A ship sway analysis system and method based on deep learning

Abstract

The present application relates to the field of marine equipment and provides a ship sway analysis system and method based on deep learning, the system comprising: a data acquisition module for acquiring time series data, the time series data comprising: ship travel time series data, ship sway time series data and meteorological time series data; a data division module for dividing the time series data into historical time series data and time series data to be predicted, and determining data labels corresponding to the historical time series data according to the time series data to be predicted, the data labels comprising: roll angle labels and pitch angle labels; a model training module for training a preset model according to the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted according to the historical time series data; a sway analysis module for predicting the effective roll angle and the effective roll angle of the ship based on the roll angle prediction model and the pitch angle prediction model.

Description

Technical Field

[0001] The present application relates to the field of marine equipment, and in particular to a ship sway analysis system and method based on deep learning. Background Art

[0002] Ships experience various swaying motions in waves, including roll, pitch, and heave. When the amplitude of the sway exceeds a certain limit, it can cause seasickness, reduce work efficiency, and even endanger lives in extreme cases. For cargo, violent swaying can shift and damage it, affecting the stability and safety of the ship. Furthermore, excessive swaying can damage a ship's equipment, impacting its normal operation. Therefore, to improve ship safety, it is crucial to predict the ship's motion response under different sea conditions. By predicting the ship's sway, measures can be taken in advance, such as adjusting speed and heading or using anti-roll devices, to avoid danger to the ship. Analyzing and predicting ship sway has become a pressing issue. Summary of the Invention

[0003] The main purpose of this application is to provide a ship sway analysis system based on deep learning, aiming to accurately predict the sway of the ship.

[0004] In a first aspect, the present application provides a ship sway analysis system based on deep learning, the system comprising:

[0005] A data acquisition module is used to acquire time series data, wherein the time series data includes: ship travel time series data, ship swing time series data and meteorological time series data;

[0006] a data partitioning module, configured to partition the time series data into historical time series data and time series data to be predicted, and determine data labels corresponding to the historical time series data based on the time series data to be predicted, wherein the data labels include: a roll angle label and a pitch angle label;

[0007] a model training module, configured to train a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data;

[0008] The roll analysis module is used to predict the effective roll angle and the effective pitch angle of the ship based on the roll angle prediction model and the pitch angle prediction model.

[0009] In some embodiments, the data partitioning module, in the process of partitioning the time series data into historical time series data and time series data to be predicted, and determining the data label corresponding to the historical time series data according to the time series data to be predicted, is configured to:

[0010] Based on a sliding window algorithm, determining time series data of a first preset length as the historical time series data, and using time series data of a second preset length following the historical time series data as the time series data to be predicted;

[0011] The roll angle data in the time series data to be predicted is used as the roll angle label corresponding to the historical time series data, and the pitch angle data in the time series data to be predicted is used as the pitch angle label corresponding to the historical time series data.

[0012] In some embodiments, the data acquisition module is used to acquire time series data, wherein the time series data includes ship travel time series data, ship swing time series data, and meteorological time series data, and is used to:

[0013] Determine the ship travel time series data according to the ship travel data sampled by the ship control system and the timestamp corresponding to the ship travel data, wherein the ship travel data includes: speed data, heading data, and heading difference data;

[0014] Determining the ship sway time series data according to the ship sway data sampled by the shipboard sensor and the timestamp corresponding to the ship sway data, wherein the ship sway data includes: roll angle data and pitch angle data;

[0015] Acquire meteorological data and a timestamp corresponding to the meteorological data to determine the meteorological time series data, wherein the meteorological data includes: wind field data, flow field data, and wave data.

[0016] In some embodiments, the data acquisition module, in the process of acquiring meteorological data released by a meteorological center and a timestamp corresponding to the meteorological data and determining the meteorological time series data, is used to:

[0017] Obtaining the original meteorological data released by the meteorological center and the timestamp corresponding to the original meteorological data;

[0018] Performing temporal interpolation and spatial interpolation on the original meteorological data according to the timestamp to obtain target meteorological data and a timestamp corresponding to the target meteorological data;

[0019] The meteorological time series data is determined according to the target meteorological data and a timestamp corresponding to the target meteorological data.

[0020] In some embodiments, the system further comprises:

[0021] The data correction module is used to correct the ship swing data according to the ship driving data and the meteorological data, and determine the ship swing time series data according to the corrected ship swing data.

[0022] In some embodiments, the data correction module, in the process of correcting the ship swing data according to the ship driving data and the meteorological data, and determining the ship swing time series data according to the corrected ship swing data, is used to:

[0023] The amplitude of the ship's motion response is calculated based on the following formula:

[0024] ;

[0025] Among them, H is the wave height data, is the ship's natural frequency, Indicates the frequency of encounters between ships and waves;

[0026] The ship roll data is corrected according to the motion response amplitude.

[0027] In some embodiments, the data correction module, in the process of correcting the ship swing data according to the ship driving data and the meteorological data, and determining the ship swing time series data according to the corrected ship swing data, is further configured to:

[0028] The encounter frequency is calculated according to the following formula:

[0029] ;

[0030] in, represents the circular frequency of the waves, V represents the speed of the ship, α represents the angle between the wave direction and the ship's heading, and L represents the length of the ship.

[0031] In some embodiments, the data correction module, in the process of correcting the ship rolling data according to the motion response amplitude, is further configured to:

[0032] Correcting the roll angle tag according to a roll motion response amplitude operator and the motion response amplitude;

[0033] The pitch angle label is corrected according to a pitch motion response magnitude operator and the motion response amplitude.

[0034] In some embodiments, the deep learning-based ship sway analysis system further includes:

[0035] The model verification module is used to determine the accuracy performance index and the generalization performance index of the roll angle prediction model and the pitch angle prediction model according to the effective roll angle output by the roll angle prediction model and the effective pitch angle output by the pitch angle prediction model.

[0036] In a second aspect, the present application further provides a ship sway analysis method based on deep learning, the method comprising:

[0037] Acquiring time series data, the time series data including: ship travel time series data, ship swing time series data, and weather time series data;

[0038] Dividing the time series data into historical time series data and time series data to be predicted, and determining data labels corresponding to the historical time series data according to the time series data to be predicted, wherein the data labels include: a roll angle label and a pitch angle label;

[0039] Training a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data;

[0040] The effective roll angle and effective pitch angle of the ship are predicted based on the roll angle prediction model and the pitch angle prediction model.

[0041] The present application provides a deep learning-based ship sway analysis system and method. The present application utilizes a data acquisition module for acquiring time series data, including ship travel time series data, ship sway time series data, and meteorological time series data. A data partitioning module is configured to partition the time series data into historical time series data and time series data to be predicted, and to determine data labels corresponding to the historical time series data based on the time series data to be predicted. The data labels include roll angle labels and pitch angle labels. A model training module is configured to train a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data. A sway analysis module is configured to predict the effective roll angle and effective roll angle of the ship based on the roll angle prediction model and the pitch angle prediction model. By constructing the roll angle prediction model and the pitch angle prediction model, respectively, the predictability of the effective roll angle and effective pitch angle is improved, which helps to prepare for the ship's sway in advance and improve the safety of the ship's navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0043] Figure 1 A schematic block diagram of a ship sway analysis system based on deep learning provided in one embodiment of the present application;

[0044] Figure 2A schematic diagram of a flow chart of a ship sway analysis method based on deep learning provided in one embodiment of the present application;

[0045] Figure 3 This is a schematic block diagram of the structure of a computer device involved in one embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0047] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0048] The embodiments of the present application provide a ship sway analysis system and method based on deep learning.

[0049] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0050] Please refer to Figure 1 , Figure 1 This is a schematic block diagram of a deep learning-based ship sway analysis system provided in one embodiment of the present application. This deep learning-based ship sway analysis system can be used in a terminal or server to accurately predict the ship's sway. The terminal can be an electronic device such as a mobile phone, tablet computer, laptop computer, desktop computer, personal digital assistant, or wearable device; the server can be a standalone server, a server cluster, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0051] like Figure 1 As shown, the deep learning-based ship sway analysis system includes a data acquisition module 110 , a data division module 120 , a model training module 130 , and a sway analysis module 140 .

[0052] The data acquisition module 110 is used to acquire time series data, wherein the time series data includes: ship travel time series data, ship swing time series data and weather time series data;

[0053] The data partitioning module 120 is configured to partition the time series data into historical time series data and time series data to be predicted, and determine data labels corresponding to the historical time series data based on the time series data to be predicted, wherein the data labels include: a roll angle label and a pitch angle label;

[0054] A model training module 130 is configured to train a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data;

[0055] The roll analysis module 140 is configured to predict the effective roll angle and the effective pitch angle of the ship based on the roll angle prediction model and the pitch angle prediction model.

[0056] For example, in the related art, the ship's sway is usually analyzed in six degrees of freedom, namely surge, sway, heave, roll, pitch and bow pitch. Among the six degrees of freedom, roll and pitch are usually the most concerned.

[0057] It is understood that roll refers to the rotational motion of a ship around its longitudinal axis. In waves, roll is the most likely motion to occur, and the sway amplitude is usually the largest. Roll may cause cargo displacement, damage to the hull structure, and even affect the stability of the ship, significantly affecting the safety of the ship. Pitch refers to the rotational motion of a ship around its transverse axis. Pitching causes the ship to pitch forward and backward, potentially affecting the ship's navigation performance and passenger comfort. In waves, pitching may cause waves on the ship's deck, increasing the risk of water ingress. Therefore, the deep learning-based ship sway analysis system provided in the embodiment of the present application predicts the effective roll angle and effective roll angle of a ship by training a roll angle prediction model and a pitch angle prediction model.

[0058] For example, the rocking motion of a ship is the result of a combination of the ship's navigation and the environmental impact brought about by meteorological factors. Therefore, this scheme trains the roll angle prediction model and the pitch angle prediction model through ship driving time series data, ship rocking time series data and meteorological time series data.

[0059] For example, the swaying motion of a ship is also related to the ship itself. Ships of different structures and shapes will produce different swaying motions in the same environment with the same driving parameters and headings. Therefore, roll angle prediction models and pitch angle prediction models can be trained separately for ships with different signals, and the trained roll angle prediction models and pitch angle prediction models can be associated with the corresponding ship models.

[0060] In some embodiments, the data partitioning module, in the process of partitioning the time series data into historical time series data and time series data to be predicted, and determining the data label corresponding to the historical time series data based on the time series data to be predicted, is configured to:

[0061] Based on a sliding window algorithm, determining time series data of a first preset length as the historical time series data, and using time series data of a second preset length following the historical time series data as the time series data to be predicted;

[0062] The roll angle data in the time series data to be predicted is used as the roll angle label corresponding to the historical time series data, and the pitch angle data in the time series data to be predicted is used as the pitch angle label corresponding to the historical time series data.

[0063] For example, during the model training process, a part of the time series data is divided into historical time series data, and the historical time series data is used as the input of the model, so that the model predicts the time series data to be predicted based on the input, outputs the prediction result of the model, and optimizes the model by comparing the prediction result with the actual time series data to be predicted, minimizing the loss function, and thus obtaining the final roll angle prediction model and pitch angle prediction model.

[0064] Exemplarily, the ship's rocking time series data includes the ship's roll angle data and pitch angle data. Since the main purpose of the embodiment of the present application is to train models that can predict the roll angle and pitch angle respectively, the roll angle data and pitch angle data are respectively used as labels of the historical time series data.

[0065] In some embodiments, the data acquisition module is used to acquire time series data, wherein the time series data includes ship travel time series data, ship swing time series data, and weather time series data, and is used to:

[0066] Determine the ship travel time series data according to the ship travel data sampled by the ship control system and the timestamp corresponding to the ship travel data, wherein the ship travel data includes: speed data, heading data, and heading difference data;

[0067] Determining the ship sway time series data according to the ship sway data sampled by the shipboard sensor and the timestamp corresponding to the ship sway data, wherein the ship sway data includes: roll angle data and pitch angle data;

[0068] Acquire meteorological data and a timestamp corresponding to the meteorological data to determine the meteorological time series data, wherein the meteorological data includes: wind field data, flow field data, and wave data.

[0069] For example, the GPS module in the ship control system can obtain the ship's position information in real time, and obtain the ship's speed relative to the ground by calculating the distance and time interval between consecutive positions as speed data; the ship's magnetic compass or gyrocompass can measure the ship's actual heading in real time as heading data; the ship's automatic steering system will compare the actual heading measured by the compass with the set command heading, and calculate the difference between the actual heading and the command heading as heading difference data.

[0070] For example, by installing gyroscopes at multiple locations on a vessel, the data detected by the gyroscopes can be calculated to obtain roll angle data and pitch angle data as the ship's roll data. For example, in addition to the roll angle data and pitch angle data, the ship's roll data may also include data on other degrees of freedom, which are not limited here.

[0071] For example, meteorological data can be extracted from databases published by meteorological centers. For example, wind field data can be extracted from the fifth-generation global reanalysis dataset ERA5 provided by the European Centre for Medium-Range Weather Forecasts (ECMWF). ERA5 covers multiple variables in the global atmosphere, land, and ocean from 1940 to the present. It combines model data with global observational data and generates temporally and spatially consistent global climate data through data assimilation technology. Similarly, flow field data can be obtained from the Sub-Mesoscale Ocean Circulation (SMOC) data released by meteorological centers, which covers relevant data on sub-mesoscale circulation phenomena in a large number of oceans around the world.

[0072] For example, the wave data can be determined by monitoring the sponge using equipment on board a ship, and may include, for example, wave height data and wave period data.

[0073] In some embodiments, the data acquisition module, in the process of acquiring meteorological data released by a meteorological center and a timestamp corresponding to the meteorological data and determining the meteorological time series data, is used to:

[0074] Obtaining the original meteorological data released by the meteorological center and the timestamp corresponding to the original meteorological data;

[0075] Performing temporal interpolation and spatial interpolation on the original meteorological data according to the timestamp to obtain target meteorological data and a timestamp corresponding to the target meteorological data;

[0076] The meteorological time series data is determined according to the target meteorological data and a timestamp corresponding to the target meteorological data.

[0077] For example, raw meteorological data from meteorological centers is typically large-scale and low-resolution. For example, the ERA5 dataset has a spatial resolution of 0.25° × 0.25° (in degrees of longitude and latitude) at the ocean surface. This resolution allows the dataset to encompass the entire global ocean and provide a general description of the global ocean flow field. However, when used for ship sway analysis, inaccuracies can easily occur due to the small size of the ship relative to the resolution scale. Therefore, interpolation of the flow field data is necessary at a specific spatial scale. Specifically, based on the flow field data from two adjacent locations, the flow field data at the midpoint between the two locations is determined to improve the data resolution.

[0078] Similarly, if the resolution of the original meteorological data on the time scale is low, the original meteorological data can also be interpolated on the time scale, which will not be described in detail here.

[0079] Exemplarily, the original meteorological data is interpolated to obtain target meteorological data, and the target meteorological data is used to construct the basis of meteorological time series data.

[0080] In some embodiments, the system further comprises:

[0081] The data correction module is used to correct the ship swing data according to the ship driving data and the meteorological data, and determine the ship swing time series data according to the corrected ship swing data.

[0082] For example, the ship's swing data is obtained by fitting the sensor data monitored by sensors installed at various locations on the ship. However, the sensors may be interfered with by various factors during the measurement process, such as environmental noise, sensor drift, deviation of the installation position, etc., resulting in errors in the measurement results. Therefore, it is necessary to correct the ship's swing data based on the ship's driving data and meteorological data to determine whether the ship's swing data corresponds to the current ship's driving data and meteorological data.

[0083] Furthermore, the data correction method provided in the embodiment of the present application can also make the ship sway data measured by the sensor more consistent with the meteorological data measured by the meteorological center.

[0084] In some embodiments, the data correction module, in the process of correcting the ship swing data according to the ship driving data and the meteorological data, and determining the ship swing time series data according to the corrected ship swing data, is configured to:

[0085] The amplitude of the ship's motion response is calculated based on the following formula:

[0086] ;

[0087] Among them, H is the wave height data, is the ship's natural frequency, Indicates the frequency of encounters between ships and waves;

[0088] The ship roll data is corrected according to the motion response amplitude.

[0089] For example, the motion response amplitude is an indicator that measures the intensity of a ship's motion in waves and is used to quantify a ship's seakeeping performance in different sea conditions. The motion response amplitude is related to waves, reflecting the wave height data and wave encounter frequency in the formula. It is also related to the nature of the ship itself, reflected in the ship's natural frequency in the formula.

[0090] For example, The inherent characteristic data of a ship, namely the natural frequency of the ship, refers to the frequency of free vibration of the ship's structure or motion system when there is no external excitation (such as waves, wind, etc.). It reflects the natural vibration characteristics of the ship's structure or motion system. It can be calculated based on parameters such as the ship's width, ship displacement, ship's depth, length between perpendiculars, etc., or it can also be determined based on actual measurements or data provided by the manufacturer.

[0091] In some embodiments, the data correction module, in the process of correcting the ship swing data according to the ship driving data and the meteorological data, and determining the ship swing time series data according to the corrected ship swing data, is further configured to:

[0092] The encounter frequency is calculated according to the following formula:

[0093] ;

[0094] in, represents the circular frequency of the waves, V represents the speed of the ship, α represents the angle between the wave direction and the ship's heading, and L represents the length of the ship.

[0095] For example, the motion response amplitude is also related to the ship's navigation data, reflected in the formula as the ship's speed and the angle between the wave direction and the ship's heading. It is also related to the ship's properties, reflected in the formula as the ship's length. The circular frequency of the waves can be determined from flow field data, and the ship's speed and the angle between the wave direction and the ship's heading can be determined from the ship's navigation data.

[0096] In some embodiments, the data correction module, when correcting the ship roll data according to the motion response amplitude, is further configured to:

[0097] Correcting the roll angle tag according to a roll motion response amplitude operator and the motion response amplitude;

[0098] The pitch angle label is corrected according to a pitch motion response magnitude operator and the motion response amplitude.

[0099] For example, the relationship between the roll angle and pitch angle and the motion response amplitude can be described by the ship's motion response amplitude operator (RAO). RAO is the ratio of the motion response amplitude of a certain degree of freedom to the wave amplitude under the action of regular waves of unit amplitude, and is used to describe the motion response characteristics of the ship in waves.

[0100] Therefore, the theoretical roll angle can be calculated based on the roll RAO ​​and the motion response amplitude. When the difference between the theoretical roll angle and the roll angle data is greater than a preset threshold, the roll angle data is corrected according to the theoretical roll angle. For example, the average value of the theoretical roll angle and the roll angle data is used as the roll angle label.

[0101] Similarly, the pitch angle label is corrected according to the pitch motion response magnitude operator and the motion response amplitude.

[0102] In some embodiments, the deep learning-based ship sway analysis system further includes:

[0103] The model verification module is used to determine the accuracy performance index and the generalization performance index of the roll angle prediction model and the pitch angle prediction model according to the effective roll angle output by the roll angle prediction model and the effective pitch angle output by the pitch angle prediction model.

[0104] Exemplarily, the roll angle prediction model and the pitch angle prediction model are validated on a validation dataset to determine the accuracy scores and generalization scores of the roll angle prediction model and the pitch angle prediction model, thereby obtaining an accuracy performance index and a generalization performance index.

[0105] For example, the roll angle prediction model and the pitch angle prediction model can be trained by a Gradient Boosting Tree (GBM), and specifically, can be trained by LightGBM.

[0106] The present application provides a deep learning-based ship sway analysis system. The system comprises a data acquisition module for acquiring time series data, including ship travel time series data, ship sway time series data, and meteorological time series data. A data partitioning module is configured to partition the time series data into historical time series data and time series data to be predicted, and to determine data labels corresponding to the historical time series data based on the time series data to be predicted. The data labels include roll angle labels and pitch angle labels. A model training module is configured to train a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data. A sway analysis module is configured to predict the effective roll angle and effective pitch angle of the ship based on the roll angle prediction model and the pitch angle prediction model. By constructing the roll angle prediction model and the pitch angle prediction model, respectively, the predictability of the effective roll angle and effective pitch angle is improved, which helps to prepare for the ship's sway in advance and improve the safety of the ship's navigation.

[0107] Please refer to Figure 2 , Figure 2 A flowchart of a ship sway analysis method based on deep learning is provided in one embodiment of the present application.

[0108] The embodiment of the present application further provides a ship sway analysis method based on deep learning, the method comprising steps S101 to S104:

[0109] Step S101: Acquire time series data, where the time series data includes: ship travel time series data, ship swing time series data, and weather time series data;

[0110] Step S102: dividing the time series data into historical time series data and time series data to be predicted, and determining data labels corresponding to the historical time series data according to the time series data to be predicted, wherein the data labels include: a roll angle label and a pitch angle label;

[0111] Step S103: training a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data;

[0112] Step S104: predicting the effective roll angle and effective pitch angle of the ship based on the roll angle prediction model and the pitch angle prediction model.

[0113] In some implementations, dividing the time series data into historical time series data and time series data to be predicted, and determining a data label corresponding to the historical time series data based on the time series data to be predicted, includes:

[0114] Based on a sliding window algorithm, determining time series data of a first preset length as the historical time series data, and using time series data of a second preset length following the historical time series data as the time series data to be predicted;

[0115] The roll angle data in the time series data to be predicted is used as the roll angle label corresponding to the historical time series data, and the pitch angle data in the time series data to be predicted is used as the pitch angle label corresponding to the historical time series data.

[0116] In some embodiments, the acquiring of time series data, wherein the time series data includes: ship travel time series data, ship swing time series data, and weather time series data, includes:

[0117] Determine the ship travel time series data according to the ship travel data sampled by the ship control system and the timestamp corresponding to the ship travel data, wherein the ship travel data includes: speed data, heading data, and heading difference data;

[0118] Determining the ship sway time series data according to the ship sway data sampled by the shipboard sensor and the timestamp corresponding to the ship sway data, wherein the ship sway data includes: roll angle data and pitch angle data;

[0119] Acquire meteorological data and a timestamp corresponding to the meteorological data to determine the meteorological time series data, wherein the meteorological data includes: wind field data, flow field data, and wave data.

[0120] In some embodiments, obtaining meteorological data released by a meteorological center and a timestamp corresponding to the meteorological data to determine the meteorological time series data includes:

[0121] Obtaining the original meteorological data released by the meteorological center and the timestamp corresponding to the original meteorological data;

[0122] Performing temporal interpolation and spatial interpolation on the original meteorological data according to the timestamp to obtain target meteorological data and a timestamp corresponding to the target meteorological data;

[0123] The meteorological time series data is determined according to the target meteorological data and a timestamp corresponding to the target meteorological data.

[0124] In some embodiments, the method further comprises:

[0125] The ship swing data is corrected according to the ship driving data and the meteorological data, and the ship swing time series data is determined according to the corrected ship swing data.

[0126] In some embodiments, the correcting the ship swing data according to the ship driving data and the meteorological data, and determining the ship swing time series data according to the corrected ship swing data, includes:

[0127] The amplitude of the ship's motion response is calculated based on the following formula:

[0128] ;

[0129] Among them, H is the wave height data, is the ship's natural frequency, Indicates the frequency of encounters between ships and waves;

[0130] The ship roll data is corrected according to the motion response amplitude.

[0131] In some embodiments, the correcting the ship swing data according to the ship driving data and the meteorological data, and determining the ship swing time series data according to the corrected ship swing data, includes:

[0132] The encounter frequency is calculated according to the following formula:

[0133] ;

[0134] in, represents the circular frequency of the waves, V represents the speed of the ship, α represents the angle between the wave direction and the ship's heading, and L represents the length of the ship.

[0135] In some embodiments, correcting the ship sway data according to the motion response amplitude includes:

[0136] Correcting the roll angle tag according to a roll motion response amplitude operator and the motion response amplitude;

[0137] The pitch angle label is corrected according to a pitch motion response magnitude operator and the motion response amplitude.

[0138] In some embodiments, the deep learning-based ship sway analysis method further includes:

[0139] According to the effective roll angle output by the roll angle prediction model and the effective pitch angle output by the pitch angle prediction model, an accuracy performance index and a generalization performance index of the roll angle prediction model and the pitch angle prediction model are determined.

[0140] See also Figure 3 , Figure 3 This is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device can be a server or a terminal.

[0141] like Figure 3 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.

[0142] The storage medium may store an operating system and a computer program. The computer program includes program instructions, which, when executed, enable the processor to execute any one of the deep learning-based ship sway analysis methods.

[0143] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0144] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any one of the deep learning-based ship sway analysis system methods.

[0145] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0146] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0147] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0148] Acquiring time series data, the time series data including: ship travel time series data, ship swing time series data, and weather time series data;

[0149] Dividing the time series data into historical time series data and time series data to be predicted, and determining data labels corresponding to the historical time series data according to the time series data to be predicted, wherein the data labels include: a roll angle label and a pitch angle label;

[0150] Training a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data;

[0151] The effective roll angle and effective pitch angle of the ship are predicted based on the roll angle prediction model and the pitch angle prediction model.

[0152] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the ship sway analysis method based on deep learning in the present application.

[0153] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0154] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0155] It should also be understood that the term "and / or" used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0156] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments. The above description is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A ship sway analysis system based on deep learning, characterized in that: The system comprises: A data acquisition module is used to acquire time series data, wherein the time series data includes: ship travel time series data, ship swing time series data and meteorological time series data; a data partitioning module, configured to partition the time series data into historical time series data and time series data to be predicted, and determine data labels corresponding to the historical time series data based on the time series data to be predicted, wherein the data labels include: a roll angle label and a pitch angle label; a model training module, configured to train a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data; a sway analysis module, configured to predict the effective roll angle and effective roll angle of the ship based on the roll angle prediction model and the pitch angle prediction model; The data correction module is used to calculate the motion response amplitude of the ship based on the following formula: ； Among them, H is the wave height data, is the ship's natural frequency, Indicates the frequency of encounters between ships and waves; and correcting the ship's sway data according to the motion response amplitude; The data acquisition module is used to acquire time series data, including ship travel time series data, ship swing time series data, and meteorological time series data, and is used to: Determine the ship travel time series data according to the ship travel data sampled by the ship control system and the timestamp corresponding to the ship travel data, wherein the ship travel data includes: speed data, heading data, and heading difference data; Determining the ship sway time series data according to the ship sway data sampled by the shipboard sensor and the timestamp corresponding to the ship sway data, wherein the ship sway data includes: roll angle data and pitch angle data; Acquire meteorological data and a timestamp corresponding to the meteorological data to determine the meteorological time series data, wherein the meteorological data includes: wind field data, flow field data, and wave data.

2. The ship sway analysis system based on deep learning according to claim 1, characterized in that: The data partitioning module is used to divide the time series data into historical time series data and time series data to be predicted, and determine the data label corresponding to the historical time series data according to the time series data to be predicted, for: Based on a sliding window algorithm, determining time series data of a first preset length as the historical time series data, and using time series data of a second preset length following the historical time series data as the time series data to be predicted; The roll angle data in the time series data to be predicted is used as the roll angle label corresponding to the historical time series data, and the pitch angle data in the time series data to be predicted is used as the pitch angle label corresponding to the historical time series data.

3. The ship sway analysis system based on deep learning according to claim 1, characterized in that: The data acquisition module is used to obtain the meteorological data released by the meteorological center and the timestamp corresponding to the meteorological data, and determine the meteorological time series data, and is used to: Obtaining the original meteorological data released by the meteorological center and the timestamp corresponding to the original meteorological data; Performing temporal interpolation and spatial interpolation on the original meteorological data according to the timestamp to obtain target meteorological data and a timestamp corresponding to the target meteorological data; The meteorological time series data is determined according to the target meteorological data and a timestamp corresponding to the target meteorological data.

4. The ship sway analysis system based on deep learning according to claim 1, characterized in that: The data correction module is also used for: The ship swing data is corrected according to the ship driving data and the meteorological data, and the ship swing time series data is determined according to the corrected ship swing data.

5. The ship sway analysis system based on deep learning according to claim 4, characterized in that: The data correction module, in the process of correcting the ship swing data according to the ship driving data and the meteorological data, and determining the ship swing time series data according to the corrected ship swing data, is further configured to: The encounter frequency is calculated according to the following formula: ； in, represents the circular frequency of the waves, V represents the speed of the ship, α represents the angle between the wave direction and the ship's heading, and L represents the length of the ship.

6. The ship sway analysis system based on deep learning according to claim 4, characterized in that: The data correction module, in the process of correcting the ship sway data according to the motion response amplitude, is further configured to: Correcting the roll angle tag according to a roll motion response amplitude operator and the motion response amplitude; The pitch angle label is corrected according to a pitch motion response magnitude operator and the motion response amplitude.

7. The ship sway analysis system based on deep learning according to any one of claims 1 to 6, characterized in that: The ship sway analysis system based on deep learning also includes: The model verification module is used to determine the accuracy performance index and the generalization performance index of the roll angle prediction model and the pitch angle prediction model according to the effective roll angle output by the roll angle prediction model and the effective pitch angle output by the pitch angle prediction model.

8. A ship sway analysis method based on deep learning, characterized in that: The method comprises: Acquiring time series data, the time series data including: ship travel time series data, ship swing time series data, and weather time series data; Dividing the time series data into historical time series data and time series data to be predicted, and determining data labels corresponding to the historical time series data according to the time series data to be predicted, wherein the data labels include: a roll angle label and a pitch angle label; Training a preset model based on the historical time series data and the data labels to obtain a roll angle prediction model and a pitch angle prediction model that can be used to determine the time series data to be predicted based on the historical time series data; Predicting the effective roll angle and effective pitch angle of the ship based on the roll angle prediction model and the pitch angle prediction model; The amplitude of the ship's motion response is calculated based on the following formula: ； Among them, H is the wave height data, is the ship's natural frequency, Indicates the frequency of encounter between the ship and the waves; and corrects the ship sway data according to the motion response amplitude; The acquiring of time series data includes: Determine the ship travel time series data according to the ship travel data sampled by the ship control system and the timestamp corresponding to the ship travel data, wherein the ship travel data includes: speed data, heading data, and heading difference data; Determining the ship sway time series data according to the ship sway data sampled by the shipboard sensor and the timestamp corresponding to the ship sway data, wherein the ship sway data includes: roll angle data and pitch angle data; Acquire meteorological data and a timestamp corresponding to the meteorological data to determine the meteorological time series data, wherein the meteorological data includes: wind field data, flow field data, and wave data.

Images