CN116202492A - Ship-following wave measurement method based on high-low frequency separation - Google Patents
Ship-following wave measurement method based on high-low frequency separation Download PDFInfo
- Publication number
- CN116202492A CN116202492A CN202310182079.3A CN202310182079A CN116202492A CN 116202492 A CN116202492 A CN 116202492A CN 202310182079 A CN202310182079 A CN 202310182079A CN 116202492 A CN116202492 A CN 116202492A
- Authority
- CN
- China
- Prior art keywords
- frequency
- low
- platform
- wave
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C13/00—Surveying specially adapted to open water, e.g. sea, lake, river or canal
- G01C13/002—Measuring the movement of open water
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M10/00—Hydrodynamic testing; Arrangements in or on ship-testing tanks or water tunnels
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Hydrology & Water Resources (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Fluid Mechanics (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
Abstract
The invention provides a method for measuring wave along with a ship based on high-low frequency separation, which comprises the following steps: developing a hydrodynamic model experiment aiming at the floating ocean platform, establishing an ocean engineering model test data set, and preprocessing data in the data set; establishing a wave surface elevation linear calculation model, and carrying out wave surface elevation linear calculation; respectively carrying out high-low frequency separation on a wave surface elevation linear estimation result and a six-degree-of-freedom motion response of the platform, decomposing a signal into a high-frequency signal and a low-frequency signal, and respectively establishing a neural network for processing the high-frequency data and the low-frequency data; the training process is monitored in real time, and the neural network parameters with optimal performance are respectively selected and used as a high-frequency calculation model and a low-frequency calculation model for calculating the rise of the real wave surface; and respectively inputting the real-time motion response data and the air gap response data of the floating ocean platform in the position of the floating ocean platform into a high-frequency neural network model and a low-frequency neural network model after high-frequency and low-frequency separation to obtain the real wave surface rise of the floating ocean platform in the position of the floating ocean platform.
Description
Technical Field
The invention relates to the technical field of ships and ocean engineering, in particular to a method for measuring wave along with a ship based on high-low frequency separation.
Background
With the recent complex deep sea environment conditions and the frequent occurrence of super typhoons, the method provides serious challenges for the safety of deep sea equipment, and has very important significance for the research and development of marine instrument equipment, deep sea detection, marine resource utilization and the like in China, especially for the measurement of extreme waves. However, the conventional wave measurement means at present have a certain limitation in this respect, and development of new technology for measuring waves in the ocean environment is needed.
At present, wave information around an ocean structure is mainly measured by using a wave measuring radar fixed on the side of the structure, however, the measuring method obtains platform air gap response at a measuring position, besides incident wave information, the platform air gap response comprises motion factors of the platform and complex nonlinear factors in the wave-structure interaction process, and the problem of low precision exists.
Therefore, there is a need to develop a method for improving the wave measurement accuracy by using high-low frequency separation and realizing accurate measurement along with the wave of the ship by using a data driving and deep learning method.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a ship-following wave measuring method based on high-low frequency separation, which can realize accurate measurement of wave surface elevation at the position of a floating ocean platform.
In order to solve the problems, the technical scheme of the invention is as follows:
a method for measuring wave along with a ship based on high-low frequency separation comprises the following steps:
developing a hydrodynamic model experiment aiming at the floating ocean platform, establishing an ocean engineering model test data set, and preprocessing data in the data set;
establishing a wave surface elevation linear calculation model, and carrying out wave surface elevation linear calculation;
respectively carrying out high-low frequency separation on a wave surface elevation linear estimation result and a six-degree-of-freedom motion response of the platform, decomposing a signal into a high-frequency signal and a low-frequency signal, and respectively establishing a neural network for processing the high-frequency data and the low-frequency data;
the method comprises the steps of monitoring a training process in real time, carrying out sensitivity analysis on each parameter and super parameter of a high-frequency part neural network and a low-frequency part neural network, and respectively selecting the neural network parameters with optimal performance as a high-frequency calculation model and a low-frequency calculation model for calculating the rise of a real wave surface;
and respectively inputting the real-time motion response data and the air gap response data of the floating ocean platform in the position of the floating ocean platform into a high-frequency neural network model and a low-frequency neural network model after high-frequency and low-frequency separation, and combining the calculation results of the high-frequency neural network model and the low-frequency neural network model to obtain the real wave surface elevation of the floating ocean platform in the position of the floating ocean platform.
