CN115630580A - Intelligent decision-making assisting method for entering and exiting port and relying on berthing of ship based on multi-source data - Google Patents
Intelligent decision-making assisting method for entering and exiting port and relying on berthing of ship based on multi-source data Download PDFInfo
- Publication number
- CN115630580A CN115630580A CN202211363786.4A CN202211363786A CN115630580A CN 115630580 A CN115630580 A CN 115630580A CN 202211363786 A CN202211363786 A CN 202211363786A CN 115630580 A CN115630580 A CN 115630580A
- Authority
- CN
- China
- Prior art keywords
- ship
- port
- berthing
- data
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/12—Timing analysis or timing optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Computational Mathematics (AREA)
- Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Geometry (AREA)
Abstract
The embodiment of the application provides an intelligent decision-making method for entering and exiting ports and berthing of ships based on multi-source data. The method comprises the following steps: acquiring marine environment data of a port area and an open sea area of the port area in a preset historical period; establishing a port environment information forecasting model according to the marine environment data; establishing a ship berthing model according to environmental data and ship data kept in the ballasting time in the historical berthing process of the ship; inputting the environmental parameters of the open sea area of the current port area into a port environmental information forecasting model to obtain environmental parameter forecasting data output by the port environmental information forecasting model; forecasting the time for the ship to enter and exit the port according to the minimum water level required by the ship to enter and exit the port on the basis of the environmental parameter forecasting data, and determining the time of starting the ship corresponding to the time for the ship to enter and exit the port; and in the berthing or debarking stage, inputting the environmental parameters of the current berthing area and the draught and trim of the ship into a ship berthing model to obtain the rotating speed and rudder angle required by the ship berthing model to keep the stability.
Description
Technical Field
The application relates to the technical field of ships, in particular to an intelligent decision-making assisting method for entering and exiting ports and relying on berthing of a ship based on multi-source data.
Background
At present, port entering and exiting and berthing are mainly controlled by a captain, so that high requirements are imposed on the personal capability of the captain, the captain can be influenced by experience, fatigue, personal preference and the like during command operation, and accidents are easily caused by personal judgment. Therefore, it is highly desirable to provide assistant decision-making suggestions for the captain to perform operations of entering and exiting ports and controlling the command by means of berthing, so as to help the captain to improve the accuracy of the decision.
Disclosure of Invention
The embodiment of the application provides an intelligent decision-making method for entering and exiting ports and berthing, which is based on multi-source data, and comprises the following steps:
marine environment data of a harbor district and an open sea area in the harbor district in a preset historical period are obtained, wherein the marine environment data comprise time sequences of environment parameters on corresponding coordinates, and the environment parameters comprise wind speed, wind direction, flow speed, flow direction and water level;
establishing a port environment information forecasting model according to the marine environment data;
acquiring environment data and ship data at the holding time in the historical berthing process of a ship, and establishing a ship berthing model according to the environment data and the ship data at the holding time in the historical berthing process of the ship;
acquiring current harbor district open sea area environment parameters, inputting the current harbor district open sea area environment parameters into the harbor environment information forecasting model, and acquiring environment parameter forecasting data output by the harbor environment information forecasting model;
forecasting the time of the ship capable of entering and leaving the port according to the minimum water level required by the ship to enter and leave the port on the basis of the environmental parameter forecasting data, and determining the time of starting the ship corresponding to the time of the ship capable of entering and leaving the port;
and in the berthing or debarking stage, acquiring the environmental parameters of the current berthing area and the draft and the trim of the ship, inputting the environmental parameters of the current berthing area and the draft and the trim of the ship into the ship berthing model, and obtaining the rotating speed and the rudder angle required by the ship berthing model to keep the stability.
In some optional embodiments, the establishing a port environment information forecasting model according to the marine environment data includes:
establishing marine environment calculation models of the harbor district and the foreign sea area of the harbor district according to the marine environment data, and determining the environmental parameters on each position in the harbor district corresponding to different environmental parameters in the foreign sea area of the harbor district according to the marine environment calculation models;
according to the marine environment data and the marine environment calculation model, determining time sequences of environmental parameters at n buoys and k sea area central positions in an open sea area of a port area and time sequences of environmental parameters at m coordinate positions in the port area;
and establishing the port environment information forecasting model by taking time series of environment parameters at n buoys and k sea area central positions in the open sea area of the port area as independent variables and time series of the environment parameters after forecasting time length corresponding to each coordinate position in the m coordinate positions as dependent variables, wherein the port environment forecasting model comprises m neural network models respectively corresponding to the m coordinate positions.
