CN113886973A - Ship navigational speed processing method, device and processing equipment based on virtual-real mapping - Google Patents
Ship navigational speed processing method, device and processing equipment based on virtual-real mapping Download PDFInfo
- Publication number
- CN113886973A CN113886973A CN202111241412.0A CN202111241412A CN113886973A CN 113886973 A CN113886973 A CN 113886973A CN 202111241412 A CN202111241412 A CN 202111241412A CN 113886973 A CN113886973 A CN 113886973A
- Authority
- CN
- China
- Prior art keywords
- ship
- data
- real
- model
- simulation
- 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.)
- Granted
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
-
- 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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a ship speed processing method, a ship speed processing device and ship speed processing equipment based on virtual-real mapping, and relates to the technical field of intelligent ships. The method comprises the steps of obtaining real-time working parameter information of a ship, inputting the real-time working parameter information of the ship into a navigational speed prediction model to obtain target navigational speed information, wherein the navigational speed prediction model is obtained through training based on a training sample set, the training sample set is constructed based on a simulation data set output by a multi-dimensional digital twin simulation model, and the multi-dimensional digital twin simulation model is used for outputting the simulation data set according to twin data of the ship. According to the method and the device, on the basis of obtaining a small amount of ship navigation data, a large amount of simulation data sets are used for training the navigation speed prediction model, and an accurate navigation speed optimization result is obtained.
Description
Technical Field
The application relates to the technical field of intelligent ships, in particular to a ship speed processing method, a ship speed processing device and ship speed processing equipment based on virtual-real mapping.
Background
In the field of ships, it is an important research topic to realize intelligent and effective management of ships, for example, intelligent optimization of ship speed.
The current intelligent optimization method of the ship speed mainly comprises the technologies of an expert system, experience guidance, a fuzzy theory, a neural network model and the like.
However, in the prior art, if an expert system, experience guidance and fuzzy theory method are used, when the navigation speed is optimized, the accuracy of the optimization result is low due to the complex working condition and more parameters of the ship; if the method of the neural network model is adopted, because ship navigation data samples are difficult to obtain, only a small number of data samples can be obtained, the training degree of the neural network model is insufficient, and the accuracy of an output optimization result is not high.
Disclosure of Invention
The application aims to provide a ship speed processing method, a ship speed processing device and ship speed processing equipment based on virtual-real mapping, aiming at the defects in the prior art, and the ship speed processing method, the ship speed processing device and the ship speed processing equipment can obtain an accurate speed optimization result according to real-time working parameter information of a ship.
In order to achieve the above purpose, the technical solutions adopted in the embodiments of the present application are as follows:
in a first aspect, an embodiment of the present application provides a ship speed processing method based on virtual-real mapping, where the method includes:
acquiring real-time working parameter information of a ship;
inputting the real-time working parameter information of the ship into a navigational speed prediction model to obtain target navigational speed information, wherein the navigational speed prediction model is obtained through training based on a training sample set, the training sample set is constructed based on a simulation data set output by a multi-dimensional digital twin simulation model, and the multi-dimensional digital twin simulation model is used for outputting the simulation data set according to twin data of the ship.
In an optional embodiment, the method further comprises:
acquiring twin data of the ship, wherein the twin data of the ship are used for identifying the operation data of the ship and the relation among the operation data;
inputting twin data of the ship into the multi-dimensional digital twin simulation model to obtain the simulation data set;
labeling the simulation data set to obtain the training sample set;
and training by using the training sample set to obtain the navigational speed prediction model.
In an optional embodiment, the method further comprises:
constructing an initial twin simulation model;
correcting the initial twin simulation model according to historical operation data of a ship and an actual simulation result output by the initial twin simulation model;
and if the corrected initial twin simulation model meets the preset conditions, taking the corrected initial twin simulation model as the multi-dimensional digital twin simulation model.
In an alternative embodiment, the training using the training sample set to obtain the navigational speed prediction model includes:
training according to the training sample set to generate a Bayesian model;
updating the Bayesian model according to the Bayesian model and the actual operation data to obtain an updated Bayesian model;
obtaining an updated training sample set according to the updated Bayesian model and the training sample set;
and correcting the navigation speed prediction model according to the updated training sample set to obtain the updated navigation speed prediction model.
In an alternative embodiment, the acquiring twin data of the ship includes:
preprocessing the real-time operation data of the ship to obtain real-time operation data with uniform dimension;
performing feature selection on the real-time operation data with unified dimensions to obtain a target feature vector, wherein the target feature vector is used for representing the operation data related to the navigational speed and the relationship between the operation data;
and performing dimensionality compression on the target characteristic vector to obtain the twin data.
In an alternative embodiment, the real-time operational data of the vessel comprises:
ship navigation state, ship running state, and empirical data obtained according to historical navigation information.
In an optional embodiment, the method further comprises:
and updating the navigational speed prediction model according to the acquired real-time working parameter information of the ship.
In a second aspect, an embodiment of the present application provides a ship speed processing apparatus based on virtual-real mapping, which is applied to a ship speed processing device, and the apparatus includes:
the acquisition module is used for acquiring real-time working parameter information of the ship;
the processing module is used for inputting the real-time working parameter information of the ship into a navigational speed prediction model to obtain target navigational speed information, the navigational speed prediction model is obtained through training based on a training sample set, the training sample set is constructed based on a simulation data set output by a multi-dimensional digital twin simulation model, and the multi-dimensional digital twin simulation model is used for outputting the simulation data set according to twin data of the ship.
In a third aspect, an embodiment of the present application provides a ship speed processing device based on a virtual-real mapping, where the ship speed processing device based on the virtual-real mapping includes: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when the electronic device is operated, the processor and the storage medium communicate with each other through the bus, and the processor executes the machine-readable instructions to execute the steps of the ship speed processing method based on the virtual-real mapping according to any one of the preceding embodiments.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps of the method in any one of the foregoing embodiments.
The beneficial effects of the embodiment of the application include, for example:
by adopting the ship speed processing method, the ship speed processing device and the ship speed processing equipment based on the virtual-real mapping provided by the embodiment of the application, firstly, the method of the neural network model is utilized to predict the speed according to the data of a plurality of real-time working parameter information which affect the speed optimization result, and the speed prediction model is used to synthesize the effects of a plurality of working parameters to obtain more accurate target speed information. Secondly, in order to overcome the problem that the training degree of the neural network model is insufficient due to too few data samples, the embodiment of the application constructs a training sample set by using a simulation data set output by a multi-dimensional digital twin simulation model, and the training sample set is used for training a navigational speed prediction model. Because the multi-dimensional digital twin simulation model can obtain corresponding navigational speed simulation results under different working conditions according to the working parameter information under different working conditions, the dependence of the accuracy of the navigational speed prediction model on the data acquisition of the physical ship data is greatly reduced, and the purposes of simplifying the navigation sample data acquisition process, expanding the training sample set and further fully training the navigational speed prediction model are achieved.
In addition, the method also comprises the steps of updating training sample parameters in the training sample set by utilizing the Bayesian model according to the stored actual operation data to obtain an updated training sample set, then training the speed prediction model by utilizing the updated training sample set, and repeating the process for multiple times until the difference value between the speed prediction result output by the speed prediction model and the actual speed corresponding to the actual operation data is smaller than the preset range. The Bayesian model is introduced, the speed prediction model can be further corrected according to actual operation data, and the speed prediction model trained by simulation data can output an accurate speed optimization result in a simulation space, so that the speed prediction model can output an accurate speed optimization result in an actual scene through a small amount of training and correction even under the condition of a small amount of actual operation data samples.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flowchart illustrating steps of a ship speed processing method based on virtual-real mapping according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a system to which a ship speed processing method based on virtual-real mapping according to an embodiment of the present application is applied;
fig. 3 is a schematic flowchart illustrating another step of a ship speed processing method based on virtual-real mapping according to an embodiment of the present application;
fig. 4 is a schematic flowchart illustrating another step of a ship speed processing method based on virtual-real mapping according to an embodiment of the present application;
fig. 5 is a schematic flowchart illustrating another step of a ship speed processing method based on virtual-real mapping according to an embodiment of the present application;
fig. 6 is a schematic flowchart illustrating another step of a ship speed processing method based on virtual-real mapping according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a ship speed processing method based on virtual-real mapping according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of a ship speed processing method based on virtual-real mapping according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of a ship speed processing device based on virtual-real mapping according to an embodiment of the present application.
Icon: 201-a data acquisition module; 2011-anemorumbometer; 2012-AIS; 2013-LOG; 2014-GPS; 2015-probe; 2016-main shaft power meter; 2017-power station PMS; 2018-a boiler system; 2019-a level measurement system; 20110-flow meter; 202-a navigational speed intelligent optimization module; 2021-twin data generation module; 2022-multidimensional digital twin simulation model; 2023-speed prediction model; 2024-bayes model; 203-data transmission module; 2031 — field bus; 2032-industrial ethernet; 501, a processor; 502-memory.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. 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 application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present application, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. are used for indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings or the orientation or positional relationship which the present invention product is usually put into use, it is only for convenience of describing the present application and simplifying the description, but it is not intended to indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and be operated, and thus, should not be construed as limiting the present application.
It should be noted that the features of the embodiments of the present application may be combined with each other without conflict.
At present, the ship speed optimization method is mainly based on the technologies of an expert system, experience guidance, a fuzzy theory, a neural network model and the like. However, the prior art can not solve the problem that the accuracy of the ship speed optimization result is not enough due to insufficient sample size of ship navigation data, complex ship working conditions and more parameters.
Based on the above, through research, the applicant provides a ship speed processing method, a ship speed processing device, a ship speed processing equipment and a ship speed processing system based on virtual-real mapping, a simulation data set is constructed by using a digital twin simulation model, the problem of insufficient training degree of a neural network model due to too few data samples is solved, and the neural network model is corrected again by using actually-operated data and a Bayesian model to obtain an accurate speed optimization result.
The digital twin simulation is used for establishing a virtual model for physical equipment in the real world and copying the working condition of the physical equipment. The virtual model established by the digital twin is connected with the actual operation data of the physical equipment, and the operation result of the physical equipment under the performance level is simulated through the virtual model on the premise of not causing loss to the physical equipment. The virtual model in the digital twin simulation can not only be output in a simulation mode according to actual running data, but also can be used for carrying out virtual tests on different working conditions according to the constructed working parameters.
The ship speed processing method, device and processing equipment based on virtual-real mapping provided by the embodiments of the present application are explained below with reference to a plurality of specific application examples.
Fig. 1 is a schematic flowchart of steps of a ship speed processing method based on virtual-real mapping according to an embodiment of the present application, where an execution subject of the method may be a ship speed processing device with computing processing capability, and the processing device may be a processing device built in a ship, or the processing device may also be a remote device, such as a cloud server. As shown in fig. 1, the method includes:
and step S101, acquiring real-time working parameter information of the ship.
The real-time working parameter information of the ship can represent real-time working parameter information acquired on the ship needing the speed prediction in actual use.
Step S102, inputting real-time working parameter information of the ship into a navigational speed prediction model to obtain target navigational speed information, wherein the navigational speed prediction model is obtained through training based on a training sample set, the training sample set is constructed based on a simulation data set output by a multi-dimensional digital twin simulation model, and the multi-dimensional digital twin simulation model is used for outputting a simulation data set according to twin data of the ship.
Referring to fig. 2, a schematic structural diagram of a system applied to a ship speed processing method based on virtual-real mapping is shown, and the method relates to a data acquisition module 201 and a speed intelligent optimization module 202. The data acquisition module 201 may be a module built in a ship, and the navigational speed intelligent optimization module 202 is a module on the ship navigational speed processing device. The data acquisition module 201 and the cruise intelligent optimization module 202 may be located in the same physical device, or may be located in different physical devices. The data acquisition module 201 and the speed intelligent optimization module 202 can communicate in a wired or wireless mode. Optionally, the real-time operating parameter information of the ship may be acquired by the data acquisition module 201, where the data acquisition module 201 may include but is not limited to: an anemorumbometer 2011, an AIS (Automatic identification System) 2012, a LOG2013, a GPS (Global Positioning System) 2014, a probe 2015, a main shaft power meter 2016, a power station PMS (power production management System) 2017, a boiler System 2018, a liquid level measurement System 2019 and a flowmeter 20110. The real-time operating parameter information of the ship collected by the data collection module 201 may include: the anemorumbometer 2011 is used for acquiring wind speed and wind direction information on the ship; the AIS2012 is used for collecting navigation state information of the ship, such as course and course; the LOG2013 is used for acquiring the water mileage information of the ship; the GPS2014 is used for acquiring longitude and latitude information of the ship; the sounding instrument 2015 is used for acquiring depth information of a ship sailing water surface; the main engine shaft power meter 2016 is used for collecting main engine power and main engine rotating speed information of a ship; the power station PMS2017 is used for acquiring power information of a generator of a ship; the boiler system 2018 is used for acquiring boiler power information of the ship; the liquid level measuring system 2019 is used for collecting four-corner draft information of a ship; the flow meter 20110 is used for acquiring oil quantity information consumed by energy consumption equipment on the ship, and the energy consumption equipment can comprise a host, a generator and a boiler.
Optionally, when the ship speed processing method based on the virtual-real mapping provided in this embodiment of the present application is actually used, the real-time operating parameter information of the ship, which is acquired by the data acquisition module 201, is input to the speed prediction model 2023, so as to obtain target speed information, where the target speed information is used to indicate an optimal speed that can be achieved by the ship predicted by the speed prediction model 2023 under the condition of the current operating parameter information.
The process of acquiring the navigational speed prediction model will be described below, and with continued reference to fig. 2, the working parameter information of the ship acquired by the data acquisition module 201 is input into the twin data generation module 2021 of the navigational speed intelligent optimization module 202, which is configured to convert the input working parameter information of the ship into twin data, and the specific conversion process will be described in detail below. The obtained twin data is input into the multi-dimensional digital twin simulation model 2022, and the multi-dimensional digital twin simulation model 2022 is a virtual model constructed in the embodiment of the present application and used for simulating the navigation control state of the ship in an actual scene, and is used for outputting a simulation data set, that is, the simulated navigation speed of the ship in the simulation scene under the condition of the working parameter information of the ship according to the twin data generated by the twin data generating module 2021. And processing the simulation data set to obtain a training sample set, wherein the training sample set is used for training a navigational speed prediction model, and the trained navigational speed prediction model is used for predicting navigational speed according to the working parameter information of the ship collected in the actual scene.
It should be noted that, when the cruise prediction model 2023 is obtained, the working parameter information of the ship used for generating the twin data is not the same as the real-time working parameter information of the ship, the real-time working parameter information of the ship represents the real-time working parameter information acquired by the ship that needs to make the cruise prediction in actual use, and the working parameter information of the ship used for generating the twin data represents the summary of the working parameter information acquired by a plurality of ships, which have differences in quantity and source.
In the embodiment, the problem of excessive and complicated parameters can be effectively solved by using the neural network model method. Through the navigation speed prediction model based on the neural network model, a plurality of pieces of real-time working parameter information can be integrated to obtain more accurate target navigation speed information. In addition, the embodiment of the application also utilizes a multi-dimensional digital twin simulation model, a simulation data set is output according to twin data of the ship, and a training sample set is obtained according to the simulation data set and is used for training the navigational speed prediction model. The simulation data set can obtain corresponding navigational speed simulation results under different working conditions, data of a training sample set for training the navigational speed prediction model are expanded, dependence of accuracy of the navigational speed prediction model on data acquisition of the physical ship data is greatly reduced, the navigational speed prediction model is fully trained, and accuracy of output results is greatly improved.
Optionally, as shown in fig. 3, on the basis of the foregoing embodiment, the ship speed processing method based on virtual-real mapping provided in the embodiment of the present application may further include:
step S301, twin data of the ship are obtained and used for identifying the operation data of the ship and the relation among the operation data.
Wherein the twin data of the vessel is used to identify operational data of the vessel and a relationship between the operational data. It will be appreciated that twin data for a vessel may be data that identifies relationships between operational data for vessels of one or more of the same type, based on actual operational data collected by those vessels, as input data to the multi-dimensional digital twin simulation model in the embodiments described below.
After the working parameter information of the ship is acquired, twin data of the ship can be constructed accordingly, optionally, the twin data of the ship can be a multi-element expression, and the multi-element expression can include the following operation data of the ship: the system comprises a ship, a power system and a power system.
Optionally, the tuple expression may also be used to identify the degree of association between the above operation data, and is expressed in a numerical manner, and it is understood that some two operation data with the largest association value show a positive correlation between the two operation data and the influence of the two operation data on the speed of the ship.
It should be noted that the numerical value representing the degree of association may be determined manually by an expert with relevant professional experience knowledge according to engineering experience, an expert library, or may be calculated and obtained by comprehensive evaluation based on historical operating parameter information, which is not limited herein.
Step S302, twin data of the ship are input into a multi-dimensional digital twin simulation model to obtain a simulation data set.
Twin data generated according to the working parameter information of the ship in the step S301 is input into a multi-dimensional digital twin simulation model, and the optimal simulated navigational speed, the multiple groups of working parameter information, the incidence relation value among each group of working parameter information and the optimal simulated navigational speed corresponding to the multiple groups of working parameter information which can be achieved by the ship under the input working parameter information can be obtained through the corresponding state of the simulated ship under the actually acquired working parameter information, so that a simulation data set is formed together.
Step S303, labeling the simulation data set to obtain a training sample set.
The simulation data set comprises a plurality of groups of working parameter information, incidence relation values among each group of working parameter information and simulation optimal navigational speed corresponding to the plurality of groups of working parameter information. Labeling the simulation data set may be a process of setting a label on the simulation data set. And setting the plurality of groups of working parameter information and the incidence relation value between each group of working parameter information as input labels, and setting the simulation optimal navigational speed corresponding to the plurality of groups of working parameter information as verification labels.
It should be noted that the process of labeling the simulation data set may be completed in a manual labeling manner, or may be completed by an algorithm in which a labeling rule is preset, and the present application is not limited herein.
And step S304, training by using a training sample set to obtain a navigational speed prediction model.
And training a navigational speed prediction model by using the obtained training sample set, inputting the data with the input labels in the training sample set into the navigational speed prediction model by using the navigational speed prediction model, comparing the output result of the navigational speed prediction model with the data which are set as verification labels in the training sample set, and finishing the training of the navigational speed prediction model if the comparison result is less than a preset threshold value. After training, the navigational speed prediction model can output the optimal navigational speed of the ship under the simulation condition of the working parameters of the ship in the multi-dimensional digital twin simulation model according to the working parameters of the ship. The specific training process of the cruise prediction model will be described in detail in the following embodiments.
In the embodiment, the optimal navigational speed which can be achieved by twin data of the ship under the simulation condition of the multi-dimensional digital twin simulation model is simulated, multiple groups of data can be obtained under the condition of not being influenced by the physical acquisition condition of the ship, and the data quantity required by the navigational speed prediction model is met. The purposes of simplifying the navigation sample data acquisition process, expanding the training sample set and further fully training the navigation speed prediction model are achieved.
Alternatively, as shown in fig. 4, the multi-dimensional digital twin simulation model in step S302 may be constructed by:
and step S401, constructing an initial twin simulation model.
The construction of the initial twin simulation model is a theoretical model for simulating ship navigation control, which is built from a ship body three-dimensional design, hydromechanics and meteorological models.
And S402, correcting the initial twin simulation model according to historical operation data of the ship and an actual simulation result output by the initial twin simulation model.
Wherein the historical operating state data comprises: the working parameter information of a plurality of groups of ships and the corresponding actual navigational speed. And inputting the working parameter information of historical running state data acquired by a plurality of ships into the initial twin simulation model, comparing the obtained actual simulation result, namely the simulation navigational speed, with the actual navigational speed corresponding to the group of working parameter information, and if the difference value of the two is greater than a preset threshold value, adjusting the parameter weight of the model of the initial twin simulation model to enable the actual simulation result output by the adjusted initial twin simulation model to be closer to the actual navigational speed than the actual simulation result before adjustment.
It should be noted that, if the difference between the actual simulation result and the actual navigational speed is always greater than the preset threshold, the process of adjusting the parameter weight of the model of the initial twin simulation model will be continued until the difference is smaller than the preset threshold, and the next step will be performed.
And step S403, if the corrected initial twin simulation model meets the preset conditions, taking the corrected initial twin simulation model as a multi-dimensional digital twin simulation model.
After the adjustment in step S402, the initial twin simulation model is adjusted perfectly to become the multi-dimensional digital twin simulation model when the difference between the actual simulation result output by the initial twin simulation model and the actual navigational speed is smaller than the preset threshold.
In the embodiment, the historical data of the ship is used for correcting the initial twin simulation model, so that the initial twin simulation model established on the theoretical basis has actual data as support, the finally obtained multi-dimensional digital twin simulation model is closer to the actual situation, and the accuracy of the simulation data is ensured.
Optionally, as shown in fig. 5, the acquiring twin data of the ship in step S301 includes the following steps:
and step S3011, preprocessing the real-time operation data of the ship to obtain real-time operation data with unified dimension.
The real-time operation data of the ship represents a plurality of pieces of working parameter information acquired when the ship operates, and the working parameter information comprises: the method comprises the following steps of obtaining wind speed and wind direction information on a ship, sailing state information, water mileage information of the ship, longitude and latitude information of the ship, depth information of a sailing water surface of the ship, host power and host rotating speed information of the ship, power information of a generator of the ship, boiler power information of the ship, draught information of four corners of the ship and oil consumption information of energy consumption equipment on the ship. The real-time operation data of these vessels do not have a uniform dimension, for example, the wind speed and wind direction information of a vessel is in m/s (meters per second), and the oil consumption information of the energy consumption equipment on the vessel is in L (liters).
The data preprocessing refers to a process of unifying dimensions of the real-time operation data of the ship and converting the real-time operation data of the ship into unified specifications. The dimension unifying method can comprise the following steps: the normalization method is not limited herein, and may be a normal distribution normalization method, an interval scaling method using characteristic value interval boundaries, or a normalization method for processing data in a row according to a characteristic matrix.
And S3012, performing feature selection on the real-time operation data with unified dimensions to obtain a target feature vector, wherein the target feature vector is used for representing the operation data related to the navigational speed and the relationship between the operation data.
Optionally, the real-time operation data with unified dimensions includes a plurality of pieces of working parameter information capable of affecting the speed of the ship, in this step, the real-time operation data with unified dimensions may be processed, the working parameter information capable of affecting the speed of the ship is selected as the target feature vector, and the plurality of pieces of working parameter information having a correlation with each other may also be used as the target feature vector, which is not limited herein.
The method for processing the real-time operation data with unified dimensions may include: a variance selection method and a correlation coefficient method, which are not limited herein.
And step S3013, performing dimension compression on the target characteristic vector to obtain twin data.
After the real-time operation data with unified dimensions are processed through the feature selection in the step S3012, the obtained target feature vector data volume is too large, which easily causes too large model calculation amount and too long training period, so the twin data for training the multidimensional digital twin simulation model can be obtained only by reducing the data dimension of the target feature vector, and this process of reducing the data dimension is dimension compression.
The dimension compression method can comprise the following steps: PCA (Principal Component Analysis), regularization, and the present application is not limited thereto.
In this embodiment, twin data is obtained by performing dimension unification, feature selection, and dimension compression processing on actual operation data of a ship. The well-processed twin data can avoid the problem of network non-convergence caused by the fact that the dimension of actual operation data of the ship is not uniform, and can also avoid errors caused by different orders of magnitude of input numerical values.
Alternatively, as shown in fig. 6, the process of training the cruise prediction model using the training sample set in step S304 may be obtained by:
step S3041, a bayesian model is generated by training according to the training sample set.
Alternatively, the bayesian model may be generated by training using the training sample set obtained in step S303, and it should be noted that the bayesian model generated in this step is updated in the following steps.
Step S3042, updating the bayesian model according to the bayesian model and the actual operation data to obtain an updated bayesian model.
The Bayesian network is a model based on a directed acyclic graph and is used for describing numerical dependency relationships among attributes. And when the Bayesian model is updated, the actual operation data is used as input training data to further train the Bayesian network, and the updated Bayesian network is obtained after the training is completed.
Step S3043, an updated training sample set is obtained according to the updated bayesian model and the training sample set.
And comparing the working parameter information contained in the training sample set and the incidence relation value between the working parameter information with the numerical dependence relation between the working parameter information described by the updated Bayesian model, and replacing the incidence relation value between the working parameter information with the numerical dependence relation between the working parameter information in the Bayesian network to complete the updating of the training sample set.
Step S3044, the speed prediction model is corrected according to the updated training sample set, so as to obtain an updated speed prediction model.
And (4) training the navigational speed prediction model again by using the updated training sample set, and updating the parameters of the navigational speed prediction model to obtain the updated navigational speed prediction model.
It should be noted that, as shown in fig. 7, the process from the step S3042 to the step S3044 is repeated for a plurality of cycles until the error between the training sample set updated by the bayesian model 2023 in the step S3043 and the actual operation data is smaller than the preset threshold, and the error between the cruise prediction result output by the cruise prediction model 2023 in the step S3044 and the actual cruise in the training sample set is smaller than the preset threshold.
In this embodiment, a bayesian model is introduced, and the cruise prediction model is further modified by using actual operation data. Because the navigation speed prediction model trained by the simulation data can output an accurate navigation speed optimization result in the simulation space, the navigation speed prediction model can output an accurate navigation speed optimization result in an actual scene through a small amount of training and correction even under the condition that the actual operation data sample size is small. Therefore, the Bayesian model improves the goodness of fit between the navigational speed optimization result and the actual operation data, overcomes the problem of incomplete navigational speed prediction model training caused by small samples, and improves the prediction accuracy.
Optionally, the real-time operation data of the ship in the step S3042 may include: ship navigation state, ship running state, and empirical data obtained according to historical navigation information.
The ship navigation state data may be a working parameter describing a surrounding environment state when the ship navigates, and may include: the navigation method comprises the following steps of obtaining wind speed and wind direction information on a ship, and navigation state information, such as course and course, water mileage information of the ship, longitude and latitude information of the ship, depth information of a navigation water surface of the ship, and four-corner draft information of the ship.
The ship operation state information may be an operation parameter describing an operation state of equipment on the ship, and may include: the method comprises the following steps of obtaining power information of a ship main engine, power information of a ship generator, boiler power information of the ship and oil consumption information of energy consumption equipment on the ship.
The empirical data obtained according to the historical navigation information can be navigation experiences of a fleet or a crew, or historical operation tracks recorded by a navigation log, and the obtained navigation speed preset empirical value can be obtained.
The data may be stored in a database.
As an optional implementation, the method further includes: and updating the navigational speed prediction model according to the acquired real-time working parameter information of the ship.
It is understood that due to the problem of data imbalance, the navigation speed prediction model obtained after the training may not be able to obtain an accurate navigation speed prediction result under all conditions. Therefore, in this embodiment, the process from step S301 to step S304 is repeated according to the real-time operating parameter information of the new ship collected when the ship runs, and the cruise prediction model is updated again.
In the embodiment, the trained samples are updated again by using the continuously acquired real-time working parameter information of the ship, so that the data volume of the navigational speed prediction model is further ensured, and the accuracy of the navigational speed prediction model is further improved.
Optionally, as shown in fig. 8, the method may further include: a data transmission module 203 comprising: a field bus 2031 and an industrial ethernet 2032.
The field bus 2031 is used for data interaction with the data acquisition module 201, and transmits real-time operation data of the ship acquired by the data acquisition module 201 to a database through a standard transmission protocol, or may directly transmit the data to the industrial ethernet 2032. The database may be: MySQL, SQLServer. The transport protocols may include, but are not limited to: modbus protocol, Profibus-DP (Decentralized peripheral) protocol, CAN protocol, and S7 protocol, which are not limited herein.
The industrial ethernet 2032 transmits the data transmitted through the fieldbus 2031 or the data in the database to the cruise intelligent optimization module 202 through an industrial ethernet protocol. Industrial ethernet protocols include, but are not limited to: TCP/IP (Transmission Control Protocol/Internet Protocol ).
This embodiment still provides a boats and ships navigational speed processing apparatus based on virtual reality mapping, is applied to boats and ships navigational speed processing equipment, and the device includes:
and the acquisition module is used for acquiring the real-time working parameter information of the ship.
The processing module is used for inputting the real-time working parameter information of the ship into the navigational speed prediction model to obtain target navigational speed information, the navigational speed prediction model is obtained through training based on a training sample set, the training sample set is constructed based on a simulation data set output by the multi-dimensional digital twin simulation model, and the multi-dimensional digital twin simulation model is used for outputting a simulation data set according to twin data of the ship.
As an optional implementation manner, the processing module is specifically configured to:
acquiring twin data of the ship, wherein the twin data of the ship are used for identifying the operation data of the ship and the relation among the operation data;
inputting twin data of a ship into a multi-dimensional digital twin simulation model to obtain a simulation data set;
labeling the simulation data set to obtain a training sample set;
and training by using a training sample set to obtain a navigational speed prediction model.
As an optional implementation manner, the processing module is specifically further configured to:
constructing an initial twin simulation model;
correcting the initial twin simulation model according to historical operation data of the ship and an actual simulation result output by the initial twin simulation model;
and if the corrected initial twin simulation model meets the preset conditions, taking the corrected initial twin simulation model as a multi-dimensional digital twin simulation model.
As an optional implementation manner, the processing module is specifically further configured to:
training according to the training sample set to generate a Bayesian model;
updating the Bayesian model according to the Bayesian model and the actual operation data to obtain an updated Bayesian model;
obtaining an updated training sample set according to the updated Bayesian model and the training sample set;
and correcting the speed prediction model according to the updated training sample set to obtain an updated speed prediction model.
As an optional implementation manner, the processing module is specifically further configured to:
preprocessing the real-time operation data of the ship to obtain real-time operation data with unified dimensions;
carrying out feature selection on real-time operation data with unified dimensions to obtain a target feature vector, wherein the target feature vector is used for representing the operation data related to the navigational speed and the relationship between the operation data;
and performing dimension compression on the target characteristic vector to obtain twin data.
Wherein, the real-time operation data of boats and ships includes:
ship navigation state, ship running state, and empirical data obtained according to historical navigation information.
As an optional implementation manner, the processing module is specifically further configured to:
and updating the navigational speed prediction model according to the acquired real-time working parameter information of the ship.
As an optional implementation, the apparatus further comprises:
and the data transmission module is used for transmitting the real-time running data of the ship acquired by the data acquisition module to the navigational speed intelligent optimization module.
This embodiment also provides a ship speed processing device based on virtual-real mapping, as shown in fig. 9, the processing device includes: the processor 501, a storage medium and a bus, the storage medium stores machine-readable instructions executable by the processor 501, when the electronic device runs, the processor 501 communicates with the storage medium through the bus, and the processor 501 executes the machine-readable instructions to execute the steps of the ship speed processing method based on the virtual-real mapping in the foregoing embodiments.
The memory 502, processor 501 and bus elements are electrically connected to each other, directly or indirectly, to enable data transfer or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The ship speed processing device comprises at least one software functional module which can be stored in a memory 502 in the form of software or firmware (firmware) or solidified in an Operating System (OS) of a computer device. The processor 501 is used for executing executable modules stored in the memory 502, such as software functional modules and computer programs included in the ship speed processing device.
The Memory 502 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
Optionally, the present application further provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program performs the steps of the above method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. 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 U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application.
Claims (10)
1. A ship speed processing method based on virtual-real mapping is characterized by comprising the following steps:
acquiring real-time working parameter information of a ship;
inputting the real-time working parameter information of the ship into a navigational speed prediction model to obtain target navigational speed information, wherein the navigational speed prediction model is obtained through training based on a training sample set, the training sample set is constructed based on a simulation data set output by a multi-dimensional digital twin simulation model, and the multi-dimensional digital twin simulation model is used for outputting the simulation data set according to twin data of the ship.
2. The virtual-real mapping-based ship speed processing method according to claim 1, further comprising:
acquiring twin data of the ship, wherein the twin data of the ship is used for identifying operation data of the ship and a relation between the operation data;
inputting the twin data of the ship into the multi-dimensional digital twin simulation model to obtain the simulation data set;
labeling the simulation data set to obtain the training sample set;
and training by using the training sample set to obtain the navigational speed prediction model.
3. The virtual-real mapping-based ship speed processing method according to claim 2, wherein the method further comprises:
constructing an initial twin simulation model;
correcting the initial twin simulation model according to historical operation data of a ship and an actual simulation result output by the initial twin simulation model;
and if the corrected initial twin simulation model meets the preset conditions, taking the corrected initial twin simulation model as the multi-dimensional digital twin simulation model.
4. The method for processing the ship speed based on the virtual-real mapping of claim 2, wherein the training with the training sample set to obtain the speed prediction model comprises:
training according to the training sample set to generate a Bayesian model;
updating the Bayesian model according to the Bayesian model and the actual operation data to obtain an updated Bayesian model;
obtaining an updated training sample set according to the updated Bayesian model and the training sample set;
and correcting the navigation speed prediction model according to the updated training sample set to obtain the updated navigation speed prediction model.
5. The virtual-real mapping-based ship speed processing method according to claim 2, wherein the obtaining the twin data of the ship comprises:
preprocessing the real-time operation data of the ship to obtain real-time operation data with unified dimensions;
performing feature selection on the real-time operation data with unified dimensions to obtain a target feature vector, wherein the target feature vector is used for representing the operation data related to the navigational speed and the relationship between the operation data;
and performing dimensionality compression on the target characteristic vector to obtain the twin data.
6. The virtual-real mapping-based ship speed processing method according to claim 5, wherein the real-time operation data of the ship comprises:
ship navigation state, ship running state, and empirical data obtained according to historical navigation information.
7. The virtual-real mapping-based ship speed processing method according to claims 1-6, characterized in that the method further comprises:
and updating the navigational speed prediction model according to the acquired real-time working parameter information of the ship.
8. A ship speed processing device based on virtual-real mapping is applied to a ship speed processing device, and the device comprises:
the acquisition module is used for acquiring real-time working parameter information of the ship;
the processing module is used for inputting the real-time working parameter information of the ship into a navigational speed prediction model to obtain target navigational speed information, the navigational speed prediction model is obtained through training based on a training sample set, the training sample set is constructed based on a simulation data set output by a multi-dimensional digital twin simulation model, and the multi-dimensional digital twin simulation model is used for outputting the simulation data set according to twin data of the ship.
9. A ship speed processing device based on virtual-real mapping is characterized by comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when the electronic device is operated, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to execute the steps of the ship speed processing method based on the virtual-real mapping according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111241412.0A CN113886973B (en) | 2021-10-25 | 2021-10-25 | Ship navigational speed processing method, device and processing equipment based on virtual-real mapping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111241412.0A CN113886973B (en) | 2021-10-25 | 2021-10-25 | Ship navigational speed processing method, device and processing equipment based on virtual-real mapping |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113886973A true CN113886973A (en) | 2022-01-04 |
| CN113886973B CN113886973B (en) | 2023-04-18 |
Family
ID=79013938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111241412.0A Active CN113886973B (en) | 2021-10-25 | 2021-10-25 | Ship navigational speed processing method, device and processing equipment based on virtual-real mapping |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113886973B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114493049A (en) * | 2022-04-07 | 2022-05-13 | 卡奥斯工业智能研究院(青岛)有限公司 | Production line optimization method and device based on digital twin, electronic equipment and medium |
| CN114655412A (en) * | 2022-03-16 | 2022-06-24 | 武汉理工大学 | Hybrid ship torque distribution method, system, device and storage medium |
| CN114707428A (en) * | 2022-06-01 | 2022-07-05 | 中科航迈数控软件(深圳)有限公司 | Method, device, terminal and storage medium for simulating unobservable links of numerical control machine tool |
| CN114784701A (en) * | 2022-04-21 | 2022-07-22 | 中国电力科学研究院有限公司 | Power distribution network live working autonomous navigation method, system, equipment and storage medium |
| CN115205706A (en) * | 2022-08-17 | 2022-10-18 | 数字太空(北京)科技股份公司 | Remote sensing data acquisition method and device, electronic equipment and computer readable medium |
| CN116108717A (en) * | 2023-01-17 | 2023-05-12 | 中山大学 | Traffic transportation equipment operation prediction method and device based on digital twin |
| CN116186907A (en) * | 2023-05-04 | 2023-05-30 | 中国人民解放军海军工程大学 | Method, system and medium for analyzing navigable state based on state of marine subsystem |
| CN116911048A (en) * | 2023-07-27 | 2023-10-20 | 中国舰船研究设计中心 | Digital twin model construction method for large ship mission system |
| CN117805877A (en) * | 2024-03-01 | 2024-04-02 | 北京智汇空间科技有限公司 | Marine positioning method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960421A (en) * | 2018-06-05 | 2018-12-07 | 哈尔滨工程大学 | The unmanned surface vehicle speed of a ship or plane online forecasting method based on BP neural network of improvement |
| CN112700072A (en) * | 2021-03-24 | 2021-04-23 | 同盾控股有限公司 | Traffic condition prediction method, electronic device, and storage medium |
| CN112906775A (en) * | 2021-02-05 | 2021-06-04 | 深圳市芯聚智科技有限公司 | Equipment fault prediction method and system |
| CN113221277A (en) * | 2021-05-14 | 2021-08-06 | 西安交通大学 | Bearing performance degradation evaluation method and system based on digital twin model |
| CN113379123A (en) * | 2021-06-09 | 2021-09-10 | 中德（珠海）人工智能研究院有限公司 | Fault prediction method, device, server and storage medium based on digital twin |
-
2021
- 2021-10-25 CN CN202111241412.0A patent/CN113886973B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960421A (en) * | 2018-06-05 | 2018-12-07 | 哈尔滨工程大学 | The unmanned surface vehicle speed of a ship or plane online forecasting method based on BP neural network of improvement |
| CN112906775A (en) * | 2021-02-05 | 2021-06-04 | 深圳市芯聚智科技有限公司 | Equipment fault prediction method and system |
| CN112700072A (en) * | 2021-03-24 | 2021-04-23 | 同盾控股有限公司 | Traffic condition prediction method, electronic device, and storage medium |
| CN113221277A (en) * | 2021-05-14 | 2021-08-06 | 西安交通大学 | Bearing performance degradation evaluation method and system based on digital twin model |
| CN113379123A (en) * | 2021-06-09 | 2021-09-10 | 中德（珠海）人工智能研究院有限公司 | Fault prediction method, device, server and storage medium based on digital twin |
Non-Patent Citations (1)
| Title |
|---|
| 李庆东: "舰船航行速度预测的非线性数学模型研究", 《舰船科学技术》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114655412A (en) * | 2022-03-16 | 2022-06-24 | 武汉理工大学 | Hybrid ship torque distribution method, system, device and storage medium |
| CN114493049A (en) * | 2022-04-07 | 2022-05-13 | 卡奥斯工业智能研究院(青岛)有限公司 | Production line optimization method and device based on digital twin, electronic equipment and medium |
| CN114784701B (en) * | 2022-04-21 | 2023-07-25 | 中国电力科学研究院有限公司 | Autonomous navigation method, system, equipment and storage medium for live working of power distribution network |
| CN114784701A (en) * | 2022-04-21 | 2022-07-22 | 中国电力科学研究院有限公司 | Power distribution network live working autonomous navigation method, system, equipment and storage medium |
| CN114707428A (en) * | 2022-06-01 | 2022-07-05 | 中科航迈数控软件(深圳)有限公司 | Method, device, terminal and storage medium for simulating unobservable links of numerical control machine tool |
| CN115205706A (en) * | 2022-08-17 | 2022-10-18 | 数字太空(北京)科技股份公司 | Remote sensing data acquisition method and device, electronic equipment and computer readable medium |
| CN116108717B (en) * | 2023-01-17 | 2023-09-26 | 中山大学 | Traffic transportation equipment operation prediction method and device based on digital twin |
| CN116108717A (en) * | 2023-01-17 | 2023-05-12 | 中山大学 | Traffic transportation equipment operation prediction method and device based on digital twin |
| CN116186907A (en) * | 2023-05-04 | 2023-05-30 | 中国人民解放军海军工程大学 | Method, system and medium for analyzing navigable state based on state of marine subsystem |
| CN116186907B (en) * | 2023-05-04 | 2023-09-15 | 中国人民解放军海军工程大学 | Method, system and medium for analyzing navigable state based on state of marine subsystem |
| CN116911048A (en) * | 2023-07-27 | 2023-10-20 | 中国舰船研究设计中心 | Digital twin model construction method for large ship mission system |
| CN116911048B (en) * | 2023-07-27 | 2024-03-22 | 中国舰船研究设计中心 | Digital twin model construction method for large ship mission system |
| CN117805877A (en) * | 2024-03-01 | 2024-04-02 | 北京智汇空间科技有限公司 | Marine positioning method and device, electronic equipment and storage medium |
| CN117805877B (en) * | 2024-03-01 | 2024-05-17 | 北京智汇空间科技有限公司 | Marine positioning method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113886973B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113886973B (en) | Ship navigational speed processing method, device and processing equipment based on virtual-real mapping | |
| CN105868853B (en) | Method for predicting short-term wind power combination probability | |
| GB2449560A (en) | Method for real-time identification of vessel performance | |
| CN109840671B (en) | Operation improvement effect calculation device, operation improvement effect calculation method, and recording medium | |
| US5126978A (en) | Undersea data collection, analysis, and display system | |
| CN101436057A (en) | Numerical control machining tool heat error Bayes network compensation method | |
| Shaw et al. | Marine big data analysis of ships for the energy efficiency changes of the hull and maintenance evaluation based on the ISO 19030 standard | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN111626359A (en) | Data fusion method and device, control terminal and ship | |
| CN116643517A (en) | Accident prevention equipment for underwater manned submersible vehicle | |
| CN118226553B (en) | Intelligent marine environment monitoring and forecasting platform and method thereof | |
| CN111611731A (en) | Satellite data fusion method and device and electronic equipment | |
| US20220307944A1 (en) | Apparatus, method, and computer-readable medium | |
| CN117253344B (en) | Seawater acidification early warning and forecasting method, system and electronic equipment | |
| US20230314144A1 (en) | System and method for estimating drift path of marine floating body | |
| Ma et al. | A fault prediction framework for Doubly‐fed induction generator under time‐varying operating conditions driven by digital twin | |
| JP2023051248A (en) | Performance evaluation method, performance evaluation program, performance evaluation system by actual monitoring analysis of vessel | |
| CN114047508A (en) | Sea radar detection range statistical evaluation method and system | |
| CN114693002B (en) | Tide level prediction method, device, electronic equipment and computer storage medium | |
| Yang et al. | Data resolution improvement for ocean of things based on improved FCM | |
| Melinc et al. | 3D‐Var data assimilation using a variational autoencoder | |
| CN114018773B (en) | PM 2.5 Method, device and equipment for acquiring concentration spatial distribution data and storage medium | |
| CN118332318B (en) | Fan gear box bearing fault positioning method, device, medium and equipment | |
| RU2796370C1 (en) | System and method for dynamic visualization of environmental pollution | |
| CN118245784B (en) | Ocean temperature and salt depth sensor data calibration method, medium and system |
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 |