algorithms and other methods to achieve intelligent berth allocation, comprehensively considering multiple factors such as ship size and berth characteristics, and can generate a highly adaptable preliminary berth plan to improve the rationality of berth allocation. When the environment changes, the particle swarm optimization algorithm can dynamically adjust the berth plan, reduce the berth occupancy time, and enhance the port's ability to respond to emergencies. At the same time, A-star path planning combines real-time monitoring and adjustment to generate precise guidance paths and update them in a timely manner to ensure efficient and safe berthing and unberthing of ships, reducing navigation time and collision risks. The efficiency of port resource utilization is calculated based on berth occupancy time, etc., which can comprehensively evaluate the port operation effect and provide data support for subsequent optimization. The entire solution realizes the dynamic optimization configuration of port berth resources and the precise guidance of ships, improves port operation efficiency, resource utilization and safety, and is of great significance to the intelligent management of ports. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 The present invention is a flowchart of a method for intelligently guiding ship berthing, unberthing and stabilizing berthing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0059] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0060] like Figure 1 As shown, this embodiment proposes a method for intelligent guidance of ship berthing, unberthing and stabilizing berthing, including:

[0061] Obtain berth allocation plans based on berth resource data, ship characteristics data and real-time environmental data;

[0062] Based on the berth allocation plan, an A-star path planning algorithm is used to generate a berthing and unberthing guidance path;

[0063] Based on the berthing and unberthing guidance path, a real-time monitoring algorithm is used to track the berthing and unberthing status of the ship, and the guidance path is updated according to the real-time position of the ship;

[0064] Optimizing the berth allocation plan based on the updated guidance path and in combination with scheduling stability;

[0065] The system obtains berth allocation, berthing and unberthing sequence and guidance path from the optimized berth allocation plan, and performs berth allocation and ship berthing and unberthing guidance.

[0066] Furthermore, obtaining the berth allocation plan includes:

[0067] Based on berth resource data, ship characteristic data, and real-time environmental data, the initial berth availability status, ship scheduling requirements, and environmental constraints are determined, and an initial berth availability list, ship berthing time windows, and environmental safety thresholds are generated. The environmental safety thresholds include wind speed thresholds, wave height thresholds, and visibility thresholds.

[0068] Based on the initial berth availability list and ship characteristic data, a genetic algorithm is used to calculate an initial berth allocation plan; wherein the initial berth allocation plan includes: the berth number allocated to the ship, the order of berthing and unberthing, and the expected berth occupancy time;

[0069] When the real-time environmental data exceeds the environmental safety threshold, the particle swarm optimization algorithm is used to adjust the berth allocation plan, with the goal of minimizing the berth occupancy time and meeting the environmental safety constraints, and generating an adjusted berth allocation plan.

[0070] Specifically, in this embodiment, obtaining a berth allocation plan based on berth resource data, ship characteristic data, and real-time environmental data includes the following:

[0071] Berth resource data, including the number, size, depth and location coordinates of berths, is obtained from the port management system. Ship characteristic data, including ship size, load and handling performance parameters, is obtained from the ship database. Real-time environmental data, including wind speed, wave height and visibility, is obtained from the meteorological system. The initial availability status of berths, ship scheduling requirements and environmental constraints are determined, and an initial berth availability list, ship berthing time window and environmental safety threshold are generated. The thresholds include wind speed threshold V1, wave height threshold H1 and visibility threshold E1.

[0072] Based on the initial berth availability list and ship characteristic data, a genetic algorithm is used to calculate the initial berth allocation plan. The fitness function is defined as a weighted objective: F = w1(1 / T)+w2M, where T is the berth occupancy time, which represents the total time for ships to berth and leave. M is the adaptation rate between ship size and berth size, calculated as M = min(ship width / berth width, berth width / ship width). w1 and w2 are preset weights. The initial berth allocation plan is generated, which includes the berth number assigned to the ship, the order of berthing and leaving, and the expected berth occupancy time T.