In some optional embodiments, the obtaining environmental data and ship data at the time of keeping the ship in the historical berthing process, and establishing a ship berthing model according to the environmental data and the ship data at the time of keeping the ship in the historical berthing process includes:
acquiring environmental parameters of keeping a fixed-time berth in a j-time berthing process in historical berthing data of the ship, the draught and the trim of the ship, and the rotating speed and the rudder angle of a main engine of the ship;
and establishing a neural network model for training by taking the environmental parameters of the berthing at the constant holding time in the j berthing process and the draught and the trim of the ship as independent variables and the corresponding main engine rotating speed and rudder angle of the ship as dependent variables to obtain the ship berthing model.
In some optional embodiments, the determining determines the departure time of the ship corresponding to the port-accessible time, including:
determining the starting time of the ship leaving the anchor land according to the time of the ship entering the port, the distance from the anchor land to the port gate and the average speed of the ship navigating in the port;
and determining the starting time of the ship leaving the berth according to the time of the ship leaving the berth, the distance from the berth to a port gate and the average speed of the ship navigating in the port.
According to the embodiment of the application, by providing the intelligent decision-making method for the ship entering and exiting port and the ship berthing based on multi-source data, marine environment data of a port area and an offshore area outside the port area in a preset historical period are obtained, wherein the marine environment data comprise time sequences of environment parameters on corresponding coordinates, and the environment parameters comprise wind speed, wind direction, flow speed, flow direction and water level; establishing a port environment information forecasting model according to the marine environment data; acquiring environment data and ship data at the holding time in the historical berthing process of the ship, and establishing a ship berthing model according to the environment data and the ship data at the holding time in the historical berthing process of the ship; acquiring environmental parameters of the open sea area of the current harbor area, and inputting the environmental parameters of the open sea area of the current harbor area into a harbor environmental information forecasting model to obtain environmental parameter forecasting data output by the harbor environmental information forecasting model; forecasting the time of the ship capable of entering and leaving the port according to the lowest water level required by the ship to enter and leave the port on the basis of the environmental parameter forecasting data, and determining the time of starting the ship corresponding to the time of the ship capable of entering and leaving the port; in a berthing or debarking stage, acquiring environmental parameters of a current berthing area and the draft and trim of a ship, and inputting the environmental parameters of the current berthing area and the draft and trim of the ship into a ship berthing model to obtain the rotating speed and rudder angle required by the ship berthing model to keep calm; the method can provide auxiliary decision suggestions when the ship executes port entering and exiting and berthing operation commands, and helps to improve the accuracy of the ship operation commands. The embodiment of the application is based on the measured data, the actual sea condition is comprehensively considered, and the decision accuracy of the model is high.
Drawings
The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed herein.
FIG. 1 is a schematic flow chart of an intelligent decision-making method for entering and exiting a port and relying on berthing of a ship based on multi-source data according to an embodiment of the present application;
FIG. 2 is a diagram illustrating independent variables and dependent variables in the process of establishing a port environment information forecasting model;
fig. 3 is a time correspondence between independent variables and dependent variables in the process of establishing a port environment information forecasting model.
Detailed Description
So that the manner in which the features and elements of the present embodiments can be understood in detail, a more particular description of the embodiments, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings.
Fig. 1 is a schematic flow chart of an intelligent decision-making method for entering and exiting a port and berthing of a ship based on multi-source data according to an embodiment of the present application. As shown in fig. 1, the embodiment of the present application provides an intelligent assistant decision-making method for entering and exiting a port and berthing of a ship based on multi-source data, which includes the following steps 11 to 16.
And 11, acquiring marine environment data of the harbor district and the open sea area of the harbor district in a preset historical period. The marine environment data comprises a time sequence of environment parameters on corresponding coordinates, wherein the environment parameters comprise wind speed, wind direction, flow speed, flow direction and water level.
And step 12, establishing a port environment information forecasting model according to the marine environment data.
In some optional embodiments, establishing a port environment information forecasting model according to the marine environment data includes:
and establishing marine environment calculation models of the harbor district and the foreign sea area of the harbor district according to the marine environment data, and determining the environmental parameters on each position in the harbor district corresponding to different environmental parameters in the foreign sea area of the harbor district according to the marine environment calculation models.
According to the marine environment data and the marine environment calculation model, time sequences of environment parameters at n buoys and k sea area central positions in the open sea area of the port area and time sequences of the environment parameters at m coordinate positions in the port area are determined.
And establishing a port environment information forecasting model by taking the time series of the environment parameters at the n buoys and the k sea area central positions in the open sea area of the port area as independent variables and the time series of the environment parameters after forecasting the time length corresponding to each coordinate position in the m coordinate positions as dependent variables, wherein the port environment forecasting model comprises m neural network models respectively corresponding to the m coordinate positions.
And step 13, acquiring the environmental data and the ship data which are kept at the stabilizing time in the historical berthing process of the ship, and establishing a ship berthing model according to the environmental data and the ship data which are kept at the stabilizing time in the historical berthing process of the ship.
In some optional embodiments, the obtaining environmental data and ship data at the time of keeping the town in the historical berthing process of the ship, and establishing a ship berthing model according to the environmental data and the ship data at the time of keeping the town in the historical berthing process of the ship comprises:
and acquiring environmental parameters for keeping the fixed-time berth of the ballast in the j berthing process in the historical berthing data of the ship, the draft and the trim of the ship, and the rotating speed and the rudder angle of a main engine of the ship.
And establishing a neural network model for training by taking the environmental parameters of the berthing at the constant time of keeping the berth and the draught and the trim of the ship as independent variables and the corresponding main engine rotating speed and rudder angle of the ship as dependent variables in the berthing process for j times to obtain a ship berthing model.
And step 14, acquiring the environmental parameters of the current open sea area of the port area, inputting the environmental parameters of the current open sea area of the port area into the port environmental information forecasting model, and acquiring environmental parameter forecasting data output by the port environmental information forecasting model.
And step 15, forecasting the time of the ship capable of entering and leaving the port according to the lowest water level required by the ship to enter and leave the port on the basis of the environmental parameter forecasting data, and determining the time of starting the ship corresponding to the time of the ship capable of entering and leaving the port.
And step 16, in the berthing or debarking stage, acquiring the environmental parameters of the current berthing area and the draft and trim of the ship, and inputting the environmental parameters of the current berthing area and the draft and trim of the ship into a ship berthing model to obtain the rotating speed and rudder angle required by the ship berthing model to keep the ship berthing.
In some optional embodiments, determining the departure time of the ship corresponding to the port-accessible time comprises:
and determining the starting time of the ship leaving the anchor land according to the time of the ship entering the port, the distance from the anchor land to the port gate and the average speed of the ship navigating in the port.
And determining the starting time of the ship leaving the berth according to the time of the ship leaving the berth, the distance from the berth to the port door of the port area and the average speed of the ship sailing in the port.
According to the embodiment of the application, auxiliary decision suggestions can be provided when the ship carries out port entering and exiting and berthing operation commands, and the accuracy of the ship operation commands is improved. The embodiment of the application is based on the measured data, the actual sea condition is comprehensively considered, and the decision accuracy of the model is high. According to the technical scheme, auxiliary decision suggestions can be provided for the captain when entering and exiting ports and operating and commanding by means of berthing, and the captain is helped to improve the decision accuracy.
Another embodiment of the present application provides an intelligent decision-making method for entering and exiting port and berthing of a ship based on multi-source data, which includes the following steps 21 to 24.
And step 21, establishing a port environment information forecasting model.
The environmental factors influencing the navigation of the ship mainly comprise: wind, waves and current, and the influence of water level is also considered when sailing in a harbor area. In a harbor district, because the waves are blocked by a breakwater, the influence on the navigation of the ship is weak, and the forecast is not made. And forecasting is needed for wind, flow and water level.
The process of establishing the port environment information forecasting model comprises the following steps s1 to s5:
step s1, historical marine environment data of a port area and a foreign sea area of the port area are collected. Here, the historical marine environment data includes time series of wind speed, wind direction, flow speed, flow direction and water level on corresponding coordinates of the inland and overseas areas of the harbor in a preset historical period.
And step s2, establishing a port area and a marine environment calculation model of the open sea area of the port area. And calculating environmental parameters of different parameter combinations in the open sea area at various positions in the harbor area.
The marine environment calculation model is that calculation grids are generated in areas (including harbors and harbors) needing forecasting by using calculation software such as SWAN, WAVEWATECH III, MIKE21 and the like so as to establish a calculation domain, and then parameters such as wave height, wave direction, flow speed, flow direction, wind speed, wind direction and the like are artificially set in the areas outside the harbor, such as wave height 5m, wave direction 30 degrees, flow speed 0.3m/s, flow direction 45 degrees, wind speed 3m/s and wind direction 30 degrees. Each set of data is a combination. When the combination of the environment parameters outside the harbor is determined, the whole calculation domain can be solved by using the calculation software, so that the corresponding environment parameters in the harbor are obtained. A group of environment parameter combinations outside the port can be solved through software to obtain a group of environment parameter combinations inside the port.
And extracting data at n buoys outside the harbor area and data at k sea area center positions. The sea area here generally refers to a sea area where ships frequently pass or are berthed. Such as main channel, anchor, etc. These data may be collectively referred to as out-of-port regional data. The data comprises historical marine environment data in step s1 and data calculated according to a marine environment calculation model in step s 2.
And step s3, dividing the area in the harbor into M grids according to the calculation force, and extracting data on each grid coordinate. And generating grids for the area needing forecasting by using computing software, wherein the number of the grids is determined by computing power.
Step s4, taking data outside port as an argument X = (X) 1 ,x 2 …) at a point in the harbor zone is strain amount Y = (Y) 1 ) The corresponding relationship between the long and short memory neural network LSTM, the independent variable and the dependent variable is established as shown in FIG. 2. When the model is trained, the time sequence of the environmental parameters needs to be dispersed into a plurality of time periods according to a K hour period, and each time period contains independent variables and dependent variables. However, the start-stop time of the independent variable is different from the start-stop time of the dependent variable. For example, when the start-stop time of the independent variable is 0 to K, the start-stop time of the dependent variable needs to be t to K + t. The parameter K, t can be determined according to the calculation power, prediction accuracy, and the like. Here, t is the length of time that needs to be forecasted. For example: the length of each training is 10, the start-stop time is from 1 to 10, the output length is also 10, but the start-stop time is from 3 to 13. When the model is adopted, data (-10-0) in the period from the moment (-10) of the last ten minutes to the moment is input, and the output result is data from the moment (-7-3) of the last seven minutes to the moment (-7-3) of the future three minutes, so that data in the future 3 minutes is obtained, and the forecast is realized. After the LSTM model training is completed, the extra-harbor data with the length from P-K time to P time is input at the time P, and the data at a certain point in the harbor within the period from P-K + t time to P + t time can be obtained, as shown in FIG. 3. Therefore, forecast data within t hours in the future can be obtained. Of course, the neural network model applicable here is not limited to LSTM, and other models may be employed.
And step s5, taking the data of each position in the harbor area as dependent variables respectively, and repeating the process of the step 4 to finally enable each position in the harbor to correspond to an LSTM neural network. Thus, an environmental parameter forecasting model of the water area in the harbor is established.
And step 22, establishing a ship berthing model. Extracting the water flow velocity V of j times of ballast keeping time of the ship in the previous berthing process c To the direction of flowWind speed V w Wind directionWater depth h, offshore distance p, draft dr, trim t, main engine rotation speed n and rudder angle sigma. The flow velocity V of the water flow c To the flow direction ofWind speed V w Wind directionDepth of water h, offshore distance p, draft dr, trim t as independent variables A = (a) 1 ,a 2 …, aj), the main machine rotation speed n, and the rudder angle σ as the dependent variable B = (B) 1 ,b 2 …, bj) and establishing an artificial neural network by taking the ship survey data as a training sample for training. Neural networks include various types, such as BP neural networks, RNN neural networks, and the like. The trained model, namely the ship berthing model, can be based on the flow velocity V c To the direction of flowWind speed V w Wind directionThe main engine rotating speed n and the rudder angle sigma required by ship stabilization are pushed by the water depth h, the offshore distance p, the draft dr and the trim t.
And step 23, forecasting the environmental parameters by using the buoy data and the ship survey environmental data. The environmental parameter forecast of the harbor district needs buoy data outside the harbor and sea area data. The buoy data is acquired automatically by the buoy, and the sea area data is acquired by averaging ship measurement data in the sea area. When a ship enters a peripheral sea area of a port, the communication equipment can be automatically connected with an information management platform of the port area, ship measurement environment data, time, coordinates and the like obtained by ship measurement are uploaded, and buoy data and sea area data of all parts are downloaded at the same time. After the data is obtained, the data is input into a harbor district environment forecasting system, and the harbor district environment forecasting information which is accurate in real time can be obtained.
The water level and flow rate and direction at the port door are key parameters in entering and exiting the port. During berthing, the water level, the flow speed and the flow direction, the wind speed and the wind direction at the berth are the key.
And step 24, providing an assistant decision suggestion.
The ship-based system forecasts when the ship can enter the port according to the lowest water level required by the ship to enter and exit the port, such as a port door, a berth and a channel from the port door to the berth, on the basis of the environment forecast data, and pushes when the ship starts to leave the anchor according to the distance q1 from the anchor of the ship to the port door of the port area and the average speed v of the ship sailing in the port. If the port can be entered at time T1, the anchor should be left at time T1-q 1/v. When the ship leaves the port, the ship-based system forecasts when the ship can leave the port according to the lowest water level required by the ship to enter and leave the port on the basis of the environment forecast data. Meanwhile, pushing when the ship starts to leave the berth according to the distance q2 from the berth to the port door of the port and the average speed v of the navigation in the port of the ship. If departure from port is possible at time T2, then the station should be left at time T2-q 2/v. The ship-based system also pushes the rotating speed n and the rudder angle sigma required by the ship to keep calm based on the forecasted environmental data in the berthing or the departing stage.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other combinations of features described above or equivalents thereof without departing from the spirit of the disclosure. For example, the above features may be formed interchangeably with, but not limited to, features disclosed in this application having similar functions.
Claims (4)
1. A ship port entering and exiting and berthing intelligent aid decision-making method based on multi-source data is characterized by comprising the following steps:
marine environment data of a harbor district and an open sea area in the harbor district in a preset historical period are obtained, wherein the marine environment data comprise time sequences of environment parameters on corresponding coordinates, and the environment parameters comprise wind speed, wind direction, flow speed, flow direction and water level;
establishing a port environment information forecasting model according to the marine environment data;
acquiring environmental data and ship data which are kept at a fixed time in the historical berthing process of a ship, and establishing a ship berthing model according to the environmental data and the ship data which are kept at the fixed time in the historical berthing process of the ship;
acquiring current harbor district open sea area environment parameters, inputting the current harbor district open sea area environment parameters into the harbor environment information forecasting model, and acquiring environment parameter forecasting data output by the harbor environment information forecasting model;
forecasting the time of the ship capable of entering and leaving the port according to the lowest water level required by the ship to enter and leave the port on the basis of the environmental parameter forecasting data, and determining the time of starting the ship corresponding to the time of the ship capable of entering and leaving the port;
and in the berthing or debarking stage, acquiring the environmental parameters of the current berthing area and the draft and the trim of the ship, inputting the environmental parameters of the current berthing area and the draft and the trim of the ship into the ship berthing model, and obtaining the rotating speed and the rudder angle required by the ship berthing model to keep the stability.
2. The method as claimed in claim 1, wherein the establishing a port environment information forecasting model according to the marine environment data comprises:
establishing marine environment calculation models of the harbor district and the foreign sea area of the harbor district according to the marine environment data, and determining the environmental parameters on each position in the harbor district corresponding to different environmental parameters in the foreign sea area of the harbor district according to the marine environment calculation models;
according to the marine environment data and the marine environment calculation model, determining time sequences of environmental parameters at n buoys and k sea area central positions in an open sea area of a port area and time sequences of environmental parameters at m coordinate positions in the port area;
and establishing the port environment information forecasting model by taking time series of environment parameters at n buoys and k sea area central positions in the open sea area of the port area as independent variables and time series of the environment parameters after forecasting time length corresponding to each coordinate position in the m coordinate positions as dependent variables, wherein the port environment forecasting model comprises m neural network models respectively corresponding to the m coordinate positions.
3. The method of claim 2, wherein the obtaining environmental data and ship data at the time of keeping the ship in the historical berthing process, and the building of the ship berthing model according to the environmental data and the ship data at the time of keeping the ship in the historical berthing process comprises:
acquiring environmental parameters of keeping a fixed-time berth in a j-time berthing process in historical berthing data of the ship, the draught and the trim of the ship, and the rotating speed and the rudder angle of a main engine of the ship;
and establishing a neural network model for training by taking the environmental parameters of the berthing at the constant holding time in the j berthing process and the draught and the trim of the ship as independent variables and the corresponding main engine rotating speed and rudder angle of the ship as dependent variables to obtain the ship berthing model.
4. The method of claim 1, wherein said determining the departure time of the vessel corresponding to said port available time comprises:
determining the starting time of the ship leaving the anchor land according to the time of the ship entering the port, the distance from the anchor land to the port gate and the average speed of the ship navigating in the port;
and determining the starting time of the ship leaving the berth according to the time of the ship leaving the berth, the distance from the berth to a port gate and the average speed of the ship navigating in the port.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211363786.4A CN115630580A (en) | 2022-11-02 | 2022-11-02 | Intelligent decision-making assisting method for entering and exiting port and relying on berthing of ship based on multi-source data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211363786.4A CN115630580A (en) | 2022-11-02 | 2022-11-02 | Intelligent decision-making assisting method for entering and exiting port and relying on berthing of ship based on multi-source data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115630580A true CN115630580A (en) | 2023-01-20 |
Family
ID=84908928
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211363786.4A Pending CN115630580A (en) | 2022-11-02 | 2022-11-02 | Intelligent decision-making assisting method for entering and exiting port and relying on berthing of ship based on multi-source data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115630580A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117437810A (en) * | 2023-10-25 | 2024-01-23 | 亿海蓝(北京)数据技术股份公司 | Method and device for determining ship berthing time and readable storage medium |
-
2022
- 2022-11-02 CN CN202211363786.4A patent/CN115630580A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117437810A (en) * | 2023-10-25 | 2024-01-23 | 亿海蓝(北京)数据技术股份公司 | Method and device for determining ship berthing time and readable storage medium |
CN117437810B (en) * | 2023-10-25 | 2024-02-23 | 亿海蓝(北京)数据技术股份公司 | Method and device for determining ship berthing time and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110967022B (en) | Ship navigational speed optimization auxiliary decision-making system | |
CN110083983B (en) | Ship sectional navigational speed optimization method and intelligent management system | |
CN113221449B (en) | Ship track real-time prediction method and system based on optimal strategy learning | |
Wei et al. | 23. Development of a 3D Dynamic Programming Method for Weather Routing | |
KR102589008B1 (en) | A device for determining the optimal route of a maritime vessel | |
JP2015523557A (en) | Method and system for route determination for ship | |
CN108711312A (en) | Ship based on BP neural network and static object mark risk of collision pre-judging method | |
KR20150021970A (en) | Method and system for predicting the performance of a ship | |
CN112699497B (en) | Method and system for establishing route and speed multi-target combined optimization model | |
CN112446096A (en) | Ship host engine oil consumption dynamic estimation method based on big navigation data | |
CN114444315B (en) | Ship platform avoidance route simulation method and system | |
Marie et al. | 1 Multi-objective optimization of motor vessel route | |
CN111199103A (en) | Full-flow automatic calculation speed optimization method and system for full-electric propulsion ship | |
CN115630580A (en) | Intelligent decision-making assisting method for entering and exiting port and relying on berthing of ship based on multi-source data | |
CN109460874B (en) | Sense wave height prediction method based on deep learning | |
CN117232520A (en) | Ship intelligent navigation system and navigation method suitable for offshore navigation | |
CN110778398B (en) | Marine diesel engine fuel management control system | |
CN116895187A (en) | Inland ship navigation risk early warning method and device | |
Krata et al. | Bayesian approach to ship speed prediction based on operational data | |
CN114841635A (en) | Ecological route planning method considering underwater radiated sound of ship | |
Coraddu et al. | Integration of seakeeping and powering computational techniques with meteo-marine forecasting data for in-service ship energy assessment | |
Vettor et al. | Multi-objective route optimization for onboard decision support system | |
Li et al. | Multi-objective optimization in ship weather routing | |
CN117742346A (en) | Real-time navigation state analysis and energy consumption control method for ship | |
CN117806311A (en) | Unmanned ship path planning method and device with multiple task points |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |