A port tug task planning method and device, electronic equipment and storage medium

Abstract

This invention provides a port tugboat task planning method, apparatus, electronic device, and storage medium. The port tugboat task planning method includes the following steps: acquiring information data, wherein the information data includes at least tugboat-related information data, port-related information data, large vessel-related information data, and driver-related information data; responding to the information data, based on preset vessel matching rules, operational requirement constraints, and resource status constraints, selecting feasible tugboats and obtaining feasible tugboat-related data; extracting starting point coordinates and target point coordinates from the feasible tugboat-related data, calling a trajectory planning algorithm to plan the trajectory of the feasible tugboats, and obtaining the planned trajectory. This invention, in the dynamic operational environment of a port, rapidly generates a safe, energy-saving, and efficient optimal comprehensive tugboat task plan based on tugboat, port, large vessel, and driver-related information data.

Description

Technical Field

[0001] This invention relates to the field of port scheduling technology, specifically to a port tugboat task planning method, apparatus, electronic device, and storage medium. Background Technology

[0002] Port tugboat navigation assistance is a crucial link in ensuring the safe berthing and unberthing of large vessels, and the quality of its scheduling directly affects port operational efficiency, energy consumption, and operational safety. The tugboat scheduling problem is essentially a combinatorial optimization problem with multiple constraints and objectives. In actual operations, tugboat scheduling must simultaneously meet multiple constraints: vessel matching constraints require tugboat horsepower to meet the operational needs of large vessels; time window constraints require tugboat navigation and operation times to fall within the permitted time window for large vessels; resource status constraints involve limitations on tugboat location, availability, and driver scheduling; and trajectory feasibility constraints must consider geographical environmental factors such as port channels, restricted areas, and water depth.

[0003] However, current port tugboat scheduling generally relies on manual experience, which leads to problems such as delayed response and suboptimal resource allocation. This results in inefficient tugboat operation routes, increased ineffective navigation, and persistently high energy consumption and carbon emissions. Summary of the Invention

[0004] The purpose of this invention is to overcome the above-mentioned technical deficiencies and propose a port tugboat task planning method to solve the technical problems of low tugboat operation path efficiency and increased ineffective navigation in the prior art.

[0005] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a port tugboat task planning method, comprising the following steps: Acquire information data, wherein the information data includes at least tugboat-related information data, port-related information data, large ship-related information data, and driver-related information data; In response to the information data, based on preset ship matching rules, operational requirement constraints and resource status constraints, feasible tugboats are selected and relevant data of feasible tugboats are obtained; The starting point coordinates and the target point coordinates are extracted from the relevant data of the feasible tugboat. The trajectory planning algorithm is called to plan the trajectory of the feasible tugboat and obtain the planned trajectory. Based on the aforementioned large ship-related information data, feasible tugboat-related data, and planned trajectories, a task duration prediction algorithm is invoked to predict the task duration of feasible tugboats, obtaining task duration data. Simultaneously, a tugboat energy consumption prediction algorithm is invoked to predict the energy consumption of feasible tugboats, obtaining energy consumption data. Based on the feasible tugboat-related data, planned trajectory, mission duration data, and energy consumption data, the tugboat mission planning algorithm is invoked to obtain a mission plan with the goal of minimizing total energy consumption.

[0006] In some embodiments, the tugboat task planning algorithm includes the following steps: Taking the entire process of tugboat navigation assistance operations as the object, and establishing an objective function with minimizing total energy consumption as the first priority; Based on the objective function and the preset constraints, a task planning model is constructed, wherein the constraints include at least ship matching constraints, time window constraints, resource status constraints, and trajectory feasibility constraints. Based on the feasible tugboat related data, planned trajectory, mission duration data and energy consumption data, a composite heuristic algorithm is invoked to solve the mission planning model, resulting in a mission scheme that satisfies all constraints and minimizes total energy consumption. The solved task solutions are then validated and their effectiveness evaluated. Output the optimal integrated tugboat mission plan. The mission plan should include at least the assigned tugboat number, the assigned driver number, the planned tugboat route, the total energy consumption of the tugboat, and the mission duration of the tugboat.

[0007] In some embodiments, the objective function is:

[0008] in, Total energy consumption for all tugboat missions; For the first Energy consumption of a tugboat performing a mission; The number of tugboats participating in the mission.

[0009] In some embodiments, the tugboat trajectory planning algorithm includes the following steps: Construct a grid map model of the port area's sea area; Based on the starting point coordinates, target point coordinates, and port area grid model, the energy-optimal A algorithm is invoked. The search algorithm performs trajectory planning to obtain a planned trajectory that satisfies the energy-optimal objective between the starting point coordinates and the target point coordinates; Output the planned trajectory.

[0010] In some embodiments, the task duration prediction algorithm includes the following steps: Extract the AIS data of the tugboat from the feasible tugboat-related data and the AIS data of the large ship from the large ship-related information data; Based on AIS track clustering processing, the free navigation track points and escort operation track points of the tugboat are output to obtain the free navigation track and escort operation track. Cluster analysis was performed on the required task durations of the free navigation trajectory and escort operation trajectory, and the mean value was taken as the predicted task duration required for a single tugboat mission. Output the predicted task duration data.