[0073] Real-time environmental data, including wind speed, wave height, and visibility, is acquired through sensors to determine whether trigger conditions are met: if wind speed exceeds threshold V1, wave height exceeds threshold H1, or visibility falls below threshold E1, a berth allocation adjustment is triggered. Based on the trigger conditions, an initial allocation plan, including berth numbers, docking and unberthing sequences, and berth occupancy times, is retrieved from the database to generate a dataset to be optimized. A particle swarm optimization algorithm is used to process the dataset, setting the objective function to minimize berth occupancy time T and environmental safety constraints, including wind speed, wave height, and visibility thresholds. The optimized berth allocation plan is then generated. The adjusted berth numbers and docking and unberthing sequences are extracted from the optimized berth allocation plan, and the adjusted berth occupancy time T1 is calculated. By comparing the initial berth occupancy time T with the adjusted berth occupancy time T1, it is determined whether T1 meets the minimization objective. If T1 is less than T, the adjusted plan is considered valid. Based on the adjusted berth allocation plan, an allocation result is generated, including the berth numbers, docking and unberthing sequences, and the adjusted berth occupancy time T1. The allocation results are output by the scheduling system, and the ship berth number, berthing and unberthing order and occupancy time T1 in the berth management system are updated to complete the berth allocation adjustment.

[0074] Specifically, assume that the initial berth allocation plan assigns three ships to three berths in the port. Ships A, B, and C are assigned to berths 1, 2, and 3, respectively. The berthing order is A first, B second, and C last. The initial berth occupancy time, T, is 8 hours for A at berth 1, 10 hours for B at berth 2, and 12 hours for C at berth 3, for a total of 30 hours. Real-time environmental data is obtained from meteorological sensors, with wind speeds of 15 m / s, wave heights of 2.5 m, and visibility of 500 m. Thresholds are set as V1 = 10 m / s, H1 = 2 m, and E1 = 1000 m. When wind speed and wave height exceed the thresholds, a berth adjustment mechanism is triggered. A particle swarm optimization (PSO) algorithm is used to adjust the allocation, with the goal of minimizing the total berth occupancy time, T1, while satisfying environmental safety constraints (such as berth depth, ship draft, and berth spacing). The PSO algorithm initializes 10 particles, each representing a berth allocation solution (e.g., [A-2, B-1, C-3]). The velocity vector is randomly generated, the inertia weight w = 0.7, and the learning factor c1 = c2 = 2. The objective function is T1 = Σ(ship berthing time + adjustment time), and the constraints are berth depth ≥ ship draft (assuming berth 1 is 10 meters deep, berth 2 is 8 meters deep, and berth 3 is 12 meters deep, with drafts of ships A, B, and C being 7 meters, 6 meters, and 8 meters, respectively) and berth spacing ≥ 50 meters. During the iterative calculation, particles update their positions based on the global optimal solution (gBest) and the individual optimal solution (pBest). Convergence is achieved after 50 iterations. The resulting solution is a new solution: ship A is assigned berth 2, ship B is assigned berth 3, and ship C is assigned berth 1. The berthing order is adjusted so that ship B berths first (because its draft matches the depth of berth 3), followed by ship A, and finally ship C. After the adjustment, A occupied berth 2 for 7 hours (optimizing loading and unloading efficiency), B occupied berth 3 for 9 hours, and C occupied berth 1 for 10 hours, for a total T1 of 26 hours. The analysis shows that PSO reduced the waiting time caused by the berth depth mismatch by adjusting the allocation. T1 is 4 hours shorter than T, meeting the safety constraint.

