CN112699497B - Method and system for establishing route and speed multi-target combined optimization model - Google Patents
Method and system for establishing route and speed multi-target combined optimization model Download PDFInfo
- Publication number
- CN112699497B CN112699497B CN202110087030.0A CN202110087030A CN112699497B CN 112699497 B CN112699497 B CN 112699497B CN 202110087030 A CN202110087030 A CN 202110087030A CN 112699497 B CN112699497 B CN 112699497B
- Authority
- CN
- China
- Prior art keywords
- ship
- model
- target
- route
- speed
- 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.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000010801 machine learning Methods 0.000 claims abstract description 20
- 238000005265 energy consumption Methods 0.000 claims description 29
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 12
- 230000003068 static effect Effects 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 8
- 230000009189 diving Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000002787 reinforcement Effects 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000007480 spreading Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 11
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 239000010432 diamond Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- 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
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- 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
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Fluid Mechanics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides a method and a system for establishing a model for establishing a multi-objective combined optimization of a route and a speed, wherein the method comprises the following steps: establishing a ship database; establishing a ship control model based on a ship database; the ship control model is a relation model between the thrust and torque required by ship navigation and a ship control instruction; establishing data sets of different ship types corresponding to different route data based on a preset ship AIS database and a ship control model to obtain a target data set; wherein one ship type corresponds to a plurality of route data; and training the preset intelligent forecasting model by using the machine learning method by taking the target data set as a training set to obtain the model for the multi-target joint optimization of the route speed. The invention relieves the technical problems of low optimization accuracy and poor optimization effect of the ship navigation task planning in the prior art.
Description
Technical Field
The invention relates to the technical field of ship navigation mission planning, in particular to a method and a system for establishing a model for establishing a multi-target combined optimization model of a route and a speed.
Background
The course and speed of the ship are the main factors affecting the energy consumption of the ship, and the two are highly coupled. However, in the prior art, when the ship sailing mission is planned, the two are often planned separately, and the influences of the marine environment, the topography, the ship steering capability and the like cannot be fully considered, so that the technical problems of low optimization accuracy and poor optimization effect on the ship sailing mission are caused.
Disclosure of Invention
In view of the above, the invention aims to provide a method and a system for establishing a model for establishing a multi-objective combined optimization model for the navigational speed of a ship, so as to solve the technical problems of low optimization accuracy and poor optimization effect of the planning of a ship navigational task in the prior art.
In a first aspect, an embodiment of the present invention provides a method for establishing a model for jointly optimizing a plurality of targets for a line speed, including: establishing a ship database; the ship database comprises ship data, a static underwater navigational speed draft-resistance meter, a wave resistance increasing transfer function meter, a wind resistance coefficient meter, a propeller thrust torque coefficient meter, a turbine steering engine performance parameter meter and a diving resistance increasing coefficient meter; establishing a ship control model based on the ship database; the ship control model is a relation model between thrust and torque required by ship navigation and a ship control instruction; establishing data sets of different ship types corresponding to different route data based on a preset ship AIS database and the ship control model to obtain a target data set; wherein, a ship type corresponds a plurality of route data, and every route data includes: route, speed, depth of water, ocean environment parameters, vessel maneuvering instructions, total energy consumption for voyage and total time for voyage; and training the preset intelligent forecasting model by using the target data set as a training set and using a machine learning method to obtain the model for the multi-target combined optimization of the course speed.
Further, based on the vessel database, establishing a vessel steering model, comprising: based on the ship database, an initial relation model between the thrust and torque required by ship navigation and the rotating speed and rudder angle of a ship propeller is established; and establishing the ship control model based on the initial relation model and the relation between the ship propeller rotating speed, the rudder angle and the ship control instruction.
Further, the initial relationship model includes ：Tp＝ρn2D2KT(V,n),NR＝-(1+αH)xRFNcosδ; wherein,T p is thrust required by ship navigation, N R is torque required by ship navigation, N is ship propeller rotating speed, delta is rudder angle of the ship, K T (V, N) is ship propeller thrust coefficient, V is navigation speed of the ship, rho is water density, D is propeller diameter, alpha H is hydrodynamic proportionality coefficient of rudder, lambda is board spreading ratio of rudder, x R is distance from steering engine to ship center of gravity, F N is intermediate parameter, A R is inflow area, and alpha R is inflow angle.