[0011] In some embodiments, the method for AIS track clustering is as follows: Preprocessing is performed on the AIS data of the tugboat to extract the speed, heading, speed change, heading change, speed change rate, and heading change rate to obtain a feature vector. The feature vectors were clustered using the K-means clustering algorithm to identify the free-sailing trajectory points of the tugboat. Preprocessing is performed on the AIS data of the large ship to extract the ship's speed, heading, speed change, and heading change to obtain a fused feature vector. Then, the fused feature vector is clustered a second time using the K-means clustering algorithm to separate the tugboat escort operation trajectory points.

[0012] In some embodiments, the tugboat energy consumption prediction algorithm includes the following steps: Extract the tugboat AIS data and meteorological data from the feasible tugboat-related data, and preprocess the tugboat AIS data and meteorological data; Based on the processed AIS data and meteorological data of the tugboat, a machine learning model is called to predict the dynamic parameters in the empirical formula for calculating the energy consumption of the tugboat. The predicted parameters are then substituted into the empirical formula to perform energy consumption prediction calculations and obtain the predicted energy consumption of the feasible tugboat. The dynamic parameters include at least a fuel consumption calibration coefficient. Output the predicted energy consumption data.

[0013] Secondly, the present invention also provides a port tugboat task planning device, the port tugboat task planning device comprising: The information data acquisition module is used to acquire information data, which includes at least tugboat-related information data, port-related information data, large ship-related information data, and driver-related information data. The tugboat screening module is used to respond to information data and, based on preset vessel matching rules, operational requirement constraints, and resource status constraints, screen out feasible tugboats and obtain relevant data on feasible tugboats. The tugboat trajectory planning module is used to extract the starting point coordinates and target point coordinates from the relevant data of feasible tugboats, call the trajectory planning algorithm, generate the trajectory plan of feasible tugboats, and obtain the planned trajectory. The tugboat duration and energy consumption prediction module is used to predict the duration of the feasible tugboat based on the relevant information data of the large ship, the relevant data of the feasible tugboat and the planned trajectory, and simultaneously call the tugboat energy consumption prediction algorithm to predict the energy consumption of the feasible tugboat and obtain the energy consumption data. The tugboat mission planning module is used to call the tugboat mission planning algorithm based on the feasible tugboat related data, planned trajectory, mission duration data and energy consumption data, with the goal of minimizing total energy consumption, to obtain a mission plan.

[0014] Thirdly, the present invention also provides an electronic device including a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the steps of the port tugboat task planning method as described in any of the preceding claims.

[0015] Fourthly, the present invention also provides a readable storage medium storing a computer program that, when executed by a processor, implements the steps of the port tugboat task planning method described in any of the preceding claims.

[0016] Compared with existing technologies, the port tugboat task planning method provided by this invention can quickly generate a safe, energy-saving, and efficient optimal comprehensive tugboat task plan based on information data of tugboats, ports, large ships, and drivers in the dynamic operation environment of ports. The tugboat task plan includes at least feasible drivers, task-executing tugboats, optimal routes, task duration, and total energy consumption, which improves the overall efficiency of port seaside operations. Furthermore, by relying on route planning and energy consumption prediction, it effectively reduces fuel consumption and carbon dioxide emissions, and strongly supports the low-carbon and intelligent transformation of port operations. Attached Figure Description

[0017] Figure 1 This is a flowchart of the port tugboat task planning method provided in an embodiment of the present invention; Figure 2 This is a flowchart of the optimal integrated tugboat task scheme method provided in the embodiments of the present invention; Figure 3 This is a flowchart of a feasible tugboat trajectory planning data algorithm between a starting point and a target point, provided in an embodiment of the present invention. Figure 4 This is a flowchart of the algorithm for predicting task duration data provided in an embodiment of the present invention; Figure 5 This is a flowchart of the AIS track clustering method provided in this embodiment of the invention; Figure 6 This is a flowchart of the algorithm for energy consumption prediction data provided in the embodiments of the present invention; Figure 7 This is a flowchart of the screening rules provided in the embodiments of the present invention; Figure 8 This is a system block diagram of the port tugboat task planning device provided in an embodiment of the present invention; Figure 9 This is a structural diagram of the electronic device provided in an embodiment of the present invention; Figure 10 This is a flowchart of the K-means clustering process provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0019] To address the technical problems of low efficiency and increased unnecessary navigation in tugboat operations, this invention provides a port tugboat task planning method. This method enables the rapid generation of a safe, energy-efficient, and highly effective optimal comprehensive tugboat task plan based on information data from tugboats, the port, large vessels, and operators within a dynamic port operating environment. The tugboat task plan includes at least feasible operators, task-executing tugboats, optimal routes, task duration, and total energy consumption. This improves the overall efficiency of port seaside operations and, relying on route planning and energy consumption prediction, effectively reduces fuel consumption and carbon dioxide emissions, strongly supporting the low-carbon and intelligent transformation of port operations.

[0020] Please see Figure 1 , Figure 1 This is a flowchart of a port tugboat task planning method according to an embodiment of the present invention. The port tugboat task planning method includes the following steps: S101. Obtain information data, wherein the information data includes at least tugboat-related information data, port-related information data, large ship-related information data, and driver-related information data; S102. In response to the information data, based on the preset ship matching rules, operational requirement constraints and resource status constraints, feasible tugboats are selected and relevant data of feasible tugboats are obtained. S103. Extract the starting point coordinates and target point coordinates from the relevant data of the feasible tugboat, call the trajectory planning algorithm to plan the trajectory of the feasible tugboat, and obtain the planned trajectory. S104. Based on the relevant information data of the large ship, the relevant data of the feasible tugboat, and the planned trajectory, call the task duration prediction algorithm to predict the task duration of the feasible tugboat, obtain the task duration data, and simultaneously call the tugboat energy consumption prediction algorithm to predict the energy consumption of the feasible tugboat, obtain the energy consumption data. S105. Based on the feasible tugboat-related data, planned trajectory, mission duration data, and energy consumption data, the tugboat mission planning algorithm is invoked to obtain a mission plan with the goal of minimizing total energy consumption.