[0075] Furthermore, based on the berth allocation plan, generating a berthing and unberthing guidance path using the A-star path planning algorithm includes:

[0076] Obtaining the order of ship berthing and unberthing, berth numbers and berth position coordinates based on the berth allocation plan;

[0077] According to the order of ships' berthing and unberthing, the control performance parameters of the corresponding ships are obtained from the ship database;

[0078] Using a preset port map, load the coordinates of obstacles and other ship positions in the map, build a two-dimensional grid environment, and mark the coordinates of the port entrance and berth;

[0079] The A-star algorithm is used to input the ship's maneuverability parameters, port entrance, berth coordinates, and a two-dimensional grid environment, calculate the path from the entrance to the berth, and generate a sequence of path point coordinates.

[0080] If there is overlap between the path point coordinate sequence and the position of an obstacle or other ship, the cost function of the A-star algorithm is readjusted, the obstacle avoidance weight is increased, and the path point coordinate sequence is regenerated;

[0081] According to the coordinate sequence of the waypoints and the ship's speed, the distance and sailing time between adjacent waypoints are calculated and the total sailing time is accumulated;

[0082] Key nodes are extracted from the path point coordinate sequence and combined with the total sailing time to generate a berthing and unberthing guidance path; wherein the berthing and unberthing guidance path includes: a coordinate sequence and an estimated sailing time.

[0083] Specifically, in this embodiment, based on the preset port map, the ship berthing and unberthing information is first extracted from the berth allocation plan. Assume that the berthing order of a certain ship A is 1st, the allocated berth number is B1, the berth position coordinates are (100,50), and the unberthing order is 3rd. The maneuvering performance parameters of ship A include a maximum speed of 5 meters per second, a steering angular velocity of 0.1 radians per second, and a minimum turning radius of 20 meters. The port map is a 1000×1000 meter grid map with a resolution of 1 meter. The entrance coordinates are (0,0), and the obstacles include other ships B located at (200,150) and fixed obstacles C in the area (300,200) to (350,250). The guidance path is generated based on the A-star algorithm, the heuristic function is defined as the Manhattan distance, and the cost function is the path length plus the turning cost (each turn increases the equivalent distance by 0.5 meters). The algorithm searches an eight-way neighborhood from (0,0) to (100,50), avoiding obstacles B and C, generating the following pathpoint sequence: (0,0), (50,25), (80,40), (100,50). The path length, L, is 110 meters, including three turns, for a total cost of 111.5 meters. The estimated voyage time is 111.5 ÷ 5 = 22.3 seconds. The analysis considers the vessel's minimum turning radius, and the distance between pathpoints is greater than 20 meters, satisfying the control constraints. Obstacle avoidance is achieved through grid marking, and the A-star algorithm prioritizes nodes close to the target to ensure an optimal path. If the berth allocation plan is adjusted, the path must be recalculated.

[0084] Furthermore, updating the guidance path according to the real-time position of the ship includes:

[0085] Get the real-time position and speed of the ship;

[0086] A real-time monitoring algorithm is used to process the real-time position and speed of the ship, and the berthing and unberthing status is determined based on time series analysis to obtain the ship's motion trajectory.

[0087] Calculating the Euclidean distance between the actual path point and the guided path point based on the ship's motion trajectory and the berthing and unberthing guidance path to obtain the path deviation;

[0088] If the path deviation exceeds the preset threshold, the A* path planning algorithm is called to generate an updated guidance path based on the current real-time position of the ship and the target berth position, and the coordinate sequence of path points is obtained.

[0089] By comparing the Euclidean distance between the updated guidance path and the actual path, it is judged whether the path deviation is lower than the preset threshold to obtain the deviation correction status; according to the deviation correction status, the interpolation algorithm is used to adjust the coordinate sequence of the path points of the updated guidance path to generate a smooth guidance path.