Preferably, the model test data comprises platform six-degree-of-freedom motion response data, relative wave surface elevation data at the measuring points and incident wave data, and the data preprocessing comprises relative wave surface elevation time histories, platform six-degree-of-freedom motion response time histories and incident wave time histories measured in the irregular wave test.
Preferably, the six degree of freedom motion response data for the platform includes three linear motions of heave, heave and three angular motions of roll, pitch and yaw.
Preferably, the step of establishing a wave surface elevation linear calculation model and performing wave surface elevation linear estimation specifically includes: and establishing a wave surface elevation linear calculation model, calculating vertical movement at the position of the corresponding wave surface elevation measuring point through six-degree-of-freedom movement of the platform, and carrying out linear estimation on the wave surface elevation at the position by combining the measured relative wave surface elevation.
Preferably, the air gap site location (X p ,Y p ,Z p ) At the center of the platform (X c ,Y c ,Z c ) Is calculated by using a space motion coordinate conversion calculation formulaThe vertical displacement at the measuring point position is calculated as follows:
wherein merge is a target p ,Sway p ,Heave p And merge c ,Sway c ,Heave c The air gap measuring point position and the platform gravity center position respectively represent the heave, swaying and swaying movements, and the conversion matrix M is expressed as:
preferably, the calculated vertical displacement of the measuring point position is utilized, the air gap response data of the position is combined, after data synchronization, the wave surface elevation of the position is calculated according to a linear method, and the calculation formula is as follows:wherein a is 0 Representing the air gap value, a, of the platform in a still water state t (t) represents the dynamic air gap response of the platform, lambda represents the influence coefficient of the roll and pitch angle of the platform on wave measurement under the action of waves, and lambda is calculated as follows:
preferably, the step of respectively performing high-frequency and low-frequency separation on the wave surface elevation linear estimation result and the six-degree-of-freedom motion response of the platform, decomposing the signals into a high-frequency signal and a low-frequency signal, and respectively establishing a neural network for processing the high-frequency data and the low-frequency data specifically includes: the wave surface elevation linearity estimation result is subjected to high-low frequency separation processing to divide the wave surface elevation linearity estimation into a high-frequency part and a low-frequency part, the six-degree-of-freedom motion response is subjected to high-low frequency separation processing to divide the motion response into a high-frequency part and a low-frequency part, and the incident wave calendar is subjected to high-low frequency separation processing to divide the incident wave into a high-frequency part and a low-frequency part.
Preferably, the step of respectively performing high-frequency and low-frequency separation on the wave surface elevation linear estimation result and the six-degree-of-freedom motion response of the platform, decomposing the signals into a high-frequency signal and a low-frequency signal, and respectively establishing a neural network for processing the high-frequency data and the low-frequency data specifically further comprises: and establishing an artificial neural network of the low frequency part, taking a wave surface elevation linear calculation low frequency signal and a six-degree-of-freedom motion low frequency response of the platform as input, taking an incident wave low frequency signal of a model test as a target value, calculating a loss function, performing supervised learning by using an optimization algorithm, and updating the model weight of the neural network.
Preferably, the step of respectively performing high-frequency and low-frequency separation on the wave surface elevation linear estimation result and the six-degree-of-freedom motion response of the platform, decomposing the signals into a high-frequency signal and a low-frequency signal, and respectively establishing an artificial neural network for processing the high-frequency data and the low-frequency data specifically further comprises the steps of: and establishing an artificial neural network of the high-frequency part, taking a wave surface elevation linear calculation high-frequency signal and a six-degree-of-freedom motion high-frequency response of the platform as inputs, taking an incident wave high-frequency signal of a model test as a target value, calculating a loss function, performing supervised learning by using an optimization algorithm, and updating the model weight of the neural network.
Preferably, the step of obtaining the real wave surface rise at the position of the floating platform by combining the calculation results of the high-frequency and low-frequency neural network models specifically includes: and respectively carrying out high-low frequency separation on the real-time motion response data and the air gap response data of the floating ocean platform, transmitting a low-frequency signal into a low-frequency neural network model, transmitting a high-frequency signal into a high-frequency neural network model, calculating and adding the results to obtain the real wave surface rise at the position of the floating ocean platform.
Compared with the prior art, the method utilizes the hydrodynamic model test data of the floating ocean platform, and respectively establishes the artificial neural networks of the high-frequency part and the low-frequency part based on the high-low frequency separation method, so as to solve the nonlinear effect of the wave-structure which influences the wave surface elevation measurement precision in real time and realize the accurate measurement of the wave surface elevation of the position where the floating ocean platform is positioned.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of a method for measuring wave along with a ship based on high-low frequency separation, which is provided by the embodiment of the invention;
fig. 2 is a schematic diagram of a method for measuring wave along with a ship based on high-low frequency separation according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present invention.
Specifically, the invention provides a method for measuring wave along with a ship based on high-low frequency separation, which is shown in fig. 1 and 2, and comprises the following steps:
s1: developing a hydrodynamic model experiment aiming at the floating ocean platform, establishing an ocean engineering model test data set, and preprocessing data in the data set;
specifically, a hydrodynamic model experiment aiming at a floating ocean platform is carried out, an ocean engineering model test data set is established, data in the data set is preprocessed 1, and the data preprocessing 1 mainly comprises a relative wave surface elevation calendar 4, a platform six-degree-of-freedom motion calendar 3 and an incident wave calendar 2, which are measured in an irregular wave test.
The six-degree-of-freedom motion response data of the platform comprises three linear motions of heave, heave and three angular motions of roll, pitch and yaw.
S2: establishing a wave surface elevation linear calculation model, and carrying out wave surface elevation linear calculation;
establishing a wave surface elevation linear calculation model, calculating vertical movement 5 at the position of a corresponding wave surface elevation measuring point through six-degree-of-freedom movement of the platform, and carrying out linear calculation 6 on the wave surface elevation of the position by combining the measured relative wave surface elevation;
specifically, based on the platform six degree of freedom motion response and air gap site location (X p ,Y p ,Z p ) At the center of the platform (X c ,Y c ,Z c ) The relative coordinates of the measuring point are calculated by using a space motion coordinate conversion calculation formula, wherein the calculation formula is as follows:wherein merge is a target p ,Sway p ,Heave p And merge c ,Sway c ,Heave c The air gap measuring point position and the platform gravity center position respectively represent the heave, swaying and swaying movements, and the conversion matrix M is expressed as:
further, the calculated vertical displacement of the measuring point position is utilized, the air gap response data of the position is combined, after data synchronization, the wave surface elevation of the position is calculated according to a linear method, and the calculation formula is as follows:wherein a is 0 Representing the air gap value, a, of the platform in a still water state t (t) represents the dynamic air gap response of the platform, lambda represents the influence coefficient of the roll and pitch angle of the platform on wave measurement under the action of waves, and the influence coefficient can be further calculated by the following formula: />
S3: respectively carrying out high-low frequency separation on a wave surface elevation linear estimation result and a six-degree-of-freedom motion response of the platform, decomposing a signal into a high-frequency signal and a low-frequency signal, and respectively establishing a neural network for processing the high-frequency data and the low-frequency data;
specifically, the high-low frequency separation processing 7 is performed on the wavefront elevation linearity estimation result, and the wavefront elevation linearity estimation is decomposed into a high-frequency part and a low-frequency part; performing high-low frequency separation processing 8 on the six-degree-of-freedom motion response, and decomposing the motion response into a high-frequency part and a low-frequency part; the high-low frequency separation processing 9 is carried out on the incident wave calendar, and the incident wave is decomposed into a high-frequency part and a low-frequency part;
an artificial neural network 10 of a low frequency part is established, a wave surface elevation linear calculation low frequency signal and a six-degree-of-freedom motion low frequency response of a platform are taken as input, an incident wave low frequency signal of a model test is taken as a target value, a loss function is calculated, and an optimization algorithm is utilized to conduct supervised learning, so that the neural network model weight 12 is updated.