[0021] The implementation process of each step is illustrated below as an example.

[0022] Step S101: Obtain information data, wherein the information data includes at least tugboat-related information data, port-related information data, large ship-related information data, and driver-related information data.

[0023] For example, through the data interface with the port's information platform, real-time data from tugboats and the shore is collected, including tugboat number, tugboat horsepower, tugboat fuel consumption information, tugboat speed and related information, electronic nautical charts, berth location and layout information, required horsepower for large vessels, large vessel mission start and end points, large vessel mission time windows, large vessel number, time taken for large vessels to travel from the mooring point to the berth and related information, as well as vessel matching rules, driver competence, and available driver number information. This raw data is then processed through structured parsing to convert data of different formats into a standardized dataset.

[0024] S102. In response to the information data, based on the preset ship matching rules, operational requirement constraints and resource status constraints, feasible tugboats are selected and relevant data of feasible tugboats are obtained.

[0025] For example, by combining the real-time status of tugboats and information on available drivers, tugboats that are idle and have available drivers with matching business capabilities are selected; based on the tugboat's speed range, economic speed range, and the large ship's mission time window, it is verified whether the sum of the tugboat's travel time from its current position to the start point of the operation and the estimated operation time is within the large ship's mission time window, ensuring that the tugboat can complete the navigation assistance task on time; by combining electronic charts, berth layout, and channel restriction information, it is verified whether the tugboat's draft, handling characteristics, etc., are suitable for the channel conditions of the operation area, tugboats with navigation safety hazards are excluded, and finally, a set of feasible tugboats that meet the operational feasibility requirements is determined.

[0026] S103. Extract the starting point coordinates and target point coordinates from the relevant data of the feasible tugboat, call the trajectory planning algorithm to plan the trajectory of the feasible tugboat, and obtain the planned trajectory.

[0027] For example, based on the port area sea area grid map model, A The optimization algorithm, as the core search algorithm, introduces a segment energy consumption evaluation factor on the basis of traditional geometric distance heuristics, ensuring that the output trajectory is not only the shortest in geometric distance, but also the best in estimated fuel consumption.

[0028] S104. Based on the relevant information data of the large ship, the relevant data of the feasible tugboat, and the planned trajectory, the task duration prediction algorithm is invoked to predict the task duration of the feasible tugboat, and the task duration data is obtained. At the same time, the tugboat energy consumption prediction algorithm is invoked to predict the energy consumption of the feasible tugboat, and the energy consumption data is obtained.

[0029] For example, the AIS data of the tugboat in the feasible tugboat-related data and the AIS data of the large ship in the large ship-related data are extracted. Combined with the task duration prediction algorithm, the average value is calculated based on the output free navigation trajectory and escort operation trajectory to output the task duration. The AIS data of the tugboat and the meteorological data in the feasible tugboat-related data are extracted. Based on the processed tugboat AIS data and meteorological data, the machine learning model is called to predict the dynamic parameters in the empirical formula for calculating the energy consumption of the tugboat. The predicted parameters are then substituted into the empirical formula to perform energy consumption prediction calculation to obtain the predicted energy consumption of the feasible tugboat.

[0030] S105. Based on the feasible tugboat-related data, planned trajectory, mission duration data, and energy consumption data, the tugboat mission planning algorithm is invoked to obtain a mission plan with the goal of minimizing total energy consumption.

[0031] For example, with the assistance of planned trajectory, mission duration data and energy consumption data, combined with tugboat mission planning algorithm, feasible scheduling schemes are randomly generated based on rules. New solutions are generated by adjusting tugboat and mission allocation, trajectory nodes, etc. Total energy consumption is used as the main evaluation index. Combined with mechanisms such as simulated annealing, some inferior solutions are accepted to escape local optima. This process is repeated until convergence or the maximum number of iterations is reached. The mission scheme includes at least the assigned tugboat number, assigned driver number, assigned tugboat planned trajectory, total tugboat energy consumption, and tugboat mission time.

[0032] Understandably, step S101 includes acquiring information and performing data preprocessing. The tugboat-related information data includes at least the tugboat number, tugboat horsepower, tugboat fuel consumption information, tugboat speed, and information related to tugboat speed. The port-related information data includes at least electronic nautical charts, berth location and layout information. The large ship-related information data includes at least the required horsepower of the large ship, the start and end points of the large ship's mission, the large ship's mission time window, the large ship number, the time taken for the large ship to travel from the mooring point to the berth, and information related to the large ship. The driver-related information data includes at least the driver's professional competence and available driver numbers. Preprocessing includes at least data cleaning and correlation analysis.

[0033] It should be noted that the executing entity of this invention can be a port tugboat task planning and trajectory planning device for energy consumption optimization, or it can be a terminal or a server; the specific implementation is not limited here. This illustrative embodiment uses a server as an example for explanation.