[0090] Specifically, in this embodiment, for example, the position P1 of a ship at a certain moment is the longitude and latitude (121.1234, 31.5678), and the speed S1 is 10 knots. AIS data is transmitted through the ship's VHF radio, and the data packet is parsed at a frequency of once per second to extract the longitude and latitude and speed fields. Then, the deviation D between the actual path and the dynamically adjusted guidance path is calculated. Suppose the guidance path is a preset point sequence {(121.1000, 31.5500), (121.1200, 31.5600), (121.1400, 31.5700)}, and the actual path point is P1. The deviation D is calculated based on the Euclidean distance, and the formula is D = √((x2 - x1)2 + (y2 - y1)2). Taking P1 and the nearest guidance path point (121.1200, 31.5600) as an example, D = √((121.1234 - 121.1200)2 + (31.5678 - 31.5600) 2 ) = 0.0085 degrees, which is approximately 0.94 kilometers. If the preset threshold D1 is 1 kilometer and D < D1, it indicates that the deviation is within the acceptable range, and continuous monitoring is carried out. If D ≥ D1, for example, D = 1.2 kilometers, the A* path planning algorithm is triggered to regenerate the guidance path. The A* algorithm takes the current P1 as the starting point and the target as the berthing point (121.1500, 31.5800), considering obstacles (such as the positions of other ships) and channel constraints, and generates a new path point sequence {(121.1250, 31.5680), (121.1350, 31.5730), (121.1500, 31.5800)}. The algorithm uses the heuristic function f(n) = g(n) + h(n), where g(n) is the actual cost from the starting point to the current node, and h(n) is the Manhattan distance estimate to the target.

[0091] Furthermore, according to the updated guidance path, in combination with the scheduling stability, the optimization of the berth allocation plan includes:

[0092] Based on the updated guidance path, calculate the berth occupancy duration in the berth allocation plan;

[0093] Based on the berth occupancy duration and the scheduling cycle time, calculate the port resource utilization efficiency and throughput;

[0094] If the port resource utilization efficiency is lower than the preset threshold or the throughput does not meet the standard, the berth allocation will be clustered and optimized using the K-means algorithm to generate an optimized berth allocation plan based on ship type and docking time.

[0095] Specifically, in this embodiment, berth occupancy time is calculated using berth occupancy time data and vessel dispatch records. Berth occupancy time is calculated using the formula T_use = ΣT1_i, where T1_i is the occupancy time of the i-th berth. Port resource utilization efficiency is calculated based on berth occupancy time and dispatch cycle time using the formula R = T_use / T_cycle, where T_cycle is 24 hours, to obtain efficiency R. The number of ships processed is obtained from ship arrival and departure records. Throughput Q is calculated using the formula Q = N / T_cycle, where N is the number of ships processed per unit time. If efficiency R falls below a preset threshold or throughput Q fails to meet the standard, berth allocation is clustered and optimized using the K-means algorithm. An optimized berth allocation plan is generated based on vessel type and berth duration. Based on the optimized berth allocation plan, the A algorithm is used to update the guidance path and calculate the path deviation D using the formula D = |P_new - P_old|, where P_new and P_old are the coordinate sequences of the new and old paths, respectively. If the path deviation D exceeds a preset threshold, a linear regression model is used to predict ship scheduling stability. The inputs are path deviation D and throughput Q, and the output is a stability index S, which yields the scheduling stability analysis results. Based on the stability index S and the optimized berth allocation plan, a final berth scheduling plan is generated, including berth allocation, guidance path, efficiency R, and throughput Q, resulting in an optimized scheduling solution.

[0096] Berth allocation, docking and undocking sequences, and guidance paths are obtained from the optimized berth scheduling plan. A genetic algorithm is used to iteratively optimize the scheduling plan to obtain the optimized berth allocation plan, docking and undocking sequence, and guidance paths. This optimized berth allocation plan, docking and undocking sequence, and guidance paths are transmitted to the port scheduling system via a data transmission interface. The data is formatted using a standardized protocol to produce a transmitted data packet. Upon receiving a data packet confirmation signal, the port scheduling system parses the data packet to obtain the berth allocation plan, docking and undocking sequence, and guidance paths. It then uses a task allocation algorithm to generate execution instructions for ship docking and undocking, resulting in an automatically executed task sequence. Based on the task sequence, the port scheduling system controls ship docking and undocking, berth allocation, and real-time berth occupancy time T2 and actual throughput Q1. Each ship's docking and undocking events are recorded using timestamps to produce real-time execution data.

[0097] This embodiment also proposes a ship berthing, unberthing and stabilizing intelligent guidance system for implementing the ship berthing, unberthing and stabilizing intelligent guidance method, the system comprising:

[0098] The berth allocation module is used to obtain berth allocation plans based on berth resource data, ship characteristic data and real-time environmental data;

[0099] A path generation module is used to generate a berthing and unberthing guidance path based on the berth allocation plan using an A-star path planning algorithm;

[0100] a path updating module for tracking the berthing and unberthing status of a ship using a real-time monitoring algorithm based on the berthing and unberthing guidance path, and updating the guidance path according to the real-time position of the ship;

[0101] an allocation optimization module, which optimizes the berth allocation plan according to the updated guidance path and in combination with scheduling stability;

[0102] The guidance module is used to obtain berth allocation, berthing and unberthing sequence and guidance path from the optimized berth allocation plan, and perform berth allocation and ship berthing and unberthing guidance.

[0103] Furthermore, the berth allocation module includes: a generation unit, a calculation unit and an adjustment unit;

[0104] The generating unit is configured to determine the initial berth availability status, ship scheduling requirements, and environmental constraints based on berth resource data, ship characteristic data, and real-time environmental data, and generate an initial berth availability list, a ship berthing time window, and an environmental safety threshold; wherein the environmental safety threshold includes: a wind speed threshold, a wave height threshold, and a visibility threshold;

[0105] The calculation unit is used to calculate an initial berth allocation plan using a genetic algorithm based on the initial berth availability list and the ship characteristic data; wherein the initial berth allocation plan includes: the berth number allocated to the ship, the order of berthing and unberthing, and the expected berth occupancy time;

[0106] The adjustment unit is used to adjust the berth allocation plan using a particle swarm optimization algorithm when the real-time environmental data exceeds the environmental safety threshold, with the goal of minimizing the berth occupancy time and satisfying the environmental safety constraints, and generate an adjusted berth allocation plan.

[0107] Furthermore, the path generation module generates a berthing and unberthing guidance path based on the berth allocation plan using an A-star path planning algorithm, including:

[0108] Obtaining the order of ship berthing and unberthing, berth numbers and berth position coordinates based on the berth allocation plan;

[0109] According to the order of ships' berthing and unberthing, the control performance parameters of the corresponding ships are obtained from the ship database;

[0110] Using a preset port map, load the coordinates of obstacles and other ship positions in the map, build a two-dimensional grid environment, and mark the coordinates of the port entrance and berth;

[0111] The A-star algorithm is used to input the ship's maneuverability parameters, port entrance, berth coordinates, and a two-dimensional grid environment, calculate the path from the entrance to the berth, and generate a sequence of path point coordinates.

[0112] If there is overlap between the path point coordinate sequence and the position of an obstacle or other ship, the cost function of the A-star algorithm is readjusted, the obstacle avoidance weight is increased, and the path point coordinate sequence is regenerated;

[0113] According to the coordinate sequence of the waypoints and the ship's speed, the distance and sailing time between adjacent waypoints are calculated and the total sailing time is accumulated;

[0114] Key nodes are extracted from the path point coordinate sequence and combined with the total sailing time to generate a berthing and unberthing guidance path; wherein the berthing and unberthing guidance path includes: a coordinate sequence and an estimated sailing time.

[0115] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A method for intelligent guidance of ship berthing, unberthing and stabilizing berthing, characterized in that: include: Obtain berth allocation plans based on berth resource data, ship characteristics data and real-time environmental data; Based on the berth allocation plan, an A-star path planning algorithm is used to generate a berthing and unberthing guidance path; Based on the berthing and unberthing guidance path, a real-time monitoring algorithm is used to track the berthing and unberthing status of the ship, and the guidance path is updated according to the real-time position of the ship; Optimizing the berth allocation plan based on the updated guidance path and in combination with scheduling stability; The system obtains berth allocation, berthing and unberthing sequence and guidance path from the optimized berth allocation plan, and performs berth allocation and ship berthing and unberthing guidance.

2. The intelligent guidance method for ship berthing, unberthing and stabilizing according to claim 1, characterized in that: Obtaining the berth allocation plan includes: Based on berth resource data, ship characteristic data, and real-time environmental data, the initial berth availability status, ship scheduling requirements, and environmental constraints are determined, and an initial berth availability list, ship berthing time windows, and environmental safety thresholds are generated. The environmental safety thresholds include wind speed thresholds, wave height thresholds, and visibility thresholds. Based on the initial berth availability list and ship characteristic data, a genetic algorithm is used to calculate an initial berth allocation plan; wherein the initial berth allocation plan includes: the berth number allocated to the ship, the order of berthing and unberthing, and the expected berth occupancy time; When the real-time environmental data exceeds the environmental safety threshold, the particle swarm optimization algorithm is used to adjust the berth allocation plan, with the goal of minimizing the berth occupancy time and meeting the environmental safety constraints, and generating an adjusted berth allocation plan.

3. The intelligent guidance method for ship berthing, unberthing and stabilizing according to claim 1, characterized in that: Based on the berth allocation plan, the A-star path planning algorithm is used to generate the berthing and unberthing guidance path, including: Obtaining the order of ship berthing and unberthing, berth numbers and berth position coordinates based on the berth allocation plan; According to the order of ships' berthing and unberthing, the control performance parameters of the corresponding ships are obtained from the ship database; Using a preset port map, load the coordinates of obstacles and other ship positions in the map, build a two-dimensional grid environment, and mark the coordinates of the port entrance and berth; The A-star algorithm is used to input the ship's maneuverability parameters, port entrance, berth coordinates, and a two-dimensional grid environment, calculate the path from the entrance to the berth, and generate a sequence of path point coordinates. If there is overlap between the path point coordinate sequence and the position of an obstacle or other ship, the cost function of the A-star algorithm is readjusted, the obstacle avoidance weight is increased, and the path point coordinate sequence is regenerated; According to the coordinate sequence of the waypoints and the ship's speed, the distance and sailing time between adjacent waypoints are calculated and the total sailing time is accumulated; Key nodes are extracted from the path point coordinate sequence and combined with the total sailing time to generate a berthing and unberthing guidance path; wherein the berthing and unberthing guidance path includes: a coordinate sequence and an estimated sailing time.

4. The method for intelligent guidance of ship berthing, unberthing and stabilizing berthing according to claim 1, characterized in that: Based on the real-time position of the vessel, the guidance path is updated including: Get the real-time position and speed of the ship; A real-time monitoring algorithm is used to process the real-time position and speed of the ship, and the berthing and unberthing status is determined based on time series analysis to obtain the ship's motion trajectory. Calculating the Euclidean distance between the actual path point and the guided path point based on the ship's motion trajectory and the berthing and unberthing guidance path to obtain the path deviation; If the path deviation exceeds the preset threshold, the A-star path planning algorithm is called to generate an updated guidance path based on the current real-time position of the ship and the target berth position, and obtain the path point coordinate sequence; By comparing the Euclidean distance between the updated guidance path and the actual path, it is determined whether the path deviation is lower than a preset threshold and the deviation correction state is obtained. According to the deviation correction state, the interpolation algorithm is used to adjust the path point coordinate sequence of the updated guidance path to generate a smooth guidance path.

