CN111709090B - Model construction method and device, electronic equipment and computer readable storage medium - Google Patents

Model construction method and device, electronic equipment and computer readable storage medium Download PDF

Info

Publication number
CN111709090B
CN111709090B CN202010557681.7A CN202010557681A CN111709090B CN 111709090 B CN111709090 B CN 111709090B CN 202010557681 A CN202010557681 A CN 202010557681A CN 111709090 B CN111709090 B CN 111709090B
Authority
CN
China
Prior art keywords
sample data
ground
speed
model
correcting
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
Application number
CN202010557681.7A
Other languages
Chinese (zh)
Other versions
CN111709090A (en
Inventor
向新桃
程宣恺
孙海素
杜鲁辉
樊翔
蔡笑驰
高文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Merchant Ship Design and Research Institute of CSSC No 604 Research Institute
Original Assignee
Shanghai Merchant Ship Design and Research Institute of CSSC No 604 Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Merchant Ship Design and Research Institute of CSSC No 604 Research Institute filed Critical Shanghai Merchant Ship Design and Research Institute of CSSC No 604 Research Institute
Priority to CN202010557681.7A priority Critical patent/CN111709090B/en
Publication of CN111709090A publication Critical patent/CN111709090A/en
Application granted granted Critical
Publication of CN111709090B publication Critical patent/CN111709090B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING 
    • B63B71/00—Designing vessels; Predicting their performance
    • B63B71/10—Designing vessels; Predicting their performance using computer simulation, e.g. finite element method [FEM] or computational fluid dynamics [CFD]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Fluid Mechanics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Mathematical Optimization (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Chemical & Material Sciences (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Algebra (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • Ocean & Marine Engineering (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Computational Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a model construction method, a model construction device, electronic equipment and a computer readable storage medium, wherein the model construction method comprises the following steps: acquiring first sample data of a ship, and determining the relation between the first sample data; wherein the first sample data is used to characterize the performance of the vessel; correcting the first sample data based on a preset correction formula and preset parameters to obtain second sample data; and constructing an axis power model based on the second sample data. The invention can shorten the data collection time and improve the applicability of the model.

Description

Model construction method and device, electronic equipment and computer readable storage medium
Technical Field
The invention relates to the technical field of ship design, in particular to a model construction method, a model construction device, electronic equipment and a computer readable storage medium.
Background
In the design stage of the ship, the output power of a ship main engine and the rotating speed of a propeller generally need to be considered under the condition of a certain navigational speed; or the ship speed which can be reached by the ship and the corresponding propeller rotating speed are under the condition of stipulating the output power of the main engine, namely the problem of rapid forecast. In the prior art, various types of data are collected in real time through a sensor during the operation of a ship, and the relationship between the shaft power (or the host power) and the speed, the displacement, the water depth and each meteorological parameter (namely a shaft power model) is determined after enough data are collected. However, in the prior art, because the prior art relies on the measured data, on one hand, sufficient data can be prepared only after long-time accumulation, and on the other hand, the collected measured data generally has a narrow parameter change range, the application range of the established model is also narrow.
Disclosure of Invention
In view of the above, the present invention provides a model building method, a model building apparatus, an electronic device, and a computer-readable storage medium, which can shorten data collection time and improve applicability of a model.
In a first aspect, an embodiment of the present invention provides a model building method, including: acquiring first sample data of a ship, and determining the relation between the first sample data; wherein the first sample data is used to characterize the performance of the vessel; correcting the first sample data based on a preset correction formula and preset parameters to obtain second sample data; and constructing an axis power model based on the second sample data.
In one embodiment, the step of obtaining first sample data of a vessel comprises: obtaining first sample data of a ship through a model test and a numerical test; the model test is a test for simulating the sailing by using a ship model, and the numerical test is a test for simulating the sailing of a ship by using a numerical calculation mode.
In one embodiment, the first sample data includes an energy consumption parameter and a speed of flight; wherein the energy consumption parameters include one or more of: shaft power, propulsion efficiency, total resistance coefficient; the navigational speed includes: speed of ground, heading of ground, and speed of water.
In one embodiment, the step of obtaining first sample data of a ship and determining a relationship between the first sample data comprises: and acquiring the energy consumption parameter and the navigational speed of the ship, and determining the relationship between the energy consumption parameter and the navigational speed.
In one embodiment, the preset parameters include one or more of the following: the flow velocity to the ground, the flow direction to the ground, the wind speed to the ground, the wind direction to the ground, the sense wave height, the wave direction to the ground, the air density, the sea water viscosity, the water displacement and the water depth; the step of correcting the first sample data based on a preset correction formula and preset parameters includes: correcting the total resistance based on a preset correction formula, the seawater density and the seawater viscosity; and/or correcting the total resistance based on a preset correction formula, the speed of the ground wind and the direction of the ground wind; and/or correcting the propulsion efficiency and the shaft power based on a preset correction formula and the corrected total resistance; and/or correcting the shaft power based on a preset correction formula and the water displacement; and/or correcting the water speed based on a preset correction formula and the water depth; and/or correcting the flow speed and the flow direction to the geo-speed and the geo-heading based on a preset correction formula.
In one embodiment, the second sample data includes one or more of the preset parameters, further including shaft power, speed to ground and heading to ground.
In one embodiment, the step of constructing the shaft power model based on the second sample data comprises: based on the second sample data, an axis power model is constructed through a deep learning algorithm and/or a machine learning algorithm; wherein, the shaft power model is a propeller shaft power model.
In a second aspect, an embodiment of the present invention provides a model building apparatus, including: the data acquisition module is used for acquiring first sample data of the ship and determining the relation between the first sample data; wherein the first sample data is used to characterize the performance of the vessel; the correction module is used for correcting the first sample data based on a preset correction formula and preset parameters to obtain second sample data; and the model building module is used for building the shaft power model based on the second sample data.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory, where the memory stores computer-executable instructions capable of being executed by the processor, and the processor executes the computer-executable instructions to implement the steps of any one of the methods provided in the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of any one of the methods provided in the first aspect.
The embodiment of the invention provides a model construction method, a model construction device, electronic equipment and a computer readable storage medium, which can firstly acquire first sample data of a ship (the first sample data is used for representing the performance of the ship) and determine the relationship between the first sample data; then, the first sample data is corrected based on a preset correction formula and preset parameters to obtain second sample data; and finally, constructing an axis power model based on the second sample data. According to the method, the first sample data is obtained through tests when the shaft power model is built, the first sample data is corrected by using the preset correction formula, and actually measured data does not need to be collected in the ship operation process, so that the data collection time can be reduced, the change range of the parameters of the obtained second sample data is wide enough, and the application range of the built model is wide.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of a model building method according to an embodiment of the present invention;
FIG. 2 is a schematic flowchart of another model construction method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the relationship between the water speed and the shaft power according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating the relationship between the speed of water and the total resistance according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating the relationship between the water speed and the propulsion efficiency according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating a relationship between a water speed and a total drag coefficient according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a model building apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, in the field of intelligent ships, a navigational speed optimization algorithm is continuously developed and applied, and the algorithm flow is generally as follows: (1) when the ship operates, various data including host power, shaft power, navigational speed, displacement, water depth and various meteorological parameters are collected in real time through the sensors. (2) After enough data is collected, the relationship between the shaft power (or the host power) and the navigation speed, the displacement, the water depth and each meteorological parameter (namely a shaft power model) is searched by applying a machine learning or deep learning method. (3) And (3) predicting the ship navigation power consumption by applying the model obtained in the step (2), and then proposing a navigation speed suggestion and the like according to the ship navigation power consumption. However, the prior art also has the following disadvantages: on the one hand the prior art relies on measured data. According to the machine learning principle, in order to obtain a sufficiently accurate model, the training data needs to meet some requirements: a) The measurement precision is ensured; b) The variation range of each parameter is wide enough, and c) the data quantity is enough. Obviously, long accumulation times are required to stage sufficient data. Therefore, the existing speed optimization algorithm can not gradually play a role until the ship runs for 3 months or even longer. On the other hand, it is generally difficult for the measured data to satisfy the requirement of "the parameter variation range is wide enough". For example, a ship sailing near the equator for a long time cannot collect low-temperature environment operation data, and the obtained model is only suitable for a high-temperature environment; if its course is suddenly adjusted to navigate along a high latitude area, the existing model is no longer applicable.
Based on this, the model construction method, the model construction device, the electronic device and the computer-readable storage medium provided by the embodiments of the present invention can improve the applicability of the model while shortening the data collection time.
To facilitate understanding of the present embodiment, first, a detailed description is given of a model building method disclosed in the embodiment of the present invention, referring to a schematic flow chart of a model building method shown in fig. 1, where the method may be executed by an electronic device, such as a smart phone, a computer, and the like, and mainly includes the following steps S102 to S106:
step S102: first sample data of the ship is obtained, and the relation between the first sample data is determined.
Wherein the first sample data is used to characterize the performance of the vessel. In one embodiment, in the design stage of the ship, the rapidity and other performances of the ship need to be verified, wherein the rapidity refers to the performance of the ship in sailing at a faster speed under a certain main engine power. Based on this, the embodiment of the invention can acquire the first sample data representing the ship performance and determine the relation between the first sample data, such as the relation between the parameters of propeller shaft power, total resistance and the like and the navigational speed.
Step S104: and correcting the first sample data based on a preset correction formula and preset parameters to obtain second sample data.
Considering that the ship is usually designed only by analyzing the rapidity of the ship under a still water condition, the shallow water effect is not considered, and the ship is also influenced by meteorological conditions, water displacement and water depth in the sailing process, the relation among the first sample data needs to be corrected, and specifically, the influence of meteorological parameters such as wind, waves and current, the water displacement and the water depth on the ship speed and the shaft power under the low sea condition can be estimated according to a plurality of empirical formulas summarized in ISO15016:2015 to obtain second sample data.
Step S106: and constructing an axis power model based on the second sample data.
In one embodiment, the second sample data may contain a plurality of parameters related to shaft power, and each sample data includes a set of input parameters (such as speed, meteorological parameters, displacement, water depth, etc.) and an objective function (shaft power). Under the support of a large number of samples, the mapping relation between the objective function and each input parameter can be determined, namely, an axis power model is constructed.
According to the model construction method provided by the embodiment of the invention, the first sample data is obtained through a test when the shaft power model is constructed, the first sample data is corrected by using the preset correction formula, and the actually measured data does not need to be collected in the ship operation process, so that the data collection time can be reduced, the variation range of the parameters of the obtained second sample data is wide enough, and the application range of the constructed model is wide.
Considering that in the prior art, a model is generally constructed by utilizing measured data, namely, data is acquired by a sensor and the like in the ship operation process, enough data is needed to improve the accuracy of the model, and therefore, long-time accumulation is needed to obtain enough data; and the measured data usually has a narrow variation range and is only suitable for the ship navigation environment. Therefore, in order to reduce the time for accumulating data and make the data change range wide enough, an embodiment of the present invention provides a specific method for acquiring first sample data of a ship, including: and obtaining first sample data of the ship through a model test and a numerical test. The model test is a test for simulating sailing by using a ship model, namely a reduced-scale water pool test, and the sailing process of a ship is simulated in a water pool through the ship model so as to acquire test data (namely first sample data); the numerical test is a test for simulating ship sailing by using a numerical calculation mode, namely, a simulation test is performed through Computational Fluid Dynamics (CFD) to obtain first sample data. Through model test and CFD numerical test, can acquire a large amount of sample data fast, need not wait for a long time, can simulate multiple different operating modes simultaneously, promote the variety of data, improve the suitability of model.
Further, the first sample data provided by this embodiment may include an energy consumption parameter and a speed; wherein the energy consumption parameters include one or more of: shaft power, propulsion efficiency, total resistance coefficient; the navigational speed includes: speed to ground, heading to ground, and speed to water. Based on this, step S102 may be performed as follows: and acquiring the energy consumption parameter and the navigational speed of the ship, and determining the relationship between the energy consumption parameter and the navigational speed. In one embodiment, parameters such as shaft power, propulsion efficiency, total resistance coefficient, and speed can be obtained through model tests and numerical tests, and then the relationship between shaft power, propulsion efficiency, total resistance coefficient, and speed is calculated respectively.
Considering that the relationship between the shaft power, the propulsion efficiency, the total resistance coefficient and the speed obtained in step S102 is only established when the test conditions are satisfied, that is, the relationship between the shaft power, the propulsion efficiency, the total resistance coefficient and the speed obtained in step S102 is established when the parameters of the still water condition, the still air and sea water density, the sea water viscosity (kinematic viscosity coefficient), the air density, the displacement and the like are also preset test values, when the shallow water effect and the influence of the water depth, the displacement and the meteorological conditions are considered, the first sample data needs to be corrected, and based on this, the preset parameters in the collapse embodiment may include one or more of the following: the flow velocity to the ground, the flow direction to the ground, the wind speed to the ground, the wind direction to the ground, the sense wave height, the wave direction to the ground, the air density, the sea water viscosity, the water displacement and the water depth; wherein, the meteorological parameters comprise the flow velocity to the ground, the flow direction to the ground, the wind speed to the ground, the wind direction to the ground, the sense wave height, the wave direction to the ground, the air density, the seawater viscosity and the like.
For convenience of understanding, an embodiment of the present invention provides a specific implementation manner for correcting the first sample data based on a preset correction formula and preset parameters, that is, the step S104 may be executed with reference to the following steps: correcting the total resistance based on a preset correction formula, the seawater density and the seawater viscosity; and/or correcting the total resistance based on a preset correction formula, the speed of the ground wind and the direction of the ground wind; and/or correcting the propulsion efficiency and the shaft power based on a preset correction formula and the corrected total resistance; and/or correcting the shaft power based on a preset correction formula and the water displacement; and/or correcting the water speed based on a preset correction formula and the water depth; and/or correcting the flow speed and the flow direction to the ground speed and the ground heading based on a preset correction formula. Specifically, the correction can be performed according to the correction formula and the constraint conditions provided in ISO15016: 2015.
And obtaining second sample data after further correction, wherein the second sample data may include one or more of preset parameters, and also include shaft power, speed to ground and heading to ground, that is, a plurality of sets of parameters including shaft power, speed to ground, heading to ground, speed to ground, flow direction to ground, wind speed to ground, wind direction to ground, sense wave height, wave direction to ground, air density, sea water viscosity, water displacement, water depth and the like.
In one embodiment, under the constraint of the condition that the correction formula is satisfied, randomly selecting input parameters, and correcting the energy consumption parameter and the speed of the ship in turn to construct any number of sample data, thereby forming a machine learning training set (i.e., second sample data). Further, an axis power model can be constructed through a deep learning algorithm and/or a machine learning algorithm based on the second sample data; wherein, the shaft power model is a propeller shaft power model. In practical application, the second sample data may be subjected to regression learning through a deep learning algorithm and/or a machine learning algorithm to obtain a mapping relation (propeller shaft power model) between an objective function (propeller shaft power) and each input parameter (a feature vector composed of the second sample data), specifically, a regression method, ensemble learning, a neural network, and the like may be adopted to train the model, and commonly used machine learning and deep learning regression methods include a generalized linear regression, a decision number regression, a support vector machine, an artificial neural network, an ensemble learning method, and the like.
According to the method provided by the embodiment of the invention, the first sample data is obtained through a test when the shaft power model is constructed, the first sample data is corrected by using the preset correction formula, and the actually measured data does not need to be acquired in the ship operation process, so that the data collection time can be reduced, the variation range of the parameters of the obtained second sample data is wide enough, and the application range of the constructed model is wide.
On the basis of the foregoing embodiment, the present embodiment provides a specific example of a model building method, see a flow diagram of another model building method shown in fig. 2, where the method mainly includes the following steps S202 to S206:
step S202: and determining the relation between the ship energy consumption coefficient and the navigational speed under the still water condition.
In one embodiment, in the ship design stage, the relationship between the ship energy consumption parameters and the ship speed under the still water condition can be analyzed through a model test, and the energy consumption parameters can be shaft power, propulsion efficiency, total resistance coefficient and the like. As the model test is difficult to provide very much sample data, a CFD numerical calculation method can be adopted to simulate more working conditions so as to enrich the sample data. The model test data and the numerical test data jointly describe the rapidity performance of the ship under the still water condition, polynomial regression is carried out on the data, and the relationship among the shaft power, the propulsion efficiency, the total resistance coefficient and the navigational speed can be obtained, wherein the formula is as follows:
P d0 ＝f (1) (V r0 ) (eq.1)
η d0 ＝f (2) (V r0 ) (eq.2)
R T0 ＝f (3) (V r0 ) (eq.3)
C T0 ＝f (4) (V r0 ) (eq.4)
wherein, V r0 Indicating the speed of water-in-water, P d0 Representing propeller shaft power, η d0 Indicating propulsive efficiency, R T0 Denotes total resistance, C T0 The total drag coefficient is expressed.
Specifically, refer to the schematic diagrams of the relationship between the power consumption related parameter and the speed, which are found by the model test and the numerical test, shown in fig. 3 to 6, and refer to the schematic diagram of the relationship between the marine speed and the axle power, which is shown in fig. 3, which illustrates the relationship between the marine speed and the axle power, which is found by the model test and the numerical test; referring to fig. 4, a schematic diagram of the relationship between the parawater speed and the total resistance is shown, which illustrates the relationship between the parawater speed and the total resistance found by the model test and the numerical test; referring to fig. 5, a schematic diagram of the relationship between the marine speed and the propulsion efficiency is shown, which illustrates the relationship between the marine speed and the propulsion efficiency, which is found by a model test and a numerical test; referring to fig. 6, a schematic diagram of the relationship between the parawater speed and the total resistance coefficient is shown, which illustrates the relationship between the parawater speed and the total resistance coefficient, which is found by model experiments and numerical experiments.
Considering that the formula (eq.1-eq.4) only contains the influence of still water and static air, does not consider the shallow water effect, and does not relate to the influence of wind, waves, flow and other meteorological parameters; the formula needs to be corrected if the effects of wind, waves, flow and water depth are accounted for. In addition to this, the present invention is,the above formula (eq.1-eq.4) corresponds to the specific test conditions, i.e. the seawater density ρ S0 Viscosity (kinematic viscosity coefficient) v of seawater S0 Air density ρ A0 Water discharge amount
Figure BDA0002543774070000101
And if the parameters are not consistent with the model test, the formula also needs to be corrected.
Step S204: and correcting the ship energy consumption coefficient, and constructing sample data containing water depth, water displacement and meteorological influence.
First, a model test state is used as a reference state. Namely: assuming that the seawater density, the seawater viscosity, the air density, the water discharge and the model test are completely consistent, the sea water density, the seawater viscosity, the air density, the water discharge and the model test are not influenced by wind, wave and flow, and the shallow water effect is not counted, so that the relation between the sailing energy consumption parameter and the water sailing speed conforms to a formula (eq.1-eq.4). Then introduces the speed of the ground G0 And heading to ground theta G0 (initialization) for water speed V, since the vessel is not influenced by flow r0 ＝V G0 Then 4 energy consumption related parameters are found according to the formula (eq.1-eq.4). And then, assuming that the sea water density, the sea water viscosity, the air density, the water displacement, the water depth, the wind, the wave and the flow are changed, and correcting the energy consumption parameters (mainly the shaft power) of the ship. The parameter correction process is described below by taking a partial correction formula provided in ISO15016:2015 as an example. It should be noted that, while the "ISO 15016: 2015" proposes a correction formula, it also indicates the applicable conditions of the correction method, and the using conditions need to be taken into account in the parameter correction process, so the step S204 mainly includes the following steps (1) to (8):
step (1): and correcting the total resistance according to the seawater density and the seawater viscosity.
Assuming that the density and viscosity of seawater change, the values are respectively rho S V and v S And sea water density ρ of reference state S0 And viscosity v of seawater S0 In contrast, and therefore causing a change in navigational resistance, the total resistance after the change can be estimated according to the following equation:
Figure BDA0002543774070000111
wherein R is AS Denotes resistance correction, S denotes wet surface area, L WL Indicates the length of water line, V r0 Representing the speed of water-in-water, p S0 Denotes the sea water density, v, in the reference state S0 Denotes the sea water viscosity in the reference state, C F0 Denotes the coefficient of frictional resistance, R, in the reference state n0 Denotes the Reynolds number, C, in the reference state T0 Denotes the total drag coefficient, ρ S Denotes the sea water density, v, in the actual state S Indicates the sea water viscosity in the actual state, C F Represents a coefficient of frictional resistance in an actual state, R n Representing the reynolds number in the actual state. S and L WL The water displacement of the ship is related and can be found through ship design data.
Step (2): and correcting the total resistance according to the ground wind speed and the ground wind direction.
In one embodiment, the wind speed and direction to ground are labeled V assuming that the vessel is affected by wind w And psi w Then can be based on the wind speed to the ground V w Wind direction psi to the ground w And speed to ground V G0 Heading to ground theta G0 Calculating the ship-to-ship wind speed and the ship-to-ship wind direction which are respectively marked as V w_ref And psi w_ref (ii) a Due to the influence of the wind, the air density is also different from the reference state, marked as ρ A Then the amount of change in the total resistance can be estimated according to the following equation:
Figure BDA0002543774070000112
wherein R is AA Indicating a resistance correction, C AA Denotes the wind resistance coefficient, V w_ref Representing wind speed to the vessel, representing wind direction to the vessel, V G Representing speed of flight, p, to the ground A Denotes the air density, p A0 Denotes the air density in the reference state, A XV Representing the transverse projected area of the part above the waterline of the ship. A. The XV Related to the displacement of ship, and the wind resistance coefficient C can be found by ship design data AA (ψ w_ref ) Wind direction psi of opposite ship w_ref The estimation value can be obtained through a wind tunnel test, and the estimation value can also be obtained by consulting data.
Further, the following applicable conditions are included for the wind correction equation (eq.6):
Figure BDA0002543774070000113
wherein L is pp Indicating the distance between the fore and aft verticals of the ship.
And (3): the total resistance is corrected according to the sense wave height and the direction of the ground waves.
In one embodiment, assuming that the vessel is affected by waves, the sense wave height and direction to the ground are labeled H and ψ s Then can be based on the speed to ground V G And wave direction psi to ground s Determining the angle psi of the incoming wave s_ref The amount of change in the total resistance can then be estimated according to the following equation:
Figure BDA0002543774070000121
wherein R is AWL Denotes the resistance correction,. Rho S Denotes sea water density, g denotes gravitational acceleration, H denotes sense wave height, # s_ref Representing the angle of attack, B the width of the vessel, L BWL Representing 95% of the maximum width distance of the bow to the waterline. B is a constant, L BWL Related to the displacement of the ship, the displacement can be found according to the design data of the ship.
Further, the following applicable conditions are included for the above wave correction equation (eq.7):
H≤2.25(L pp /100) 1/2 (eq.C2)
wherein L is pp Indicating the distance between the fore and aft verticals of the ship.
And (4): and correcting the propulsion efficiency and the shaft power according to the corrected total resistance.
In one embodiment, after obtaining the corrected resistance, the propulsion efficiency may be corrected by the following equation:
Figure BDA0002543774070000122
the corrected shaft power can then be obtained by the following formula:
P d1 ＝P d0 +(R AS +R awl +R AA )V r0 /η d1 (eq.9)
wherein, P d1 Representing the corrected shaft power, eta d1 Indicating the corrected propulsion efficiency, P d0 Representing the shaft power, η, before correction d0 Shows the propulsive efficiency before correction, V r0 Indicating the speed of water-in-water, R T0 Indicates the total resistance before correction, R AS Representing the resistance correction, R, caused by the change in seawater density and seawater viscosity AWL Indicating wave-induced drag correction, R AA Indicating wind-induced drag correction, ξ P Representing varying load factor, ξ P Can be measured by model test.
And (5): and correcting the shaft power according to the displacement of the ship.
In one embodiment, assuming that the displacement of the vessel changes, the shaft power may be corrected by the following equation:
Figure BDA0002543774070000131
wherein, P d2 Representing the corrected shaft power, P d1 The shaft power before the correction is represented,
Figure BDA0002543774070000132
indicating the amount of water displaced after the change,
Figure BDA0002543774070000133
showing a referenceAnd (4) water discharge amount.
And (6): and correcting the navigational speed according to the water depth.
In one embodiment, assuming that the vessel is affected by the shallow water effect resulting in a reduced speed, the change to the speed of the water can be estimated by the following formula:
Figure BDA0002543774070000134
further, the speed to ground is:
V G1 ＝V r1 (eq.12)
wherein, V r1 Indicating corrected parawater speed, V r0 Representing the parawater speed before correction, h representing the water depth, A M Representing the area of the cross section in the underwater vessel, B the width of the vessel, T M Mean draught is indicated and g is the acceleration of gravity. B is a constant, A M And T M The correlation with the water discharge can be found through design data.
Further, the following applicable conditions are included for the shallow water correction formula (eq.12) described above:
Figure BDA0002543774070000135
and (7): and correcting the speed to the ground and the heading to the ground according to the speed to the ground and the heading to the ground.
In one embodiment, the para-flow velocity and para-flow direction are labeled V assuming the vessel is affected by the flow c 、ψ c Then the speed and course of the ground are no longer equal to those of the parawater, and the corrected speed V can be obtained by vector operation according to the following formula G2 And heading to ground theta G ：
Figure BDA0002543774070000141
Wherein, V G2 Indicating the corrected speed of the ground-based navigation,θ G indicating the corrected course to the ground, V G1 Indicates the speed of the flight to the ground before correction, theta G0 Indicating the heading, V, before correction c Indicating the ground flow velocity, # c Indicating a ground flow direction.
And (8): a data set is constructed containing the effects of meteorological parameters.
In an embodiment, the relationship between the ship energy consumption coefficient and the ship speed under the still water condition may be sequentially corrected according to a formula (eq.1-eq.13), and finally 13 parameters including the speed of the ship to the ground, the heading to the ground, the flow speed to the ground, the flow direction to the ground, the wind speed to the ground, the wind direction to the ground, the wave height to the ground, the wave direction to the ground, the air density, the seawater viscosity, the water discharge amount, the water depth and the like are obtained, and the specific establishment process of the data set may refer to a sample data set establishment flow chart shown in table 1.
TABLE 1 sample data set construction flow sheet
Figure BDA0002543774070000142
Figure BDA0002543774070000151
In summary, a sample data set can be obtained, which represents the objective function Y = P d2 And 13-dimensional feature vector
Figure BDA0002543774070000152
The relationship between them. Therefore, under the constraint of the condition that the correction formula is satisfied, namely under the constraint of the formula (eq.c 1-eq.c 3), the input parameters can be randomly selected, and the formula (eq.1-eq.13) can be sequentially operated, so that any number of sample data can be constructed to form a machine learning training set. After enough sample data is obtained, the model can be trained by a machine learning method or a deep learning method, and the relation between the shaft power and the speed, the meteorological parameters, the displacement and the water depth is obtained, namely:
Y＝f(X) (eq.14)
step S206: and constructing an axis power model by adopting a machine learning algorithm and/or a deep learning algorithm based on the sample data.
In practical application, under the support of sufficient sample data, a machine learning algorithm and/or a deep learning algorithm can be adopted to train the shaft power model, namely, the formula (eq.14) is trained to be close to the sample data optimally or credibly, and the shaft power model obtained thereby can be used for predicting the shaft power of the ship.
Considering that the objective function Y is a continuous value, the embodiment may train the model by using a regression-type method. Common machine learning and deep learning regression methods include generalized linear regression, decision number regression, support vector machines, artificial neural networks, ensemble learning methods, and the like. In the embodiment, taking generalized linear regression as an example, the training process of the model includes the following three aspects:
in a first aspect, a linear regression problem.
For investigating the objective function Y and the feature vector (x) 1 ,x 2 ,...,x n ) The relation between the sample data sets D is measured:
Figure BDA0002543774070000161
it can be assumed that Y and (x) 1 ,x 2 ,...,x n ) The linear relationship is satisfied:
f＝w 1 x 1 +w 2 x 2 +...+w n x n (eq.15)
then the regression coefficient w = (w) is determined 1 ,w 2 ,...,w n ) T By "optimally" approximating f (X) to Y, a solution to the problem can be obtained.
In a second aspect, the generalization of the linear regression problem.
For the above formula (eq.15) one can include the intercept, equivalent to "adding x to the feature vector 0 =1", the formula (eq.15) can also be extended to a polynomial equation, equivalent to" each term of the polynomial constitutes a new eigenvector ", the formula (eq.15) can also nest a known function (linear or nonlinear) at the outer layer, equivalent to outputting the functionThe number Y is transformed once.
In a third aspect, the problem is solved.
Assuming that the model is optimal when the mean square error of f (X) and Y is minimum, the linear regression problem is transformed into an optimization problem:
Figure BDA0002543774070000162
Figure BDA0002543774070000163
which may also be referred to as a loss function. And solving the value of w when the loss function is minimized, so as to obtain the solution of the original problem. In the field of machine learning, regularization constraints are often added to the formula (eq.16) to limit the size of w. Regularization constraint can reduce the complexity of the model and improve the generalization capability of the model. There are four types of constraint methods that are commonly used:
1) L2 norm constraint
Figure BDA0002543774070000164
2) L1 norm constraint
Figure BDA0002543774070000171
3) L0 norm constraint
Figure BDA0002543774070000172
4) L2 and L1 hybrid constraints
Figure BDA0002543774070000173
And alpha, rho and N in the model are hyper-parameters and can be debugged manually.
Methods of minimizing the loss function include least squares and iterative methods. An analytic solution of the problem can be obtained by using a least square method; if the matrix is too large to be calculated conveniently or is not reversible, an approximate solution can be obtained through an iterative method, such as a coordinate descent method, a gradient descent method, a minimum angle regression method and the like.
In summary, the model construction method provided by the embodiment of the present invention constructs a training set sample by using design data (i.e., model test data and numerical test data) and a modification formula, and trains a model by using a machine learning or deep learning method on the basis of sufficient sample data to obtain the relationship between the shaft power and the parameters of the speed, the meteorological parameters, the displacement and the water depth, so as to be used for prediction. The method does not depend on actual measurement data in the model building process, so that a data collection process does not need to be waited, and in addition, compared with the actual measurement data, the parameter change range obtained by the embodiment is wide, and the built model has good applicability.
For the model building method provided in the foregoing embodiment, an embodiment of the present invention further provides a model building apparatus, referring to a schematic structural diagram of the model building apparatus shown in fig. 7, where the apparatus may include the following components:
the data acquisition module 701 is used for acquiring first sample data of a ship and determining the relationship between the first sample data; wherein the first sample data is used to characterize the performance of the vessel.
And the correcting module 702 is configured to correct the first sample data based on a preset correcting formula and preset parameters to obtain second sample data.
And a model building module 703, configured to build the shaft power model based on the second sample data.
According to the model construction device provided by the embodiment of the invention, the first sample data is obtained through a test when the shaft power model is constructed, the first sample data is corrected by using the preset correction formula, and the actually measured data does not need to be collected in the ship operation process, so that the data collection time can be reduced, the variation range of the parameters of the obtained second sample data is wide enough, and the application range of the constructed model is wide.
In an embodiment, the data obtaining module 701 is further configured to obtain first sample data of the ship through a model test and a numerical test; the model test is a test for simulating the sailing by using a ship model, and the numerical test is a test for simulating the sailing of a ship by using a numerical calculation mode.
In one embodiment, the first sample data includes an energy consumption parameter and a speed of flight; wherein the energy consumption parameter comprises one or more of: shaft power, propulsion efficiency, total resistance coefficient; the navigational speed includes: speed of ground, heading of ground, and speed of water.
In an embodiment, the data obtaining module 701 is further configured to obtain an energy consumption parameter and a speed of the ship, and determine a relationship between the energy consumption parameter and the speed of the ship.
In one embodiment, the preset parameters include one or more of the following: the flow velocity to the ground, the flow direction to the ground, the wind speed to the ground, the wind direction to the ground, the sense wave height, the wave direction to the ground, the air density, the sea water viscosity, the water displacement and the water depth; the correction module 702 is further configured to correct the total resistance based on a preset correction formula, the seawater density, and the seawater viscosity; and/or correcting the total resistance based on a preset correction formula, the speed of the ground wind and the direction of the ground wind; and/or correcting the propulsion efficiency and the shaft power based on a preset correction formula and the corrected total resistance; and/or correcting the shaft power based on a preset correction formula and the water displacement; and/or correcting the water speed based on a preset correction formula and the water depth; and/or correcting the flow speed and the flow direction to the geo-speed and the geo-heading based on a preset correction formula.
In an embodiment, the second sample data includes one or more of preset parameters, shaft power, speed to ground and heading to ground.
In an embodiment, the model building module 703 is further configured to build an axis power model through a deep learning algorithm and/or a machine learning algorithm based on the second sample data; wherein, the shaft power model is a propeller shaft power model.
The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.
The embodiment of the invention also provides electronic equipment, which specifically comprises a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the method of any of the above embodiments.
Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 100 includes: the system comprises a processor 80, a memory 81, a bus 82 and a communication interface 83, wherein the processor 80, the communication interface 83 and the memory 81 are connected through the bus 82; the processor 80 is arranged to execute executable modules, such as computer programs, stored in the memory 81.
The Memory 81 may include a Random Access Memory (RAM) and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 83 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.
Bus 82 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 8, but that does not indicate only one bus or one type of bus.
The memory 81 is used for storing a program, the processor 80 executes the program after receiving an execution instruction, and the method performed by the apparatus defined by the flow disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 80, or implemented by the processor 80.
The processor 80 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 80. The Processor 80 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory 81, and the processor 80 reads the information in the memory 81 and performs the steps of the above method in combination with its hardware.
The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the foregoing method embodiment, which is not described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (5)

1. A method of model construction, comprising:
acquiring first sample data of a ship, and determining the relation between the first sample data; wherein the first sample data is used to characterize a performance of the vessel;
correcting the first sample data based on a preset correction formula and preset parameters to obtain second sample data;
constructing an axis power model based on the second sample data;
the first sample data comprises an energy consumption parameter and a navigational speed; wherein the energy consumption parameters include one or more of: shaft power, propulsion efficiency, total resistance coefficient; the navigational speed includes: speed, heading and speed of water-to-ground;
the step of obtaining first sample data of a ship and determining a relationship between the first sample data includes: acquiring an energy consumption parameter and a navigation speed of a ship, and determining a relation between the energy consumption parameter and the navigation speed;
the preset parameters include the following multiple types: the flow velocity to the ground, the flow direction to the ground, the wind speed to the ground, the wind direction to the ground, the sense wave height, the wave direction to the ground, the air density, the sea water viscosity, the water displacement and the water depth; the step of correcting the first sample data based on a preset correction formula and preset parameters includes: correcting the total resistance based on a preset correction formula, the seawater density and the seawater viscosity; and correcting the total resistance based on a preset correction formula, the ground wind speed and the ground wind direction; and correcting the propulsion efficiency and the shaft power based on a preset correction formula and the corrected total resistance; and correcting the shaft power based on a preset correction formula and the water displacement; correcting the water speed based on a preset correction formula and the water depth; and correcting the speed and the heading of the ground based on a preset correction formula, the speed and the heading of the ground;
the second sample data comprises one or more of the preset parameters, the shaft power, the speed to ground and the heading to ground; the step of constructing an axis power model based on the second sample data includes: based on the second sample data, an axis power model is constructed through a deep learning algorithm and/or a machine learning algorithm; the shaft power model is a propeller shaft power model.
2. The method of claim 1, wherein the step of obtaining first sample data of a vessel comprises:
obtaining first sample data of a ship through a model test and a numerical test; the model test is a test for simulating sailing by using a ship model, and the numerical test is a test for simulating sailing by using a numerical calculation mode.
3. A model building apparatus, comprising:
the data acquisition module is used for acquiring first sample data of a ship and determining the relation between the first sample data; wherein the first sample data is used to characterize a performance of the vessel;
the correction module is used for correcting the first sample data based on a preset correction formula and preset parameters to obtain second sample data;
the model building module is used for building an axis power model based on the second sample data;
the first sample data comprises an energy consumption parameter and a navigational speed; wherein the energy consumption parameters include one or more of: shaft power, propulsion efficiency, total resistance coefficient; the navigational speed includes: speed, heading and speed of water-to-ground;
the data acquisition module is further configured to: acquiring an energy consumption parameter and a navigation speed of a ship, and determining a relation between the energy consumption parameter and the navigation speed;
the preset parameters include the following multiple types: the flow velocity to the ground, the flow direction to the ground, the wind speed to the ground, the wind direction to the ground, the sense wave height, the wave direction to the ground, the air density, the sea water viscosity, the water displacement and the water depth; the correction module is further configured to: correcting the total resistance based on a preset correction formula, the seawater density and the seawater viscosity; and correcting the total resistance based on a preset correction formula, the ground wind speed and the ground wind direction; and correcting the propulsion efficiency and the shaft power based on a preset correction formula and the corrected total resistance; and correcting the shaft power based on a preset correction formula and the water displacement; correcting the water speed based on a preset correction formula and the water depth; and correcting the speed and the heading of the ground based on a preset correction formula, the speed and the heading of the ground;
the second sample data comprises one or more of the preset parameters, the shaft power, the speed to ground and the heading to ground; the model building module is further configured to: based on the second sample data, an axis power model is constructed through a deep learning algorithm and/or a machine learning algorithm; the shaft power model is a propeller shaft power model.
4. An electronic device comprising a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to perform the steps of the method of any one of claims 1 to 2.
5. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of the preceding claims 1 to 2.
CN202010557681.7A 2020-06-17 2020-06-17 Model construction method and device, electronic equipment and computer readable storage medium Active CN111709090B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010557681.7A CN111709090B (en) 2020-06-17 2020-06-17 Model construction method and device, electronic equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010557681.7A CN111709090B (en) 2020-06-17 2020-06-17 Model construction method and device, electronic equipment and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN111709090A CN111709090A (en) 2020-09-25
CN111709090B true CN111709090B (en) 2023-04-07

Family

ID=72541044

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010557681.7A Active CN111709090B (en) 2020-06-17 2020-06-17 Model construction method and device, electronic equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN111709090B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112503789B (en) * 2020-12-09 2021-09-03 西安交通大学 Intermediate pressure control method for cascade refrigeration system
CN113642105B (en) * 2021-08-03 2023-10-27 中国船舶重工集团公司第七一九研究所 Multi-scale model construction method and device for ship power system and electronic equipment
CN114056509B (en) * 2021-12-10 2023-05-26 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） Ship construction method, device and system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3330747A1 (en) * 2016-11-30 2018-06-06 Offshore Navigation Limited Apparatus for providing a metocean forecast
WO2018182171A1 (en) * 2017-03-27 2018-10-04 한국해양과학기술원 Method for performing standard sailing conditions speed-power analysis of sailing vessel
CN109866875A (en) * 2019-03-06 2019-06-11 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） Ship performance assessment and prediction technique and device
CN110705631A (en) * 2019-09-27 2020-01-17 中国船舶工业***工程研究院 SVM-based bulk cargo ship equipment state detection method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3330747A1 (en) * 2016-11-30 2018-06-06 Offshore Navigation Limited Apparatus for providing a metocean forecast
WO2018182171A1 (en) * 2017-03-27 2018-10-04 한국해양과학기술원 Method for performing standard sailing conditions speed-power analysis of sailing vessel
CN109866875A (en) * 2019-03-06 2019-06-11 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） Ship performance assessment and prediction technique and device
CN110705631A (en) * 2019-09-27 2020-01-17 中国船舶工业***工程研究院 SVM-based bulk cargo ship equipment state detection method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
牟小辉 ; 袁裕鹏 ; 严新平 ; 赵光普 ; .基于随机森林算法的内河船舶油耗预测模型.交通信息与安全.2017,(04),全文. *
陈伟南 ; 黄连忠 ; 张勇 ; 路通 ; .基于BP神经网络的船舶主机能效状态评估.中国舰船研究.2018,(04),全文. *

Also Published As

Publication number Publication date
CN111709090A (en) 2020-09-25

Similar Documents

Publication Publication Date Title
CN111709090B (en) Model construction method and device, electronic equipment and computer readable storage medium
US8761975B2 (en) Method and apparatus for real-time polars
CN109541730A (en) A kind of method and apparatus of pollutant prediction
CN111811694B (en) Temperature calibration method, device, equipment and storage medium
KR102319145B1 (en) Method and device for generating high-resolution ocean data
CN111767612A (en) Model construction method, ship control device and electronic equipment
CN116108995A (en) Tidal river reach ship oil consumption prediction method and device and electronic equipment
CN111824357B (en) Test method, test device, electronic equipment and computer readable storage medium
US11656367B2 (en) Rapid assessment of vehicle relative speed performance
US11507114B2 (en) Closed course navigation through a moving medium
WO2019110957A1 (en) Estimating fatigue damage in a structure
Marie et al. Sail-assisted motor vessels weather routing using a fuzzy logic model
WO2023054039A1 (en) Performance evaluation method, performance evaluation program, and performance evaluation system through actual ship monitoring analysis of ship
CN111260529B (en) Ship environment data determining method and device and ship
CN113495562B (en) Simulation path generation method, device, equipment and computer storage medium
CN112660331B (en) Navigation speed and trim joint optimization method and device and electronic equipment
US11567219B2 (en) Estimating vehicle speed through an advecting medium
CN116050554A (en) Scenic spot passenger flow volume prediction method and device, computing equipment and storage medium
KR20220159746A (en) Method and appratus for determining the path of a typhoon
CN111709089B (en) Axle power model training method and device and electronic equipment
CN116757102B (en) Apparent optical characteristic profile distribution estimation method based on inherent optical characteristics
US20240061977A1 (en) Data informed ocean simulations
Esmailian et al. A new power prediction method toward efficient ship design and operation
CN116228335A (en) Revenue prediction method, device and server
CN107246871B (en) ECDIS-based green ocean route design method

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