[0034] In one embodiment, please refer to Figure 2 In step S105, the specific method for determining the optimal integrated tugboat task scheme is as follows: S201. Taking the entire process of tugboat navigation assistance operations as the object, and establishing an objective function with minimizing total energy consumption as the first priority; S202. Based on the objective function and the preset constraints, construct a task planning model, wherein the constraints include at least ship matching constraints, time window constraints, resource status constraints, and trajectory feasibility constraints. S203. Based on the feasible tugboat related data, planned trajectory, mission duration data and energy consumption data, call the composite heuristic algorithm to solve the mission planning model and obtain a mission scheme that satisfies all constraints and minimizes total energy consumption. S204. Perform model verification and effect evaluation on the solved task solution; S205. Output the optimal integrated tugboat mission plan. The mission plan shall include at least the assigned tugboat number, the assigned driver number, the assigned tugboat planned route, the total energy consumption of the tugboat, and the tugboat mission duration.

[0035] In this embodiment, the objective function in step S201 is:

[0036] in: Total energy consumption for all tugboat missions; For the first Energy consumption of a tugboat performing a mission; The number of tugboats participating in the mission.

[0037] Understandably, the model aims to optimize the total energy consumption of all tugboat tasks, and the number of tugboats participating in the task is at least one, but not limited to one.

[0038] In this embodiment, the constraints in step S202 are as follows: Ship matching constraints, the content of which is tugboat horsepower The required horsepower for large ships must be met. The minimum requirement, namely ; The time window constraint is the travel time of the tugboat from its current position to the start point of the operation. Compared with the estimated time of the mission The sum needs to be calculated within the large ship mission time window. within, that is ; Resource status constraints stipulate that the tugboat and the driver must be in an available state, and the driver's skills must match the task type.

[0039] The feasibility constraints of a route include the requirement that the planned route must be based on electronic nautical charts and channel heat maps, avoid obstacles, and comply with port navigation rules.

[0040] In this embodiment, in step S203, a composite heuristic algorithm, such as combining genetic algorithms, simulated annealing, or dynamic priority strategies, is used to quickly approximate the optimal solution while satisfying constraints. The algorithm generates feasible scheduling schemes randomly based on rules; generates new solutions by adjusting tugboat and task allocation, track nodes, etc.; uses total energy consumption as the main evaluation index, and combines mechanisms such as simulated annealing to accept some inferior solutions to escape local optima; repeats until convergence or the maximum number of iterations is reached.

[0041] Understandably, the goal of a composite heuristic algorithm is to find the scheduling scheme with the lowest energy consumption while satisfying all hard rules. It does not calculate the optimal solution all at once, but rather iterates extensively, starting from an initial feasible solution, continuously trying to fine-tune it, retaining good adjustments and accepting some seemingly worse adjustments, and finally converging to a relatively optimal solution. This is a mature existing algorithm, and will not be elaborated on further here.

[0042] In this embodiment, in step S204, the following steps are used to ensure the effectiveness and practicality of the model: using historical operation data to verify the consistency between the model output and the actual operation; analyzing the impact of key parameters such as speed, task duration, and environmental factors on the scheduling results; and adjusting the algorithm parameters based on actual operation feedback to improve the solution efficiency and quality.

[0043] Understandably, model verification confirms that the solved task solution does not violate any hard constraints, ensuring the theoretical feasibility of the solution; performance evaluation measures the actual performance of the solution in terms of energy consumption optimization, computational efficiency, and practicality, verifying whether the model is truly superior to existing methods.

[0044] In this embodiment, in step S205, the final output of the model includes the assigned tugboat number. Driver number assignment Assign the optimal tugboat route and estimate total energy consumption. Duration of a single tugboat trip The scheduling scheme.

[0045] In one embodiment, please refer to Figure 3 In step S102, the tugboat trajectory planning algorithm includes the following steps: S301. Construct a grid map model of the port area's sea area; S302. Based on the starting point coordinates, target point coordinates, and port area grid map model, call the energy-optimal A... The search algorithm performs trajectory planning to obtain a planned trajectory that satisfies the energy-optimal objective between the starting point coordinates and the target point coordinates; S303, Output the planned trajectory.

[0046] In this embodiment, in step S301, the port electronic nautical chart and historical ship trajectories are first extracted from the port-related information data; then, the port electronic nautical chart is decomposed and rasterized to divide the continuous water area into a uniform grid, resulting in a port area grid map; then, high-frequency path segments in the historical ship trajectories are extracted by combining the channel heat map analysis to construct a track passage probability map that reflects actual navigation preferences and safe passage probability; based on the track passage probability map, the node weights in the port area sea area grid map are adjusted to construct a port area sea area grid map model.

[0047] Furthermore, in step S302, based on the port area sea area grid map model, the starting point coordinate data of feasible tugboats, and the target point coordinate data, A is used. The algorithm was optimized by introducing a segment energy consumption assessment factor to obtain trajectory planning data. Among these, A was used based on a port area sea area grid map model. The optimization algorithm, as the core search algorithm, introduces a segment energy consumption evaluation factor on the basis of traditional geometric distance heuristics, ensuring that the output trajectory is not only the shortest in geometric distance, but also the best in estimated fuel consumption.

[0048] Furthermore, in step S302, parallel computing is used to improve the efficiency of data processing and path search, and node adjustments are made to optimize the node selection and expansion strategy in the path search process.

[0049] Furthermore, in step S303, the optimal recommended flight path that conforms to the actual operation stage and energy consumption optimization objectives is output.