5. The intelligent guidance method for ship berthing, unberthing and stabilizing according to claim 1, characterized in that: According to the updated guidance path and in combination with scheduling stability, the berth allocation plan is optimized including: Calculate the berth occupancy time in the berth allocation plan based on the updated guidance path; Calculate port resource utilization efficiency and throughput based on berth occupancy time and scheduling cycle time; If the port resource utilization efficiency is lower than the preset threshold or the throughput does not meet the standard, the berth allocation will be clustered and optimized using the K-means algorithm to generate an optimized berth allocation plan based on ship type and docking time.

6. A ship berthing and unberthing - stabilizing intelligent guidance system, characterized in that: The system is used to implement the intelligent guidance method for ship berthing, unberthing and stabilizing berthing according to any one of claims 1 to 5, comprising: The berth allocation module is used to obtain berth allocation plans based on berth resource data, ship characteristic data and real-time environmental data; A path generation module is used to generate a berthing and unberthing guidance path based on the berth allocation plan using an A-star path planning algorithm; a path updating module for tracking the berthing and unberthing status of a ship using a real-time monitoring algorithm based on the berthing and unberthing guidance path, and updating the guidance path according to the real-time position of the ship; an allocation optimization module, which optimizes the berth allocation plan according to the updated guidance path and in combination with scheduling stability; The guidance module is used to obtain berth allocation, berthing and unberthing sequence and guidance path from the optimized berth allocation plan, and perform berth allocation and ship berthing and unberthing guidance.

7. The ship berthing, unberthing and stabilizing intelligent guidance system according to claim 6, characterized in that: The berth allocation module includes: a generation unit, a calculation unit and an adjustment unit; The generating unit is configured to determine the initial berth availability status, ship scheduling requirements, and environmental constraints based on berth resource data, ship characteristic data, and real-time environmental data, and generate an initial berth availability list, a ship berthing time window, and an environmental safety threshold; wherein the environmental safety threshold includes: a wind speed threshold, a wave height threshold, and a visibility threshold; The calculation unit is used to calculate an initial berth allocation plan using a genetic algorithm based on the initial berth availability list and the ship characteristic data; wherein the initial berth allocation plan includes: the berth number allocated to the ship, the order of berthing and unberthing, and the expected berth occupancy time; The adjustment unit is used to adjust the berth allocation plan using a particle swarm optimization algorithm when the real-time environmental data exceeds the environmental safety threshold, with the goal of minimizing the berth occupancy time and satisfying the environmental safety constraints, and generate an adjusted berth allocation plan.

8. The ship berthing, unberthing and stabilizing intelligent guidance system according to claim 6, characterized in that: The path generation module generates a berthing and unberthing guidance path based on the berth allocation plan using the A-star path planning algorithm, including: Obtaining the order of ship berthing and unberthing, berth numbers and berth position coordinates based on the berth allocation plan; According to the order of ships' berthing and unberthing, the control performance parameters of the corresponding ships are obtained from the ship database; Using a preset port map, load the coordinates of obstacles and other ship positions in the map, build a two-dimensional grid environment, and mark the coordinates of the port entrance and berth; The A-star algorithm is used to input the ship's maneuverability parameters, port entrance, berth coordinates, and a two-dimensional grid environment, calculate the path from the entrance to the berth, and generate a sequence of path point coordinates. If there is overlap between the path point coordinate sequence and the position of an obstacle or other ship, the cost function of the A-star algorithm is readjusted, the obstacle avoidance weight is increased, and the path point coordinate sequence is regenerated; According to the coordinate sequence of the waypoints and the ship's speed, the distance and sailing time between adjacent waypoints are calculated and the total sailing time is accumulated; Key nodes are extracted from the path point coordinate sequence and combined with the total sailing time to generate a berthing and unberthing guidance path; wherein the berthing and unberthing guidance path includes: a coordinate sequence and an estimated sailing time.

Images