Further, based on a preset ship AIS database and the ship control model, establishing data sets of different ship types corresponding to different route data to obtain a target data set, including: extracting the airlines corresponding to different ship types from the preset ship AIS database; a ship shape corresponds to a plurality of airlines; carrying out sectional processing on each route corresponding to different ship types, and setting initial route data for each route section; optimizing the initial route data based on the ship control model and a preset optimization threshold value to obtain route data of each route corresponding to different ship types; and taking the route data of each route corresponding to different ship types as the target data set.
Further, training a preset intelligent forecasting model by using a machine learning method to obtain a model for combining and optimizing the speeds of the airlines and the multiple targets, wherein the method comprises the following steps: training a preset intelligent forecasting model by using a machine learning method to obtain an intelligent forecasting model after training; the method of machine learning includes any one of: a deep neural network algorithm, a reinforcement learning algorithm; the independent variables of the preset intelligent forecasting model comprise: ship type, route starting point, marine environment parameters; the strain amount of the preset intelligent forecasting model comprises the following steps: route, speed, distance, time, command and energy consumption; setting a preset optimizing algorithm on the intelligent forecasting model after training to obtain a model of the combined optimization of the route speed and the multiple targets; the model is a model for determining the optimized route speed based on the target optimizing target; the target optimization target comprises at least one of the following: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable.
Further, after obtaining the model for the course speed multi-objective joint optimization, the method further comprises: acquiring initial parameters of a target ship in the navigation process; the initial parameters include: the ship shape of the target ship, the route starting point and the marine environment parameters of the target ship in the navigation process; acquiring a target optimizing target of the target ship in the sailing process; the target optimization target comprises at least one of the following: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable; and optimizing the navigational speed route of the target ship by utilizing the navigational speed multi-target combined optimization model based on the initial parameters and the target optimizing target to obtain the navigational speed route after optimization.
In a second aspect, the embodiment of the invention also provides a system for establishing a model for establishing a multi-objective joint optimization model of the navigational speed of a navigation route, which comprises the following steps: the system comprises a first building module, a second building module, a third building module and a training module, wherein the first building module is used for building a ship database; the ship database comprises ship data, a static underwater navigational speed draft-resistance meter, a wave resistance increasing transfer function meter, a wind resistance coefficient meter, a propeller thrust torque coefficient meter, a turbine steering engine performance parameter meter and a diving resistance increasing coefficient meter; the second building module is used for building a ship control model based on the ship database; the ship control model is a relation model between thrust and torque required by ship navigation and a ship control instruction; the third building module is used for building data sets of different ship types corresponding to different route data based on a preset ship AIS database and the ship control model to obtain a target data set; wherein, a ship type corresponds a plurality of route data, and every route data includes: route, speed, depth of water, ocean environment parameters, vessel maneuvering instructions, total energy consumption for voyage and total time for voyage; the training module is used for training a preset intelligent forecasting model by using the target data set as a training set and utilizing a machine learning method to obtain a route speed multi-target combined optimization model.
Further, the system further comprises: an optimization module for: acquiring initial parameters of a target ship in the navigation process; the initial parameters include: the ship shape of the target ship, the route starting point and the marine environment parameters of the target ship in the navigation process; acquiring a target optimizing target of the target ship in the sailing process; the target optimization target comprises at least one of the following: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable; and optimizing the navigational speed route of the target ship by utilizing the navigational speed multi-target combined optimization model based on the initial parameters and the target optimizing target to obtain the navigational speed route after optimization.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor executes the computer program to implement the steps of the method described in the first aspect.
In a fourth aspect, embodiments of the present invention also provide a computer readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the method of the first aspect.
The embodiment of the invention provides a method and a system for establishing a model for multi-objective joint optimization of the navigational speed of a navigational route, which are characterized in that a ship database is established, a ship control model is established, then data sets corresponding to different navigational route data of different ship types are established, finally, a preset intelligent prediction model is trained by utilizing the data sets to obtain the model for multi-objective joint optimization of the navigational speed of the navigational route, thereby realizing the overall planning of multiple factors, the joint optimization of the navigational speed of the navigational route, improving the optimization accuracy, improving the optimization effect, and relieving the technical problems of low optimization accuracy and poor optimization effect on the planning of navigational tasks of the navigational route of the ship in the prior art.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for establishing a model for establishing a multi-objective joint optimization of the speed of a route, which is provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of a model building system for establishing a multi-objective joint optimization model for the speed of a route according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another model building system for combining multiple navigational speeds and multiple objectives according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one:
FIG. 1 is a flow chart of a method for establishing a model for establishing a multi-objective joint optimization model for a course speed according to an embodiment of the present invention. As shown in fig. 1, the method specifically includes the following steps:
Step S102, establishing a ship database; the ship database comprises ship data, a speed draft-resistance table under static water, a wave resistance increasing transfer function table, a wind resistance coefficient table, a propeller thrust torque coefficient table, a turbine steering engine performance parameter table and a diving resistance increasing coefficient table. Specifically, each ship in the ship database contains all the data, the parameters of different ship types are different, and the performance parameters of the same ship are different along with the use time of the ship, so that the measured data on the ship are required to be analyzed regularly, and then the parameters in the ship database are updated.