[0050] In one embodiment, please refer to Figure 4 In step S104, the task duration prediction algorithm includes the following steps: S401. Extract the AIS data of the tugboat from the feasible tugboat related data and the AIS data of the large ship from the large ship related information data; S402. Based on AIS track clustering processing, output the free navigation trajectory points and escort operation trajectory points of the tugboat to obtain the free navigation trajectory and escort operation trajectory. S403. Perform cluster analysis on the required task duration of the free navigation trajectory and escort operation trajectory, and take the mean as the predicted task duration required for a single tugboat task. S404, Output the predicted task duration data.

[0051] Understandably, tugboat AIS data refers to raw data collected through the Automatic Identification System (AIS) that reflects the real-time dynamic and static information of tugboats. Tugboat AIS data is a spatiotemporal sequence of data acquired by the AIS, containing information such as tugboat identity, real-time location, speed, heading, and draft. It is the core data foundation for tugboat trajectory planning, energy consumption prediction, status monitoring, and scheduling optimization. AIS is a ship broadcasting system; tugboats automatically transmit their identity, location, and motion status information to shore-based base stations, satellites, and other vessels via AIS equipment. This data is the basic input for applications such as tugboat scheduling optimization, energy consumption prediction, and trajectory planning. Similarly, large ship AIS data is a spatiotemporal sequence of data acquired by the AIS, containing information such as the large ship's identity, real-time location, speed, estimated arrival / departure time, and draft. In tugboat scheduling, it defines the demand side of operational tasks, including core constraint parameters such as task triggering timing, time window boundaries, required tugboat horsepower, and operational rendezvous positions.

[0052] For further details, please refer to Figure 5 The method for clustering AIS tracks is as follows: S501. Based on the AIS data of the tugboat, preprocess the data to extract the speed, heading, speed change, heading change, speed change rate, and heading change rate to obtain a feature vector. S502. The feature vectors are clustered using the K-means clustering algorithm to identify the free-sailing trajectory points of the tugboat; S503. Based on the AIS data of the large ship, preprocess the ship's speed, heading, speed change, and heading change to obtain a fused feature vector. S504. Then, the fused feature vector is clustered a second time using the K-means clustering algorithm to separate the tugboat escort operation trajectory points.

[0053] Please refer to Figure 10 The K-means clustering algorithm includes: Randomly select K data points as the initial centroids, denoted as K. Where K is the number of clusters specified by the user, and the centroid represents the center point of each cluster. The initial selection is usually based on random sampling or heuristic methods. For each data point Calculate the Euclidean distance from each point to all centroids and assign each point to the cluster of the nearest centroid, thus dividing the data into K clusters. Each cluster contains a set of points, where the Euclidean distance formula is:

[0054] in, It is a data dimension. It is a point In the Dimension value, It is the center of mass. In the The value of the dimension; Recalculate the centroid of each cluster, repeating the assignment and update steps until the stopping condition is met, then output the result. The formula for calculating the centroid of each cluster is as follows:

[0055] in, It is a cluster The number of midpoints.

[0056] Understandably, the K-means clustering algorithm is a feasible method in AIS track clustering. By grouping the spatial locations of a large number of track points, it extracts key waypoints, typical sections or operating areas in the port area, providing a structured and reusable route network foundation for tugboat track planning.

[0057] Furthermore, by combining the AIS track clustering method with the port entry track duration prediction algorithm, the time required for a large ship to travel from the mooring point to the berth for a single port entry or departure can be obtained, serving as extractable feature data from the relevant information data of large ships.

[0058] Specifically, to obtain the time required for a large vessel to travel from the mooring point to the berth during a single port entry or departure, the method is as follows: Firstly, for AIS track clustering, the processed AIS data of large vessels in the port is acquired; large vessel types are classified based on different vessel characteristics; the AIS data is analyzed and track clustering is performed. Since the historical tracks in the system only have continuous tracks and cannot distinguish the start and end points of single operations, a two-stage track clustering algorithm is adopted. In the first stage, the original AIS data of tugboats is preprocessed to extract parameters such as speed, heading, speed change, heading change, speed change rate, and heading change rate to obtain feature vectors. The K-means clustering algorithm is used to perform cluster analysis on the feature vectors to identify the free navigation track points of tugboats. In the second stage, the original AIS data of large vessels is preprocessed to further extract parameters such as speed, heading, speed change, and heading change to obtain fused feature vectors. The K-means clustering algorithm is then used to perform secondary clustering on the fused feature vectors to separate the tugboat escort operation track points and the large vessel berthing and unberthing operation track points. Finally, the large vessel tracks classified by vessel type are output.

[0059] Secondly, for the prediction of the time required for the ship to enter the port, historical trajectory data of the berthing operation area of ​​large ships are read, and the trajectory information of different types of large ships output by AIS trajectory clustering is combined. The K-means clustering algorithm is used to cluster the time required for the large ship to travel from the mooring point to the berth, and the average value is taken as the predicted value of the time required for the large ship to travel from the mooring point to the berth.

[0060] Understandably, tugboat operation time is an output variable that the model needs to calculate and optimize, directly affecting resource usage and energy consumption; the time from mooring point to berth is usually a known input parameter, representing the fixed time consumption of the last segment of large vessel operations; the connection between the two needs to be clearly defined in the time window constraint: whether the tugboat operation time includes the time period from mooring point to berth determines the tugboat arrival time requirement and the overall time window verification logic.

[0061] In one embodiment, please refer to Figure 6 In step S104, the algorithm for the energy consumption prediction data is as follows: S601. Extract the tugboat AIS data and meteorological data from the feasible tugboat related data, and preprocess the tugboat AIS data and meteorological data. S602. Based on the processed tugboat AIS data and meteorological data, call the machine learning model to predict the dynamic parameters in the empirical formula for calculating tugboat energy consumption, and substitute the predicted parameters into the empirical formula to perform energy consumption prediction calculation to obtain the predicted energy consumption of the feasible tugboat. The dynamic parameters include at least the fuel consumption calibration coefficient. S603, outputs predicted energy consumption data.

[0062] The empirical formula for calculating tugboat energy consumption is as follows:

[0063] in Indicates flight segment Fuel consumption per nautical mile (tons / nautical mile); Indicates flight segment Fuel consumption calibration factor; Indicates flight segment The speed sensitivity coefficient; Indicates that the ship is in section The cruising speed (knots); the economic cruising speed range is ( ≤ ≤ ).

[0064] Understandably, the fuel consumption calibration coefficient is used to correct the dynamic deviation between theoretical and actual energy consumption, while the speed sensitivity coefficient is used to characterize the nonlinear growth law of energy consumption with speed. The two form the physical framework in the empirical formula, while the machine learning model is responsible for predicting and calibrating the fuel consumption calibration coefficient based on real-time information such as AIS data and meteorological data, making the prediction more accurate.

[0065] In one embodiment, please refer to Figure 7 The process of executing step S102, which involves screening feasible tugboats, may specifically include the following steps: S701. According to the ship matching rules, extract the tug horsepower from the tug relevant information data and the required horsepower of the large ship from the large ship relevant information data, match the tug horsepower with the required horsepower of the large ship, and obtain the corresponding tug number of the horsepower data matching. S702. Based on the obtained tugboat number, extract the real-time status of the corresponding tugboat from the tugboat-related information data, extract the available driver number and business capability data from the driver-related information data, and filter out candidate tugboats that are in an idle state and have available drivers with matching business capabilities. S703. Extract and, based on the tugboat's speed range, economic speed interval, and the large ship's mission time window, verify whether the sum of the tugboat's travel time from its current position to the start point of the operation and the estimated operation time is within the large ship's mission time window, ensuring that the tugboat can complete the navigation assistance mission on time. S704. Combining electronic nautical charts, berth layouts, and channel restrictions, verify whether the tugboat's draft and handling characteristics are suitable for the channel conditions of the operating area, eliminate tugboats with potential navigation safety hazards, and finally determine a set of feasible tugboats that meet the operational feasibility requirements.

[0066] In step S701, the compatibility between the tugboat's horsepower and the horsepower required by the large ship is verified to ensure that the tugboat's horsepower meets the minimum power requirements for the large ship's navigation assistance operations, while eliminating non-optimal candidate tugboats with excessive horsepower that would lead to energy waste.

[0067] According to the port tugboat task planning method provided in this embodiment, information data is acquired, wherein the information data includes at least tugboat-related information data, port-related information data, large vessel-related information data, and driver-related information data; in response to the information data, feasible tugboats are selected based on preset vessel matching rules, operational requirement constraints, and resource status constraints, and feasible tugboat-related data is obtained; starting point coordinates and target point coordinates are extracted from the feasible tugboat-related data, and a trajectory planning algorithm is invoked to plan the trajectory of the feasible tugboats, obtaining a planned trajectory; based on the large vessel-related information data, feasible tugboat-related data, and planned trajectory, a task duration prediction algorithm is invoked to predict the task duration of the feasible tugboats, obtaining task duration data, and simultaneously, a tugboat energy consumption prediction algorithm is invoked to predict the energy consumption of the feasible tugboats, obtaining energy consumption data; based on the feasible tugboat-related data, planned trajectory, task duration data, and energy consumption data, a tugboat task planning algorithm is invoked with the goal of minimizing total energy consumption to obtain a task plan.

[0068] In the dynamic operating environment of the port, based on information data of tugboats, ports, large ships and drivers, the optimal comprehensive tugboat task plan is quickly generated, which is safe, energy-saving and efficient. The tugboat task plan includes at least feasible drivers, task tugboats, optimal routes, task duration and total energy consumption, which improves the overall efficiency of port seaside operations and effectively reduces fuel consumption by relying on route planning and energy consumption prediction.

[0069] The above describes the port tugboat task planning method in the embodiments of the present invention. The following describes the port tugboat task planning device in the embodiments of the present invention. Please refer to [link / reference]. Figure 8 In this embodiment of the invention, the port tugboat task planning device 800 includes an information data acquisition module 801, a tugboat screening module 802, a tugboat trajectory planning module 803, a tugboat duration and energy consumption prediction module 804, and a tugboat task planning module 805.

[0070] In this embodiment, the information data acquisition module 801 is used to acquire information data, which includes at least tugboat-related information data, port-related information data, large ship-related information data, and driver-related information data.

[0071] Understandably, the information and data acquisition module 801 serves as an interaction channel between the system and the external port system. It is used to receive standardized operation instructions and data parameters, and to encapsulate the optimal scheduling scheme generated internally by the system into structured data or visual instructions, and return them to the port scheduling terminal. This interface supports real-time data exchange and status synchronization, ensuring seamless integration between scheduling decisions and the actual port production process.