An artificial neural network 11 of a high-frequency part is established, a wave surface elevation linear estimation high-frequency signal and a six-degree-of-freedom motion high-frequency response of a platform are taken as inputs, an incident wave high-frequency signal of a model test is taken as a target value, a loss function is calculated, and an optimization algorithm is utilized to conduct supervised learning, so that the neural network model weight 12 is updated.
S4: the method comprises the steps of monitoring a training process in real time, carrying out sensitivity analysis on each parameter and super parameter of a high-frequency part neural network and a low-frequency part neural network, and respectively selecting the neural network parameters with optimal performance as a high-frequency calculation model and a low-frequency calculation model for calculating the rise of a real wave surface;
s5: and respectively inputting the real-time motion response data and the air gap response data of the floating ocean platform in the position of the floating ocean platform into a high-frequency neural network model and a low-frequency neural network model after high-frequency and low-frequency separation, and combining the calculation results of the high-frequency neural network model and the low-frequency neural network model to obtain the real wave surface elevation of the floating ocean platform in the position of the floating ocean platform.
Specifically, according to the trained low-frequency calculation model and high-frequency calculation model, respectively performing high-frequency and low-frequency separation on real-time motion response data and air gap response data of the floating ocean platform, transmitting a low-frequency signal into the low-frequency calculation model 14, transmitting a high-frequency signal into the high-frequency calculation model 13, calculating and adding the results to obtain the actual wave surface rise at the position of the floating platform.
Compared with the prior art, the method utilizes the hydrodynamic model test data of the floating ocean platform, and respectively establishes the artificial neural networks of the high-frequency part and the low-frequency part based on the high-low frequency separation method, so as to solve the nonlinear effect of the wave-structure which influences the wave surface elevation measurement precision in real time and realize the accurate measurement of the wave surface elevation of the position where the floating ocean platform is positioned.
The foregoing describes specific embodiments of the present invention. It is to be understood that the invention is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the invention. The embodiments of the present application and features in the embodiments may be combined with each other arbitrarily without conflict.
Claims (10)
1. The method for measuring the wave along with the ship based on high-low frequency separation is characterized by comprising the following steps of:
developing a hydrodynamic model experiment aiming at the floating ocean platform, establishing an ocean engineering model test data set, and preprocessing data in the data set;
establishing a wave surface elevation linear calculation model, and carrying out wave surface elevation linear calculation;
respectively carrying out high-low frequency separation on a wave surface elevation linear estimation result and a six-degree-of-freedom motion response of the platform, decomposing a signal into a high-frequency signal and a low-frequency signal, and respectively establishing a neural network for processing the high-frequency data and the low-frequency data;
the method comprises the steps of monitoring a training process in real time, carrying out sensitivity analysis on each parameter and super parameter of a high-frequency part neural network and a low-frequency part neural network, and respectively selecting the neural network parameters with optimal performance as a high-frequency calculation model and a low-frequency calculation model for calculating the rise of a real wave surface;
and respectively inputting the real-time motion response data and the air gap response data of the floating ocean platform in the position of the floating ocean platform into a high-frequency neural network model and a low-frequency neural network model after high-frequency and low-frequency separation, and combining the calculation results of the high-frequency neural network model and the low-frequency neural network model to obtain the real wave surface elevation of the floating ocean platform in the position of the floating ocean platform.
2. The method for measuring wave along with ship based on high-low frequency separation according to claim 1, wherein the model test data comprises six-degree-of-freedom motion response data of a platform, relative wave surface elevation data at a measuring point and incident wave data.
3. The method of measuring wave following a ship according to claim 2, wherein the six degrees of freedom motion response data of the platform includes three linear motions of heave, heave and roll and three angular motions of roll, pitch and yaw.
4. The method for measuring wave along with ship based on high-low frequency separation according to claim 1, wherein the step of establishing a wave surface elevation linear calculation model and performing wave surface elevation linear calculation specifically comprises the steps of: and establishing a wave surface elevation linear calculation model, calculating vertical movement at the position of the corresponding wave surface elevation measuring point through six-degree-of-freedom movement of the platform, and carrying out linear estimation on the wave surface elevation at the position by combining the measured relative wave surface elevation.
5. The method for measuring wave along with ship based on high-low frequency separation according to claim 4, wherein the measuring point position (X p ,Y p ,Z p ) At the center of the platform (X c ,Y c ,Z c ) The relative coordinates of the measuring point are calculated by using a space motion coordinate conversion calculation formula, wherein the calculation formula is as follows:
wherein merge is a target p ,Sway p ,Heave p And merge c ,Sway c ,Heave c Respectively represent air gapsThe heave, heave and heave motions at the site and platform center of gravity position are represented by the transformation matrix M:
6. the method for measuring wave along with ship based on high-low frequency separation according to claim 5, wherein the vertical displacement at the calculated measuring point position is utilized, the wave surface rise at the position is calculated according to a linear method after data synchronization by combining the air gap response data of the position, and the calculation formula is as follows:wherein a is 0 Representing the air gap value, a, of the platform in a still water state t (t) represents the dynamic air gap response of the platform, lambda represents the influence coefficient of the roll and pitch angle of the platform on wave measurement under the action of waves, and lambda is calculated as follows: />
7. The method for measuring wave following a ship according to claim 1, wherein the steps of respectively performing high-frequency and low-frequency separation on the wave surface elevation linearity estimation result and the six-degree-of-freedom motion response of the platform, decomposing the signals into high-frequency signals and low-frequency signals, and respectively establishing a neural network for processing the high-frequency data and the low-frequency data comprise: the wave surface elevation linearity estimation result is subjected to high-low frequency separation processing to divide the wave surface elevation linearity estimation into a high-frequency part and a low-frequency part, the six-degree-of-freedom motion response is subjected to high-low frequency separation processing to divide the motion response into a high-frequency part and a low-frequency part, and the incident wave calendar is subjected to high-low frequency separation processing to divide the incident wave into a high-frequency part and a low-frequency part.
8. The method for measuring wave following a ship according to claim 7, wherein the steps of respectively performing high-frequency and low-frequency separation on the wave surface elevation linearity estimation result and the six-degree-of-freedom motion response of the platform, decomposing the signals into high-frequency signals and low-frequency signals, and respectively establishing a neural network for processing the high-frequency data and the low-frequency data comprise: and establishing an artificial neural network of the low frequency part, taking a wave surface elevation linear calculation low frequency signal and a six-degree-of-freedom motion low frequency response of the platform as input, taking an incident wave low frequency signal of a model test as a target value, calculating a loss function, performing supervised learning by using an optimization algorithm, and updating the model weight of the neural network.
9. The method for measuring wave along with ship based on high-low frequency separation according to claim 7, wherein the steps of respectively performing high-low frequency separation on the wave surface elevation linearity estimation result and the six-degree-of-freedom motion response of the platform, decomposing the signals into high-frequency signals and low-frequency signals, and respectively establishing artificial neural networks for processing the high-frequency data and the low-frequency data specifically further comprise: and establishing an artificial neural network of the high-frequency part, taking a wave surface elevation linear calculation high-frequency signal and a six-degree-of-freedom motion high-frequency response of the platform as inputs, taking an incident wave high-frequency signal of a model test as a target value, calculating a loss function, performing supervised learning by using an optimization algorithm, and updating the model weight of the neural network.
10. The method for measuring wave along with ship based on high-low frequency separation according to claim 1, wherein the step of obtaining the real wave surface rise at the position of the floating platform by combining the calculation results of the high-frequency and low-frequency neural network models comprises the following steps: and respectively carrying out high-low frequency separation on the real-time motion response data and the air gap response data of the floating ocean platform, transmitting a low-frequency signal into a low-frequency neural network model, transmitting a high-frequency signal into a high-frequency neural network model, calculating and adding the results to obtain the real wave surface rise at the position of the floating ocean platform.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310182079.3A CN116202492A (en) | 2023-02-27 | 2023-02-27 | Ship-following wave measurement method based on high-low frequency separation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310182079.3A CN116202492A (en) | 2023-02-27 | 2023-02-27 | Ship-following wave measurement method based on high-low frequency separation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116202492A true CN116202492A (en) | 2023-06-02 |
Family
ID=86512540
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310182079.3A Pending CN116202492A (en) | 2023-02-27 | 2023-02-27 | Ship-following wave measurement method based on high-low frequency separation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116202492A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117851760A (en) * | 2024-03-07 | 2024-04-09 | 青岛哈尔滨工程大学创新发展中心 | Wave intelligent forecasting model optimization method and system based on frequency band preprocessing |
-
2023
- 2023-02-27 CN CN202310182079.3A patent/CN116202492A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117851760A (en) * | 2024-03-07 | 2024-04-09 | 青岛哈尔滨工程大学创新发展中心 | Wave intelligent forecasting model optimization method and system based on frequency band preprocessing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109900256B (en) | Self-adaptive ocean mobile acoustic tomography system and method | |
CN107145647B (en) | Method for correcting deviation of measured data of sea surface wind speed and wind direction of ship | |
CN111241740B (en) | Fast and accurate calculation method for FPSO soft rigid arm stress | |
CN112598113A (en) | Ocean sound velocity profile acquisition method based on self-organizing competitive neural network | |
CN116202492A (en) | Ship-following wave measurement method based on high-low frequency separation | |
CN116502478B (en) | Submarine topography monitoring-based pile-off auxiliary decision-making method for self-lifting platform | |
CN109579850A (en) | Deep water intelligent navigation method based on speed through water auxiliary inertial navigation | |
CN1776555A (en) | Marine power positioning control method based on fuzzy adaptive algorithm | |
Jiao et al. | Predictions of wave induced ship motions and loads by large-scale model measurement at sea and numerical analysis | |
CN110703205B (en) | Ultra-short baseline positioning method based on self-adaptive unscented Kalman filtering | |
CN117104452A (en) | Method and system for inverting waves by ship-following swinging motion based on artificial neural network | |
CN114692520A (en) | Multi-scene-oriented unmanned ship virtual simulation test platform and test method | |
CN114218860A (en) | Laser radar wind measurement motion compensation method and system based on machine learning | |
CN116805028B (en) | Wave surface inversion method and system based on floating body motion response | |
Yao et al. | Motion and load prediction of floating platform in South China Sea using deep learning and prototype monitoring information | |
Cademartori et al. | A review on ship motions and quiescent periods prediction models | |
CN116242323A (en) | Method for measuring wave along with ship for floating ocean platform | |
CN110767322B (en) | Ocean floating platform hot spot stress calculation method based on response surface model | |
CN116242584A (en) | Floating ocean platform along with ship wave measuring device based on BP neural network | |
Bisinotto et al. | Assessment of Sea State Estimation With Convolutional Neural Networks Based on the Motion of a Moored FPSO Subjected to High-Frequency Wave Excitation | |
Xu et al. | Prediction of Total Force and Moment of Ship Based on Improved BP Neural Network | |
CN113009491B (en) | Horizontal suspension array real-time array shape estimation method based on auxiliary sensor | |
CN112131653B (en) | Ship simulation platform gesture analysis method and mechanism | |
CN117550034A (en) | Ship motion attitude prediction method at target point location based on artificial neural network | |
CN118052170B (en) | Method, system, equipment and medium for calculating internal wave propagation speed based on hydrodynamic force of navigation body |
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 |