Step S104, building a ship control model based on a ship database; the ship steering model is a relationship model between thrust and torque required for ship navigation and a ship steering command.
Step S106, based on a preset ship AIS database and a ship control model, establishing data sets of different ship types corresponding to different route data to obtain a target data set; wherein, a ship type corresponds a plurality of route data, and every route data includes: route, speed, depth of water, marine environmental parameters, vessel maneuvering instructions, total energy consumption for voyage and total time for voyage.
And S108, training a preset intelligent forecasting model by using a machine learning method by taking the target data set as a training set to obtain the model of the combined optimization of the route and the speed.
The embodiment of the invention provides a method for establishing a model for multi-objective joint optimization of the navigational speed of a navigational route, which is characterized in that a ship database is established, a ship control model is established, then data sets corresponding to different navigational route data of different ship types are established, finally, a preset intelligent forecasting model is trained by utilizing the data sets to obtain the model for multi-objective joint optimization of the navigational speed of the navigational route, thereby realizing overall planning of various factors, the joint optimization of the navigational speed of the navigational route, improving the optimization accuracy, improving the optimization effect, and relieving the technical problems of low optimization accuracy and poor optimization effect on the planning of navigational tasks of the ship in the prior art.
Specifically, the ship type data includes: the ship length, the ship width, the square and diamond coefficients under different draft longitudinal directions, the water discharge amount under different draft longitudinal directions, the wet surface area, the water plane length and the like can be inquired from a ship loading manual, and the ship loading manual is generally not updated.
The speed draft-resistance meter under the static water can be calculated by a pool experiment or computational fluid dynamics (Computational Fluid Dynamics, CFD), and when the speed and draft are determined, the static water resistance value of the ship can be obtained through table lookup.
Wave resistance increasing transfer function in wave resistance increasing transfer function table(H is wave height and F (T, θ, V, dr) is wave force) can be understood as the wave force generated by the unit wave height, which is a function related to the wave period T, the angle of attack θ, the navigational speed V, and the draft dr. And determining by using a model test, numerical calculation and the like, wherein when the navigational speed and the draft are determined, the wave resistance is F wave＝∫∫∫f(T,θ,V0,dr0) dHdTd theta.
The wind resistance coefficient C A (psi) in the wind resistance coefficient table is a function of the wind direction angle psi and can be obtained by wind tunnel experiment or CFD calculation, and the wind resistance is calculatedWhere V wind is wind speed and A is windward area.
The thrust coefficient K T (V, n) and the torque coefficient K Q (V, n) in the propeller thrust torque coefficient table are functions of the ship speed V and the propeller rotating speed n, and can be obtained by using a pool experiment or CFD.
Each performance parameter in the turbine steering engine performance parameter table is an inherent attribute of the equipment and is obtained by a parameter table provided by equipment manufacturer.
The diving resistance-increasing coefficient K (V, h, C b, dr) in the shallow water resistance-increasing coefficient table is a function of the navigational speed V, the water depth h, the square coefficient Cb and the draft dr, and can be obtained through a pool experiment or CFD calculation.
Specifically, step S104 further includes the following steps:
Step S1041, based on the ship database, establishing an initial relation model between the thrust and torque required by ship navigation and the rotating speed and rudder angle of the ship propeller.
Step S1042, a ship control model is built based on the initial relation model and the relation between the ship propeller rotating speed, rudder angle and the ship control command.
Optionally, the ship steering model further comprises:
and determining the sailing power of the ship and the sailing total energy consumption of the ship based on the rotating speed of the ship propeller.
Specifically, when the speed and draft of the ship are determined and the conditions such as wind, wave and water depth are known, the data in the ship database and the initial relation model can be used for calculating the thrust and torque required by the ship navigation, and the thrust and torque are respectively provided by the propeller and rudder of the ship. Specifically, the initial relationship model includes:
Tp＝ρn2D2KT(V,n),NR＝-(1+αH)xRFNcosδ；
Wherein, T p is thrust required by ship navigation, N R is torque required by ship navigation, N is ship propeller rotating speed, delta is rudder angle of the ship, K T (V, N) is ship propeller thrust coefficient, V is navigation speed of the ship, rho is water density, D is propeller diameter, alpha H is hydrodynamic proportionality coefficient of rudder, lambda is board spreading ratio of rudder, x R is distance from steering engine to ship center of gravity, F N is intermediate parameter, A R is inflow area, and alpha R is inflow angle. All the parameters can be obtained by checking a steering engine performance parameter table or installing the steering engine performance parameter table in a manual.
