CN117818850A - Performance evaluation and auxiliary decision making system and method for ship real sea navigation - Google Patents
Performance evaluation and auxiliary decision making system and method for ship real sea navigation Download PDFInfo
- Publication number
- CN117818850A CN117818850A CN202410245683.0A CN202410245683A CN117818850A CN 117818850 A CN117818850 A CN 117818850A CN 202410245683 A CN202410245683 A CN 202410245683A CN 117818850 A CN117818850 A CN 117818850A
- Authority
- CN
- China
- Prior art keywords
- ship
- wave
- sea
- navigation
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 146
- 238000011156 evaluation Methods 0.000 title claims abstract description 54
- 238000001228 spectrum Methods 0.000 claims abstract description 54
- 230000033001 locomotion Effects 0.000 claims abstract description 50
- 230000004044 response Effects 0.000 claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000013136 deep learning model Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 31
- 238000011176 pooling Methods 0.000 claims description 25
- 238000004088 simulation Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 18
- 238000013210 evaluation model Methods 0.000 claims description 17
- 230000014509 gene expression Effects 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000001788 irregular Effects 0.000 claims description 10
- 230000003595 spectral effect Effects 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 238000013459 approach Methods 0.000 claims description 6
- 230000010355 oscillation Effects 0.000 claims description 6
- 238000005316 response function Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000013277 forecasting method Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010183 spectrum analysis Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims 3
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000013527 convolutional neural network Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 11
- 238000009826 distribution Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 7
- 238000012952 Resampling Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013341 scale-up Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000001970 hydrokinetic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Navigation (AREA)
Abstract
The invention belongs to the field of marine environment prediction technology and ship motion response calculation, and discloses a ship real sea navigation-oriented performance evaluation and auxiliary decision-making system and method. According to the method, sea wave data calculated in a numerical mode are utilized, statistical values, wave spectrums and other information of regional sea waves are predicted by utilizing a deep learning model, and a ship real sea area swaying motion calculation method is constructed by combining ship sailing performance, so that real sea area environment prediction and ship navigability assessment are realized. The invention can provide more accurate and timely marine environment data and ship swaying performance evaluation data for the navigation of the ship, provides more applicable decision information for the navigation of the ship, and ensures the safety of the navigation of the ship in the real sea area.
Description
Technical Field
The invention belongs to the field of marine environment prediction technology and ship motion response calculation, and particularly relates to a performance evaluation and auxiliary decision-making system and method for ship real sea navigation.
Background
When the ship is on duty at sea, although the weather forecast numerical products provide the hydrological weather forecast numerical products such as wind fields, waves and the like, the hydrological weather information of the sea area near the route can be provided for ship operating personnel, but the specific evaluation result of the swaying of the ship in the wind and wave environment can not be obtained, so the sailing of the ship depends on judgment of the captain and the like. However, when the marine environment with poor sea condition and low visibility is encountered, the marine environment is evaluated empirically, which may lead to errors in ship navigation decisions, threaten the safety of ship navigation and generate unnecessary energy consumption. Therefore, the method has important significance in evaluating the navigability of the navigation ship in the real sea area by rapidly forecasting the ocean environment in the real sea area and combining the ship motion response.
Based on the background of the marine navigation operation of the ship and the actual requirements of the safe navigation of the ship, the invention provides a performance evaluation and auxiliary decision-making system for the real sea navigation of the ship. Firstly, quick prediction of the marine environment is realized based on machine learning, then a ship sway performance evaluation model is developed based on real sea area wind wave environment prediction data, direct and accurate auxiliary judgment information is provided for ship and sea navigation planning, and technical means are provided for guaranteeing safe navigation of ships in real sea areas and executing tasks at sea.
Currently, research is available that acquires real-time weather data or hydrological weather forecast data through a shore base, and further evaluates risk levels of various sea areas on a route through ship performance parameters or a ship motion response library.
Through the above analysis, the problems and defects existing in the prior art are as follows: in the current ship seaworthiness evaluation research, related researches of acquiring real sea area environment data through a shore base or an weather table and evaluating the sway of a ship exist, but most of environment data used in forecasting are open source data, certain hysteresis exists in information, and the ship cannot acquire marine environment data timely and accurately in the sailing process, so that the sway evaluation is not timely and inaccurate and other problems are caused.
Disclosure of Invention
In order to overcome the problems in the related art, the embodiment of the invention provides a performance evaluation and auxiliary decision making system and method for ship real sea navigation. And more particularly to a method of assessing vessel motion from forecasted marine environmental data.
The technical scheme is as follows: the performance evaluation and auxiliary decision making method for the ship real sea navigation comprises the following steps:
s1, forecasting regional sea waves: calculating the wave environment of a typical sea area by using a SWAN wave model, and constructing a data set based on wave data obtained by calculation; establishing an intelligent sea wave forecasting model based on a CNN model, and verifying the accuracy of the intelligent sea wave forecasting model by using MAE and MAPE evaluation indexes to finish forecasting of regional sea waves;
s2, constructing a marine wave-resistant water power library: the ship wave resistance is verified and compared by using a slicing method and a two-dimensional semi-theory, and ship amplitude response prediction is completed; based on the amplitude response database of the small navigational speed interval, obtaining the amplitude response of ship navigation by using an interpolation method;
s3, ship sailing performance evaluation: and (3) combining regional sea wave simulation with ship wave resistance calculation by using a ship motion statistical forecasting method in irregular waves, constructing a real sea area ship rocking performance evaluation model, and verifying the feasibility of the real sea area ship rocking performance evaluation model by using the data of the real ship motion.
In step S1, the calculating the sea wave environment of the typical sea area using the SWAN sea wave model includes: and obtaining target sea area wind field information and terrain information through the disclosed environment data set, and setting configuration parameters for SWAN mode operation to operate the SWAN mode, wherein the configuration parameters comprise simulation time, simulation range and simulation resolution information.
In step S1, the intelligent sea wave forecasting model is input into the calculated domain wind field data and past wave data, and is output into the calculated domain current wave data; the CNN performs filtering operation by using a convolution kernel to check an input matrix, wherein the filtering operation is to multiply and then add the convolution kernel and the input data, and the expression is as follows:
；
in the method, in the process of the invention,for the feature map of the current layer, +.>To activate the function +.>For the set of feature maps, +.>Mapping for the features of the upper layer, +.>Is->Layer->Weights corresponding to convolution filters of the positions, < +.>Is biased;
the input data is；
The CNN performs downsampling on the input matrix by utilizing the pooling check, and filters out the salient feature information of each part of the input matrix; pooling with maximum poolingMean pooling->Maximum value pooling is to extract the maximum value of the pooled check corresponding position matrix, and levelThe average value is the extracted average value, and the expressions are respectively:
；
；
in the method, in the process of the invention,for the number after mean pooling, +.>For the maximum pooled number, +.>Local matrix acting as pooling nucleus, +.>The number of digits of the local matrix that is active is the number of elements in the local matrix.
In step S1, the calculation formulas of the MAE and MAPE evaluation indexes are as follows:
；
；
in the method, in the process of the invention,for the number of samples->Is true value +.>For predictive value +.>Mean absolute error, +.>Is the average relative error.
In step S2, the marine vessel seakeeping hydrokinetic energy reservoir construction comprises: modeling the ship body through known model values and molded line data based on Catia modeling software, and smoothing the curved surface of the ship body according to a horizontal sectional line drawing and a longitudinal sectional line drawing of the ship body;
slicing and dividing the curved surface of the ship body based on UG software, and uniformly distributing points by cutting out contour lines of the ship body at slicing positions to obtain half width and draft values of all slicing points;
based on the constructed ship type data file and the working condition configured by the user, dividing the speed according to the Froude number, and calculating to obtain ship motion response by adopting a slicing method during low-speed navigation and a two-dimensional semi-method during high-speed navigation to form a ship hydrodynamic motion response database under different heading and navigation speeds.
In step S2, the interpolation method includes: the amplitude response of the similar navigational speed in the navigational speed searching database of the known navigational route ships is calculated by utilizing an interpolation formula, and the expression is as follows:
；
in the method, in the process of the invention,the unit is m/s for the ship speed on the route; />For the approach ∈in the database>Is given in m/s; />For the approach ∈in the database>Higher speeds in m/s; />For the ship amplitude response on the course, +.>For +.>Amplitude response at speed, +.>For +.>Amplitude response at voyage speed.
In step S3, the constructing a real sea area ship sway performance evaluation model includes: based on regional wind and wave data obtained by the deep learning model, ITTC double-parameter spectrum calculation is carried out, and the sea wave spectrum is fitted, wherein the expression is as follows:
；
；
；
in the method, in the process of the invention,for the characteristic period of waves, < > j->If the wave characteristic period data is lacking, taking the average period +.>I.e. +.>，/>Is sense wave height +.>As a function of spectral density>For parameters determined by sense wave height and wave period +.>For wave frequency +.>Is a parameter determined by the wave period.
Further, the formula of the ITTC dual-parameter spectrum calculation is as follows:
；
in the method, in the process of the invention,for the first moment of the sea wave spectrum to the origin, < >>The differentiation of the frequency gives:
；
；
；
；
；
after substitution, obtaining a double-parameter ocean wave spectrum:
；
in the method, in the process of the invention,the unit is m, which is the sense wave height; />Is the characteristic period of the wave, and the unit is s; />For the 0 th moment of the sea wave spectrum to the origin, < + >>The units are +.>；
In the absence of the wave data,taken as the average observation period, when +.>When (I)>Reach maximum value of->；
After obtaining the sea wave spectrum, combining a ship amplitude-frequency response function obtained by a slicing method and a two-dimensional semi-method, and obtaining a ship oscillation energy spectrum according to the relation between the wave energy spectrum and the ship oscillation energy spectrum by utilizing a spectrum analysis theory; based on the ship swinging energy spectrum, the sense value of the ship motion is obtained through integral calculation.
In step S3, the method for statistical prediction of ship motion in irregular waves includes: under the condition of no navigational speed, the wave energy spectral density function is made to beThe ship sway energy spectrum density function is +.>The expression is:
；
in the method, in the process of the invention,the units are +.>，/>As a function of the ship's sway spectral density,is a frequency response function;
when the ship sails, the expression of the encountered frequency is:
；
in the method, in the process of the invention,to encounter frequency, units are rad/s; />The real frequency of the wave is in rad/s; />The unit is m/s for the navigational speed of the ship; />For gravitational acceleration, the unit is->；/>Is the wave angle, the unit is the degree;
conversion according to jacobian:
；
the conversion of wave energy spectrum only causes the frequency of disturbance force acting on the ship to change by the navigational speed, but the corresponding wave is not changed, so the total energy of the wave is unchanged, namely:
；
substituting the formula obtained by conversion according to jacobian into the formula to obtain:
；
the wave energy spectrum of the encountered frequency is calculated, and the motion spectrum of the ship under the condition of the navigational speed is calculated, namely:
；
thereby obtaining a sense value of the vessel motion by integrating the vessel motion spectrum.
Another object of the present invention is to provide a performance evaluation and decision-making assistance system for real sea navigation of a ship, the system implementing the performance evaluation and decision-making assistance method for real sea navigation of a ship, the system comprising:
the regional sea wave forecasting module is used for calculating the sea wave environment of a typical sea area by using the SWAN sea wave model and constructing a data set based on the calculated sea wave data; establishing an intelligent sea wave forecasting model based on a CNN model, and verifying the accuracy of the intelligent sea wave forecasting model by using MAE and MAPE evaluation indexes to finish forecasting of regional sea waves;
the ship wave resistance hydrodynamic library construction module is used for verifying and comparing the ship wave resistance by using a slicing method and a two-dimensional semi-theory to finish ship amplitude response prediction; based on the amplitude response database of the small navigational speed interval, obtaining the amplitude response of ship navigation by using an interpolation method;
the ship sailing performance evaluation module is used for combining regional sea wave simulation with ship wave resistance calculation by using a ship motion statistical prediction method in irregular waves to construct a real sea area ship swaying performance evaluation model, and verifying the feasibility of the real sea area ship swaying performance evaluation model by using data of real ship motion.
By combining all the technical schemes, the invention has the following beneficial effects: the invention provides a ship real sea navigation performance evaluation and auxiliary decision-making system, which combines deep learning with ship navigation performance to construct a ship real sea area swinging motion calculation method, and can realize real sea area environment prediction and ship navigability evaluation by the system, so as to provide direct and accurate auxiliary judgment information for ship and sea navigation planning and provide technical means for guaranteeing safe navigation of a ship in a real sea area and executing tasks at sea.
According to the sea wave data calculated through the numerical mode, the statistical value, the wave spectrum and other information of regional sea waves are predicted by using the deep learning model, and the ship sailing performance is combined to construct a ship real sea area swaying motion calculation method, so that real sea area environment prediction and ship navigability assessment are realized. Compared with the traditional method, the method uses the machine learning model to forecast the marine environment on the route, can rapidly and accurately forecast the sea wave factors such as sense wave height, wave period and the like at different advance times and different positions, thereby being combined with the ship motion response and better realizing the evaluation of the ship swaying performance. The invention can provide more accurate and timely marine environment data and ship swaying performance evaluation data for the navigation of the ship, provides more applicable decision information for the navigation of the ship, and ensures the safety of the navigation of the ship in the real sea area.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure;
FIG. 1 is a flow chart of a performance evaluation and decision-making aid method for real sea navigation of ships, which is provided by the embodiment of the invention;
FIG. 2 is a schematic diagram of a performance evaluation and decision-making aid method for real sea navigation of ships provided by the embodiment of the invention;
FIG. 3 is a block diagram of a regional storm forecast model provided by an embodiment of the invention;
FIG. 4 is a graph of correspondence between inputs and outputs of a predictive model based on a sequenced wind field provided by an embodiment of the present invention;
FIG. 5 is a graph showing MAE error distribution based on a predicted value and a true value of a 1h front wave height according to an embodiment of the present invention;
FIG. 6 is a graph showing MAE error distribution based on a predicted value and a true value of a 6h front wave height according to an embodiment of the present invention;
FIG. 7 is a graph showing MAE error distribution based on a predicted value and a true value of a 12h front wave height according to an embodiment of the present invention;
FIG. 8 is a map of MAPE error distribution based on a predicted value and a true value of a 1h front wave height according to an embodiment of the present invention;
FIG. 9 is a map of MAPE error distribution based on a predicted value and a true value of 6h front wave height according to an embodiment of the present invention;
FIG. 10 is a map of MAPE error distribution based on a forecast value and a true value of a 12h front wave height according to an embodiment of the present invention;
FIG. 11 is a graph of MAPE change between predicted and measured values according to an embodiment of the present invention;
FIG. 12 is a graph comparing sense amplitude values of rolling motions of a ship provided by an embodiment of the present invention;
FIG. 13 is a schematic diagram of a performance evaluation and decision-making aid system for real sea navigation of ships provided by an embodiment of the invention;
in the figure: 1. a regional sea wave forecasting module; 2. the marine wave resistance water power library construction module; 3. and the ship sailing performance evaluation module.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to the appended drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The invention may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit or scope of the invention, which is therefore not limited to the specific embodiments disclosed below.
The performance evaluation and decision-making assisting system and method for ship real sea navigation provided by the embodiment of the invention have the innovation points that:
the invention predicts the marine environment based on the deep learning model and combines the marine environment with the ship motion response. The method can rapidly and accurately give the swinging evaluation result of the ship on the aviation line, and provide data support for the navigation decision of the ship.
Embodiment 1 the method for evaluating and assisting decision-making performance of ship-oriented real sea navigation provided by the embodiment of the invention comprises the following steps: regional sea wave forecasting, construction of a ship wave resistance hydrodynamic base and ship sailing performance evaluation. The regional sea wave forecast provides future medium-large scale marine environment information for the ship, the ship wave resistance hydrodynamic library is constructed to provide excitation characteristics of the ship under different waves, and the regional sea wave forecast and the marine environment information are combined to realize ship sailing performance assessment. As shown in fig. 1, the method specifically includes:
s1, forecasting regional sea waves: calculating the wave environment of a typical sea area by using a SWAN wave model, and constructing a data set based on wave data obtained by calculation; establishing an intelligent sea wave forecasting model based on a CNN model, and verifying the accuracy of the intelligent sea wave forecasting model by using MAE and MAPE evaluation indexes to finish forecasting of regional sea waves;
the wave environment of a typical sea area is calculated using a SWAN wave model (simulating wave search), and then a dataset is constructed based on the calculated wave data. Further, based on a CNN model (Convolitional NeuralNetworks), an intelligent ocean wave forecasting model is established, and accuracy of the model is verified by using evaluation indexes such as MAE (MeanAbsoluteError) and MAPE (MeanAbsolutePercentageError), so that regional ocean waves can be forecasted rapidly. Provides rapid sea wave environment support for ships and provides basic external environment data for subsequent sailing performance evaluation.
Illustratively, the calculating of the sea wave environment of the typical sea area using the SWAN sea wave model includes: and obtaining target sea area wind field information and terrain information through the disclosed environment data set, and setting configuration parameters for SWAN mode operation to operate the SWAN mode, wherein the configuration parameters comprise simulation time, simulation range and simulation resolution information.
S2, constructing a marine wave-resistant water power library: the ship wave resistance is verified and compared by using a slicing method and a two-dimensional semi-theory, and ship amplitude response prediction is completed; based on the amplitude response database of the small navigational speed interval, obtaining the amplitude response of ship navigation by using an interpolation method;
s3, ship sailing performance evaluation: and (3) combining regional sea wave simulation with ship wave resistance calculation by using a ship motion statistical forecasting method in irregular waves, constructing a real sea area ship rocking performance evaluation model, and verifying the feasibility of the real sea area ship rocking performance evaluation model by using the data of the real ship motion.
An exemplary embodiment, as shown in fig. 2, is a principle of a performance evaluation and auxiliary decision making method for real sea navigation of ships provided by the embodiment of the invention.
Example 2, as another implementation manner of the present invention, the performance evaluation and auxiliary decision-making method for real sea navigation of ships provided by the embodiment of the present invention includes:
(1) Regional sea wave forecasting: aiming at the problems of acquisition of environmental information and the like, a sea wave field simulation research based on a SWAN wave mode is developed, a mode calculation scheme and a parameterized configuration scheme are designed based on the environmental information such as terrain, wind fields and the like, and high-precision wind wave simulation of a target sea area is realized. Training the deep learning model by using numerical mode simulation data, constructing an area sea wave intelligent forecasting model, and verifying the accuracy of the model by using evaluation indexes such as MAE, MAPE and the like.
(2) Building a marine wave-resistant water power base: the construction and research of the marine wave resistance hydrodynamic library utilizes a slicing method and a two-dimensional semi-theory to verify and compare the marine wave resistance, so that accurate and rapid marine amplitude response prediction is realized. And based on the amplitude response database of the small navigational speed interval, the amplitude response of the ship navigation is obtained by using an interpolation method, and a condition is provided for the real sea area ship swinging performance evaluation.
(3) And (3) ship sailing performance evaluation: the ship sailing performance evaluation research combines regional sea wave simulation and ship wave resistance calculation by using a ship motion statistical prediction method in irregular waves, so that a real sea area ship rocking performance evaluation model is constructed, and the feasibility of the model thought is verified by using the data of real ship motion.
In the embodiment of the present invention, the mode calculation scheme in the step (1) specifically refers to: and a wave simulation model of a target sea area is established based on the SWAN wave mode, and nonlinear interaction of three component waves is added, so that conversion of shallow water wave energy is more reasonably considered, and the wave simulation precision of the shallow water area is improved. And describing a wind energy input item and a bottom friction item based on wind field information and topographic data provided in the open source data, and solving a wave action quantity balance equation to obtain wave information of a target sea area.
In the embodiment of the present invention, in the step (1), the regional ocean wave intelligent prediction model refers to: and constructing a data set by using the sea wave data obtained by calculating the SWAN sea wave model. And further establishing an intelligent ocean wave forecasting model based on the CNN model. In the regional sea wave intelligent forecasting model, the input is calculated regional wind field data and past wave data, and the output is calculated regional current wave data. As shown in fig. 3, the CNN performs a filtering operation of multiplying and then adding the convolution kernel and input data by using a convolution kernel input matrix, where the input data isThe method comprises the steps of carrying out a first treatment on the surface of the The input data of the model, the first layer convolution module, the pooling module and the second layer convolution module are sequentially from left to right in FIG. 3The system comprises an up-sampling module, a third layer convolution module and output data of a model. The expression is:
；
in the method, in the process of the invention,for the feature map of the current layer, +.>To activate the function +.>For the set of feature maps, +.>Mapping for the features of the upper layer, +.>Is->Layer->Weights corresponding to convolution filters of the positions, < +.>Is biased;
the values in fig. 3 are dimensions of data input by each module, and specifically include: firstly, a wind speed matrix with the dimension of 40 multiplied by 2 is input, after the first convolution module operation, the dimension is changed into 40 multiplied by 16, then the pooling module operation is carried out, the dimension is changed into 20 multiplied by 16, then the second convolution module operation is carried out, the dimension is kept to be 20 multiplied by 16, then the up-sampling module operation is carried out, the dimension of the matrix is changed into 40 multiplied by 16, and finally the third convolution module is carried out, the dimension is changed into 40 multiplied by 40, and the final wave height matrix is obtained.
CNN uses pooling to check input matrix for downsampling, and the salient features of the input matrix are obtained everywhereScreening out information; pooling with maximum poolingMean pooling->Maximum value pooling is the maximum value of the extraction pooling check corresponding position matrix, average value pooling is the extraction average value, and expressions are respectively:
；
；
in the method, in the process of the invention,for the number after mean pooling, +.>For the maximum pooled number, +.>Local matrix acting as pooling nucleus, +.>The number of digits of the local matrix that is active is the number of elements in the local matrix.
CNN uses the upsampling layer to scale up the previous layer output matrix to the appropriate size. The most common upsampling method is resampling. Resampling refers to equal-scale amplification of the initial matrix and repeated filling of the initial matrix data. As shown in fig. 4, assuming that the wave height matrix at the time t needs to be forecasted at present and that the wind speed matrix at the time t-5 is available, a plurality of wind speed matrices at the time t can be selected as input according to actual needs to forecast the wave height matrix at the time t.
The up-sampling method comprises the following steps: CNN uses the upsampling layer to scale up the previous layer output matrix to the appropriate size. The invention adopts a resampling method to carry out upsampling. Resampling means that the initial matrix is amplified in equal proportion, and then the initial matrix data is filled in repeatedly, and the size of the initial matrix can be restored to the greatest extent through resampling.
CNNs interconnect all neurons of two adjacent layers using a fully connected layer. The fully connected layer has the same connection structure as a traditional neural network, is usually arranged at the end of the network and can integrate local information with obvious characteristics in a lower layer of convolution and pooling layers so as to acquire high-level characteristics of an image.
In the embodiment of the present invention, in the step (1), the calculation formulas of MAE and MAPE are as follows:
；
；
in the method, in the process of the invention,for the number of samples->Is true value +.>For predictive value +.>Mean absolute error, +.>Is the average relative error. As shown in fig. 5-11.
In the embodiment of the present invention, in the step (2), the method for constructing the marine wave-resistant water power bank is as follows: and carrying out ship hydrodynamic motion response database research, and carrying out ship navigability assessment based on the wave energy spectrum on the target airlines. Based on Catia modeling software, modeling the ship body through known model values and molded line data, and smoothing the curved surface of the ship body according to a transverse sectional line drawing and a longitudinal sectional line drawing of the ship body. And slicing and dividing the curved surface of the ship body based on UG software, and uniformly distributing points by cutting out contour lines of the ship body at slicing positions to obtain half width and draft values of all slicing points. Based on the constructed ship type data file and the working condition configured by the user, dividing the speed according to the Froude number, and calculating to obtain ship motion response by adopting a slicing method during low-speed navigation and a two-dimensional semi-method during high-speed navigation to form a ship hydrodynamic motion response database under different heading and navigation speeds.
In the embodiment of the present invention, in the step (2), the interpolation method specifically includes: the amplitude response of the similar navigational speeds in the navigational speed searching database of the known navigational route ships is calculated by utilizing an interpolation formula, and the specific formula is as follows:
；
in the method, in the process of the invention,the unit is m/s for the ship speed on the route; />For the approach ∈in the database>Is given in m/s; />For the approach ∈in the database>Higher speeds in m/s; />For the ship amplitude response on the course, +.>For +.>Amplitude response at speed, +.>For +.>Amplitude response at voyage speed.
Therefore, the amplitude response of the ship sailing at any sailing speed can be obtained rapidly and accurately, and the ship wave resistance data support is provided for the ship swing performance evaluation software based on mesoscale wind wave simulation.
In the embodiment of the invention, in the step (3), the real sea area ship sway performance evaluation model construction method comprises the following steps: firstly, based on regional storm data obtained by a deep learning model, ITTC (International Ship model test pool conference) double-parameter spectrum calculation is carried out, and a sea wave spectrum is fitted, wherein a specific formula is as follows.
；
；
；
In the method, in the process of the invention,for the characteristic period of waves, < > j->If the wave characteristic period data is lacking, taking the average period +.>I.e. +.>，/>Is sense wave height +.>As a function of spectral density>For parameters determined by sense wave height and wave period +.>For wave frequency +.>Is a parameter determined by the wave period. The wave energy spectrum is at a frequency +.>The maximum value is->The method comprises the steps of carrying out a first treatment on the surface of the At->The frequencies corresponding to the peaks of the single-parameter spectrum and the double-parameter spectrum are the same.
Based on ITTC spectra:
；
in the method, in the process of the invention,for the first moment of the sea wave spectrum to the origin, < >>The differentiation of the frequency gives:
；
；
；
；
；
after substitution, obtaining a double-parameter ocean wave spectrum:
；
in the method, in the process of the invention,the unit is m, which is the sense wave height; />Is the characteristic period of the wave, and the unit is s; />For the 0 th moment of the sea wave spectrum to the origin, < + >>The units are +.>；
In the absence of the wave data,taken as the average observation period, when +.>When (I)>Reach the maximumLarge value, maximum value->；
After the sea wave spectrum is obtained, a ship amplitude-frequency response function obtained by combining a slicing method and a two-dimensional semi-method is utilized, and a ship oscillation energy spectrum is obtained according to the relation between the wave energy spectrum and the ship oscillation energy spectrum by utilizing a spectrum analysis theory. Based on the ship swinging energy spectrum, the sense value of the ship motion is obtained through integral calculation. Based on the S175 container ship and the DB5415 ship, the response performance prediction analysis of the swinging motion of the ship is carried out under different sailing states such as top waves, smooth waves, oblique waves and the like under different loads such as full load, standard load, no load and the like.
In the embodiment of the present invention, in the step (3), the statistical prediction method for the motion of the ship in the irregular wave specifically includes: under the condition of no navigational speed, the wave energy spectral density function is made to beThe ship sway energy spectrum density function is +.>The expression is:
；
in the method, in the process of the invention,the units are +.>，/>As a function of the ship's sway spectral density,is a frequency response function;
when the ship sails, the encountered frequency is:
；
in the method, in the process of the invention,to encounter frequency, units are rad/s; />The real frequency of the wave is in rad/s; />The unit is m/s for the navigational speed of the ship; />For gravitational acceleration, the unit is->；/>Is the wave angle, the unit is the degree;
conversion according to jacobian:
；
the conversion of wave energy spectrum only causes the frequency of disturbance force acting on the ship to change by the navigational speed, but the corresponding wave is not changed, so the total energy of the wave is unchanged, namely:
；
substituting the formula obtained by conversion according to jacobian into the formula to obtain:
；
the wave energy spectrum of the encountered frequency is calculated, and the motion spectrum of the ship under the condition of the navigational speed is calculated, namely:
；
thereby integrating the vessel motion spectrum to obtain a sense of the vessel motion, as shown in fig. 12.
According to the embodiment, the swinging motion of the ship on the preset navigation line is predicted, so that a ship operator can predict the danger possibly encountered by the ship in advance, the casualties and the cargo loss caused by the severe navigation condition are avoided, and the safety driving and the navigation of related personnel and carried cargoes are protected.
The control decision of the ship in the stormy waves often depends on the experience of a driver, and a method for quantitatively evaluating the navigation state of the ship by utilizing marine environment information is lacking. According to the invention, the real sea area wind and wave environment is combined with the ship swinging, and the simulation efficiency is improved through the deep learning method, so that a ship operator can directly and quantitatively acquire the future running condition of the ship, and the accurate decision of the next operation is convenient.
Embodiment 2, as shown in fig. 13, the embodiment of the present invention provides a performance evaluation and auxiliary decision-making system for real sea navigation of ships, comprising:
the regional sea wave forecasting module 1 is used for calculating the sea wave environment of a typical sea area by using a SWAN sea wave model, and then constructing a data set based on the calculated sea wave data; further establishing an intelligent ocean wave forecasting model based on the CNN model, and verifying the accuracy of the intelligent ocean wave forecasting model by using MAE and MAPE evaluation indexes to finish forecasting of regional ocean waves;
the ship wave resistance hydrodynamic library construction module 2 is used for verifying and comparing the ship wave resistance by using a slicing method and a two-dimensional semi-theory to finish the ship amplitude response forecast; based on the amplitude response database of the small navigational speed interval, obtaining the amplitude response of ship navigation by using an interpolation method;
and the ship sailing performance evaluation module 3 is used for combining regional sea wave simulation with ship wave resistance calculation by using an irregular wave ship motion statistical prediction method to construct a real sea area ship swaying performance evaluation model, and simultaneously verifying the feasibility of the real sea area ship swaying performance evaluation model by using the data of the real ship motion.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
The content of the information interaction and the execution process between the devices/units and the like is based on the same conception as the method embodiment of the present invention, and specific functions and technical effects brought by the content can be referred to in the method embodiment section, and will not be described herein.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention. For specific working processes of the units and modules in the system, reference may be made to corresponding processes in the foregoing method embodiments.
The embodiment of the invention also provides a computer device, which comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, which when executed by the processor performs the steps of any of the various method embodiments described above.
Embodiments of the present invention also provide a computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of the respective method embodiments described above.
The embodiment of the invention also provides an information data processing terminal, which is used for providing a user input interface to implement the steps in the method embodiments when being implemented on an electronic device, and the information data processing terminal is not limited to a mobile phone, a computer and a switch.
The embodiment of the invention also provides a server, which is used for realizing the steps in the method embodiments when being executed on the electronic device and providing a user input interface.
Embodiments of the present invention provide a computer program product which, when run on an electronic device, causes the electronic device to perform the steps of the method embodiments described above.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing apparatus/terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RandomAccessMemory, RAM), electrical carrier signal, telecommunication signal, and software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc.
In order to prove the creative and technical value of the technical scheme of the invention, the technical scheme of the invention is applied to specific products or related technologies in the following embodiments:
the performance evaluation and decision-making assisting method for the ship real sea navigation provided by the application embodiment of the invention is applied to computer equipment, wherein the computer equipment comprises a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor, so that the processor executes the steps of the performance evaluation and decision-making assisting method for the ship real sea navigation.
The performance evaluation and decision-making assisting method for the ship real sea navigation provided by the application embodiment of the invention is applied to an information data processing terminal, and the information data processing terminal is used for realizing the performance evaluation and decision-making assisting method for the ship real sea navigation.
5-11, embodiments of the present invention provide error maps that predict sense wave heights 1-12h in advance; fig. 5-7 are MAE errors for predicting sense wave height 1h, 6h, 12h in advance, respectively. Fig. 8-10 are MAPE errors for predicting sense wave height 1h, 6h, 12h in advance, respectively. FIG. 11 shows the variation of sense wave height prediction error with increasing prediction advance time.
As shown in fig. 12, embodiments of the present invention provide a comparison of predicted values of vessel roll motions with actual values for different waypoints.
While the invention has been described with respect to what is presently considered to be the most practical and preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (10)
1. A performance evaluation and auxiliary decision-making method for ship real sea navigation is characterized by comprising the following steps:
s1, forecasting regional sea waves: calculating the wave environment of a typical sea area by using a SWAN wave model, and constructing a data set based on wave data obtained by calculation; establishing an intelligent sea wave forecasting model based on a CNN model, and verifying the accuracy of the intelligent sea wave forecasting model by using MAE and MAPE evaluation indexes to finish forecasting of regional sea waves;
s2, constructing a marine wave-resistant water power library: the ship wave resistance is verified and compared by using a slicing method and a two-dimensional semi-theory, and ship amplitude response prediction is completed; based on the amplitude response database of the small navigational speed interval, obtaining the amplitude response of ship navigation by using an interpolation method;
s3, ship sailing performance evaluation: and (3) combining regional sea wave simulation with ship wave resistance calculation by using a ship motion statistical forecasting method in irregular waves, constructing a real sea area ship rocking performance evaluation model, and verifying the feasibility of the real sea area ship rocking performance evaluation model by using the data of the real ship motion.
2. The method for evaluating and assisting decision-making performance of real sea navigation for ships according to claim 1, wherein in step S1, the calculating the sea wave environment of a typical sea area using SWAN sea wave model comprises: acquiring target sea area wind field information and terrain information through the disclosed environment data set, and setting configuration parameters of SWAN mode operation to operate the SWAN mode; the configuration parameters comprise simulation time, simulation range and simulation resolution information.
3. The method for evaluating and assisting decision-making according to claim 1, wherein in step S1, the intelligent sea wave forecasting model inputs calculated domain wind field data and past wave data, and outputs calculated domain current wave data; the CNN performs filtering operation by using a convolution kernel to check an input matrix, wherein the filtering operation is to multiply and then add the convolution kernel and the input data, and the expression is as follows:
；
in the method, in the process of the invention,for the feature map of the current layer, +.>To activate the function +.>For the set of feature maps, +.>Mapping for the features of the upper layer, +.>Is->Layer->Weights corresponding to convolution filters of the positions, < +.>Is biased;
the input data is；
The CNN performs downsampling on the input matrix by utilizing the pooling check, and filters out the salient feature information of each part of the input matrix; pooling with maximum poolingMean pooling->Maximum value pooling is the maximum value of the extraction pooling check corresponding position matrix, average value pooling is the extraction average value, and expressions are respectively:
；
；
in the method, in the process of the invention,for the number after mean pooling, +.>For the maximum pooled number, +.>Local matrix acting as pooling nucleus, +.>The number of digits of the local matrix that is active is the number of elements in the local matrix.
4. The method for evaluating and assisting decision-making according to claim 1, wherein in step S1, the calculation formulas of MAE and MAPE evaluation indexes are as follows:
；
；
in the method, in the process of the invention,for the number of samples->Is true value +.>For predictive value +.>Mean absolute error, +.>Is the average relative error.
5. The method for evaluating and assisting decision-making according to claim 1, wherein in step S2, the construction of the marine vessel wave-resistant hydrodynamics base comprises: modeling the ship body through known model values and molded line data based on Catia modeling software, and smoothing the curved surface of the ship body according to a horizontal sectional line drawing and a longitudinal sectional line drawing of the ship body;
slicing and dividing the curved surface of the ship body based on UG software, and uniformly distributing points by cutting out contour lines of the ship body at slicing positions to obtain half width and draft values of all slicing points;
based on the constructed ship type data file and the working condition configured by the user, dividing the speed according to the Froude number, and calculating to obtain ship motion response by adopting a slicing method during low-speed navigation and a two-dimensional semi-method during high-speed navigation to form a ship hydrodynamic motion response database under different heading and navigation speeds.
6. The method for evaluating and assisting decision-making according to claim 1, wherein in step S2, the interpolation method comprises: the amplitude response of the similar navigational speed in the navigational speed searching database of the known navigational route ships is calculated by utilizing an interpolation formula, and the expression is as follows:
；
in the method, in the process of the invention,the unit is m/s for the ship speed on the route; />For the approach ∈in the database>Is given in m/s; />For the approach ∈in the database>Higher speeds in m/s; />For the ship amplitude response on the course, +.>For +.>Amplitude response at speed, +.>For +.>Amplitude response at voyage speed.
7. The method for evaluating and assisting decision-making according to claim 1, wherein in step S3, the constructing the real sea area ship sway performance evaluation model comprises: based on regional wind and wave data obtained by the deep learning model, ITTC double-parameter spectrum calculation is carried out, and the sea wave spectrum is fitted, wherein the expression is as follows:
；
；
；
in the method, in the process of the invention,for the characteristic period of waves, < > j->If the wave characteristic period data is lacking, taking the average period +.>I.e. +.>，/>Is sense wave height +.>As a function of spectral density>For parameters determined by sense wave height and wave period +.>For wave frequency +.>Is a parameter determined by the wave period.
8. The method for evaluating and assisting decision-making according to claim 7, wherein the ITTC dual-parameter spectrum calculation is as follows:
；
in the method, in the process of the invention,for the first moment of the sea wave spectrum to the origin, < >>For frequency->Is obtained by differentiating:
；
；
；
；
；
after substitution, obtaining a double-parameter ocean wave spectrum:
；
in the method, in the process of the invention,the unit is m, which is the sense wave height; />Is the characteristic period of the wave, and the unit is s; />For the 0 th moment of the sea wave spectrum to the origin, < + >>As a function of wave energy spectral density;
in the absence of the wave data,taken as the average observation period, when +.>When (I)>Reach maximum value of->；
After obtaining the sea wave spectrum, combining a ship amplitude-frequency response function obtained by a slicing method and a two-dimensional semi-method, and obtaining a ship oscillation energy spectrum according to the relation between the wave energy spectrum and the ship oscillation energy spectrum by utilizing a spectrum analysis theory; based on the ship swinging energy spectrum, the sense value of the ship motion is obtained through integral calculation.
9. The method for evaluating and assisting decision-making according to claim 1, wherein in step S3, the irregular wave-in-ship motion statistical prediction method comprises: under the condition of no navigational speed, the wave energy spectral density function is made to beThe ship sway energy spectrum density function is +.>Expression ofThe formula is:
；
in the method, in the process of the invention,the units are +.>，/>Is a ship sway spectral density function, +.>Is a frequency response function;
when the ship sails, the expression of the encountered frequency is:
；
in the method, in the process of the invention,to encounter frequency, units are rad/s; />The real frequency of the wave is in rad/s; />The unit is m/s for the navigational speed of the ship; />For gravitational acceleration, the unit is->；/>Is the wave angle, the unit is the degree;
conversion according to jacobian:
；
the conversion of wave energy spectrum only causes the frequency of disturbance force acting on the ship to change by the navigational speed, but the corresponding wave is not changed, so the total energy of the wave is unchanged, namely:
；
substituting the formula obtained by conversion according to jacobian into the formula to obtain:
；
the wave energy spectrum of the encountered frequency is calculated, and the motion spectrum of the ship under the condition of the navigational speed is calculated, namely:
；
thereby obtaining a sense value of the vessel motion by integrating the vessel motion spectrum.
10. A performance evaluation and decision-making aid system for real sea navigation of a ship, characterized in that the system implements the performance evaluation and decision-making aid method for real sea navigation of a ship according to any one of claims 1 to 9, the system comprising:
the regional sea wave forecasting module (1) is used for calculating the sea wave environment of a typical sea area by using the SWAN sea wave model and constructing a data set based on the calculated sea wave data; establishing an intelligent sea wave forecasting model based on a CNN model, and verifying the accuracy of the intelligent sea wave forecasting model by using MAE and MAPE evaluation indexes to finish forecasting of regional sea waves;
the ship wave resistance hydrodynamic library construction module (2) is used for verifying and comparing the ship wave resistance by using a slicing method and a two-dimensional semi-theory to finish the ship amplitude response forecast; based on the amplitude response database of the small navigational speed interval, obtaining the amplitude response of ship navigation by using an interpolation method;
and the ship sailing performance evaluation module (3) is used for combining regional sea wave simulation with ship wave resistance calculation by using an irregular wave ship motion statistical prediction method to construct a real sea area ship swaying performance evaluation model, and verifying the feasibility of the real sea area ship swaying performance evaluation model by using the data of the real ship motion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410245683.0A CN117818850B (en) | 2024-03-05 | 2024-03-05 | Performance evaluation and auxiliary decision making system and method for ship real sea navigation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410245683.0A CN117818850B (en) | 2024-03-05 | 2024-03-05 | Performance evaluation and auxiliary decision making system and method for ship real sea navigation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117818850A true CN117818850A (en) | 2024-04-05 |
| CN117818850B CN117818850B (en) | 2024-05-24 |
Family
ID=90513817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410245683.0A Active CN117818850B (en) | 2024-03-05 | 2024-03-05 | Performance evaluation and auxiliary decision making system and method for ship real sea navigation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117818850B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103900541A (en) * | 2014-03-06 | 2014-07-02 | 哈尔滨工程大学 | Marine condition estimator |
| US20190161152A1 (en) * | 2017-11-27 | 2019-05-30 | Applied Physical Sciences Corp. | Systems and methods for wave sensing and ship motion forecasting with operational period indicators |
| KR102042356B1 (en) * | 2018-09-18 | 2019-11-07 | 한국해양대학교 산학협력단 | Method and system for estimating ship motion performance using artificial intelligence |
| CN110516972A (en) * | 2019-08-30 | 2019-11-29 | 哈尔滨工程大学 | A kind of ship sails and operation on the sea comprehensive forecasting assessment system |
| CN110852619A (en) * | 2019-11-12 | 2020-02-28 | 山东交通学院 | Method for correcting sea wave resistance in ship performance evaluation |
| KR102258257B1 (en) * | 2020-01-14 | 2021-05-28 | 한국해양대학교 산학협력단 | Lateral Oscillation Motion Prediction System of Ship Using Machine Learning Technique |
| KR20220107446A (en) * | 2021-01-25 | 2022-08-02 | 대우조선해양 주식회사 | System for predicting wave information through machine learning of sea level image using lidar |
| CN116395097A (en) * | 2023-02-17 | 2023-07-07 | 江苏佼燕船舶设备有限公司 | Ship anti-capsizing self-righting control method based on attitude fitting prediction |
| CN116644608A (en) * | 2023-06-14 | 2023-08-25 | 青岛哈尔滨工程大学创新发展中心 | Real sea area ship motion forecasting method and system based on marine environment data |
| CN117104452A (en) * | 2023-08-19 | 2023-11-24 | 青岛哈尔滨工程大学创新发展中心 | Method and system for inverting waves by ship-following swinging motion based on artificial neural network |
-
2024
- 2024-03-05 CN CN202410245683.0A patent/CN117818850B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103900541A (en) * | 2014-03-06 | 2014-07-02 | 哈尔滨工程大学 | Marine condition estimator |
| US20190161152A1 (en) * | 2017-11-27 | 2019-05-30 | Applied Physical Sciences Corp. | Systems and methods for wave sensing and ship motion forecasting with operational period indicators |
| KR102042356B1 (en) * | 2018-09-18 | 2019-11-07 | 한국해양대학교 산학협력단 | Method and system for estimating ship motion performance using artificial intelligence |
| CN110516972A (en) * | 2019-08-30 | 2019-11-29 | 哈尔滨工程大学 | A kind of ship sails and operation on the sea comprehensive forecasting assessment system |
| CN110852619A (en) * | 2019-11-12 | 2020-02-28 | 山东交通学院 | Method for correcting sea wave resistance in ship performance evaluation |
| KR102258257B1 (en) * | 2020-01-14 | 2021-05-28 | 한국해양대학교 산학협력단 | Lateral Oscillation Motion Prediction System of Ship Using Machine Learning Technique |
| KR20220107446A (en) * | 2021-01-25 | 2022-08-02 | 대우조선해양 주식회사 | System for predicting wave information through machine learning of sea level image using lidar |
| CN116395097A (en) * | 2023-02-17 | 2023-07-07 | 江苏佼燕船舶设备有限公司 | Ship anti-capsizing self-righting control method based on attitude fitting prediction |
| CN116644608A (en) * | 2023-06-14 | 2023-08-25 | 青岛哈尔滨工程大学创新发展中心 | Real sea area ship motion forecasting method and system based on marine environment data |
| CN117104452A (en) * | 2023-08-19 | 2023-11-24 | 青岛哈尔滨工程大学创新发展中心 | Method and system for inverting waves by ship-following swinging motion based on artificial neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117818850B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bukhari et al. | An intelligent real-time multi-vessel collision risk assessment system from VTS view point based on fuzzy inference system | |
| CN116644608B (en) | Real sea area ship motion forecasting method and system based on marine environment data | |
| Wu et al. | Long-voyage route planning method based on multi-scale visibility graph for autonomous ships | |
| CN110516972B (en) | Comprehensive forecasting and evaluating system for ship sailing and offshore operation | |
| CN107944648A (en) | A kind of accurate Forecasting Methodology of large ship speed of a ship or plane rate of fuel consumption | |
| CN113033073A (en) | Unmanned ship energy efficiency digital twinning method and system based on data driving | |
| CN104483845A (en) | Ship autopilot algorithm testing simulation system | |
| CN104933899A (en) | Ship seaworthiness early-warning system and method | |
| CN107735695A (en) | Oceanographic phenomena estimating device and oceanographic phenomena presumption method | |
| Yu et al. | A direction-constrained space-time prism-based approach for quantifying possible multi-ship collision risks | |
| CN105836066A (en) | Method and system for predicting posture of ship moored at open type wharf | |
| CN115660137B (en) | Accurate estimation method for wind wave navigation energy consumption of ship | |
| CN113112059A (en) | Ship berthing time prediction method and system | |
| Yang et al. | An approach to ship behavior prediction based on AIS and RNN optimization model | |
| Majidian et al. | Part. B: A review of the real-time sea-state estimation, using wave buoy analogy; a decuple benchmark and future outlook | |
| Xu et al. | Risk evaluation system of navigation security based on coupled wind and wave model: a case of study of Qiongzhou strait | |
| CN113962426A (en) | Offshore water navigation safety intelligent forecasting method and device | |
| Marie et al. | Sail-assisted motor vessels weather routing using a fuzzy logic model | |
| Spiliopoulos et al. | A Big Data framework for Modelling and Simulating high-resolution hydrodynamic models in sea harbours | |
| CN117818850B (en) | Performance evaluation and auxiliary decision making system and method for ship real sea navigation | |
| CN115410419B (en) | Ship mooring early warning method, system, electronic equipment and storage medium | |
| Jing et al. | Motion modeling and simulation of maritime autonomous surface ships in realistic environmental disturbances | |
| Lin et al. | Multi-parameter stochastic inversion for first and second moment mass properties of a model-scale ship with topside ice accumulation | |
| Cademartori et al. | A review on ship motions and quiescent periods prediction models | |
| Bons et al. | EconomyPlanner; optimal use of inland waterways |
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 |