[0072] Furthermore, the tugboat screening module 802 is used to respond to information data, and based on preset ship matching rules, operational requirement constraints and resource status constraints, to screen out feasible tugboats and obtain relevant data on feasible tugboats.

[0073] Understandably, after acquiring the information data, the tugboat screening module 802 filters out feasible tugboats based on preset ship matching rules, operational requirement constraints, and resource status constraints, and obtains relevant data on feasible tugboats.

[0074] Furthermore, the tugboat trajectory planning module 803 is used to extract the starting point coordinates and target point coordinates from the relevant data of feasible tugboats, call the trajectory planning algorithm, generate the trajectory planning of feasible tugboats, and obtain the planned trajectory.

[0075] Understandably, after receiving the target location and available tug information for a specific task, the tugboat trajectory planning module 803 calls the tugboat trajectory planning algorithm to output feasible tugboat planning trajectories, planning a safe, efficient, and feasible trajectories from the current location to the work point for each candidate tugboat, and providing accurate spatial path input for subsequent energy consumption prediction.

[0076] Furthermore, the tugboat duration and energy consumption prediction module 804 is used to, based on the relevant information data of the large ship, the relevant data of the feasible tugboat, and the planned trajectory, call the task duration prediction algorithm to predict the task duration of the feasible tugboat, obtain the task duration data, and simultaneously call the tugboat energy consumption prediction algorithm to predict the energy consumption of the feasible tugboat, obtain the energy consumption data.

[0077] Understandably, the tugboat duration energy consumption prediction module 804 receives the planned trajectory output by the tugboat trajectory planning module 803, and combines it with the tugboat's real-time operation data, wind and wave environment data, and ship characteristic parameters. Through an integrated machine learning prediction model and energy consumption empirical formula, it performs CO2 emission prediction, providing key energy efficiency analysis and evaluation basis for the mission planning module and assisting in intelligent navigation decision-making.

[0078] Furthermore, the tugboat mission planning module 805 is used to call the tugboat mission planning algorithm based on the feasible tugboat related data, planned trajectory, mission duration data and energy consumption data, with the goal of minimizing total energy consumption, to obtain a mission plan.

[0079] Understandably, the tugboat task planning module 805, as the core decision-making unit of the system, is used to integrate the operational requirements from the interface, the status of available tugboats and drivers, the planned trajectory and the corresponding predicted energy consumption. Based on the tugboat task duration, tugboat energy consumption and the acquired data output by the tugboat energy consumption prediction module, it calculates and outputs the final optimized scheduling scheme, including tugboat assignment, driver allocation, recommended execution trajectory and estimated total energy consumption, by calling the tugboat task planning algorithm.

[0080] In another implementation, please refer to Figure 8 The port tugboat mission planning device 800 also includes an entry trajectory duration prediction module 806, which, based on the AIS data of large ships in the port, obtains the time required for a single entry or departure of a large ship from the mooring point to the berth, and uses this as feature data that can be extracted from the relevant information data of the large ship.

[0081] above Figure 8 The port tugboat task planning and trajectory planning device for energy consumption optimization in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The electronic equipment in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0082] Please refer to Figure 9The present invention provides a structural diagram of a specific embodiment of an electronic device. The electronic device includes a memory 90 for storing computer programs. The resources stored in the memory 90 may include an operating system 902 and data 903, and the storage method may be temporary or permanent storage. The operating system 902 may include Windows, Unix, Linux, etc. The data 903 may include, but is not limited to, input and output data of a port tugboat task planning and trajectory planning device for energy consumption optimization. A processor 91 is used to execute the computer program to implement the steps of the port tugboat task planning and trajectory planning method for energy consumption optimization mentioned in any of the above embodiments. The processor 91 may include one or more processing cores, such as a 4-core processor or a 9-core processor. The processor 91 may also be a controller, microcontroller, microprocessor, or other data processing chip.

[0083] In some embodiments, the above-mentioned electronic device may further include a display screen 92, an input / output interface 93, a communication interface 94 or network interface, various sensors 95, a communication bus 96, and a power supply 97; wherein, the display screen may be an LED display screen, an LCD display screen, a touch LCD display screen, or an OLED (Organic Light-Emitting Diode) touch screen, etc. The communication interface 94 may optionally include a wired interface and / or a wireless interface, such as a WI-FI interface, a Bluetooth interface, etc., which is usually used to establish a communication connection between the electronic device and other electronic devices. The communication bus 96 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc., and this bus may be divided into an address bus, a data bus, a control bus, etc.

[0084] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the electronic device. It may include more or fewer components than shown.

[0085] Based on this, the present invention also provides a readable storage medium storing a computer program, wherein when executed by a processor, the computer program performs the steps of the port tugboat task planning method described in any of the above embodiments. This computer-readable storage medium can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when executed by a processor, the computer program implements the port tugboat task planning method disclosed in the embodiments of the present invention.

[0086] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0087] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Units with the same function may be grouped into one unit. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, or may be electrical, mechanical, or other forms of connection.

[0088] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0089] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0090] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, a backend server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks.

[0091] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A port tugboat task planning method, characterized in that, Includes the following steps: Acquire information data, wherein the information data includes at least tugboat-related information data, port-related information data, large ship-related information data, and driver-related information data; In response to the information data, based on preset ship matching rules, operational requirement constraints and resource status constraints, feasible tugboats are selected and relevant data of feasible tugboats are obtained; The starting point coordinates and the target point coordinates are extracted from the relevant data of the feasible tugboat. The trajectory planning algorithm is called to plan the trajectory of the feasible tugboat and obtain the planned trajectory. Based on the aforementioned large ship-related information data, feasible tugboat-related data, and planned trajectories, a task duration prediction algorithm is invoked to predict the task duration of feasible tugboats, obtaining task duration data. Simultaneously, a tugboat energy consumption prediction algorithm is invoked to predict the energy consumption of feasible tugboats, obtaining energy consumption data. Based on the feasible tugboat-related data, planned trajectory, mission duration data, and energy consumption data, the tugboat mission planning algorithm is invoked to obtain a mission plan with the goal of minimizing total energy consumption.

2. The port tugboat task planning method according to claim 1, characterized in that, The tugboat task planning algorithm includes the following steps: Taking the entire process of tugboat navigation assistance operations as the object, and establishing an objective function with minimizing total energy consumption as the first priority; Based on the objective function and the preset constraints, a task planning model is constructed, wherein the constraints include at least ship matching constraints, time window constraints, resource status constraints, and trajectory feasibility constraints. Based on the feasible tugboat related data, planned trajectory, mission duration data and energy consumption data, a composite heuristic algorithm is invoked to solve the mission planning model, resulting in a mission scheme that satisfies all constraints and minimizes total energy consumption. The solved task solutions are then validated and their effectiveness evaluated. Output the optimal integrated tugboat mission plan. The mission plan should include at least the assigned tugboat number, the assigned driver number, the planned tugboat route, the total energy consumption of the tugboat, and the mission duration of the tugboat.

3. The port tugboat task planning method according to claim 2, characterized in that, The objective function is: in, Total energy consumption for all tugboat missions; For the first Energy consumption of a tugboat performing a mission; The number of tugboats participating in the mission.

4. The port tugboat task planning method according to claim 1, characterized in that, The tugboat trajectory planning algorithm includes the following steps: Construct a grid map model of the port area's sea area; Based on the starting point coordinates, target point coordinates, and port area grid model, the energy-optimal A algorithm is invoked. The search algorithm performs trajectory planning to obtain a planned trajectory that satisfies the energy-optimal objective between the starting point coordinates and the target point coordinates; Output the planned trajectory.

5. The port tugboat task planning method according to claim 1, characterized in that, The task duration prediction algorithm includes the following steps: Extract the AIS data of the tugboat from the feasible tugboat-related data and the AIS data of the large ship from the large ship-related information data; Based on AIS track clustering processing, the free navigation track points and escort operation track points of the tugboat are output to obtain the free navigation track and escort operation track. Cluster analysis was performed on the required task durations of the free navigation trajectory and escort operation trajectory, and the mean value was taken as the predicted task duration required for a single tugboat mission. Output the predicted task duration data.

6. The port tugboat task planning method according to claim 5, characterized in that, The method for AIS track clustering is as follows: Preprocessing is performed on the AIS data of the tugboat to extract the speed, heading, speed change, heading change, speed change rate, and heading change rate to obtain a feature vector. The feature vectors were clustered using the K-means clustering algorithm to identify the free-sailing trajectory points of the tugboat. Preprocessing is performed on the AIS data of the large ship to extract the ship's speed, heading, speed change, and heading change to obtain a fused feature vector. Then, the fused feature vector is clustered a second time using the K-means clustering algorithm to separate the tugboat escort operation trajectory points.

7. The port tugboat task planning method according to claim 1, characterized in that, The tugboat energy consumption prediction algorithm includes the following steps: Extract the tugboat AIS data and meteorological data from the feasible tugboat-related data, and preprocess the tugboat AIS data and meteorological data; Based on the processed AIS data and meteorological data of the tugboat, a machine learning model is called to predict the dynamic parameters in the empirical formula for calculating the energy consumption of the tugboat. The predicted parameters are then substituted into the empirical formula to perform energy consumption prediction calculations and obtain the predicted energy consumption of the feasible tugboat. The dynamic parameters include at least a fuel consumption calibration coefficient. Output the predicted energy consumption data.

8. A port tugboat task planning device, characterized in that, The port tugboat task planning device includes: The information data acquisition module is used to acquire information data, which includes at least tugboat-related information data, port-related information data, large ship-related information data, and driver-related information data. The tugboat screening module is used to respond to information data and, based on preset vessel matching rules, operational requirement constraints, and resource status constraints, screen out feasible tugboats and obtain relevant data on feasible tugboats. The tugboat trajectory planning module is used to extract the starting point coordinates and target point coordinates from the relevant data of feasible tugboats, call the trajectory planning algorithm, generate the trajectory plan of feasible tugboats, and obtain the planned trajectory. The tugboat duration and energy consumption prediction module is used to predict the duration of the feasible tugboat based on the relevant information data of the large ship, the relevant data of the feasible tugboat and the planned trajectory, and simultaneously call the tugboat energy consumption prediction algorithm to predict the energy consumption of the feasible tugboat and obtain the energy consumption data. The tugboat mission planning module is used to call the tugboat mission planning algorithm based on the feasible tugboat related data, planned trajectory, mission duration data and energy consumption data, with the goal of minimizing total energy consumption, to obtain a mission plan.

9. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to implement the steps of the port tugboat task planning method as described in any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the port tugboat task planning method as described in any one of claims 1 to 7.

Images