Then, given the thrust and torque, the propeller rotational speed and rudder angle can be obtained by using the relational expression in the initial relational model, thereby obtaining the steering command.
Optionally, after obtaining the propeller rotational speed n, the following relation is used: p=2pi nQ P＝2πρn3D5KQ (V, n), the power of the vessel sailing can be obtained, and the power is integrated: e= ≡pdt can calculate the total energy consumption of ship sailing.
Optionally, step S106 further includes the steps of:
Step S1061, extracting routes corresponding to different ship types from a preset ship AIS database; a ship shape corresponds to a plurality of airlines.
Step S1062, segment processing is performed on each route corresponding to different ship types, and initial route data is set for each route segment.
Step S1063, optimizing the initial route data based on the ship control model and a preset optimization threshold value to obtain route data of each route corresponding to different ship types.
In step S1064, the route data of each route corresponding to a different ship type is used as the target data set.
In the embodiment of the invention, various sailing routes of the ship are extracted from the existing preset ship AIS database, and sailing routes of the ship with different ship types are different due to different goods and the like. The ship types of the same type are different in the sailing line of each ship due to different ship handling habits of crews and different requirements of shipservice companies, but the difference is not great. These airlines are determined empirically by crews over years.
Specifically, the routes are classified according to different ship types, and the routes of the same ship type are separated together. And taking the maximum range of each route change of the same ship shape as the optimizing range of the route optimizing in the route speed multi-target combined optimizing model provided by the embodiment of the invention.
Then, aiming at a specific ship model, a starting point is randomly set in a route optimizing range to randomly generate a route, after the ship route is determined, the water depth on the route is determined, and the ship resistance increase caused by the corresponding shallow water effect is also determined. Dividing the route into N sections according to the calculation force of the computer, wherein the larger the calculation force is, the larger N is. And the ship speed V is randomly arranged on the N sections of routes, and marine environment parameters (wind, waves and currents) are randomly designed. It should be noted that the influence of wind and waves on the ship is to increase the resistance, and the influence of flow on the ship is to influence the speed of the ship: v=v+v c. Where V is the actual speed of the ship over water, V is the actual speed of the ship over the ground, is the randomly allocated speed over N legs, and V c is the component of the flow rate in the direction of the legs. After the parameters of the route, the water depth, the navigational speed and the marine environment are determined, the control instruction, the total navigational energy consumption and the total navigational time of the ship can be calculated by utilizing the relation type in the ship control model. If any one of the maximum change amplitude, the maximum change speed and the like of the propeller or rudder angle exceeds the allowable value of the equipment (namely, a preset optimization threshold value) in the calculated control instruction, deleting the piece of data. The above process is repeated for M times, and the magnitude of M is set according to the calculation force, and the larger the calculation force is, the larger M is. Repeating the above process for different ship types creates a data set for each ship type.
Specifically, step S108 further includes the steps of:
Step S1081, training a preset intelligent forecasting model by using a machine learning method to obtain a trained intelligent forecasting model; the method of machine learning includes any one of the following: a deep neural network algorithm, a reinforcement learning algorithm; the preset independent variables of the intelligent forecasting model comprise: ship type, route starting point, marine environment parameters; the preset strain quantity of the intelligent forecasting model comprises the following steps: route, speed, course, time, command and energy consumption.
Step S1082, setting a preset optimizing algorithm on the trained intelligent forecasting model to obtain a route speed multi-target combined optimizing model; the model of the route and the speed multi-target combined optimization is a model for determining the optimized route and speed based on the target optimizing target; the target optimization target includes at least one of: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable.
In the embodiment of the invention, for the intelligent forecasting model after training, a plurality of groups of forecasting results of the route and the speed are obtained under the same ship shape, starting point and marine environment parameters, and a plurality of groups of results of the sailing distance, sailing time, operating instructions and energy consumption are obtained correspondingly; therefore, on the basis of the intelligent prediction model after training, a preset optimizing algorithm is set, and according to different optimizing targets, such as: the requirements of the fastest speed, the shortest distance, the lowest energy consumption, the most stable operation and the like are met, and the corresponding combination of the route and the navigational speed is determined as the final optimizing result.
Optionally, after establishing the model for combining optimization of the line speed and the multiple targets, the method provided by the embodiment of the invention further comprises the following steps: and deploying the model with the multi-target combined optimization of the course speed, periodically executing the optimizing process of the course speed in the course of the ship navigation, and pushing the latest course speed result to the crewman on the ship. Meanwhile, according to big data acquired during navigation of the ship, the route and speed multi-target combined optimization model is updated regularly. Specifically, the method comprises the following steps:
Acquiring initial parameters of a target ship in the navigation process; the initial parameters include: the ship shape of the target ship, the route starting point and the marine environment parameters of the target ship in the course of navigation; acquiring a target optimizing target of a target ship in the sailing process; the target optimization target includes at least one of: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable; and optimizing the navigational speed route of the target ship by utilizing the navigational speed multi-target combined optimization model based on the initial parameters and the target optimizing target to obtain the navigational speed route after optimization.
As can be seen from the above description, the embodiment of the invention provides a method for establishing a model for multi-objective joint optimization of the course and the course, which establishes data sets of different ship types corresponding to different course data by comprehensively utilizing a ship database and a ship operation model, and finally trains a preset intelligent prediction model by utilizing the data sets to obtain the model for multi-objective joint optimization of the course and the course, and the model finally obtained by utilizing the method provided by the embodiment of the invention optimizes the course and the course of the ship, and the influence of the marine environment, topography, ship operation capability and the like is fully considered in the optimizing process, so that the optimizing result can be more accurate and the optimizing effect is more obvious.
Embodiment two:
FIG. 2 is a schematic diagram of a model building system for model building for multiple target joint optimization of course speed according to an embodiment of the present invention. As shown in fig. 2, the system includes: a first setup module 10, a second setup module 20, a third setup module 30, and a training module 40.
Specifically, the first building module 10 is configured to build a ship database; the ship database comprises ship data, a speed draft-resistance table under static water, a wave resistance increasing transfer function table, a wind resistance coefficient table, a propeller thrust torque coefficient table, a turbine steering engine performance parameter table and a diving resistance increasing coefficient table.
A second building module 20 for building a ship steering model based on the ship database; the ship steering model is a relationship model between thrust and torque required for ship navigation and a ship steering command.
A third establishing module 30, configured to establish data sets corresponding to different ship types and different route data based on a preset ship AIS database and a ship control model, so as to obtain a target data set; wherein, a ship type corresponds a plurality of route data, and every route data includes: route, speed, depth of water, marine environmental parameters, vessel maneuvering instructions, total energy consumption for voyage and total time for voyage.
The training module 40 is configured to train the preset intelligent prediction model by using a machine learning method with the target data set as a training set, so as to obtain a model for combining and optimizing the speeds of the airlines and the multiple targets.
The embodiment of the invention provides a system for establishing a model for multi-objective joint optimization of the navigational speed of a navigational route, which is characterized in that a ship database is established, a ship control model is established, then data sets corresponding to different navigational route data of different ship types are established, finally, a preset intelligent forecasting model is trained by utilizing the data sets to obtain the model for multi-objective joint optimization of the navigational speed of the navigational route, thereby realizing overall planning of various factors, the joint optimization of the navigational speed of the navigational route, improving the optimization accuracy, improving the optimization effect, and relieving the technical problems of low optimization accuracy and poor optimization effect on the planning of navigational tasks of the ship in the prior art.
Specifically, the second establishing module 20 is further configured to: based on a ship database, an initial relation model between thrust and torque required by ship navigation and the rotating speed and rudder angle of a ship propeller is established; based on the initial relation model and the relation between the rotating speed of the ship propeller, the rudder angle and the ship control command, establishing a ship control model; and determining the sailing power of the ship and the sailing total energy consumption of the ship based on the rotating speed of the ship propeller. Specifically, the initial relationship model includes:
Tp＝ρn2D2KT(V,n),NR＝-(1+αH)xRFNcosδ；
Wherein, T p is thrust required by ship navigation, N R is torque required by ship navigation, N is ship propeller rotating speed, delta is rudder angle of the ship, K T (V, N) is ship propeller thrust coefficient, V is navigation speed of the ship, rho is water density, D is propeller diameter, alpha H is hydrodynamic proportionality coefficient of rudder, lambda is board spreading ratio of rudder, x R is distance from steering engine to ship center of gravity, F N is intermediate parameter, A R is inflow area, and alpha R is inflow angle. All the parameters can be obtained by checking a steering engine performance parameter table or installing the steering engine performance parameter table in a manual.
Optionally, the third setup module 30 is further configured to: extracting the airlines corresponding to different ship types from a preset ship AIS database; a ship shape corresponds to a plurality of airlines; carrying out sectional processing on each route corresponding to different ship types, and setting initial route data for each route section; optimizing the initial route data based on the ship control model and a preset optimization threshold value to obtain route data of each route corresponding to different ship types; and taking the route data of each route corresponding to different ship types as a target data set.
Optionally, fig. 3 is a schematic diagram of another system for establishing a model for jointly optimizing a plurality of targets at a plurality of speeds, according to an embodiment of the present invention, and as shown in fig. 3, the training module 40 further includes: a training unit 41 and a setting unit 42.
Specifically, the training unit 41 is configured to: training a preset intelligent forecasting model by using a machine learning method to obtain an intelligent forecasting model after training; the method of machine learning includes any one of the following: a deep neural network algorithm, a reinforcement learning algorithm; the preset independent variables of the intelligent forecasting model comprise: ship type, route starting point, marine environment parameters; the preset strain quantity of the intelligent forecasting model comprises the following steps: route, speed, course, time, command and energy consumption.
A setting unit 42 for: setting a preset optimizing algorithm on the intelligent forecasting model after training to obtain a model of the combined optimization of the route speed and the multiple targets; the model of the route and the speed multi-target combined optimization is a model for determining the optimized route and speed based on the target optimizing target; the target optimization target includes at least one of: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable.
Optionally, as shown in fig. 3, the system further includes: an optimization module 50 for: acquiring initial parameters of a target ship in the navigation process; the initial parameters include: the ship shape of the target ship, the route starting point and the marine environment parameters of the target ship in the course of navigation; acquiring a target optimizing target of a target ship in the sailing process; the target optimization target includes at least one of: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable; and optimizing the navigational speed route of the target ship by utilizing the navigational speed multi-target combined optimization model based on the initial parameters and the target optimizing target to obtain the navigational speed route after optimization.
The embodiment of the invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the method in the first embodiment.
The present invention also provides a computer-readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the method of the first embodiment.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (9)
1. A method for establishing a model for establishing a multi-objective joint optimization of a route and a speed is characterized by comprising the following steps:
Establishing a ship database; the ship database comprises ship data, a static underwater navigational speed draft-resistance meter, a wave resistance increasing transfer function meter, a wind resistance coefficient meter, a propeller thrust torque coefficient meter, a turbine steering engine performance parameter meter and a diving resistance increasing coefficient meter;
Establishing a ship control model based on the ship database; the ship control model is a relation model between thrust and torque required by ship navigation and a ship control instruction;
Establishing data sets of different ship types corresponding to different route data based on a preset ship AIS database and the ship control model to obtain a target data set; wherein, a ship type corresponds a plurality of route data, and every route data includes: route, speed, depth of water, ocean environment parameters, vessel maneuvering instructions, total energy consumption for voyage and total time for voyage;
Training a preset intelligent forecasting model by using the machine learning method to obtain a model of multi-objective combined optimization of the air course and the speed, wherein the training of the preset intelligent forecasting model by using the machine learning method to obtain the model of multi-objective combined optimization of the air course and the speed comprises the following steps: training a preset intelligent forecasting model by using a machine learning method to obtain an intelligent forecasting model after training; the method of machine learning includes any one of: a deep neural network algorithm, a reinforcement learning algorithm; the independent variables of the preset intelligent forecasting model comprise: ship type, route starting point, marine environment parameters; the strain amount of the preset intelligent forecasting model comprises the following steps: route, speed, distance, time, command and energy consumption; setting a preset optimizing algorithm on the intelligent forecasting model after training to obtain a model of the combined optimization of the route speed and the multiple targets; the model is a model for determining the optimized route speed based on the target optimizing target; the target optimization target comprises at least one of the following: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable.
2. The method of claim 1, wherein building a vessel steering model based on the vessel database comprises:
Based on the ship database, an initial relation model between the thrust and torque required by ship navigation and the rotating speed and rudder angle of a ship propeller is established;
And establishing the ship control model based on the initial relation model and the relation between the ship propeller rotating speed, the rudder angle and the ship control instruction.
3. The method of claim 2, wherein the initial relationship model comprises:
Tp＝ρn2D2KT(V,n),NR＝-(1+αH)xRFNcosδ；
Wherein, T p is thrust required by ship navigation, N R is torque required by ship navigation, N is ship propeller rotating speed, delta is rudder angle of the ship, K T (V, N) is ship propeller thrust coefficient, V is navigation speed of the ship, rho is water density, D is propeller diameter, alpha H is hydrodynamic proportionality coefficient of rudder, lambda is board spreading ratio of rudder, x R is distance from steering engine to ship center of gravity, F N is intermediate parameter, A R is inflow area, and alpha R is inflow angle.
4. The method of claim 1, wherein establishing a dataset for different ship types corresponding to different route data based on a preset ship AIS database and the ship steering model to obtain a target dataset comprises:
extracting the airlines corresponding to different ship types from the preset ship AIS database; a ship shape corresponds to a plurality of airlines;
Carrying out sectional processing on each route corresponding to different ship types, and setting initial route data for each route section;
Optimizing the initial route data based on the ship control model and a preset optimization threshold value to obtain route data of each route corresponding to different ship types;
And taking the route data of each route corresponding to different ship types as the target data set.
5. The method of claim 1, wherein after deriving the course speed multi-objective joint optimization model, the method further comprises:
Acquiring initial parameters of a target ship in the navigation process; the initial parameters include: the ship shape of the target ship, the route starting point and the marine environment parameters of the target ship in the navigation process;
acquiring a target optimizing target of the target ship in the sailing process; the target optimization target comprises at least one of the following: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable;
And optimizing the navigational speed route of the target ship by utilizing the navigational speed multi-target combined optimization model based on the initial parameters and the target optimizing target to obtain the navigational speed route after optimization.
6. A system for establishing a model for establishing a multi-objective joint optimization model of a route and a speed, which is characterized by comprising the following components: a first building module, a second building module, a third building module and a training module, wherein,
The first building module is used for building a ship database; the ship database comprises ship data, a static underwater navigational speed draft-resistance meter, a wave resistance increasing transfer function meter, a wind resistance coefficient meter, a propeller thrust torque coefficient meter, a turbine steering engine performance parameter meter and a diving resistance increasing coefficient meter;
The second building module is used for building a ship control model based on the ship database; the ship control model is a relation model between thrust and torque required by ship navigation and a ship control instruction;
The third building module is used for building data sets of different ship types corresponding to different route data based on a preset ship AIS database and the ship control model to obtain a target data set; wherein, a ship type corresponds a plurality of route data, and every route data includes: route, speed, depth of water, ocean environment parameters, vessel maneuvering instructions, total energy consumption for voyage and total time for voyage;
The training module is configured to train a preset intelligent prediction model by using a machine learning method with the target data set as a training set to obtain a model for combined optimization of the air course and the speed, wherein the training module trains the preset intelligent prediction model by using the machine learning method to obtain the model for combined optimization of the air course and the speed, and the training module comprises: training a preset intelligent forecasting model by using a machine learning method to obtain an intelligent forecasting model after training; the method of machine learning includes any one of: a deep neural network algorithm, a reinforcement learning algorithm; the independent variables of the preset intelligent forecasting model comprise: ship type, route starting point, marine environment parameters; the strain amount of the preset intelligent forecasting model comprises the following steps: route, speed, distance, time, command and energy consumption; setting a preset optimizing algorithm on the intelligent forecasting model after training to obtain a model of the combined optimization of the route speed and the multiple targets; the model is a model for determining the optimized route speed based on the target optimizing target; the target optimization target comprises at least one of the following: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable.
7. The system of claim 6, wherein the system further comprises: an optimization module for:
Acquiring initial parameters of a target ship in the navigation process; the initial parameters include: the ship shape of the target ship, the route starting point and the marine environment parameters of the target ship in the navigation process;
acquiring a target optimizing target of the target ship in the sailing process; the target optimization target comprises at least one of the following: the speed is the fastest, the distance is the shortest, the energy consumption is the lowest, and the operation is the most stable;
And optimizing the navigational speed route of the target ship by utilizing the navigational speed multi-target combined optimization model based on the initial parameters and the target optimizing target to obtain the navigational speed route after optimization.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of the preceding claims 1 to 5 when the computer program is executed.
9. A computer readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110087030.0A CN112699497B (en) | 2021-01-22 | 2021-01-22 | Method and system for establishing route and speed multi-target combined optimization model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110087030.0A CN112699497B (en) | 2021-01-22 | 2021-01-22 | Method and system for establishing route and speed multi-target combined optimization model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112699497A CN112699497A (en) | 2021-04-23 |
| CN112699497B true CN112699497B (en) | 2024-05-28 |
Family
ID=75515934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110087030.0A Active CN112699497B (en) | 2021-01-22 | 2021-01-22 | Method and system for establishing route and speed multi-target combined optimization model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112699497B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113433934B (en) * | 2021-04-27 | 2022-04-12 | 武汉海兰鲸科技有限公司 | Method for optimizing navigational speed of commercial ship |
| CN113096481B (en) * | 2021-05-19 | 2022-09-02 | 江苏科技大学 | Ship path planning training system for laboratory |
| CN113868765B (en) * | 2021-09-28 | 2023-09-05 | 中国舰船研究设计中心 | Ship main scale parameter optimization method based on approximate model |
| CN115270644B (en) * | 2022-09-30 | 2023-01-17 | 武汉理工大学 | Intelligent ship energy-saving sailing formation method, electronic equipment and storage medium |
| CN115993118A (en) * | 2022-11-29 | 2023-04-21 | 上海船舶运输科学研究所有限公司 | Shortest route planning method and system |
| CN116663696A (en) * | 2023-01-14 | 2023-08-29 | 武汉理工大学 | Method and device for optimizing north-south east-north route multi-target speed based on genetic algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111767612A (en) * | 2020-07-01 | 2020-10-13 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Model construction method, ship control device and electronic equipment |
| KR20200127111A (en) * | 2019-04-30 | 2020-11-10 | 대우조선해양 주식회사 | System and method for providing performance of a vessel and computer-readable recording medium thereof |
| CN111930123A (en) * | 2020-08-13 | 2020-11-13 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Multi-objective comprehensive optimization decision method and device and electronic equipment |
-
2021
- 2021-01-22 CN CN202110087030.0A patent/CN112699497B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200127111A (en) * | 2019-04-30 | 2020-11-10 | 대우조선해양 주식회사 | System and method for providing performance of a vessel and computer-readable recording medium thereof |
| CN111767612A (en) * | 2020-07-01 | 2020-10-13 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Model construction method, ship control device and electronic equipment |
| CN111930123A (en) * | 2020-08-13 | 2020-11-13 | 上海船舶研究设计院（中国船舶工业集团公司第六0四研究院） | Multi-objective comprehensive optimization decision method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 基于实船监测数据的定航线船舶智能航速优化;马冉祺;黄连忠;魏茂苏;柳霆;刘伊凡;王寰宇;;大连海事大学学报(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112699497A (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699497B (en) | Method and system for establishing route and speed multi-target combined optimization model | |
| Carrica et al. | Near-surface self propulsion of a generic submarine in calm water and waves | |
| CN108564202B (en) | Unmanned ship route optimization method based on environment forecast information | |
| Papanikolaou et al. | Energy efficient safe ship operation (SHOPERA) | |
| CN108416152A (en) | The optimal global path planning method of unmanned boat ant colony energy consumption based on electronic chart | |
| KR102589008B1 (en) | A device for determining the optimal route of a maritime vessel | |
| KR20150018610A (en) | Method and system for determination of a route for a ship | |
| Sutulo et al. | On the application of empiric methods for prediction of ship manoeuvring properties and associated uncertainties | |
| Rudzki et al. | A decision-making system supporting selection of commanded outputs for a ship's propulsion system with a controllable pitch propeller | |
| CN104765368A (en) | Unmanned ship heading and speed cooperative control method based on fuzzy adaptive algorithm | |
| CN108427406A (en) | A kind of carrier landing control and stern stream suppressing method based on PREDICTIVE CONTROL | |
| CN107179693A (en) | Based on the Huber robust adaptive filtering estimated and method for estimating state | |
| CN107776859A (en) | AUV deep motion buoyancy compensation control methods latent greatly | |
| CN107657144A (en) | A kind of offshore flow field inversion method based on watercraft AIS and log data | |
| CN107108000A (en) | The navigation accessory system of ship and the navigation householder method of ship | |
| CN110778398B (en) | Marine diesel engine fuel management control system | |
| Życzkowski et al. | Multi-objective weather routing of sailboats considering wave resistance | |
| Philpott et al. | Yacht velocity prediction using mathematical programming | |
| Kramer et al. | Drift forces—Wingsails vs. Flettner rotors | |
| CN108482577B (en) | Draft loading control method for engineering ship | |
| CN115630580A (en) | Intelligent decision-making assisting method for entering and exiting port and relying on berthing of ship based on multi-source data | |
| Ferguson et al. | A Markov decision process model for strategic decision making in sailboat racing | |
| Werner et al. | Speed trial verification for a wind assisted ship | |
| Szelangiewicz et al. | Mathematical model for predicting the ship speed in the actual weather conditions on the planned ocean route | |
| Sutulo et al. | Analysis of manoeuvrability criteria and standards in view of environmental factors and EEDI impact |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |